system

Abstract

We provide the system. [Solution] Means for collecting work information, opinion data, and health information, Means for preprocessing the collected data, A generative AI module that calculates the degree of employee involvement using the aforementioned preprocessed data, A means of issuing a warning when the calculated level of involvement falls below the standard value, A means of proposing corrective measures based on the aforementioned warning, A means for visualizing the degree of involvement and the proposed improvement measures, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With the spread of remote work and diverse workstyles, it has become difficult to uniformly grasp and manage the degree of employee engagement within an organization. As a result, it has become an issue to detect early on employees' dissatisfaction and productivity decline and take appropriate measures before problems become apparent. Also, it is required to identify specific signs and causes of the decline in the degree of engagement and promptly propose effective improvement measures. A system is needed to solve these problems and improve collaboration and productivity within the organization.

Means for Solving the Problems

[0005] This invention utilizes a generative AI module that collects work information, opinion data, and health information, and preprocesses this data to calculate the degree of employee engagement. If the calculated engagement level falls below a certain threshold, it immediately issues a warning and provides means to propose specific improvement measures such as workload reallocation, vacation suggestions, and improved health management. Furthermore, by visualizing the engagement level and proposed improvement measures, the invention effectively solves the above-mentioned problems by enabling HR personnel and managers to understand the situation in real time and take appropriate action.

[0006] "Work information" refers to data related to employees' working hours and job duties.

[0007] "Opinion data" refers to information including feedback and survey results collected from employees.

[0008] "Health information" refers to data related to employees' health status and lifestyle habits.

[0009] "Preprocessing" refers to the process of cleaning and formatting collected data to make it suitable for analysis.

[0010] A "generative AI module" refers to a software component that uses artificial intelligence technology to analyze data and calculate specific information or scores.

[0011] "Level of involvement" refers to an indicator that shows the degree of commitment and proactiveness that employees have towards the organization.

[0012] A "warning" refers to a notification or alert that informs you of a potential problem.

[0013] "Improvement measures" refer to specific actions or strategies proposed to solve a particular problem.

[0014] "Visualization" refers to the process of visually displaying numerical data and analysis results in the form of graphs, charts, and other visual media. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0016] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] 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.

[0019] 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.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] In this embodiment of the invention, the system for managing employee engagement levels operates on a cloud-based platform. The system primarily consists of servers, terminals, and users.

[0037] First, the server automatically collects data from related systems through APIs for aggregating work information, opinion data, and health information. The server then performs preprocessing on this collected data, such as data cleaning and normalization, to convert it into a format suitable for analysis.

[0038] Next, the server inputs the pre-processed data into the generating AI module, which calculates the level of involvement of each employee in real time. Based on a model derived from past data, the generating AI module analyzes the employee's work patterns, feedback content, health status, etc., and dynamically evaluates the level of involvement.

[0039] Furthermore, if the calculated level of involvement falls below a pre-set threshold, the server immediately issues a warning and suggests optimal improvement measures. These include suggestions for task redistribution, vacation time, and introductions to health management support programs. This information is automatically generated and provides specific strategies to mitigate the decline in involvement.

[0040] The device provides a dashboard accessible to staff and administrators. The dashboard on the device visually displays changes in engagement levels, deviations from baseline values, and suggested improvement measures, making it easy for users to intuitively understand the situation.

[0041] Finally, users (primarily HR personnel and managers) can use the device's dashboard to monitor the level of engagement of the entire team or individual employees in real time, plan feedback sessions as needed, and enhance communication with employees.

[0042] As a concrete example, suppose a team member working on a project is detected to have decreased engagement based on recent work data. Based on the relevant data, the server suggests reducing the employee's task load and conducting weekly one-on-one meetings. These suggestions and the engagement score are prominently displayed on the terminal's dashboard, allowing the user to take quick action based on them.

[0043] Thus, the system of the present invention can improve employee engagement through a data-driven approach and support the creation of a more comfortable working environment within an organization.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server automatically collects data via APIs from systems such as work management systems, project management tools, feedback platforms, and health management systems. This allows for centralized collection of daily work hours, project progress, employee feedback, and health-related data.

[0047] Step 2:

[0048] The server performs data cleaning on the collected raw data. This involves imputing missing values, detecting and removing outliers, and normalizing the data into an analyzable format to generate a high-quality dataset.

[0049] Step 3:

[0050] The server inputs pre-processed data into a generating AI module. The AI ​​module, having learned from past data, calculates the level of involvement for each employee. This process runs in real time, and the score is constantly updated based on the latest information.

[0051] Step 4:

[0052] The server compares the calculated involvement score to a baseline value. If the score falls below the baseline, it predicts a problem and triggers an early warning. At the same time, a detailed analysis is performed to identify the cause of the score drop.

