system

Abstract

We provide the system. [Solution] A means of collecting the activity results of each piece of work equipment, A means for evaluating activity outcomes and generating scores based on generated evaluation criteria, A means of generating evaluation results as a report document, A means of collecting user feedback and updating evaluation criteria, A means for dynamically generating criteria for analyzing collected activity results, A means of evaluating the efficiency and quality of work equipment based on the analyzed evaluation criteria and proposing optimizations, 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, the method including receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the evaluation of employees' work within a company, it often relies on subjective judgments, and there is a problem that unfair evaluations are conducted. With such an evaluation method, employees who achieve high-quality results in a short time may not be appropriately evaluated, and employees who work long hours may sometimes be highly evaluated. As a result, there is a problem that the motivation of employees decreases and productivity is impaired. In order to solve this problem, a system that can objectively and quantitatively evaluate the contribution of employees is required.

Means for Solving the Problems

[0005] This invention provides an evaluation system that utilizes AI technology to objectively and quantitatively evaluate employees' work performance. Specifically, it provides a means to collect each employee's work performance, analyzes it based on unified evaluation criteria, and generates a score. The generated evaluation results are output as a report, and a function to collect user feedback is also incorporated. By flexibly updating the evaluation criteria based on the feedback, a fair and transparent evaluation is achieved. In this way, the aim is to improve employee motivation and productivity.

[0006] "Business results" is a general term for information generated by employees through their work, including their achievement status, the quality of deliverables, and efficiency.

[0007] "Generated criteria" refer to a set of indicators and scales used to evaluate work performance, which are dynamically created using AI technology.

[0008] "Generating a score" means creating a numerical value that represents an employee's performance, calculated based on collected work results and according to evaluation criteria.

[0009] A "report" is a document that presents evaluation results visually or in written form, showing each employee's evaluation score and areas for improvement.

[0010] "Feedback" refers to opinions and suggestions for improvement provided by users who have received evaluations, and is information that contributes to improving the evaluation system. [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, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. 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).

[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 relates to an evaluation system using AI technology for fairly evaluating employees' work performance. In the embodiment of the invention, a server-centered system is constructed, and processes are performed to collect and evaluate employees' work performance.

[0033] Data collection and integration

[0034] The server automatically collects data on each employee's work activities from various business support systems. The data used includes project progress, working hours, and deliverable quality information. This data is integrated into a database and organized by employee using their ID.

[0035] Generation of evaluation criteria

[0036] The AI ​​agent dynamically generates evaluation criteria using generative AI based on collected data. This establishes objective and unified evaluation standards.

[0037] Evaluation of work results

[0038] The AI ​​agent uses generated evaluation criteria to analyze each employee's work performance using a smart algorithm. This calculates a score indicating each employee's contribution. This score is composed of various aspects such as work quality, efficiency, and productivity.

[0039] Reporting results and obtaining feedback

[0040] The resulting scores and analysis results are generated as a report and presented to administrators and those being evaluated, along with compelling evidence. Feedback is collected from users via terminals, and improvement suggestions are made, thereby promoting continuous improvement of the system.

[0041] System update

[0042] Based on the collected feedback, the server updates its evaluation criteria and analysis algorithms, reflecting these changes in the next evaluation. This process allows the system to adapt to the organization's needs and changes in the external environment, ensuring that it continues to provide fair evaluations over the long term.

[0043] Through these processes, fair and transparent employee evaluations can be achieved, leading to improved employee motivation and productivity. For example, project progress data is collected in a timely manner, and the results are used to visualize employees' contributions to their work, ensuring transparency and fairness in evaluations.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server automatically collects employee work data from project management and time management systems via APIs. In particular, it retrieves task completion status, work time, and deliverable quality metrics, and stores them in a database.

[0047] Step 2:

[0048] The server formats the collected data and converts it into an analyzable format. During this process, it detects and cleans up duplicate and missing data. Employee-specific work data is then integrated into a database based on unique IDs.

[0049] Step 3:

[0050] The AI ​​agent uses generative AI to dynamically generate evaluation criteria based on formatted data. These criteria include elements such as quality, efficiency, and productivity, and each element is weighted accordingly.

[0051] Step 4:

[0052] The AI ​​agent analyzes each employee's work output by applying predefined evaluation criteria. Based on these criteria, it calculates productivity and quality scores, and derives an overall evaluation result.

[0053] Step 5:

[0054] The server generates a detailed evaluation report based on the analysis results. The report includes each employee's evaluation score, strengths of performance, and areas for improvement, presented in a visually easy-to-understand format.

[0055] Step 6:

[0056] Users (administrators and employees) can view evaluation reports through their terminals and see their own evaluations and feedback within the report. They can also provide feedback and make improvement suggestions as needed.

[0057] Step 7:

[0058] Based on feedback from users, the server's AI agent updates its evaluation criteria and algorithms. Adjustments are made to ensure a fairer and more transparent evaluation for the next assessment.

[0059] (Example 1)

[0060] 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."

[0061] Fair and objective evaluation of employee performance is crucial for improving organizational efficiency, but traditional evaluation methods can be susceptible to human bias and lack of transparency. There is a need to address these issues and provide accurate and transparent evaluations.

[0062] 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.

[0063] In this invention, the server includes means for collecting information on each employee's work activities, means for generating dynamic evaluation criteria based on the collected information using a generative AI model, and means for analyzing work results using a smart algorithm and calculating a contribution score. This improves the objectivity and transparency of evaluations and enables fair employee evaluation within the organization.

[0064] "Employee" refers to an individual person who belongs to an organization and performs business activities.

[0065] "Information related to business activities" refers to all data related to the performance of employees' work, such as project progress, working hours, and quality data of deliverables generated during work.

[0066] A "generative AI model" refers to artificial intelligence technology used to generate dynamic and objective evaluation criteria based on collected information.

[0067] "Dynamic evaluation criteria" refer to standards for evaluating employee work activities that are constructed by a generated AI model using collected information, and have the characteristic of being flexibly changed according to the situation.

[0068] A "smart algorithm" refers to an advanced computational method that uses dynamically generated evaluation criteria to analyze employee work performance and calculate a contribution score.

[0069] A "contribution score" refers to an indicator that quantifies an employee's contribution by comprehensively evaluating their work performance.

[0070] "Reporting materials" refer to documents created to document evaluation results and analysis content and to present them to employees and managers.

[0071] "Feedback" refers to user reactions and opinions on the presented evaluation results, and is used to improve the evaluation process.

[0072] "Analysis method" refers to the techniques and processes used to evaluate information about collected business activities.

[0073] In this system, the server connects to multiple business support systems to efficiently collect information on each employee's work activities. This allows it to obtain project progress data, work hours, and deliverable quality information from project management tools and time management tools. This data is essential for evaluating work performance.

[0074] The server integrates the collected information into the organization's database and organizes it by employee. This organization utilizes unique IDs, allowing for centralized management of the information and conversion into a format suitable for analysis. This improves data integrity and analytical efficiency.

[0075] The server uses a generative AI model to dynamically generate evaluation criteria from collected information. A generation prompt such as "Extract the characteristics of successful projects from the previous quarter and create new evaluation criteria based on them" can be used. This prompt allows the AI ​​to analyze past successes and generate appropriate evaluation metrics.

[0076] The smart algorithm uses dynamically generated evaluation criteria within the server to analyze work outcomes in detail. This analysis scores each employee's contribution, enabling fair evaluation within the organization. Scoring is performed from multiple perspectives, including work quality, efficiency, and productivity.

[0077] The server automatically generates reports based on the analysis results and presents them to administrators and employees via terminals. These reports clearly show the evaluation results and their rationale, ensuring highly convincing feedback.

[0078] The terminal receives feedback from users and sends it back to the server. The server updates the evaluation criteria and analysis methods based on the collected feedback and incorporates them into the next evaluation process. This cyclical process allows the evaluation system to continuously adapt flexibly to changes within the organization.

[0079] These operations are expected to enable transparent and fair employee evaluations, thereby improving overall organizational efficiency and motivation.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects information about each employee's work activities from business support systems. Inputs include data from project management tools and time management tools. The server retrieves data in real time or periodically through interfaces such as APIs. This information collection accumulates the necessary data in the company's database. The output is the raw data stored in the database.

[0083] Step 2:

[0084] The server organizes the collected information and converts it into a format that is easy to analyze. The input is the raw data collected in step 1. The server classifies the data by employee ID and unifies the data structure. This formatting process generates a dataset optimized for analysis. The output is the integrated dataset.

[0085] Step 3:

[0086] The server generates evaluation criteria using a generative AI model. The input consists of a formatted dataset and a predefined prompt. For example, a prompt such as "Extract success characteristics from past quarters and create new evaluation criteria" might be used. The server runs the AI ​​model to build dynamic evaluation criteria. The output is a set of evaluation criteria.

[0087] Step 4:

[0088] The server uses a smart algorithm to evaluate work performance. Inputs include a set of evaluation criteria and a formatted dataset. The server analyzes each employee's data based on the criteria and calculates a contribution score. This analysis uses performance quality, efficiency, and productivity as evaluation indicators. The output is each employee's contribution score.

[0089] Step 5:

[0090] The server generates a report using contribution scores. The inputs are contribution scores and evaluation criteria. The server sets the report format and creates a document containing data demonstrating the validity of the scores and criteria. The output is the report.

[0091] Step 6:

[0092] The terminal displays the generated report to administrators and employees. The input is the report created in step 5. The terminal displays the document on a display device and notifies relevant parties of the detailed evaluation results. The output is the displayed report.

[0093] Step 7:

[0094] Users provide feedback based on the report. The input is the evaluation results described in the report. Users frequently send back their opinions and suggestions for improvement regarding the evaluation. This feedback is used in subsequent processes. The output is the feedback sent to the server.

[0095] Step 8:

[0096] The server updates evaluation criteria and analysis methods based on collected feedback. The input is user feedback. The server analyzes the feedback and revises evaluation criteria and adjusts smart algorithms. The output is an optimized evaluation system for the next evaluation process.

[0097] (Application Example 1)

[0098] 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."

[0099] Fair and efficient evaluation of the performance of work equipment used in industrial facilities is a crucial issue for improving product quality and productivity. Conventional methods are prone to subjective human evaluation and lack clear evaluation criteria, making it difficult to accurately grasp the performance of work equipment and provide optimal feedback and improvement suggestions.

[0100] 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.

[0101] In this invention, the server includes means for collecting the activity results of each work device, means for evaluating the activity results based on generated evaluation criteria and generating a score, and means for generating the evaluation results as a report document. This enables objective evaluation of the work device's activity and fair scoring. Furthermore, it is possible to dynamically update the evaluation criteria based on user feedback and provide improvement suggestions to maintain optimal work efficiency and quality at all times.

[0102] "Work equipment" refers to devices that automatically perform specific tasks in industrial facilities.

[0103] "Activity results" refers to the collective data that shows the results and performance of work performed by the work equipment.

[0104] "Evaluation criteria" are standards or standards predetermined for objectively evaluating the performance of work equipment.

[0105] A "score" is a numerical value that quantifies the performance of work equipment based on evaluation criteria.

[0106] A "report document" is a document that describes the results of the evaluation and the analysis, and is presented to the user.

[0107] "Feedback" refers to information such as opinions and suggestions for improvement received from users.

[0108] To implement this invention, a system is needed to monitor and evaluate work equipment within a factory. The system collects the activity results of the work equipment, analyzes the activity results using evaluation criteria, and generates evaluation results.

[0109] The server automatically collects data from work equipment operating in industrial facilities. The hardware used is the work equipment itself, and the software used includes TENSORFLOW®, a platform for data processing and analysis. The data includes work time, operational efficiency, and quality indicators. Once the data is collected, the server formats it into a suitable format for analysis and dynamically generates evaluation criteria.

[0110] A generative AI model is used to generate evaluation criteria. The server then assigns a score to the activity output of each piece of equipment based on the generated evaluation criteria. This scoring ensures a fair and objective evaluation.

[0111] The evaluation results are automatically generated as a report document and presented to the administrator's terminal. Through the terminal, users can provide feedback on the displayed scores and analysis results. This collected feedback is then used to update the evaluation criteria for future evaluations.

[0112] As a concrete example, in a certain factory, a screw assembly machine operates 24 hours a day, and the operational data during that time is accumulated on a server. The data includes the time and accuracy required for assembly, and AI analyzes this data. In some cases, the system may suggest improvement plans based on best practices.

[0113] An example of a prompt might be, "Please tell me what data should be considered in order to dynamically generate evaluation criteria for work equipment." This prompt clarifies information that is important for determining criteria in an AI model.