[0053] Step 5:

[0054] The server automatically generates effective improvement measures based on the cause of the performance degradation. These measures may include adjusting workloads, suggesting vacation time, and implementing health programs. This information is compiled into a proposal document and immediately notified to HR personnel and managers.

[0055] Step 6:

[0056] The terminal visually displays changes in involvement levels, warnings, and suggested improvements via a dashboard used by staff and managers. This information is presented clearly using graphs and charts, enabling users to make quick decisions.

[0057] Step 7:

[0058] Users (HR personnel, administrators) can utilize the dashboard on their devices to view real-time data and, if necessary, schedule meetings or feedback sessions with employees to quickly implement corrective measures.

[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] There is a growing need to improve productivity and a better work environment within organizations by appropriately evaluating employee engagement and proposing improvement measures early on. However, traditional methods often involve manual data collection and analysis, making real-time responses difficult. Furthermore, the evaluation of engagement may not be sufficiently precise, sometimes resulting in the inability to propose appropriate improvement measures.

[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 activity data, means for organizing the collected information, and a generating AI module that calculates the degree of worker involvement using the organized information. This makes it possible to evaluate the degree of involvement within an organization in real time and to quickly propose appropriate improvement measures.

[0064] "Activity data" refers to information related to work, such as employee work status, feedback, and health information.

[0065] "Preparation" refers to the process of performing preprocessing such as data cleaning and normalization on collected information and converting it into an analyzable format.

[0066] The "Generative AI Module" refers to a function that uses AI technology modeled based on past data to evaluate and calculate the degree of employee involvement.

[0067] A "benchmark value" refers to a standard or target value used when evaluating the degree of employee engagement, and this value is used to determine whether improvement is necessary.

[0068] "Means of notification" refers to a system for sending warnings to managers or responsible persons when the level of involvement falls below a certain threshold.

[0069] "Improvement measures" refer to specific actions taken to increase employee engagement.

[0070] "Means of presentation" refers to methods of visually displaying the degree of involvement and improvement measures so that managers and staff can review them.

[0071] The term "administration screen" refers to an interface that displays collected data and analysis results, allowing administrators to easily access and review them.

[0072] "Means of planning dialogue" refers to how users can set up feedback sessions and meetings to enhance communication with employees.

[0073] This invention is an information processing system for managing employee engagement levels, and it operates in a cloud-based environment. The system mainly consists of servers, terminals, and users.

[0074] The server has the functionality to collect activity data from internal and external data sources within the company, obtaining work status, feedback, and health information via APIs. This data collection process is automated, primarily using digital communication technology, and is performed regularly every day.

[0075] Next, the server organizes the collected information. Specifically, it uses the Python Pandas library to perform data cleaning and normalization, and converts the data into a format suitable for analysis.

[0076] Subsequently, the server inputs the compiled information into a generative AI model, which evaluates each employee's level of involvement in real time. This generative AI module is built using TENSORFLOW® and utilizes a model based on historical data to calculate employee involvement based on their work patterns and feedback content.

[0077] If the calculated level of involvement falls below a predetermined threshold, the server has a function to immediately notify the responsible person, for example, using the Slack API. Furthermore, it also has a means of suggesting improvement measures, and the server will present individually tailored improvement plans.

[0078] The device provides a user-accessible administration screen. Using React.js, a visual interface is built to visually display involvement levels and improvement suggestions. This administration screen is designed to be intuitively understandable to users.

[0079] Finally, users (primarily HR personnel and managers) can monitor employee engagement levels through the terminal display and plan interactions as needed. For example, prompts can be used with the generated AI model to evaluate engagement levels and suggest appropriate improvement measures. For instance, inputting a prompt such as, "Evaluate employee engagement levels based on the latest work data and suggest appropriate improvement measures if the level falls below the threshold," can yield appropriate output.

[0080] This system makes it easier to increase engagement within the organization and strengthen communication with employees.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server collects activity data, including various types of data such as work information, feedback, and health information. As input, the server retrieves necessary data from relevant systems via APIs. The output is the collected raw data, which is stored in a dedicated database. Specifically, the server calls the API at a designated time each day to automatically retrieve new information.

[0084] Step 2:

[0085] The server preprocesses the collected data. It uses the raw data obtained in Step 1 as input. Here, data cleaning and normalization are performed to prepare the data for analysis. The output is a clean and consistent dataset. Specifically, the Python Pandas library is used to handle missing and outlier values ​​and to format the data frame.

[0086] Step 3:

[0087] The server inputs the prepared data into a generating AI model to calculate the level of involvement. The input is the data preprocessed in step 2. As part of the process, the AI ​​model analyzes the data and evaluates the level of involvement for each employee in real time. The output is the level of involvement score for each employee. Specifically, a model trained using TensorFlow calculates these scores and generates the results in JSON format.

[0088] Step 4:

[0089] The server will issue a warning to the person in charge if the calculated level of involvement falls below a certain threshold. The involvement score from step 3 is used as input. The process will trigger an alert if the level falls below a specific threshold. The output is a notification message. Specifically, the warning is sent in real time via the Slack API.

[0090] Step 5:

[0091] The server proposes the optimal improvement measures based on the involvement score. It references the evaluation data from Step 3 as input. During processing, the AI ​​generates appropriate countermeasures and presents feasible improvements. The output is the specific improvement measures. In terms of action, the server sends the generated improvements to the terminal and provides actionable instructions.

[0092] Step 6:

[0093] The terminal provides visualization through the management screen. The input is the information generated in steps 4 and 5. Here, the engagement score and suggested improvement measures are displayed on the dashboard. The output is a visually organized management screen. Specifically, an interface using React.js is used to update and display information to the user in real time.

[0094] Step 7:

[0095] Users monitor data through the administration panel and plan interactions as needed. They refer to the information displayed in step 6 as input. During processing, they plan communication with employees based on the displayed improvement suggestions. The output is an action plan, such as a specific feedback session. As concrete actions, users schedule meetings in Google Calendar based on the information and implement feedback and improvement suggestions.

[0096] (Application Example 1)

[0097] 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."

[0098] Machine malfunctions and inefficient operation in production facilities reduce the overall efficiency of the manufacturing process, ultimately undermining a company's competitiveness. To address these problems, it is necessary to accurately and in real time evaluate the operating status of machinery and to quickly implement necessary improvements. However, conventional systems have the problem of taking too long to monitor the state of machinery and detect abnormalities, resulting in a lack of appropriate corrective measures.

[0099] 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.

[0100] In this invention, the server includes means for collecting operational information, environmental data, and machine status data; means for preprocessing the collected data; and a generating AI module for evaluating the machine's operational status using the preprocessed data. This enables real-time analysis of the machine's operational status and allows for rapid response.

[0101] "Operational information" refers to specific data that indicates the operating status of machinery and equipment.

[0102] "Environmental data" refers to information that describes the physical conditions of the environment in which a machine is operating.

[0103] "Machine condition data" refers to information that describes the internal and external condition of a machine.

[0104] "Means of collection" refers to the methods and equipment used to acquire data.

[0105] "Preprocessing means" refers to methods and devices for processing collected data into a format suitable for analysis and use.

[0106] A "generative AI module" is a component used to analyze data and derive results using artificial intelligence.

[0107] "Evaluating the operating state" means determining whether a machine is functioning normally or abnormally, and whether it is operating efficiently.

[0108] "Means of issuing warnings" refers to mechanisms or functions that draw attention when standards are not met.

[0109] "Means of proposing improvement measures" refers to components that show specific methods or actions to resolve the problem.

[0110] "Means of visualization" refer to methods and devices for displaying information and data in a way that is easy for people to understand.

[0111] To implement this invention, three elements—a server, a terminal, and a user—work together to constitute a system.

[0112] The server uses IoT gateways and sensors to collect operational information, environmental data, and machine status data from various machines operating within the factory. The collected data is preprocessed on the server, including data cleaning and normalization. The preprocessed data is then input into a generative AI model to evaluate the machine's operating status in real time. The generative AI model uses a model trained on a large amount of historical data to analyze abnormalities in operation and identify areas for improvement. If an abnormality is detected, the server issues a warning and proposes corrective measures to the user. These corrective measures include readjusting the operating load and suggesting maintenance.

[0113] The terminal functions as a dashboard easily accessible to factory managers and operators. This dashboard provides real-time visualization of machine operating status and improvement suggestions. The software used includes an application structure designed to provide a user-friendly UI interface.

[0114] This dashboard allows users to monitor the situation within the factory and take quick action when necessary. By acting on the suggested improvements, users can optimize machine performance and achieve efficient factory operations.

[0115] For example, if abnormal vibrations are detected in an assembly machine on a particular line, the system will analyze the cause and suggest that there is wear on a part of the machine. Based on this, the user will be advised to replace the part, thereby maintaining the factory's operational efficiency.

[0116] An example of a prompt for a generative AI is, "Based on the latest system data, please suggest the cause of the anomaly and the best course of action." By using this prompt, the generative AI model can perform appropriate analysis and provide effective solutions.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects operational information, environmental data, and machine status data from each machine in the factory using sensors and an IoT gateway. It receives real-time data from machine sensors as input and stores it in cloud storage.

[0120] Step 2:

[0121] The server cleans and normalizes the collected data. This includes denoising the data and imputing missing values. Using the raw data obtained in step 1 as input, it produces well-formed data suitable for analysis as output.

[0122] Step 3:

[0123] The server inputs pre-processed data into a generating AI model. This model is trained on historical data and evaluates the current operating state of the machine. The input is well-formed data, and the output is a machine operation evaluation score and the likelihood of anomalies occurring.