[0114] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0115] Step 1:

[0116] The server collects activity result data from work equipment within the factory. It receives operational data from each piece of equipment (e.g., work time, operational efficiency, quality indicators) as input. This data is collected by the server via IoT devices and stored in a database. The output is raw, unformatted data.

[0117] Step 2:

[0118] The server formats the collected data and converts it into a format that is easy to analyze. The input is the collected raw data. This data is then cleansed and normalized and converted into the required format. The output is formatted, analyzable data. Specific operations include handling missing values ​​and detecting outliers.

[0119] Step 3:

[0120] The server dynamically generates evaluation criteria using a generative AI model. The input is formatted data. Based on this input, the generative AI model applies machine learning algorithms to generate evaluation criteria used for scoring work equipment. The output is the evaluation criteria themselves. During training of the generative AI model, the prompt "What data should be considered to generate criteria for evaluating the activity results of work equipment?" is used.

[0121] Step 4:

[0122] The server evaluates activity outcomes based on generated evaluation criteria and generates scores. Inputs are evaluation criteria and formatted data. Based on these inputs, the server performs scoring based on efficiency, quality, and other key performance indicators. Outputs are scores representing the activity outcomes of each work machine. Specifically, it calculates indices for time and accuracy in each work process.

[0123] Step 5:

[0124] The user's terminal displays the evaluation results sent from the server as a report document. The input consists of the generated score and the evaluation result. These are documented and output through the terminal's interface so that administrators can view and understand them. Specific actions include graphing the score and displaying comparison results.

[0125] Step 6:

[0126] Using a terminal, users provide feedback on the evaluation results. Input consists of user opinions and suggestions for improvement. This feedback is sent to the server for later updating of the evaluation criteria. Output is the data used as adjustment material during the update process.

[0127] Step 7:

[0128] The server updates the evaluation criteria based on the collected feedback and uses this for the next scoring. The input is the feedback information. Based on this, the AI ​​system is retrained and the evaluation criteria are fine-tuned. The output is the updated evaluation criteria. Specifically, this includes actions such as changing the weighting of the evaluation criteria according to the feedback.

[0129] 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.

[0130] This invention provides a system for fairly evaluating employee performance that incorporates an emotion engine to recognize user emotions, thereby enabling more appropriate evaluation feedback and adjustment of evaluation criteria. A server at the center of the system collects work data from each employee, and an AI agent dynamically generates evaluation criteria using the information stored in the database.

[0131] Introducing emotion recognition

[0132] The device uses emotion recognition technology to collect emotional data, such as facial expressions and voice tone, while the user is viewing the evaluation report. The emotion engine analyzes this data to identify the user's emotional state.

[0133] Feedback optimization

[0134] The emotional information recognized by the emotion engine is analyzed in conjunction with the user's feedback. Based on this information, the server dynamically adjusts the evaluation report and presents it in a way that best suits the user's emotional state. This makes the evaluation more readily accepted and results in more effective feedback.

[0135] Adjustment of evaluation criteria

[0136] The server flexibly adjusts evaluation criteria based on collected feedback and sentiment data. The AI ​​agent updates the criteria for the next evaluation, taking sentiment analysis results into consideration. This process reflects changes in the organization's culture and motivation, resulting in adaptive and continuous improvement.

[0137] As a concrete example, the server evaluates data obtained from the project management system, and the emotion engine improves the evaluation criteria based on the feedback received. If a user expresses negative emotions, the system analyzes the reasons and obtains suggestions for making the evaluation criteria fairer.

[0138] By incorporating an emotional engine in this way, evaluation systems can achieve a more flexible and user-friendly evaluation process while maintaining fairness. This can enhance trust throughout the organization and improve employee motivation and productivity.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects employee work data from project management tools and other related systems via APIs. This data includes the time taken to complete tasks, project progress, and deliverable quality metrics.

[0142] Step 2:

[0143] The server formats the collected data into an analyzable format. It performs data cleaning to remove duplicates and missing data, and integrates it into a database using a unique ID for each employee.

[0144] Step 3:

[0145] An AI agent dynamically generates evaluation criteria based on formatted data. This process utilizes generative AI to include elements such as quality, efficiency, and productivity in the evaluation criteria, and assigns appropriate weights to each element.

[0146] Step 4:

[0147] The device uses emotion recognition technology to collect data such as the user's facial expressions and voice tone when the user views the evaluation report.

[0148] Step 5:

[0149] The emotion engine analyzes collected emotion data to determine the user's emotional state. This allows it to quantify how the user feels about the evaluation.

[0150] Step 6:

[0151] The server integrates emotion recognition data with user feedback to optimize and display the evaluation report. In this process, it selects a display method that aligns with the user's emotions, ensuring that the evaluation results are appropriately received.

[0152] Step 7:

[0153] Users provide feedback based on the evaluation report provided, sending their opinions and suggestions for improvement regarding their evaluation via their device.

[0154] Step 8:

[0155] The server's AI agent flexibly adjusts evaluation criteria based on user feedback and sentiment data. This improves the system to establish fairer and more effective evaluation criteria for future assessments.

[0156] (Example 2)

[0157] 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 as the "terminal".

[0158] Conventional evaluation systems often evaluated employees based solely on their work performance, without considering their emotional state. As a result, evaluation results were not properly communicated, potentially leading to decreased employee motivation and performance. This invention aims to solve these problems and provide a system that offers fair and highly acceptable evaluations.

[0159] 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.

[0160] In this invention, the server includes means for acquiring information about work activities, means for evaluating work activities based on generated evaluation criteria and creating indicators, and means for identifying the emotional state of users. This enables adaptive evaluation that takes into account the emotions of individual employees.

[0161] "Information related to business activities" refers to all data generated or acquired by employees in the course of performing their duties, and specifically includes project progress information and task completion status.

[0162] "Evaluation criteria" refer to the indicators and conditions used to measure and evaluate employees' work activities, and individual work performance is calculated based on these criteria.

[0163] "Means for creating indicators" refers to methods or devices for quantifying or categorizing employee performance based on acquired information about work activities.

[0164] "Reactions" refer to feedback such as emotions and opinions expressed by employees when they receive their evaluation results.

[0165] "Means for identifying emotional states" refers to technologies, methods, or devices for detecting an employee's emotions at any given time based on their facial expressions, tone of voice, etc.

[0166] "Means of dynamically adjusting documents" refers to technologies and methods for modifying and optimizing the content of evaluation reports and other documents in real time based on the user's emotional state.

[0167] Embodiments for carrying out this invention are described below.

[0168] The server first retrieves information about work activities from an external data management device. This information includes employee project progress and completed tasks. The server stores this information in a database and prepares it for processing. The server also uses a generative AI model to generate evaluation criteria for assessing employee activities from this data. These criteria are dynamically updated to provide a fairer and more adaptive evaluation.

[0169] The terminal uses a camera and microphone to sense the user's facial expressions and voice tone in real time when displaying evaluation reports. The data acquired from these devices is analyzed using emotion recognition software to identify the user's emotional state. The emotion engine detects the user's positive or negative responses in real time and sends the results to the server.

[0170] After the user's response is identified by the emotion engine, the server dynamically adjusts the content of the evaluation report. This process utilizes user emotion data and generative AI models to optimize the evaluation document, making it more acceptable and eliciting positive feedback. As a concrete example, an example of a prompt might be, "Suggest ways to adjust the feedback to improve the user's negative emotions."

[0171] As described above, this invention provides a flexible and adaptive evaluation system that takes into account the emotional state of employees, thereby increasing trust within the organization and improving employee motivation and productivity.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server retrieves information about business activities from an external data management device. This input includes employee project progress and task completion information. The server formats this data and stores it in a database. This ensures that the information is maintained in a unified format, making subsequent processing easier.

[0175] Step 2:

[0176] The device uses its camera and microphone to collect facial expressions and voice tone while the user is viewing the evaluation report. This input data is analyzed by emotion recognition software within the device. This analysis outputs an emotional state indicating how the user is reacting to the displayed content.

[0177] Step 3:

[0178] The server receives emotion data from emotion recognition software and uses it to further analyze user feedback. It detects specific influencing factors and sends prompt messages to the generating AI model. An example of such a prompt message is, "Suggest ways to adjust the feedback to improve the user's negative emotions." The report content is updated based on the feedback adjustment suggestions output by the generating AI model.

[0179] Step 4:

[0180] Users view an evaluation report that includes emotional information and feedback adjustments. This report, dynamically adjusted by the server, is presented in a way that users can easily understand and accept the evaluation. This enables feedback that takes users' emotions into consideration, thereby improving employee motivation.

[0181] Step 5:

[0182] The server integrates all feedback and sentiment data and updates the evaluation criteria. In this process, an AI algorithm calculates which criteria are fairer based on the collected data. As a result, new evaluation criteria are generated and stored in the database. This iterative process continuously optimizes the system.

[0183] (Application Example 2)

[0184] 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".

[0185] In evaluating the work results of team members, conventional evaluation methods fail to take into account the emotions and stress levels of the members, resulting in inaccurate and fair evaluations. Furthermore, because the feedback is not provided in a way that is easily accepted by the members, there is a challenge in that the evaluation results do not easily lead to increased motivation or productivity among the members.

[0186] 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.

[0187] In this invention, the server includes means for collecting the work results of each member, means for collecting emotional data of the members using emotion recognition technology, and means for dynamically adjusting evaluation criteria based on the collected emotional data and providing feedback based on emotional state. This enables fair and emotionally sensitive evaluations, and the evaluation results can effectively lead to improved motivation and productivity among members.

[0188] "Members" refer to individuals who are responsible for specific roles or tasks within an organization or facility.

[0189] "Work results" refers to the outcomes of the tasks and activities performed by the members, as well as the content of the completed activities.

[0190] "Evaluation criteria" refers to a set of indicators or rules used to evaluate work results.

[0191] "Emotion recognition technology" refers to technology that identifies an individual's emotional state by analyzing their facial expressions and voice.

[0192] "Emotional data" refers to data that indicates the emotional state of the members, and is information generated by emotion recognition technology.

[0193] "Feedback" refers to evaluation results and advice provided to members, and is information aimed at improving subsequent behavior and increasing motivation.

[0194] A "server" refers to a computer system that provides services and data over a network and processes requests from multiple users or clients.

[0195] The system for realizing this application provides a series of processes for collecting and evaluating the work results of each member. The server collects work result data from each terminal connected to the network and further analyzes the collected emotional data using emotion recognition technology. This system is responsible for dynamically adjusting the evaluation criteria to take into account the emotional state of the members and generating optimal feedback.

[0196] The server implements an emotion recognition model using the Python programming language and machine learning libraries such as TensorFlow. This allows it to analyze members' facial and voice data in real time to understand their emotional states. The analyzed emotion data is then formatted using the pandas library and used to refine evaluation criteria.

[0197] Users access this system through devices such as smartphones and smart glasses to view the generated reports. Feedback is provided in a way that takes into account the receptiveness of the members, enabling more effective evaluations. This allows organizations to improve the work efficiency of their members and support their emotional well-being.

[0198] A concrete example of this system is the staff of a nursing care facility. The server monitors the emotional state of the facility's staff during the day and suggests adjustments to break times and reassignments of tasks based on their stress levels. This reduces stress for the staff and enables them to provide higher quality care to the residents.

[0199] An example of a prompt for a generative AI model would be: "We want to develop a system for evaluating the emotions of staff in a nursing home. Please tell us how to create a system that can recognize the emotions of staff members in real time while they are interacting with residents and provide feedback to adjust the criteria for performance evaluation."

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server collects work result data from each member's terminal via the network. It receives data such as work details, time, and completion status as input, and stores this data in a database, making it possible to track the performance of each member.

[0203] Step 2:

[0204] The terminal uses emotion recognition technology to acquire facial expressions and voice data of its members in real time. It uses camera footage and microphone audio as input to identify the emotional state of each member, and then sends this modeled emotion data to the server.

[0205] Step 3:

[0206] The server uses the TensorFlow library to analyze the received emotion data. It processes the emotion data as input and performs data calculations to quantify the emotional state of the members. This quantified data is used to adjust the evaluation criteria.

[0207] Step 4:

[0208] The server uses the pandas library to integrate work result data and sentiment data, and formats it into a format that is easy to analyze. This allows for the extraction of all the information necessary for feedback. The formatted data is then used as the basis for the next step in generating the evaluation report.

[0209] Step 5:

[0210] The server generates an evaluation report based on the formatted data. Using integrated data as input, it generates a comprehensive evaluation based on the members' work performance and emotional state. This evaluation includes specific feedback for improving member performance.