[0124] Step 4:

[0125] The server uses the output of the generated AI model to issue a warning if the machine's operating status falls below a certain threshold. This warning indicates that an anomaly has been detected and that improvement is necessary. The operation evaluation score is used as input, and a warning message is generated as output.

[0126] Step 5:

[0127] The server generates corrective actions based on the warnings. These actions include suggestions for adjusting the operating load and performing component maintenance. The input is the result of the anomaly detection, and the output is a specific corrective action plan.

[0128] Step 6:

[0129] The terminal visualizes the machine's operating status and improvement measures received from the server on a dashboard. This allows administrators to understand the machine's status at a glance. The input is the improvement action plan, and the output is a visual dashboard display.

[0130] Step 7:

[0131] Users can quickly adjust and maintain machinery based on reports and suggestions from the dashboard. This helps maintain the factory's operational efficiency. The input is dashboard information, and the output is the stabilization of machine operation.

[0132] 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.

[0133] In this embodiment of the invention, a system for managing the level of employee engagement operates on a cloud-based platform and consists of three elements: a server, a terminal, and a user.

[0134] The server connects with relevant corporate systems via various APIs to collect employee work information, opinion data, and health information. It also features an emotion engine that uses natural language processing to analyze collected opinion data and recognize employee emotions. This allows for the scoring of emotions, such as positive or negative, and is used to calculate the level of engagement.

[0135] Next, the server inputs the pre-processed data and emotional information obtained from the emotion engine into the generating AI module, which then uses this information to calculate the level of involvement for each employee. In this process, the emotional information is used in particular to weight the opinion data, improving the accuracy of the involvement level calculation.

[0136] If the calculated level of involvement falls below a certain threshold, the server sends an automatically generated warning to HR personnel and managers. The warning then suggests corrective actions such as workload redistribution, vacation suggestions, and improved health management. These corrective actions are individually optimized based on the identified emotional information.

[0137] The device provides an administrator dashboard that displays engagement levels, emotional trends, and suggested improvements in real time. The dashboard is graphically designed, allowing users to intuitively understand the situation and make quick decisions.

[0138] Users (administrators and HR personnel) can leverage the terminal's dashboard to make data-driven decisions and direct specific actions for improvement. Accessing detailed information about each employee, including emotional data, helps provide effective communication and support.

[0139] For example, if negative emotions are frequently detected in an employee's opinion data, indicating a decrease in their level of engagement, the server will detect this and suggest implementing a stress reduction program or individual counseling to that employee. This allows users to quickly understand the problem and take appropriate action.

[0140] Thus, the system of the present invention can accurately evaluate the degree of employee engagement by combining data and emotion recognition, and can support the improvement of the workplace environment.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] The server continuously collects data via APIs from the work management system, feedback collection tools, and health tracking applications. This data includes each employee's work information, submitted feedback, and health indicators. The server ingests this data into a centralized data store.

[0144] Step 2:

[0145] The server performs data cleaning on the collected data. This cleaning includes interpolating missing values, removing invalid data entries, and normalizing the data format. This preprocessing enables analysis with high accuracy.

[0146] Step 3:

[0147] The server activates an emotion engine on the opinion data and uses natural language processing to analyze the sentiment of each comment. The sentiment is scored as positive, negative, or neutral and stored in the data store. This provides a quantitative representation of employees' emotional tendencies.

[0148] Step 4:

[0149] The server inputs pre-processed work information, health information, and scored sentiment information into a generating AI module to calculate each employee's level of involvement. This generating AI module learns from past data and performs precise scoring by evaluating the level of involvement in a multidimensional way.

[0150] Step 5:

[0151] The calculated level of involvement is compared to a baseline value. If the level of involvement falls below the baseline value, the server detects this as an anomaly and issues a warning. The warning includes an analysis of the cause of the decrease in involvement, and immediate action is required to take countermeasures.

[0152] Step 6:

[0153] The server automatically generates suggested improvements based on identified emotional information and the reasons for decreased engagement. These improvements may include, for example, adjusting workload, recommending vacations, and implementing health programs. The generated improvements are automatically notified to the responsible person.

[0154] Step 7:

[0155] The device provides a dashboard accessible to administrators and HR personnel, visually displaying engagement levels, sentiment information, alerts, and suggested improvements. The graphs and charts are concise and easy to understand, facilitating quick decision-making by users.

[0156] Step 8:

[0157] Users (administrators or HR personnel) use the information provided on the dashboard to plan interviews and feedback sessions with employees and strive to improve their level of engagement in the workplace by implementing specific improvement measures.

[0158] This processing flow allows the system of the present invention to analyze the degree of employee involvement in detail and to present effective improvement measures at the appropriate time.

[0159] (Example 2)

[0160] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0161] Accurately assessing the level of employee and individual involvement, and promptly providing appropriate improvement measures as needed, is crucial for improving the workplace environment and overall organizational efficiency. However, conventional systems have struggled to accurately analyze emotions, preprocess data, and integrate various types of information for effective evaluation, making it difficult to identify rapid and effective improvement measures.

[0162] 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.

[0163] In this invention, the server includes a function for acquiring information, a function for analyzing emotions using language processing technology, and a function for preprocessing data using the analysis results. This enables precise evaluation of the degree of involvement of employees or individuals, and the immediate presentation of appropriate improvement measures.

[0164] The "function for acquiring information" refers to the means of collecting necessary information from external systems or databases.

[0165] The "function to analyze emotions using language processing technology" refers to a method of identifying and analyzing emotions from text data using natural language processing technology.

[0166] A "data preprocessing function" is a means of preparing raw data into a format suitable for analysis and input to models.

[0167] A "generative model" refers to a machine learning algorithm used to calculate the characteristics and level of involvement of employees or individuals based on specific input data.

[0168] The "warning function" is a means of sending an alert to relevant parties when the results do not meet predetermined criteria.

[0169] The "function that proposes improvement measures" is a means of automatically generating and presenting appropriate countermeasures for a problem based on the calculated results.

[0170] A "visualization function" is a means of visualizing acquired data and analysis results on a graphical user interface, allowing stakeholders to intuitively understand the information.

[0171] This invention is a highly automated system for evaluating the level of involvement within companies and organizations and proposing improvement measures. Its main components are a server, terminals, and users, which work together to function.

[0172] The server operates on a cloud-based platform and collects work information, opinion data, and health information using various APIs. For example, it retrieves data from attendance management systems and opinion collection tools. The collected data is analyzed by an emotion analysis engine using natural language processing technology and converted into emotion scores such as positive and negative. This data is then used by generative models to calculate the degree of involvement.

[0173] Next, the server calculates the level of involvement of each employee or individual by inputting prompt messages into a generating AI model based on pre-processed data and sentiment information. A specific example of a prompt message is, "Analyze employee A's latest opinion data and provide sentiment score and level of involvement." As a result, if the server detects an involvement level below a certain threshold, it automatically generates a warning and sends it to managers or HR personnel.

[0174] The device receives data from the server and displays engagement levels, sentiment trends, and suggested improvements in real time on an administrator dashboard. This allows the device to function as a support tool for users to intuitively understand the data, quickly grasp the situation, and make decisions.

[0175] Users (administrators and HR personnel) can utilize the terminal's dashboard to access detailed information about each employee and provide effective communication and support. For example, they can suggest stress reduction programs or individual counseling to employees who frequently exhibit negative emotions and have decreased engagement.

[0176] Thus, the embodiment of the present invention achieves effective human resource management within an organization by using integrated technology, from data collection, sentiment analysis, and calculation of involvement levels to the proposal of improvement measures.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The server retrieves work information, opinion data, and health information from external systems via APIs. This input data is stored in a database and prepared as material for pre-processing and relationship building. Specifically, the process involves sending data retrieval requests to the API endpoint, receiving responses, and storing them.

[0180] Step 2:

[0181] The server uses a natural language processing engine to analyze emotions from acquired opinion data. Here, text data is taken as input, and positive or negative emotion scores are output. Specifically, it applies a text analysis algorithm and processes the data through an emotion classification model.

[0182] Step 3:

[0183] The server integrates the sentiment analysis results with other data and performs preprocessing. This generates a normalized dataset, which is then prepared as input for the generative AI model. Specifically, it performs data processing such as data cleaning, normalization, and feature selection.

[0184] Step 4:

[0185] The server inputs pre-processed data using prompts into a generative AI model to calculate the level of involvement for each employee. For example, it might send a prompt such as, "Analyze employee A's latest opinion data and provide a sentiment score and level of involvement." The output is the individual level of involvement score.

[0186] Step 5:

[0187] The server sends an automatically generated warning to HR personnel or managers if the calculated level of involvement falls below a certain threshold. Here, it receives a low involvement score as input and sends a warning message as output. Specific actions include distributing warnings via email or notification systems.

[0188] Step 6:

[0189] The terminal displays data received from the server on a dashboard. Input data includes involvement scores and related sentiment tendency information, while output is displayed as visually easy-to-understand graphs and charts. Specifically, it generates real-time graphics using a data visualization library.

[0190] Step 7:

[0191] Users (administrators and HR personnel) implement specific improvement measures based on the information displayed on the dashboard. Here, users receive information from the dashboard as input and decide on and execute improvement actions as output. Specific examples of actions include arranging face-to-face consultations with employees and proposing stress reduction programs.

[0192] (Application Example 2)

[0193] 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".