[0211] Step 6:

[0212] Users receive evaluation reports through their smartphones or smart glasses displays. This information is framed in a way that is easy for members to understand and accept. Members can then review their own work processes based on the feedback.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] This invention relates to an evaluation system using AI technology for fairly evaluating employees' work performance. In the embodiment of the invention, a server-centered system is constructed, and processes are performed to collect and evaluate employees' work performance.

[0230] Data collection and integration

[0231] The server automatically collects data on each employee's work activities from various business support systems. The data used includes project progress, working hours, and deliverable quality information. This data is integrated into a database and organized by employee using their ID.

[0232] Generation of evaluation criteria

[0233] The AI ​​agent dynamically generates evaluation criteria using generative AI based on collected data. This establishes objective and unified evaluation standards.

[0234] Evaluation of work results

[0235] The AI ​​agent uses generated evaluation criteria to analyze each employee's work performance using a smart algorithm. This calculates a score indicating each employee's contribution. This score is composed of various aspects such as work quality, efficiency, and productivity.

[0236] Reporting results and obtaining feedback

[0237] The resulting scores and analysis results are generated as a report and presented to administrators and those being evaluated, along with compelling evidence. Feedback is collected from users via terminals, and improvement suggestions are made, thereby promoting continuous improvement of the system.

[0238] System update

[0239] Based on the collected feedback, the server updates its evaluation criteria and analysis algorithms, reflecting these changes in the next evaluation. This process allows the system to adapt to the organization's needs and changes in the external environment, ensuring that it continues to provide fair evaluations over the long term.

[0240] Through these processes, fair and transparent employee evaluations can be achieved, leading to improved employee motivation and productivity. For example, project progress data is collected in a timely manner, and the results are used to visualize employees' contributions to their work, ensuring transparency and fairness in evaluations.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The server automatically collects employee work data from project management and time management systems via APIs. In particular, it retrieves task completion status, work time, and deliverable quality metrics, and stores them in a database.

[0244] Step 2:

[0245] The server formats the collected data and converts it into an analyzable format. During this process, it detects and cleans up duplicate and missing data. Employee-specific work data is then integrated into a database based on unique IDs.

[0246] Step 3:

[0247] The AI ​​agent uses generative AI to dynamically generate evaluation criteria based on formatted data. These criteria include elements such as quality, efficiency, and productivity, and each element is weighted accordingly.

[0248] Step 4:

[0249] The AI ​​agent analyzes each employee's work output by applying predefined evaluation criteria. Based on these criteria, it calculates productivity and quality scores, and derives an overall evaluation result.

[0250] Step 5:

[0251] The server generates a detailed evaluation report based on the analysis results. The report includes each employee's evaluation score, strengths of performance, and areas for improvement, presented in a visually easy-to-understand format.

[0252] Step 6:

[0253] Users (administrators and employees) can view evaluation reports through their terminals and see their own evaluations and feedback within the report. They can also provide feedback and make improvement suggestions as needed.

[0254] Step 7:

[0255] Based on feedback from users, the server's AI agent updates its evaluation criteria and algorithms. Adjustments are made to ensure a fairer and more transparent evaluation for the next assessment.

[0256] (Example 1)

[0257] 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."

[0258] Fair and objective evaluation of employee performance is crucial for improving organizational efficiency, but traditional evaluation methods can be susceptible to human bias and lack of transparency. There is a need to address these issues and provide accurate and transparent evaluations.

[0259] 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.

[0260] In this invention, the server includes means for collecting information on each employee's work activities, means for generating dynamic evaluation criteria based on the collected information using a generative AI model, and means for analyzing work results using a smart algorithm and calculating a contribution score. This improves the objectivity and transparency of evaluations and enables fair employee evaluation within the organization.

[0261] "Employee" refers to an individual person who belongs to an organization and performs business activities.

[0262] "Information related to business activities" refers to all data related to the performance of employees' work, such as project progress, working hours, and quality data of deliverables generated during work.

[0263] A "generative AI model" refers to artificial intelligence technology used to generate dynamic and objective evaluation criteria based on collected information.

[0264] "Dynamic evaluation criteria" refer to standards for evaluating employee work activities that are constructed by a generated AI model using collected information, and have the characteristic of being flexibly changed according to the situation.

[0265] A "smart algorithm" refers to an advanced computational method that uses dynamically generated evaluation criteria to analyze employee work performance and calculate a contribution score.

[0266] A "contribution score" refers to an indicator that quantifies an employee's contribution by comprehensively evaluating their work performance.

[0267] "Reporting materials" refer to documents created to document evaluation results and analysis content and to present them to employees and managers.

[0268] "Feedback" refers to user reactions and opinions on the presented evaluation results, and is used to improve the evaluation process.

[0269] "Analysis method" refers to the techniques and processes used to evaluate information about collected business activities.

[0270] In this system, the server connects to multiple business support systems to efficiently collect information on each employee's work activities. This allows it to obtain project progress data, work hours, and deliverable quality information from project management tools and time management tools. This data is essential for evaluating work performance.

[0271] The server integrates the collected information into the organization's database and organizes it by employee. This organization utilizes unique IDs, allowing for centralized management of the information and conversion into a format suitable for analysis. This improves data integrity and analytical efficiency.

[0272] The server uses a generative AI model to dynamically generate evaluation criteria from collected information. A generation prompt such as "Extract the characteristics of successful projects from the previous quarter and create new evaluation criteria based on them" can be used. This prompt allows the AI ​​to analyze past successes and generate appropriate evaluation metrics.

[0273] The smart algorithm uses dynamically generated evaluation criteria within the server to analyze work outcomes in detail. This analysis scores each employee's contribution, enabling fair evaluation within the organization. Scoring is performed from multiple perspectives, including work quality, efficiency, and productivity.

[0274] The server automatically generates reports based on the analysis results and presents them to administrators and employees via terminals. These reports clearly show the evaluation results and their rationale, ensuring highly convincing feedback.

[0275] The terminal receives feedback from users and sends it back to the server. The server updates the evaluation criteria and analysis methods based on the collected feedback and incorporates them into the next evaluation process. This cyclical process allows the evaluation system to continuously adapt flexibly to changes within the organization.

[0276] These operations are expected to enable transparent and fair employee evaluations, thereby improving overall organizational efficiency and motivation.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The server collects information on the business activities of each employee from the business support system. The inputs include data from project management tools and time management tools. The server retrieves data in real time or periodically through interfaces such as APIs. Through this information collection, the necessary data is accumulated in the in-house database. The output is the raw data accumulated in the database.

[0280] Step 2:

[0281] The server organizes the collected information and converts it into a format that is easy to analyze. The input is the raw data collected in Step 1. The server classifies the data by the ID of each employee and performs a process to unify the data structure. Through this formatting process, a dataset optimized for analysis is generated. The output is the integrated dataset.

[0282] Step 3:

[0283] The server uses the generated AI model to generate evaluation criteria. The inputs include the formatted dataset and a pre-defined prompt sentence. For example, a prompt such as "Extract the successful characteristics of the past quarter and create new evaluation criteria" is used. The server executes the AI model to construct dynamic evaluation criteria. The output is a set of evaluation criteria.

[0284] Step 4:

[0285] The server evaluates business results using a smart algorithm. The inputs include a set of evaluation criteria and the formatted dataset. The server analyzes the data of each employee based on the criteria and calculates a contribution score. In this analysis, the quality, efficiency, productivity, etc. of the business are used as evaluation indicators. The output is the contribution score of each employee.

[0286] Step 5:

[0287] The server generates a report using contribution scores. The inputs are contribution scores and evaluation criteria. The server sets the report format and creates a document containing data demonstrating the validity of the scores and criteria. The output is the report.

[0288] Step 6:

[0289] The terminal displays the generated report to administrators and employees. The input is the report created in step 5. The terminal displays the document on a display device and notifies relevant parties of the detailed evaluation results. The output is the displayed report.

[0290] Step 7:

[0291] Users provide feedback based on the report. The input is the evaluation results described in the report. Users frequently send back their opinions and suggestions for improvement regarding the evaluation. This feedback is used in subsequent processes. The output is the feedback sent to the server.

[0292] Step 8:

[0293] The server updates evaluation criteria and analysis methods based on collected feedback. The input is user feedback. The server analyzes the feedback and revises evaluation criteria and adjusts smart algorithms. The output is an optimized evaluation system for the next evaluation process.

[0294] (Application Example 1)

[0295] 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."

[0296] Fair and efficient evaluation of the performance of work equipment used in industrial facilities is a crucial issue for improving product quality and productivity. Conventional methods are prone to subjective human evaluation and lack clear evaluation criteria, making it difficult to accurately grasp the performance of work equipment and provide optimal feedback and improvement suggestions.

[0297] 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.

[0298] In this invention, the server includes means for collecting the activity results of each work device, means for evaluating the activity results based on generated evaluation criteria and generating a score, and means for generating the evaluation results as a report document. This enables objective evaluation of the work device's activity and fair scoring. Furthermore, it is possible to dynamically update the evaluation criteria based on user feedback and provide improvement suggestions to maintain optimal work efficiency and quality at all times.

[0299] "Work equipment" refers to devices that automatically perform specific tasks in industrial facilities.

[0300] "Activity results" refers to the collective data that shows the results and performance of work performed by the work equipment.

[0301] "Evaluation criteria" are standards or standards predetermined for objectively evaluating the performance of work equipment.

[0302] A "score" is a numerical value that quantifies the performance of work equipment based on evaluation criteria.

[0303] A "report document" is a document that describes the results of the evaluation and the analysis, and is presented to the user.

[0304] "Feedback" refers to information such as opinions and suggestions for improvement received from users.

[0305] To implement this invention, a system for monitoring and evaluating working equipment in a factory is required. The system collects the activity results of the working equipment, analyzes the activity results using evaluation criteria, and generates evaluation results.

[0306] The server automatically collects data from working equipment operating in an industrial facility. The hardware used is the working equipment itself, and the software used includes TensorFlow, a platform for data processing and analysis. The data includes working hours, operating efficiency, quality indicators, etc. When the data is collected, the server formats it into a suitable form for analysis and dynamically generates evaluation criteria.

[0307] To generate the evaluation criteria, a generative AI model is used. The server assigns scores to the activity results of each working equipment based on the generated evaluation criteria. This scoring enables a fair and objective evaluation.

[0308] The evaluation results are automatically generated as a report document and presented to the administrator's terminal. Through the terminal, the user can provide feedback on the displayed scores and analysis results. The feedback thus collected is used for updating the evaluation criteria in subsequent evaluations.

[0309] As a specific example, in a certain factory, a screw assembly device operates for 24 hours, and the operating data during that period is accumulated in the server. The data includes the time and accuracy required for assembly, and the AI analyzes this. In some cases, improvement plans may be presented by the system based on best practices.

[0310] As an example of a prompt sentence, "Please tell me what data should be considered to dynamically generate the evaluation criteria for working equipment." can be considered. This is a prompt that clarifies information contributing to important criterion determination in the AI model.

[0311] The flow of a specific process in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The server collects activity result data from work equipment within the factory. It receives operational data from each piece of equipment (e.g., work time, operational efficiency, quality indicators) as input. This data is collected by the server via IoT devices and stored in a database. The output is raw, unformatted data.

[0314] Step 2:

[0315] The server formats the collected data and converts it into a format that is easy to analyze. The input is the collected raw data. This data is then cleansed and normalized and converted into the required format. The output is formatted, analyzable data. Specific operations include handling missing values ​​and detecting outliers.

[0316] Step 3:

[0317] The server dynamically generates evaluation criteria using a generative AI model. The input is formatted data. Based on this input, the generative AI model applies machine learning algorithms to generate evaluation criteria used for scoring work equipment. The output is the evaluation criteria themselves. During training of the generative AI model, the prompt "What data should be considered to generate criteria for evaluating the activity results of work equipment?" is used.

[0318] Step 4:

[0319] The server evaluates activity outcomes based on generated evaluation criteria and generates scores. Inputs are evaluation criteria and formatted data. Based on these inputs, the server performs scoring based on efficiency, quality, and other key performance indicators. Outputs are scores representing the activity outcomes of each work machine. Specifically, it calculates indices for time and accuracy in each work process.

[0320] Step 5:

[0321] The user's terminal displays the evaluation results sent from the server as a report document. The input consists of the generated score and the evaluation result. These are documented and output through the terminal's interface so that administrators can view and understand them. Specific actions include graphing the score and displaying comparison results.

[0322] Step 6:

[0323] Using a terminal, users provide feedback on the evaluation results. Input consists of user opinions and suggestions for improvement. This feedback is sent to the server for later updating of the evaluation criteria. Output is the data used as adjustment material during the update process.

[0324] Step 7:

[0325] The server updates the evaluation criteria based on the collected feedback and uses this for the next scoring. The input is the feedback information. Based on this, the AI ​​system is retrained and the evaluation criteria are fine-tuned. The output is the updated evaluation criteria. Specifically, this includes actions such as changing the weighting of the evaluation criteria according to the feedback.

[0326] 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.

[0327] This invention provides a system for fairly evaluating employee performance that incorporates an emotion engine to recognize user emotions, thereby enabling more appropriate evaluation feedback and adjustment of evaluation criteria. A server at the center of the system collects work data from each employee, and an AI agent dynamically generates evaluation criteria using the information stored in the database.

[0328] Introducing emotion recognition

[0329] The device uses emotion recognition technology to collect emotional data, such as facial expressions and voice tone, while the user is viewing the evaluation report. The emotion engine analyzes this data to identify the user's emotional state.

[0330] Feedback optimization

[0331] The emotional information recognized by the emotion engine is analyzed in conjunction with the user's feedback. Based on this information, the server dynamically adjusts the evaluation report and presents it in a way that best suits the user's emotional state. This makes the evaluation more readily accepted and results in more effective feedback.

[0332] Adjustment of evaluation criteria

[0333] The server flexibly adjusts evaluation criteria based on collected feedback and sentiment data. The AI ​​agent updates the criteria for the next evaluation, taking sentiment analysis results into consideration. This process reflects changes in the organization's culture and motivation, resulting in adaptive and continuous improvement.

[0334] As a concrete example, the server evaluates data obtained from the project management system, and the emotion engine improves the evaluation criteria based on the feedback received. If a user expresses negative emotions, the system analyzes the reasons and obtains suggestions for making the evaluation criteria fairer.

[0335] By incorporating an emotional engine in this way, evaluation systems can achieve a more flexible and user-friendly evaluation process while maintaining fairness. This can enhance trust throughout the organization and improve employee motivation and productivity.

[0336] The following describes the processing flow.

[0337] Step 1:

[0338] The server collects employee work data from project management tools and other related systems via APIs. This data includes the time taken to complete tasks, project progress, and deliverable quality metrics.

[0339] Step 2:

[0340] The server formats the collected data into an analyzable format. It performs data cleaning to remove duplicates and missing data, and integrates it into a database using a unique ID for each employee.

[0341] Step 3:

[0342] An AI agent dynamically generates evaluation criteria based on formatted data. This process utilizes generative AI to include elements such as quality, efficiency, and productivity in the evaluation criteria, and assigns appropriate weights to each element.

[0343] Step 4:

[0344] The device uses emotion recognition technology to collect data such as the user's facial expressions and voice tone when the user views the evaluation report.

[0345] Step 5:

[0346] The emotion engine analyzes collected emotion data to determine the user's emotional state. This allows it to quantify how the user feels about the evaluation.

[0347] Step 6:

[0348] The server integrates emotion recognition data with user feedback to optimize and display the evaluation report. In this process, it selects a display method that aligns with the user's emotions, ensuring that the evaluation results are appropriately received.

[0349] Step 7:

[0350] Users provide feedback based on the evaluation report provided, sending their opinions and suggestions for improvement regarding their evaluation via their device.

[0351] Step 8:

[0352] The server's AI agent flexibly adjusts evaluation criteria based on user feedback and sentiment data. This improves the system to establish fairer and more effective evaluation criteria for future assessments.

[0353] (Example 2)

[0354] 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".

[0355] Conventional evaluation systems often evaluated employees based solely on their work performance, without considering their emotional state. As a result, evaluation results were not properly communicated, potentially leading to decreased employee motivation and performance. This invention aims to solve these problems and provide a system that offers fair and highly acceptable evaluations.

[0356] 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.

[0357] In this invention, the server includes means for acquiring information about work activities, means for evaluating work activities based on generated evaluation criteria and creating indicators, and means for identifying the emotional state of users. This enables adaptive evaluation that takes into account the emotions of individual employees.

[0358] "Information related to business activities" refers to all data generated or acquired by employees in the course of performing their duties, and specifically includes project progress information and task completion status.

[0359] "Evaluation criteria" refer to the indicators and conditions used to measure and evaluate employees' work activities, and individual work performance is calculated based on these criteria.

[0360] "Means for creating indicators" refers to methods or devices for quantifying or categorizing employee performance based on acquired information about work activities.

[0361] "Reactions" refer to feedback such as emotions and opinions expressed by employees when they receive their evaluation results.

[0362] "Means for identifying emotional states" refers to technologies, methods, or devices for detecting an employee's emotions at any given time based on their facial expressions, tone of voice, etc.

[0363] "Means of dynamically adjusting documents" refers to technologies and methods for modifying and optimizing the content of evaluation reports and other documents in real time based on the user's emotional state.

[0364] Embodiments for carrying out this invention are described below.

[0365] The server first retrieves information about work activities from an external data management device. This information includes employee project progress and completed tasks. The server stores this information in a database and prepares it for processing. The server also uses a generative AI model to generate evaluation criteria for assessing employee activities from this data. These criteria are dynamically updated to provide a fairer and more adaptive evaluation.

[0366] The terminal uses a camera and microphone to sense the user's facial expressions and voice tone in real time when displaying evaluation reports. The data acquired from these devices is analyzed using emotion recognition software to identify the user's emotional state. The emotion engine detects the user's positive or negative responses in real time and sends the results to the server.

[0367] After the user's response is identified by the emotion engine, the server dynamically adjusts the content of the evaluation report. This process utilizes user emotion data and generative AI models to optimize the evaluation document, making it more acceptable and eliciting positive feedback. As a concrete example, an example of a prompt might be, "Suggest ways to adjust the feedback to improve the user's negative emotions."

[0368] As described above, this invention provides a flexible and adaptive evaluation system that takes into account the emotional state of employees, thereby increasing trust within the organization and improving employee motivation and productivity.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server retrieves information about business activities from an external data management device. This input includes employee project progress and task completion information. The server formats this data and stores it in a database. This ensures that the information is maintained in a unified format, making subsequent processing easier.

[0372] Step 2:

[0373] The device uses its camera and microphone to collect facial expressions and voice tone while the user is viewing the evaluation report. This input data is analyzed by emotion recognition software within the device. This analysis outputs an emotional state indicating how the user is reacting to the displayed content.

[0374] Step 3:

[0375] The server receives emotion data from emotion recognition software and uses it to further analyze user feedback. It detects specific influencing factors and sends prompt messages to the generating AI model. An example of such a prompt message is, "Suggest ways to adjust the feedback to improve the user's negative emotions." The report content is updated based on the feedback adjustment suggestions output by the generating AI model.

[0376] Step 4:

[0377] Users view an evaluation report that includes emotional information and feedback adjustments. This report, dynamically adjusted by the server, is presented in a way that users can easily understand and accept the evaluation. This enables feedback that takes users' emotions into consideration, thereby improving employee motivation.

[0378] Step 5:

[0379] The server integrates all feedback and sentiment data and updates the evaluation criteria. In this process, an AI algorithm calculates which criteria are fairer based on the collected data. As a result, new evaluation criteria are generated and stored in the database. This iterative process continuously optimizes the system.

[0380] (Application Example 2)

[0381] 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 as the "terminal".

[0382] In evaluating the work results of team members, conventional evaluation methods fail to take into account the emotions and stress levels of the members, resulting in inaccurate and fair evaluations. Furthermore, because the feedback is not provided in a way that is easily accepted by the members, there is a challenge in that the evaluation results do not easily lead to increased motivation or productivity among the members.

[0383] 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.

[0384] In this invention, the server includes means for collecting the work results of each member, means for collecting emotional data of the members using emotion recognition technology, and means for dynamically adjusting evaluation criteria based on the collected emotional data and providing feedback based on emotional state. This enables fair and emotionally sensitive evaluations, and the evaluation results can effectively lead to improved motivation and productivity among members.

[0385] "Members" refer to individuals who are responsible for specific roles or tasks within an organization or facility.

[0386] "Work results" refers to the outcomes of the tasks and activities performed by the members, as well as the content of the completed activities.

[0387] "Evaluation criteria" refers to a set of indicators or rules used to evaluate work results.

[0388] "Emotion recognition technology" refers to technology that identifies an individual's emotional state by analyzing their facial expressions and voice.

[0389] "Emotional data" refers to data that indicates the emotional state of the members, and is information generated by emotion recognition technology.

[0390] "Feedback" refers to evaluation results and advice provided to members, and is information aimed at improving subsequent behavior and increasing motivation.

[0391] A "server" refers to a computer system that provides services and data over a network and processes requests from multiple users or clients.

[0392] The system for realizing this application provides a series of processes for collecting and evaluating the work results of each member. The server collects work result data from each terminal connected to the network and further analyzes the collected emotional data using emotion recognition technology. This system is responsible for dynamically adjusting the evaluation criteria to take into account the emotional state of the members and generating optimal feedback.

[0393] The server implements an emotion recognition model using the Python programming language and machine learning libraries such as TensorFlow. This allows it to analyze members' facial and voice data in real time to understand their emotional states. The analyzed emotion data is then formatted using the pandas library and used to refine evaluation criteria.

[0394] Users access this system through devices such as smartphones and smart glasses to view the generated reports. Feedback is provided in a way that takes into account the receptiveness of the members, enabling more effective evaluations. This allows organizations to improve the work efficiency of their members and support their emotional well-being.

[0395] A concrete example of this system is the staff of a nursing care facility. The server monitors the emotional state of the facility's staff during the day and suggests adjustments to break times and reassignments of tasks based on their stress levels. This reduces stress for the staff and enables them to provide higher quality care to the residents.

[0396] An example of a prompt for a generative AI model would be: "We want to develop a system for evaluating the emotions of staff in a nursing home. Please tell us how to create a system that can recognize the emotions of staff members in real time while they are interacting with residents and provide feedback to adjust the criteria for performance evaluation."

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] The server collects work result data from each member's terminal via the network. It receives data such as work details, time, and completion status as input, and stores this data in a database, making it possible to track the performance of each member.

[0400] Step 2:

[0401] The terminal uses emotion recognition technology to acquire facial expressions and voice data of its members in real time. It uses camera footage and microphone audio as input to identify the emotional state of each member, and then sends this modeled emotion data to the server.

[0402] Step 3:

[0403] The server uses the TensorFlow library to analyze the received emotion data. It processes the emotion data as input and performs data calculations to quantify the emotional state of the members. This quantified data is used to adjust the evaluation criteria.

[0404] Step 4:

[0405] The server uses the pandas library to integrate work result data and sentiment data, and formats it into a format that is easy to analyze. This allows for the extraction of all the information necessary for feedback. The formatted data is then used as the basis for the next step in generating the evaluation report.

[0406] Step 5:

[0407] The server generates an evaluation report based on the formatted data. Using integrated data as input, it generates a comprehensive evaluation based on the members' work performance and emotional state. This evaluation includes specific feedback for improving member performance.

[0408] Step 6:

[0409] Users receive evaluation reports through their smartphones or smart glasses displays. This information is framed in a way that is easy for members to understand and accept. Members can then review their own work processes based on the feedback.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] 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.

[0416] 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).

[0417] 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.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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".

[0426] This invention relates to an evaluation system using AI technology for fairly evaluating employees' work performance. In the embodiment of the invention, a server-centered system is constructed, and processes are performed to collect and evaluate employees' work performance.

[0427] Data collection and integration

[0428] The server automatically collects data on each employee's work activities from various business support systems. The data used includes project progress, working hours, and deliverable quality information. This data is integrated into a database and organized by employee using their ID.

[0429] Generation of evaluation criteria

[0430] The AI ​​agent dynamically generates evaluation criteria using generative AI based on collected data. This establishes objective and unified evaluation standards.

[0431] Evaluation of work results

[0432] The AI ​​agent uses generated evaluation criteria to analyze each employee's work performance using a smart algorithm. This calculates a score indicating each employee's contribution. This score is composed of various aspects such as work quality, efficiency, and productivity.

[0433] Reporting results and obtaining feedback

[0434] The resulting scores and analysis results are generated as a report and presented to administrators and those being evaluated, along with compelling evidence. Feedback is collected from users via terminals, and improvement suggestions are made, thereby promoting continuous improvement of the system.