[0194] In an aging society, it is crucial for family members and caregivers to appropriately understand the emotional state of individuals and provide appropriate interventions as needed. However, current systems and devices are insufficient in recognizing emotions through everyday conversations and behaviors, and in automatically suggesting appropriate improvement measures based on the situation, making it difficult to respond effectively.

[0195] 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.

[0196] In this invention, the server includes means for collecting work information, opinion data, and health information; means for preprocessing the collected data; and a generative AI module that calculates the degree of involvement of individuals using the preprocessed data. This makes it possible to accurately grasp the emotions and degree of involvement of individuals in real time and to propose and support improvement measures as needed.

[0197] "Work information" refers to information related to an employee's working hours and job duties.

[0198] "Opinion data" refers to the thoughts and feelings expressed by individuals, collected as text data.

[0199] "Health information" refers to information about an individual's physical or mental health status.

[0200] "Preprocessing" refers to the process of organizing and processing collected data before analysis or training.

[0201] A "generative AI module" is a program module that uses artificial intelligence technology to generate specific results from data.

[0202] "Degree of involvement" is an indicator that shows how actively a person is involved in an activity or organization.

[0203] A "warning" refers to a notification that alerts you to a situation that deviates from the established criteria.

[0204] "Improvement measures" refer to specific means or suggestions for solving a problem and improving the situation.

[0205] "Visualization" is a technique that helps understand data and information by displaying them visually.

[0206] "Means of collecting opinion data from conversations and actions" refers to methods of collecting information through individuals' statements and actions.

[0207] "Means of recognizing emotions" refers to the processes and techniques for analyzing and evaluating a person's emotional state.

[0208] "Means of providing improvement measures based on emotional scores through assistive devices" refers to methods of providing feedback and countermeasures based on emotional analysis using assistive devices.

[0209] The system for implementing this invention centers around three elements: a server, a terminal, and a user. The server is responsible for collecting and managing individual work information, opinion data, and health information. Data collection is performed on a cloud platform using various APIs. Furthermore, the server is equipped with an emotion recognition engine and performs text analysis on the collected opinion data using natural language processing technology. This recognizes emotions and scores them as positive or negative.

[0210] Next, the generating AI module calculates an individual's level of involvement based on emotional information and other pre-processed data. Emotional information is particularly important for weighting opinion data, contributing to improved evaluation accuracy. If the calculated level of involvement falls below a certain threshold, the server automatically issues a warning and suggests improvement measures. These suggestions include workload reallocation, vacation suggestions, and improvements to health management, all optimized based on individual emotional information.

[0211] The device provides an interactive dashboard accessible to administrators, displaying individual engagement levels, emotional tendencies, and suggested improvements in real time. The dashboard is graphically designed, allowing administrators and stakeholders to intuitively understand the situation.

[0212] Users, or administrators and staff, can utilize the device's dashboard to make data-driven decisions and provide specific instructions for improvement. This enables effective communication and support, reducing the need for user intervention. Furthermore, access to detailed information, including emotional data, allows for appropriate responses tailored to the situation.

[0213] As a concrete example, in a home equipped with assistive devices, a robot analyzes speech and behavior, and if negative emotions are detected, it provides stress reduction measures and activity suggestions. Furthermore, the generating AI model uses prompts such as, "Generate a report that evaluates the level of engagement based on the user's recent emotions and opinions, and suggests improvement measures." This system enables efficient support that improves the quality of life for the elderly and individuals.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server collects work information, opinion data, and health information using APIs. This input data includes digital information on each employee's working hours, daily opinion records, and health status. This forms the basis for data collection.

[0217] Step 2:

[0218] The server preprocesses the collected data. Specifically, it removes unnecessary information, standardizes the format, and performs word segmentation and normalization on text data. The input is the digital data collected in step 1, and the output is cleaned data suitable for analysis.

[0219] Step 3:

[0220] The server uses an emotion recognition engine to analyze pre-processed opinion data and score the emotions. The input for this step is pre-processed text data, which is classified as positive or negative using natural language processing techniques and outputs an emotion score.

[0221] Step 4:

[0222] The server uses a generation AI module to calculate the degree of involvement based on sentiment scores and other data. Sentiment scores are used to weight opinion data, contributing to improved accuracy of the involvement level. Inputs here are sentiment scores and health / work information, and output is the individual's involvement level.

[0223] Step 5:

[0224] The server checks if the calculated level of involvement falls below a certain threshold and issues a warning if it does. The input is the level of involvement data from step 4, and the output is the necessary warning message. The warning message is sent to the person in charge or the administrator.

[0225] Step 6:

[0226] The server suggests appropriate corrective actions based on the warning message. In this step, it utilizes involvement levels, emotional scores, and health data to automatically generate corrective actions such as workload redistribution, stress management, and vacation suggestions. The input is the warning information from step 5, and the output is the personalized corrective actions.