[0435] System update

[0436] Based on the collected feedback, the server updates its evaluation criteria and analysis algorithms, reflecting these changes in the next evaluation. This process allows the system to adapt to the organization's needs and changes in the external environment, ensuring that it continues to provide fair evaluations over the long term.

[0437] Through these processes, fair and transparent employee evaluations can be achieved, leading to improved employee motivation and productivity. For example, project progress data is collected in a timely manner, and the results are used to visualize employees' contributions to their work, ensuring transparency and fairness in evaluations.

[0438] The following describes the processing flow.

[0439] Step 1:

[0440] The server automatically collects employee work data from project management and time management systems via APIs. In particular, it retrieves task completion status, work time, and deliverable quality metrics, and stores them in a database.

[0441] Step 2:

[0442] The server formats the collected data and converts it into an analyzable format. During this process, it detects and cleans up duplicate and missing data. Employee-specific work data is then integrated into a database based on unique IDs.

[0443] Step 3:

[0444] The AI ​​agent uses generative AI to dynamically generate evaluation criteria based on formatted data. These criteria include elements such as quality, efficiency, and productivity, and each element is weighted accordingly.

[0445] Step 4:

[0446] The AI ​​agent analyzes each employee's work output by applying predefined evaluation criteria. Based on these criteria, it calculates productivity and quality scores, and derives an overall evaluation result.

[0447] Step 5:

[0448] The server generates a detailed evaluation report based on the analysis results. The report includes each employee's evaluation score, strengths of performance, and areas for improvement, presented in a visually easy-to-understand format.

[0449] Step 6:

[0450] Users (administrators and employees) can view evaluation reports through their terminals and see their own evaluations and feedback within the report. They can also provide feedback and make improvement suggestions as needed.

[0451] Step 7:

[0452] Based on feedback from users, the server's AI agent updates its evaluation criteria and algorithms. Adjustments are made to ensure a fairer and more transparent evaluation for the next assessment.

[0453] (Example 1)

[0454] 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."

[0455] Fair and objective evaluation of employee performance is crucial for improving organizational efficiency, but traditional evaluation methods can be susceptible to human bias and lack of transparency. There is a need to address these issues and provide accurate and transparent evaluations.

[0456] 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.

[0457] In this invention, the server includes means for collecting information on each employee's work activities, means for generating dynamic evaluation criteria based on the collected information using a generative AI model, and means for analyzing work results using a smart algorithm and calculating a contribution score. This improves the objectivity and transparency of evaluations and enables fair employee evaluation within the organization.

[0458] "Employee" refers to an individual person who belongs to an organization and performs business activities.

[0459] "Information related to business activities" refers to all data related to the performance of employees' work, such as project progress, working hours, and quality data of deliverables generated during work.

[0460] A "generative AI model" refers to artificial intelligence technology used to generate dynamic and objective evaluation criteria based on collected information.

[0461] "Dynamic evaluation criteria" refer to standards for evaluating employee work activities that are constructed by a generated AI model using collected information, and have the characteristic of being flexibly changed according to the situation.

[0462] A "smart algorithm" refers to an advanced computational method that uses dynamically generated evaluation criteria to analyze employee work performance and calculate a contribution score.

[0463] A "contribution score" refers to an indicator that quantifies an employee's contribution by comprehensively evaluating their work performance.

[0464] "Reporting materials" refer to documents created to document evaluation results and analysis content and to present them to employees and managers.

[0465] "Feedback" refers to user reactions and opinions on the presented evaluation results, and is used to improve the evaluation process.

[0466] "Analysis method" refers to the techniques and processes used to evaluate information about collected business activities.

[0467] In this system, the server connects to multiple business support systems to efficiently collect information on each employee's work activities. This allows it to obtain project progress data, work hours, and deliverable quality information from project management tools and time management tools. This data is essential for evaluating work performance.

[0468] The server integrates the collected information into the organization's database and organizes it by employee. This organization utilizes unique IDs, allowing for centralized management of the information and conversion into a format suitable for analysis. This improves data integrity and analytical efficiency.

[0469] The server uses a generative AI model to dynamically generate evaluation criteria from collected information. A generation prompt such as "Extract the characteristics of successful projects from the previous quarter and create new evaluation criteria based on them" can be used. This prompt allows the AI ​​to analyze past successes and generate appropriate evaluation metrics.

[0470] The smart algorithm uses dynamically generated evaluation criteria within the server to analyze work outcomes in detail. This analysis scores each employee's contribution, enabling fair evaluation within the organization. Scoring is performed from multiple perspectives, including work quality, efficiency, and productivity.

[0471] The server automatically generates reports based on the analysis results and presents them to administrators and employees via terminals. These reports clearly show the evaluation results and their rationale, ensuring highly convincing feedback.

[0472] The terminal receives feedback from users and sends it back to the server. The server updates the evaluation criteria and analysis methods based on the collected feedback and incorporates them into the next evaluation process. This cyclical process allows the evaluation system to continuously adapt flexibly to changes within the organization.

[0473] These operations are expected to enable transparent and fair employee evaluations, thereby improving overall organizational efficiency and motivation.

[0474] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0475] Step 1:

[0476] The server collects information about each employee's work activities from business support systems. Inputs include data from project management tools and time management tools. The server retrieves data in real time or periodically through interfaces such as APIs. This information collection accumulates the necessary data in the company's database. The output is the raw data stored in the database.

[0477] Step 2:

[0478] The server organizes the collected information and converts it into a format that is easy to analyze. The input is the raw data collected in step 1. The server classifies the data by employee ID and unifies the data structure. This formatting process generates a dataset optimized for analysis. The output is the integrated dataset.

[0479] Step 3:

[0480] The server generates evaluation criteria using a generative AI model. The input consists of a formatted dataset and a predefined prompt. For example, a prompt such as "Extract success characteristics from past quarters and create new evaluation criteria" might be used. The server runs the AI ​​model to build dynamic evaluation criteria. The output is a set of evaluation criteria.

[0481] Step 4:

[0482] The server uses a smart algorithm to evaluate work performance. Inputs include a set of evaluation criteria and a formatted dataset. The server analyzes each employee's data based on the criteria and calculates a contribution score. This analysis uses performance quality, efficiency, and productivity as evaluation indicators. The output is each employee's contribution score.

[0483] Step 5:

[0484] The server generates a report using contribution scores. The inputs are contribution scores and evaluation criteria. The server sets the report format and creates a document containing data demonstrating the validity of the scores and criteria. The output is the report.

[0485] Step 6:

[0486] The terminal displays the generated report to administrators and employees. The input is the report created in step 5. The terminal displays the document on a display device and notifies relevant parties of the detailed evaluation results. The output is the displayed report.

[0487] Step 7:

[0488] Users provide feedback based on the report. The input is the evaluation results described in the report. Users frequently send back their opinions and suggestions for improvement regarding the evaluation. This feedback is used in subsequent processes. The output is the feedback sent to the server.

[0489] Step 8:

[0490] The server updates evaluation criteria and analysis methods based on collected feedback. The input is user feedback. The server analyzes the feedback and revises evaluation criteria and adjusts smart algorithms. The output is an optimized evaluation system for the next evaluation process.

[0491] (Application Example 1)

[0492] 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."

[0493] Fair and efficient evaluation of the performance of work equipment used in industrial facilities is a crucial issue for improving product quality and productivity. Conventional methods are prone to subjective human evaluation and lack clear evaluation criteria, making it difficult to accurately grasp the performance of work equipment and provide optimal feedback and improvement suggestions.

[0494] 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.

[0495] In this invention, the server includes means for collecting the activity results of each work device, means for evaluating the activity results based on generated evaluation criteria and generating a score, and means for generating the evaluation results as a report document. This enables objective evaluation of the work device's activity and fair scoring. Furthermore, it is possible to dynamically update the evaluation criteria based on user feedback and provide improvement suggestions to maintain optimal work efficiency and quality at all times.

[0496] "Work equipment" refers to devices that automatically perform specific tasks in industrial facilities.

[0497] "Activity results" refers to the collective data that shows the results and performance of work performed by the work equipment.

[0498] "Evaluation criteria" are standards or standards predetermined for objectively evaluating the performance of work equipment.

[0499] A "score" is a numerical value that quantifies the performance of work equipment based on evaluation criteria.

[0500] A "report document" is a document that describes the results of the evaluation and the analysis, and is presented to the user.

[0501] "Feedback" refers to information such as opinions and suggestions for improvement received from users.

[0502] To implement this invention, a system is needed to monitor and evaluate work equipment within a factory. The system collects the activity results of the work equipment, analyzes the activity results using evaluation criteria, and generates evaluation results.

[0503] The server automatically collects data from work equipment operating in industrial facilities. The hardware used is the work equipment itself, and the software used includes TensorFlow, a platform for data processing and analysis. The data includes work time, operational efficiency, and quality indicators. Once the data is collected, the server formats it into a suitable format for analysis and dynamically generates evaluation criteria.

[0504] A generative AI model is used to generate evaluation criteria. The server then assigns a score to the activity output of each piece of equipment based on the generated evaluation criteria. This scoring ensures a fair and objective evaluation.

[0505] The evaluation results are automatically generated as a report document and presented to the administrator's terminal. Through the terminal, users can provide feedback on the displayed scores and analysis results. This collected feedback is then used to update the evaluation criteria for future evaluations.

[0506] As a concrete example, in a certain factory, a screw assembly machine operates 24 hours a day, and the operational data during that time is accumulated on a server. The data includes the time and accuracy required for assembly, and AI analyzes this data. In some cases, the system may suggest improvement plans based on best practices.

[0507] An example of a prompt might be, "Please tell me what data should be considered in order to dynamically generate evaluation criteria for work equipment." This prompt clarifies information that is important for determining criteria in an AI model.

[0508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0509] Step 1:

[0510] The server collects activity result data from work equipment within the factory. It receives operational data from each piece of equipment (e.g., work time, operational efficiency, quality indicators) as input. This data is collected by the server via IoT devices and stored in a database. The output is raw, unformatted data.

[0511] Step 2:

[0512] The server formats the collected data and converts it into a format that is easy to analyze. The input is the collected raw data. This data is then cleansed and normalized and converted into the required format. The output is formatted, analyzable data. Specific operations include handling missing values ​​and detecting outliers.

[0513] Step 3:

[0514] The server dynamically generates evaluation criteria using a generative AI model. The input is formatted data. Based on this input, the generative AI model applies machine learning algorithms to generate evaluation criteria used for scoring work equipment. The output is the evaluation criteria themselves. During training of the generative AI model, the prompt "What data should be considered to generate criteria for evaluating the activity results of work equipment?" is used.

[0515] Step 4:

[0516] The server evaluates activity outcomes based on generated evaluation criteria and generates scores. Inputs are evaluation criteria and formatted data. Based on these inputs, the server performs scoring based on efficiency, quality, and other key performance indicators. Outputs are scores representing the activity outcomes of each work machine. Specifically, it calculates indices for time and accuracy in each work process.

[0517] Step 5:

[0518] The user's terminal displays the evaluation results sent from the server as a report document. The input consists of the generated score and the evaluation result. These are documented and output through the terminal's interface so that administrators can view and understand them. Specific actions include graphing the score and displaying comparison results.

[0519] Step 6:

[0520] Using a terminal, users provide feedback on the evaluation results. Input consists of user opinions and suggestions for improvement. This feedback is sent to the server for later updating of the evaluation criteria. Output is the data used as adjustment material during the update process.

[0521] Step 7:

[0522] The server updates the evaluation criteria based on the collected feedback and uses this for the next scoring. The input is the feedback information. Based on this, the AI ​​system is retrained and the evaluation criteria are fine-tuned. The output is the updated evaluation criteria. Specifically, this includes actions such as changing the weighting of the evaluation criteria according to the feedback.

[0523] 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.

[0524] This invention provides a system for fairly evaluating employee performance that incorporates an emotion engine to recognize user emotions, thereby enabling more appropriate evaluation feedback and adjustment of evaluation criteria. A server at the center of the system collects work data from each employee, and an AI agent dynamically generates evaluation criteria using the information stored in the database.

[0525] Introducing emotion recognition

[0526] The device uses emotion recognition technology to collect emotional data, such as facial expressions and voice tone, while the user is viewing the evaluation report. The emotion engine analyzes this data to identify the user's emotional state.

[0527] Feedback optimization

[0528] The emotional information recognized by the emotion engine is analyzed in conjunction with the user's feedback. Based on this information, the server dynamically adjusts the evaluation report and presents it in a way that best suits the user's emotional state. This makes the evaluation more readily accepted and results in more effective feedback.

[0529] Adjustment of evaluation criteria

[0530] The server flexibly adjusts evaluation criteria based on collected feedback and sentiment data. The AI ​​agent updates the criteria for the next evaluation, taking sentiment analysis results into consideration. This process reflects changes in the organization's culture and motivation, resulting in adaptive and continuous improvement.

[0531] As a concrete example, the server evaluates data obtained from the project management system, and the emotion engine improves the evaluation criteria based on the feedback received. If a user expresses negative emotions, the system analyzes the reasons and obtains suggestions for making the evaluation criteria fairer.

[0532] By incorporating an emotional engine in this way, evaluation systems can achieve a more flexible and user-friendly evaluation process while maintaining fairness. This can enhance trust throughout the organization and improve employee motivation and productivity.

[0533] The following describes the processing flow.

[0534] Step 1:

[0535] The server collects employee work data from project management tools and other related systems via APIs. This data includes the time taken to complete tasks, project progress, and deliverable quality metrics.

[0536] Step 2:

[0537] The server formats the collected data into an analyzable format. It performs data cleaning to remove duplicates and missing data, and integrates it into a database using a unique ID for each employee.

[0538] Step 3:

[0539] An AI agent dynamically generates evaluation criteria based on formatted data. This process utilizes generative AI to include elements such as quality, efficiency, and productivity in the evaluation criteria, and assigns appropriate weights to each element.

[0540] Step 4:

[0541] The device uses emotion recognition technology to collect data such as the user's facial expressions and voice tone when the user views the evaluation report.

[0542] Step 5:

[0543] The emotion engine analyzes collected emotion data to determine the user's emotional state. This allows it to quantify how the user feels about the evaluation.

[0544] Step 6:

[0545] The server integrates emotion recognition data with user feedback to optimize and display the evaluation report. In this process, it selects a display method that aligns with the user's emotions, ensuring that the evaluation results are appropriately received.

[0546] Step 7:

[0547] Users provide feedback based on the evaluation report provided, sending their opinions and suggestions for improvement regarding their evaluation via their device.

[0548] Step 8:

[0549] The server's AI agent flexibly adjusts evaluation criteria based on user feedback and sentiment data. This improves the system to establish fairer and more effective evaluation criteria for future assessments.

[0550] (Example 2)

[0551] 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."

[0552] Conventional evaluation systems often evaluated employees based solely on their work performance, without considering their emotional state. As a result, evaluation results were not properly communicated, potentially leading to decreased employee motivation and performance. This invention aims to solve these problems and provide a system that offers fair and highly acceptable evaluations.

[0553] 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.

[0554] In this invention, the server includes means for acquiring information about work activities, means for evaluating work activities based on generated evaluation criteria and creating indicators, and means for identifying the emotional state of users. This enables adaptive evaluation that takes into account the emotions of individual employees.

[0555] "Information related to business activities" refers to all data generated or acquired by employees in the course of performing their duties, and specifically includes project progress information and task completion status.

[0556] "Evaluation criteria" refer to the indicators and conditions used to measure and evaluate employees' work activities, and individual work performance is calculated based on these criteria.

[0557] "Means for creating indicators" refers to methods or devices for quantifying or categorizing employee performance based on acquired information about work activities.

[0558] "Reactions" refer to feedback such as emotions and opinions expressed by employees when they receive their evaluation results.

[0559] "Means for identifying emotional states" refers to technologies, methods, or devices for detecting an employee's emotions at any given time based on their facial expressions, tone of voice, etc.

[0560] "Means of dynamically adjusting documents" refers to technologies and methods for modifying and optimizing the content of evaluation reports and other documents in real time based on the user's emotional state.

[0561] Embodiments for carrying out this invention are described below.

[0562] The server first retrieves information about work activities from an external data management device. This information includes employee project progress and completed tasks. The server stores this information in a database and prepares it for processing. The server also uses a generative AI model to generate evaluation criteria for assessing employee activities from this data. These criteria are dynamically updated to provide a fairer and more adaptive evaluation.

[0563] The terminal uses a camera and microphone to sense the user's facial expressions and voice tone in real time when displaying evaluation reports. The data acquired from these devices is analyzed using emotion recognition software to identify the user's emotional state. The emotion engine detects the user's positive or negative responses in real time and sends the results to the server.

[0564] After the user's response is identified by the emotion engine, the server dynamically adjusts the content of the evaluation report. This process utilizes user emotion data and generative AI models to optimize the evaluation document, making it more acceptable and eliciting positive feedback. As a concrete example, an example of a prompt might be, "Suggest ways to adjust the feedback to improve the user's negative emotions."

[0565] As described above, this invention provides a flexible and adaptive evaluation system that takes into account the emotional state of employees, thereby increasing trust within the organization and improving employee motivation and productivity.

[0566] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0567] Step 1:

[0568] The server retrieves information about business activities from an external data management device. This input includes employee project progress and task completion information. The server formats this data and stores it in a database. This ensures that the information is maintained in a unified format, making subsequent processing easier.

[0569] Step 2:

[0570] The device uses its camera and microphone to collect facial expressions and voice tone while the user is viewing the evaluation report. This input data is analyzed by emotion recognition software within the device. This analysis outputs an emotional state indicating how the user is reacting to the displayed content.

[0571] Step 3:

[0572] The server receives emotion data from emotion recognition software and uses it to further analyze user feedback. It detects specific influencing factors and sends prompt messages to the generating AI model. An example of such a prompt message is, "Suggest ways to adjust the feedback to improve the user's negative emotions." The report content is updated based on the feedback adjustment suggestions output by the generating AI model.

[0573] Step 4:

[0574] Users view an evaluation report that includes emotional information and feedback adjustments. This report, dynamically adjusted by the server, is presented in a way that users can easily understand and accept the evaluation. This enables feedback that takes users' emotions into consideration, thereby improving employee motivation.

[0575] Step 5:

[0576] The server integrates all feedback and sentiment data and updates the evaluation criteria. In this process, an AI algorithm calculates which criteria are fairer based on the collected data. As a result, new evaluation criteria are generated and stored in the database. This iterative process continuously optimizes the system.

[0577] (Application Example 2)

[0578] 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."

[0579] In evaluating the work results of team members, conventional evaluation methods fail to take into account the emotions and stress levels of the members, resulting in inaccurate and fair evaluations. Furthermore, because the feedback is not provided in a way that is easily accepted by the members, there is a challenge in that the evaluation results do not easily lead to increased motivation or productivity among the members.

[0580] 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.

[0581] In this invention, the server includes means for collecting the work results of each member, means for collecting emotional data of the members using emotion recognition technology, and means for dynamically adjusting evaluation criteria based on the collected emotional data and providing feedback based on emotional state. This enables fair and emotionally sensitive evaluations, and the evaluation results can effectively lead to improved motivation and productivity among members.

[0582] "Members" refer to individuals who are responsible for specific roles or tasks within an organization or facility.

[0583] "Work results" refers to the outcomes of the tasks and activities performed by the members, as well as the content of the completed activities.

[0584] "Evaluation criteria" refers to a set of indicators or rules used to evaluate work results.

[0585] "Emotion recognition technology" refers to technology that identifies an individual's emotional state by analyzing their facial expressions and voice.

[0586] "Emotional data" refers to data that indicates the emotional state of the members, and is information generated by emotion recognition technology.

[0587] "Feedback" refers to evaluation results and advice provided to members, and is information aimed at improving subsequent behavior and increasing motivation.

[0588] A "server" refers to a computer system that provides services and data over a network and processes requests from multiple users or clients.

[0589] The system for realizing this application provides a series of processes for collecting and evaluating the work results of each member. The server collects work result data from each terminal connected to the network and further analyzes the collected emotional data using emotion recognition technology. This system is responsible for dynamically adjusting the evaluation criteria to take into account the emotional state of the members and generating optimal feedback.

[0590] The server implements an emotion recognition model using the Python programming language and machine learning libraries such as TensorFlow. This allows it to analyze members' facial and voice data in real time to understand their emotional states. The analyzed emotion data is then formatted using the pandas library and used to refine evaluation criteria.

[0591] Users access this system through devices such as smartphones and smart glasses to view the generated reports. Feedback is provided in a way that takes into account the receptiveness of the members, enabling more effective evaluations. This allows organizations to improve the work efficiency of their members and support their emotional well-being.

[0592] A concrete example of this system is the staff of a nursing care facility. The server monitors the emotional state of the facility's staff during the day and suggests adjustments to break times and reassignments of tasks based on their stress levels. This reduces stress for the staff and enables them to provide higher quality care to the residents.

[0593] An example of a prompt for a generative AI model would be: "We want to develop a system for evaluating the emotions of staff in a nursing home. Please tell us how to create a system that can recognize the emotions of staff members in real time while they are interacting with residents and provide feedback to adjust the criteria for performance evaluation."

[0594] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0595] Step 1:

[0596] The server collects work result data from each member's terminal via the network. It receives data such as work details, time, and completion status as input, and stores this data in a database, making it possible to track the performance of each member.

[0597] Step 2:

[0598] The terminal uses emotion recognition technology to acquire facial expressions and voice data of its members in real time. It uses camera footage and microphone audio as input to identify the emotional state of each member, and then sends this modeled emotion data to the server.

[0599] Step 3:

[0600] The server uses the TensorFlow library to analyze the received emotion data. It processes the emotion data as input and performs data calculations to quantify the emotional state of the members. This quantified data is used to adjust the evaluation criteria.

[0601] Step 4:

[0602] The server uses the pandas library to integrate work result data and sentiment data, and formats it into a format that is easy to analyze. This allows for the extraction of all the information necessary for feedback. The formatted data is then used as the basis for the next step in generating the evaluation report.

[0603] Step 5:

[0604] The server generates an evaluation report based on the formatted data. Using integrated data as input, it generates a comprehensive evaluation based on the members' work performance and emotional state. This evaluation includes specific feedback for improving member performance.

[0605] Step 6:

[0606] Users receive evaluation reports through their smartphones or smart glasses displays. This information is framed in a way that is easy for members to understand and accept. Members can then review their own work processes based on the feedback.

[0607] 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.

[0608] 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.

[0609] 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.

[0610] [Fourth Embodiment]

[0611] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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".

[0624] This invention relates to an evaluation system using AI technology for fairly evaluating employees' work performance. In the embodiment of the invention, a server-centered system is constructed, and processes are performed to collect and evaluate employees' work performance.

[0625] Data collection and integration

[0626] The server automatically collects data on each employee's work activities from various business support systems. The data used includes project progress, working hours, and deliverable quality information. This data is integrated into a database and organized by employee using their ID.

[0627] Generation of evaluation criteria

[0628] The AI ​​agent dynamically generates evaluation criteria using generative AI based on collected data. This establishes objective and unified evaluation standards.

[0629] Evaluation of work results

[0630] The AI ​​agent uses generated evaluation criteria to analyze each employee's work performance using a smart algorithm. This calculates a score indicating each employee's contribution. This score is composed of various aspects such as work quality, efficiency, and productivity.

[0631] Reporting results and obtaining feedback

[0632] The resulting scores and analysis results are generated as a report and presented to administrators and those being evaluated, along with compelling evidence. Feedback is collected from users via terminals, and improvement suggestions are made, thereby promoting continuous improvement of the system.

[0633] System update

[0634] Based on the collected feedback, the server updates its evaluation criteria and analysis algorithms, reflecting these changes in the next evaluation. This process allows the system to adapt to the organization's needs and changes in the external environment, ensuring that it continues to provide fair evaluations over the long term.

[0635] Through these processes, fair and transparent employee evaluations can be achieved, leading to improved employee motivation and productivity. For example, project progress data is collected in a timely manner, and the results are used to visualize employees' contributions to their work, ensuring transparency and fairness in evaluations.

[0636] The following describes the processing flow.

[0637] Step 1:

[0638] The server automatically collects employee work data from project management and time management systems via APIs. In particular, it retrieves task completion status, work time, and deliverable quality metrics, and stores them in a database.

[0639] Step 2:

[0640] The server formats the collected data and converts it into an analyzable format. During this process, it detects and cleans up duplicate and missing data. Employee-specific work data is then integrated into a database based on unique IDs.

[0641] Step 3:

[0642] The AI ​​agent uses generative AI to dynamically generate evaluation criteria based on formatted data. These criteria include elements such as quality, efficiency, and productivity, and each element is weighted accordingly.

[0643] Step 4:

[0644] The AI ​​agent analyzes each employee's work output by applying predefined evaluation criteria. Based on these criteria, it calculates productivity and quality scores, and derives an overall evaluation result.