[0227] Step 7:

[0228] On the dashboard provided by the terminal, users can view individual levels of involvement, emotional tendencies, and suggested improvement measures in real time. With data visualization and interactive elements, this dashboard is intuitive to operate and understand, enabling users to make quick decisions. Inputs consist of various data from the system, and output is visually organized information.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] In this embodiment of the invention, the system for managing employee engagement levels operates on a cloud-based platform. The system primarily consists of servers, terminals, and users.

[0246] First, the server automatically collects data from related systems through APIs for aggregating work information, opinion data, and health information. The server then performs preprocessing on this collected data, such as data cleaning and normalization, to convert it into a format suitable for analysis.

[0247] Next, the server inputs the pre-processed data into the generating AI module, which calculates the level of involvement of each employee in real time. Based on a model derived from past data, the generating AI module analyzes the employee's work patterns, feedback content, health status, etc., and dynamically evaluates the level of involvement.

[0248] Furthermore, if the calculated level of involvement falls below a pre-set threshold, the server immediately issues a warning and suggests optimal improvement measures. These include suggestions for task redistribution, vacation time, and introductions to health management support programs. This information is automatically generated and provides specific strategies to mitigate the decline in involvement.

[0249] The device provides a dashboard accessible to staff and administrators. The dashboard on the device visually displays changes in engagement levels, deviations from baseline values, and suggested improvement measures, making it easy for users to intuitively understand the situation.

[0250] Finally, users (primarily HR personnel and managers) can use the device's dashboard to monitor the level of engagement of the entire team or individual employees in real time, plan feedback sessions as needed, and enhance communication with employees.

[0251] As a concrete example, suppose a team member working on a project is detected to have decreased engagement based on recent work data. Based on the relevant data, the server suggests reducing the employee's task load and conducting weekly one-on-one meetings. These suggestions and the engagement score are prominently displayed on the terminal's dashboard, allowing the user to take quick action based on them.

[0252] Thus, the system of the present invention can improve employee engagement through a data-driven approach and support the creation of a more comfortable working environment within an organization.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The server automatically collects data via APIs from systems such as work management systems, project management tools, feedback platforms, and health management systems. This allows for centralized collection of daily work hours, project progress, employee feedback, and health-related data.

[0256] Step 2:

[0257] The server performs data cleaning on the collected raw data. This involves imputing missing values, detecting and removing outliers, and normalizing the data into an analyzable format to generate a high-quality dataset.

[0258] Step 3:

[0259] The server inputs pre-processed data into a generating AI module. The AI ​​module, having learned from past data, calculates the level of involvement for each employee. This process runs in real time, and the score is constantly updated based on the latest information.

[0260] Step 4:

[0261] The server compares the calculated involvement score to a baseline value. If the score falls below the baseline, it predicts a problem and triggers an early warning. At the same time, a detailed analysis is performed to identify the cause of the score drop.

[0262] Step 5:

[0263] The server automatically generates effective improvement measures based on the cause of the performance degradation. These measures may include adjusting workloads, suggesting vacation time, and implementing health programs. This information is compiled into a proposal document and immediately notified to HR personnel and managers.

[0264] Step 6:

[0265] The terminal visually displays changes in involvement levels, warnings, and suggested improvements via a dashboard used by staff and managers. This information is presented clearly using graphs and charts, enabling users to make quick decisions.

[0266] Step 7:

[0267] Users (HR personnel, administrators) can utilize the dashboard on their devices to view real-time data and, if necessary, schedule meetings or feedback sessions with employees to quickly implement corrective measures.

[0268] (Example 1)

[0269] 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."

[0270] There is a growing need to improve productivity and a better work environment within organizations by appropriately evaluating employee engagement and proposing improvement measures early on. However, traditional methods often involve manual data collection and analysis, making real-time responses difficult. Furthermore, the evaluation of engagement may not be sufficiently precise, sometimes resulting in the inability to propose appropriate improvement measures.

[0271] 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.

[0272] In this invention, the server includes means for collecting activity data, means for organizing the collected information, and a generating AI module that calculates the degree of worker involvement using the organized information. This makes it possible to evaluate the degree of involvement within an organization in real time and to quickly propose appropriate improvement measures.

[0273] "Activity data" refers to information related to work, such as employee work status, feedback, and health information.

[0274] "Preparation" refers to the process of performing preprocessing such as data cleaning and normalization on collected information and converting it into an analyzable format.

[0275] The "Generative AI Module" refers to a function that uses AI technology modeled based on past data to evaluate and calculate the degree of employee involvement.

[0276] A "benchmark value" refers to a standard or target value used when evaluating the degree of employee engagement, and this value is used to determine whether improvement is necessary.

[0277] "Means of notification" refers to a system for sending warnings to managers or responsible persons when the level of involvement falls below a certain threshold.