[0645] Step 5:

[0646] The server generates a detailed evaluation report based on the analysis results. The report includes each employee's evaluation score, strengths of performance, and areas for improvement, presented in a visually easy-to-understand format.

[0647] Step 6:

[0648] Users (administrators and employees) can view evaluation reports through their terminals and see their own evaluations and feedback within the report. They can also provide feedback and make improvement suggestions as needed.

[0649] Step 7:

[0650] Based on feedback from users, the server's AI agent updates its evaluation criteria and algorithms. Adjustments are made to ensure a fairer and more transparent evaluation for the next assessment.

[0651] (Example 1)

[0652] 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".

[0653] Fair and objective evaluation of employee performance is crucial for improving organizational efficiency, but traditional evaluation methods can be susceptible to human bias and lack of transparency. There is a need to address these issues and provide accurate and transparent evaluations.

[0654] 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.

[0655] In this invention, the server includes means for collecting information on each employee's work activities, means for generating dynamic evaluation criteria based on the collected information using a generative AI model, and means for analyzing work results using a smart algorithm and calculating a contribution score. This improves the objectivity and transparency of evaluations and enables fair employee evaluation within the organization.

[0656] "Employee" refers to an individual person who belongs to an organization and performs business activities.

[0657] "Information related to business activities" refers to all data related to the performance of employees' work, such as project progress, working hours, and quality data of deliverables generated during work.

[0658] A "generative AI model" refers to artificial intelligence technology used to generate dynamic and objective evaluation criteria based on collected information.

[0659] "Dynamic evaluation criteria" refer to standards for evaluating employee work activities that are constructed by a generated AI model using collected information, and have the characteristic of being flexibly changed according to the situation.

[0660] A "smart algorithm" refers to an advanced computational method that uses dynamically generated evaluation criteria to analyze employee work performance and calculate a contribution score.

[0661] A "contribution score" refers to an indicator that quantifies an employee's contribution by comprehensively evaluating their work performance.

[0662] "Reporting materials" refer to documents created to document evaluation results and analysis content and to present them to employees and managers.

[0663] "Feedback" refers to user reactions and opinions on the presented evaluation results, and is used to improve the evaluation process.

[0664] "Analysis method" refers to the techniques and processes used to evaluate information about collected business activities.

[0665] In this system, the server connects to multiple business support systems to efficiently collect information on each employee's work activities. This allows it to obtain project progress data, work hours, and deliverable quality information from project management tools and time management tools. This data is essential for evaluating work performance.

[0666] The server integrates the collected information into the organization's database and organizes it by employee. This organization utilizes unique IDs, allowing for centralized management of the information and conversion into a format suitable for analysis. This improves data integrity and analytical efficiency.

[0667] The server uses a generative AI model to dynamically generate evaluation criteria from collected information. A generation prompt such as "Extract the characteristics of successful projects from the previous quarter and create new evaluation criteria based on them" can be used. This prompt allows the AI ​​to analyze past successes and generate appropriate evaluation metrics.

[0668] The smart algorithm uses dynamically generated evaluation criteria within the server to analyze work outcomes in detail. This analysis scores each employee's contribution, enabling fair evaluation within the organization. Scoring is performed from multiple perspectives, including work quality, efficiency, and productivity.

[0669] The server automatically generates reports based on the analysis results and presents them to administrators and employees via terminals. These reports clearly show the evaluation results and their rationale, ensuring highly convincing feedback.

[0670] The terminal receives feedback from users and sends it back to the server. The server updates the evaluation criteria and analysis methods based on the collected feedback and incorporates them into the next evaluation process. This cyclical process allows the evaluation system to continuously adapt flexibly to changes within the organization.

[0671] These operations are expected to enable transparent and fair employee evaluations, thereby improving overall organizational efficiency and motivation.

[0672] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0673] Step 1:

[0674] The server collects information about each employee's work activities from business support systems. Inputs include data from project management tools and time management tools. The server retrieves data in real time or periodically through interfaces such as APIs. This information collection accumulates the necessary data in the company's database. The output is the raw data stored in the database.

[0675] Step 2:

[0676] The server organizes the collected information and converts it into a format that is easy to analyze. The input is the raw data collected in step 1. The server classifies the data by employee ID and unifies the data structure. This formatting process generates a dataset optimized for analysis. The output is the integrated dataset.

[0677] Step 3:

[0678] The server generates evaluation criteria using a generative AI model. The input consists of a formatted dataset and a predefined prompt. For example, a prompt such as "Extract success characteristics from past quarters and create new evaluation criteria" might be used. The server runs the AI ​​model to build dynamic evaluation criteria. The output is a set of evaluation criteria.

[0679] Step 4:

[0680] The server uses a smart algorithm to evaluate work performance. Inputs include a set of evaluation criteria and a formatted dataset. The server analyzes each employee's data based on the criteria and calculates a contribution score. This analysis uses performance quality, efficiency, and productivity as evaluation indicators. The output is each employee's contribution score.

[0681] Step 5:

[0682] The server generates a report using contribution scores. The inputs are contribution scores and evaluation criteria. The server sets the report format and creates a document containing data demonstrating the validity of the scores and criteria. The output is the report.

[0683] Step 6:

[0684] The terminal displays the generated report to administrators and employees. The input is the report created in step 5. The terminal displays the document on a display device and notifies relevant parties of the detailed evaluation results. The output is the displayed report.

[0685] Step 7:

[0686] Users provide feedback based on the report. The input is the evaluation results described in the report. Users frequently send back their opinions and suggestions for improvement regarding the evaluation. This feedback is used in subsequent processes. The output is the feedback sent to the server.

[0687] Step 8:

[0688] The server updates evaluation criteria and analysis methods based on collected feedback. The input is user feedback. The server analyzes the feedback and revises evaluation criteria and adjusts smart algorithms. The output is an optimized evaluation system for the next evaluation process.

[0689] (Application Example 1)

[0690] 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".

[0691] Fair and efficient evaluation of the performance of work equipment used in industrial facilities is a crucial issue for improving product quality and productivity. Conventional methods are prone to subjective human evaluation and lack clear evaluation criteria, making it difficult to accurately grasp the performance of work equipment and provide optimal feedback and improvement suggestions.

[0692] 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.

[0693] In this invention, the server includes means for collecting the activity results of each work device, means for evaluating the activity results based on generated evaluation criteria and generating a score, and means for generating the evaluation results as a report document. This enables objective evaluation of the work device's activity and fair scoring. Furthermore, it is possible to dynamically update the evaluation criteria based on user feedback and provide improvement suggestions to maintain optimal work efficiency and quality at all times.

[0694] "Work equipment" refers to devices that automatically perform specific tasks in industrial facilities.

[0695] "Activity results" refers to the collective data that shows the results and performance of work performed by the work equipment.

[0696] "Evaluation criteria" are standards or standards predetermined for objectively evaluating the performance of work equipment.

[0697] A "score" is a numerical value that quantifies the performance of work equipment based on evaluation criteria.

[0698] A "report document" is a document that describes the results of the evaluation and the analysis, and is presented to the user.

[0699] "Feedback" refers to information such as opinions and suggestions for improvement received from users.

[0700] To implement this invention, a system is needed to monitor and evaluate work equipment within a factory. The system collects the activity results of the work equipment, analyzes the activity results using evaluation criteria, and generates evaluation results.

[0701] The server automatically collects data from work equipment operating in industrial facilities. The hardware used is the work equipment itself, and the software used includes TensorFlow, a platform for data processing and analysis. The data includes work time, operational efficiency, and quality indicators. Once the data is collected, the server formats it into a suitable format for analysis and dynamically generates evaluation criteria.

[0702] A generative AI model is used to generate evaluation criteria. The server then assigns a score to the activity output of each piece of equipment based on the generated evaluation criteria. This scoring ensures a fair and objective evaluation.

[0703] The evaluation results are automatically generated as a report document and presented to the administrator's terminal. Through the terminal, users can provide feedback on the displayed scores and analysis results. This collected feedback is then used to update the evaluation criteria for future evaluations.

[0704] As a concrete example, in a certain factory, a screw assembly machine operates 24 hours a day, and the operational data during that time is accumulated on a server. The data includes the time and accuracy required for assembly, and AI analyzes this data. In some cases, the system may suggest improvement plans based on best practices.

[0705] An example of a prompt might be, "Please tell me what data should be considered in order to dynamically generate evaluation criteria for work equipment." This prompt clarifies information that is important for determining criteria in an AI model.

[0706] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0707] Step 1:

[0708] The server collects activity result data from work equipment within the factory. It receives operational data from each piece of equipment (e.g., work time, operational efficiency, quality indicators) as input. This data is collected by the server via IoT devices and stored in a database. The output is raw, unformatted data.

[0709] Step 2:

[0710] The server formats the collected data and converts it into a format that is easy to analyze. The input is the collected raw data. This data is then cleansed and normalized and converted into the required format. The output is formatted, analyzable data. Specific operations include handling missing values ​​and detecting outliers.

[0711] Step 3:

[0712] The server dynamically generates evaluation criteria using a generative AI model. The input is formatted data. Based on this input, the generative AI model applies machine learning algorithms to generate evaluation criteria used for scoring work equipment. The output is the evaluation criteria themselves. During training of the generative AI model, the prompt "What data should be considered to generate criteria for evaluating the activity results of work equipment?" is used.

[0713] Step 4:

[0714] The server evaluates activity outcomes based on generated evaluation criteria and generates scores. Inputs are evaluation criteria and formatted data. Based on these inputs, the server performs scoring based on efficiency, quality, and other key performance indicators. Outputs are scores representing the activity outcomes of each work machine. Specifically, it calculates indices for time and accuracy in each work process.

[0715] Step 5:

[0716] The user's terminal displays the evaluation results sent from the server as a report document. The input consists of the generated score and the evaluation result. These are documented and output through the terminal's interface so that administrators can view and understand them. Specific actions include graphing the score and displaying comparison results.

[0717] Step 6:

[0718] Using a terminal, users provide feedback on the evaluation results. Input consists of user opinions and suggestions for improvement. This feedback is sent to the server for later updating of the evaluation criteria. Output is the data used as adjustment material during the update process.

[0719] Step 7:

[0720] The server updates the evaluation criteria based on the collected feedback and uses this for the next scoring. The input is the feedback information. Based on this, the AI ​​system is retrained and the evaluation criteria are fine-tuned. The output is the updated evaluation criteria. Specifically, this includes actions such as changing the weighting of the evaluation criteria according to the feedback.

[0721] 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.

[0722] This invention provides a system for fairly evaluating employee performance that incorporates an emotion engine to recognize user emotions, thereby enabling more appropriate evaluation feedback and adjustment of evaluation criteria. A server at the center of the system collects work data from each employee, and an AI agent dynamically generates evaluation criteria using the information stored in the database.

[0723] Introducing emotion recognition

[0724] The device uses emotion recognition technology to collect emotional data, such as facial expressions and voice tone, while the user is viewing the evaluation report. The emotion engine analyzes this data to identify the user's emotional state.

[0725] Feedback optimization

[0726] The emotional information recognized by the emotion engine is analyzed in conjunction with the user's feedback. Based on this information, the server dynamically adjusts the evaluation report and presents it in a way that best suits the user's emotional state. This makes the evaluation more readily accepted and results in more effective feedback.

[0727] Adjustment of evaluation criteria

[0728] The server flexibly adjusts evaluation criteria based on collected feedback and sentiment data. The AI ​​agent updates the criteria for the next evaluation, taking sentiment analysis results into consideration. This process reflects changes in the organization's culture and motivation, resulting in adaptive and continuous improvement.

[0729] As a concrete example, the server evaluates data obtained from the project management system, and the emotion engine improves the evaluation criteria based on the feedback received. If a user expresses negative emotions, the system analyzes the reasons and obtains suggestions for making the evaluation criteria fairer.

[0730] By incorporating an emotional engine in this way, evaluation systems can achieve a more flexible and user-friendly evaluation process while maintaining fairness. This can enhance trust throughout the organization and improve employee motivation and productivity.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] The server collects employee work data from project management tools and other related systems via APIs. This data includes the time taken to complete tasks, project progress, and deliverable quality metrics.

[0734] Step 2:

[0735] The server formats the collected data into an analyzable format. It performs data cleaning to remove duplicates and missing data, and integrates it into a database using a unique ID for each employee.

[0736] Step 3:

[0737] An AI agent dynamically generates evaluation criteria based on formatted data. This process utilizes generative AI to include elements such as quality, efficiency, and productivity in the evaluation criteria, and assigns appropriate weights to each element.

[0738] Step 4:

[0739] The device uses emotion recognition technology to collect data such as the user's facial expressions and voice tone when the user views the evaluation report.

[0740] Step 5:

[0741] The emotion engine analyzes collected emotion data to determine the user's emotional state. This allows it to quantify how the user feels about the evaluation.

[0742] Step 6:

[0743] The server integrates emotion recognition data with user feedback to optimize and display the evaluation report. In this process, it selects a display method that aligns with the user's emotions, ensuring that the evaluation results are appropriately received.

[0744] Step 7:

[0745] Users provide feedback based on the evaluation report provided, sending their opinions and suggestions for improvement regarding their evaluation via their device.

[0746] Step 8:

[0747] The server's AI agent flexibly adjusts evaluation criteria based on user feedback and sentiment data. This improves the system to establish fairer and more effective evaluation criteria for future assessments.

[0748] (Example 2)

[0749] 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".

[0750] Conventional evaluation systems often evaluated employees based solely on their work performance, without considering their emotional state. As a result, evaluation results were not properly communicated, potentially leading to decreased employee motivation and performance. This invention aims to solve these problems and provide a system that offers fair and highly acceptable evaluations.

[0751] 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.

[0752] In this invention, the server includes means for acquiring information about work activities, means for evaluating work activities based on generated evaluation criteria and creating indicators, and means for identifying the emotional state of users. This enables adaptive evaluation that takes into account the emotions of individual employees.

[0753] "Information related to business activities" refers to all data generated or acquired by employees in the course of performing their duties, and specifically includes project progress information and task completion status.

[0754] "Evaluation criteria" refer to the indicators and conditions used to measure and evaluate employees' work activities, and individual work performance is calculated based on these criteria.

[0755] "Means for creating indicators" refers to methods or devices for quantifying or categorizing employee performance based on acquired information about work activities.

[0756] "Reactions" refer to feedback such as emotions and opinions expressed by employees when they receive their evaluation results.

[0757] "Means for identifying emotional states" refers to technologies, methods, or devices for detecting an employee's emotions at any given time based on their facial expressions, tone of voice, etc.

[0758] "Means of dynamically adjusting documents" refers to technologies and methods for modifying and optimizing the content of evaluation reports and other documents in real time based on the user's emotional state.

[0759] Embodiments for carrying out this invention are described below.

[0760] The server first retrieves information about work activities from an external data management device. This information includes employee project progress and completed tasks. The server stores this information in a database and prepares it for processing. The server also uses a generative AI model to generate evaluation criteria for assessing employee activities from this data. These criteria are dynamically updated to provide a fairer and more adaptive evaluation.

[0761] The terminal uses a camera and microphone to sense the user's facial expressions and voice tone in real time when displaying evaluation reports. The data acquired from these devices is analyzed using emotion recognition software to identify the user's emotional state. The emotion engine detects the user's positive or negative responses in real time and sends the results to the server.

[0762] After the user's response is identified by the emotion engine, the server dynamically adjusts the content of the evaluation report. This process utilizes user emotion data and generative AI models to optimize the evaluation document, making it more acceptable and eliciting positive feedback. As a concrete example, an example of a prompt might be, "Suggest ways to adjust the feedback to improve the user's negative emotions."

[0763] As described above, this invention provides a flexible and adaptive evaluation system that takes into account the emotional state of employees, thereby increasing trust within the organization and improving employee motivation and productivity.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] The server retrieves information about business activities from an external data management device. This input includes employee project progress and task completion information. The server formats this data and stores it in a database. This ensures that the information is maintained in a unified format, making subsequent processing easier.

[0767] Step 2:

[0768] The device uses its camera and microphone to collect facial expressions and voice tone while the user is viewing the evaluation report. This input data is analyzed by emotion recognition software within the device. This analysis outputs an emotional state indicating how the user is reacting to the displayed content.

[0769] Step 3:

[0770] The server receives emotion data from emotion recognition software and uses it to further analyze user feedback. It detects specific influencing factors and sends prompt messages to the generating AI model. An example of such a prompt message is, "Suggest ways to adjust the feedback to improve the user's negative emotions." The report content is updated based on the feedback adjustment suggestions output by the generating AI model.

[0771] Step 4:

[0772] Users view an evaluation report that includes emotional information and feedback adjustments. This report, dynamically adjusted by the server, is presented in a way that users can easily understand and accept the evaluation. This enables feedback that takes users' emotions into consideration, thereby improving employee motivation.

[0773] Step 5:

[0774] The server integrates all feedback and sentiment data and updates the evaluation criteria. In this process, an AI algorithm calculates which criteria are fairer based on the collected data. As a result, new evaluation criteria are generated and stored in the database. This iterative process continuously optimizes the system.

[0775] (Application Example 2)

[0776] 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".

[0777] In evaluating the work results of team members, conventional evaluation methods fail to take into account the emotions and stress levels of the members, resulting in inaccurate and fair evaluations. Furthermore, because the feedback is not provided in a way that is easily accepted by the members, there is a challenge in that the evaluation results do not easily lead to increased motivation or productivity among the members.

[0778] 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.

[0779] In this invention, the server includes means for collecting the work results of each member, means for collecting emotional data of the members using emotion recognition technology, and means for dynamically adjusting evaluation criteria based on the collected emotional data and providing feedback based on emotional state. This enables fair and emotionally sensitive evaluations, and the evaluation results can effectively lead to improved motivation and productivity among members.

[0780] "Members" refer to individuals who are responsible for specific roles or tasks within an organization or facility.

[0781] "Work results" refers to the outcomes of the tasks and activities performed by the members, as well as the content of the completed activities.

[0782] "Evaluation criteria" refers to a set of indicators or rules used to evaluate work results.

[0783] "Emotion recognition technology" refers to technology that identifies an individual's emotional state by analyzing their facial expressions and voice.

[0784] "Emotional data" refers to data that indicates the emotional state of the members, and is information generated by emotion recognition technology.

[0785] "Feedback" refers to evaluation results and advice provided to members, and is information aimed at improving subsequent behavior and increasing motivation.

[0786] A "server" refers to a computer system that provides services and data over a network and processes requests from multiple users or clients.

[0787] The system for realizing this application provides a series of processes for collecting and evaluating the work results of each member. The server collects work result data from each terminal connected to the network and further analyzes the collected emotional data using emotion recognition technology. This system is responsible for dynamically adjusting the evaluation criteria to take into account the emotional state of the members and generating optimal feedback.

[0788] The server implements an emotion recognition model using the Python programming language and machine learning libraries such as TensorFlow. This allows it to analyze members' facial and voice data in real time to understand their emotional states. The analyzed emotion data is then formatted using the pandas library and used to refine evaluation criteria.

[0789] Users access this system through devices such as smartphones and smart glasses to view the generated reports. Feedback is provided in a way that takes into account the receptiveness of the members, enabling more effective evaluations. This allows organizations to improve the work efficiency of their members and support their emotional well-being.

[0790] A concrete example of this system is the staff of a nursing care facility. The server monitors the emotional state of the facility's staff during the day and suggests adjustments to break times and reassignments of tasks based on their stress levels. This reduces stress for the staff and enables them to provide higher quality care to the residents.

[0791] An example of a prompt for a generative AI model would be: "We want to develop a system for evaluating the emotions of staff in a nursing home. Please tell us how to create a system that can recognize the emotions of staff members in real time while they are interacting with residents and provide feedback to adjust the criteria for performance evaluation."

[0792] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0793] Step 1:

[0794] The server collects work result data from each member's terminal via the network. It receives data such as work details, time, and completion status as input, and stores this data in a database, making it possible to track the performance of each member.

[0795] Step 2:

[0796] The terminal uses emotion recognition technology to acquire facial expressions and voice data of its members in real time. It uses camera footage and microphone audio as input to identify the emotional state of each member, and then sends this modeled emotion data to the server.

[0797] Step 3:

[0798] The server uses the TensorFlow library to analyze the received emotion data. It processes the emotion data as input and performs data calculations to quantify the emotional state of the members. This quantified data is used to adjust the evaluation criteria.

[0799] Step 4:

[0800] The server uses the pandas library to integrate work result data and sentiment data, and formats it into a format that is easy to analyze. This allows for the extraction of all the information necessary for feedback. The formatted data is then used as the basis for the next step in generating the evaluation report.

[0801] Step 5:

[0802] The server generates an evaluation report based on the formatted data. Using integrated data as input, it generates a comprehensive evaluation based on the members' work performance and emotional state. This evaluation includes specific feedback for improving member performance.

[0803] Step 6:

[0804] Users receive evaluation reports through their smartphones or smart glasses displays. This information is framed in a way that is easy for members to understand and accept. Members can then review their own work processes based on the feedback.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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."

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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 to be incorporated by reference.

[0826] The following is further disclosed regarding the embodiments described above.

[0827] (Claim 1)

[0828] A means of collecting the work results of each employee,

[0829] A means for evaluating work performance and generating a score based on generated criteria,

[0830] A means of generating evaluation results as a report,

[0831] A means of collecting feedback and updating evaluation criteria,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, comprising means for formatting collected work results and converting them into a format that is easy to analyze.

[0835] (Claim 3)

[0836] The system according to claim 1, further comprising means for displaying the generated report on a display device and receiving feedback from the user thereon.

[0837] "Example 1"

[0838] (Claim 1)

[0839] Means for collecting information on the work activities of each employee,

[0840] A means for generating dynamic evaluation criteria based on collected information using a generative AI model,

[0841] A method for analyzing work results using a smart algorithm and calculating a contribution score,

[0842] A means of generating and presenting evaluation results and analyses as report materials,

[0843] A means of collecting user feedback on the presented evaluation results and revising the evaluation criteria and analysis methods based on that feedback,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, comprising means for formatting collected information on business activities and converting it into a format that is easy to analyze.

[0847] (Claim 3)

[0848] The system according to claim 1, further comprising means for displaying generated report materials on a display device and receiving user feedback thereon.

[0849] "Application Example 1"

[0850] (Claim 1)

[0851] A means of collecting the activity results of each piece of work equipment,

[0852] A means for evaluating activity outcomes and generating scores based on generated evaluation criteria,

[0853] A means of generating evaluation results as a report document,

[0854] A means of collecting user feedback and updating evaluation criteria,

[0855] A means for dynamically generating criteria for analyzing collected activity results,

[0856] A means of evaluating the efficiency and quality of work equipment based on the analyzed evaluation criteria and proposing optimizations,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, comprising means for formatting collected activity results and converting them into a format that facilitates evaluation.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for displaying the generated report document on a display device and receiving user feedback obtained therefrom.

[0862] "Example 2 of combining an emotion engine"

[0863] (Claim 1)

[0864] Means of obtaining information related to business activities,

[0865] A means of evaluating business activities and creating indicators based on generated evaluation criteria,

[0866] Means for creating evaluation results as a document,

[0867] Means for collecting responses and adjusting evaluation criteria,

[0868] A means of identifying the emotional state of the user,

[0869] A means of dynamically adjusting a document based on emotional state,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising means for processing acquired information on business activities and converting it into a format that is easy to analyze.

[0873] (Claim 3)

[0874] The system according to claim 1, further comprising means for displaying the created document on a display device and receiving a response from the user thereto.

[0875] "Application example 2 when combining with an emotional engine"

[0876] (Claim 1)

[0877] A means of collecting the work results of each member,

[0878] A means for evaluating work results and generating indicators based on generated criteria,

[0879] A means of generating evaluation results as a report,

[0880] A means of collecting emotional data of members using emotion recognition technology,

[0881] A means of dynamically adjusting evaluation criteria based on collected emotional data and providing feedback based on emotional state,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, comprising means for formatting collected work results and converting them into a format that is easy to analyze.

[0885] (Claim 3)

[0886] The system according to claim 1, further comprising means for displaying the generated report on an output device and receiving feedback from the user thereon. [Explanation of Symbols]

[0887] 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

1. A means of collecting the activity results of each piece of work equipment, A means for evaluating activity outcomes and generating scores based on generated evaluation criteria, A means of generating evaluation results as a report document, A means of collecting user feedback and updating evaluation criteria, A means for dynamically generating criteria for analyzing collected activity results, A means of evaluating the efficiency and quality of work equipment based on the analyzed evaluation criteria and proposing optimizations, A system that includes this.

2. The system according to claim 1, comprising means for formatting collected activity results and converting them into a format that facilitates evaluation.

3. The system according to claim 1, further comprising means for displaying the generated report document on a display device and receiving user feedback obtained therefrom.

Images