[0278] "Improvement measures" refer to specific actions taken to increase employee engagement.

[0279] "Means of presentation" refers to methods of visually displaying the degree of involvement and improvement measures so that managers and staff can review them.

[0280] The term "administration screen" refers to an interface that displays collected data and analysis results, allowing administrators to easily access and review them.

[0281] "Means of planning dialogue" refers to how users can set up feedback sessions and meetings to enhance communication with employees.

[0282] This invention is an information processing system for managing employee engagement levels, and it operates in a cloud-based environment. The system mainly consists of servers, terminals, and users.

[0283] The server has a function to collect activity data from data sources within and outside the company. Here, work status, feedback, health information, etc. are obtained through APIs. This data collection process is mainly automated using digital communication technologies and is performed regularly every day.

[0284] Next, the server organizes the collected information. Specifically, it performs data cleaning and normalization, etc. on the data using the Pandas library in Python and converts it into a format suitable for analysis.

[0285] After that, the server inputs the organized information into a generative AI model and evaluates the engagement level of each employee in real time. This generative AI module is built using TensorFlow and utilizes a model based on past data to calculate the engagement level based on employees' work patterns and feedback content.

[0286] When the calculated engagement level falls below a preset reference value, the server has a function to immediately notify the person in charge using, for example, the Slack API as a means of notification. Furthermore, it also has means to propose improvement measures, and the server presents appropriate improvement measures individually.

[0287] The terminal provides a management screen accessible to users. Here, by using React.js, a visual interface is constructed to visually display the engagement level and improvement measures. This management screen is designed to be intuitively understandable by users.

[0288] Finally, the user (mainly the personnel in charge and administrators) monitors the engagement level of employees through the display of the terminal and plans interactions as needed. As a specific example, it is possible to use prompt sentences for the generative AI model to evaluate the engagement level and propose appropriate improvement measures. For example, by inputting a prompt sentence such as "Evaluate the engagement level of employees based on the latest work data and propose appropriate improvement measures when it is below the reference value.", appropriate output can be obtained.

[0289] This system makes it easier to increase engagement within the organization and strengthen communication with employees.

[0290] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0291] Step 1:

[0292] The server collects activity data, including various types of data such as work information, feedback, and health information. As input, the server retrieves necessary data from relevant systems via APIs. The output is the collected raw data, which is stored in a dedicated database. Specifically, the server calls the API at a designated time each day to automatically retrieve new information.

[0293] Step 2:

[0294] The server preprocesses the collected data. It uses the raw data obtained in Step 1 as input. Here, data cleaning and normalization are performed to prepare the data for analysis. The output is a clean and consistent dataset. Specifically, the Python Pandas library is used to handle missing and outlier values ​​and to format the data frame.

[0295] Step 3:

[0296] The server inputs the prepared data into a generating AI model to calculate the level of involvement. The input is the data preprocessed in step 2. As part of the process, the AI ​​model analyzes the data and evaluates the level of involvement for each employee in real time. The output is the level of involvement score for each employee. Specifically, a model trained using TensorFlow calculates these scores and generates the results in JSON format.

[0297] Step 4:

[0298] The server will issue a warning to the person in charge if the calculated level of involvement falls below a certain threshold. The involvement score from step 3 is used as input. The process will trigger an alert if the level falls below a specific threshold. The output is a notification message. Specifically, the warning is sent in real time via the Slack API.

[0299] Step 5:

[0300] The server proposes the optimal improvement measures based on the involvement score. It references the evaluation data from Step 3 as input. During processing, the AI ​​generates appropriate countermeasures and presents feasible improvements. The output is the specific improvement measures. In terms of action, the server sends the generated improvements to the terminal and provides actionable instructions.

[0301] Step 6:

[0302] The terminal provides visualization through the management screen. The input is the information generated in steps 4 and 5. Here, the engagement score and suggested improvement measures are displayed on the dashboard. The output is a visually organized management screen. Specifically, an interface using React.js is used to update and display information to the user in real time.

[0303] Step 7:

[0304] Users monitor data through the administration panel and plan interactions as needed. They refer to the information displayed in step 6 as input. During processing, they plan communication with employees based on the displayed improvement suggestions. The output is an action plan, such as a specific feedback session. As concrete action, users schedule meetings in Google Calendar based on the information and implement feedback and improvement suggestions.

[0305] (Application Example 1)

[0306] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0307] In a production site, the occurrence of machine malfunctions and inefficient operations reduces the efficiency of the entire manufacturing process, and as a result, becomes a factor that impairs the competitiveness of an enterprise. To address these problems, it is required to accurately and real-time evaluate the operating state of the machine and promptly make necessary improvements. However, in the conventional system, there is a problem that it takes time to monitor the state of the machine and detect abnormalities, and appropriate improvement measures cannot be taken.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0309] In this invention, the server includes means for collecting operation information, environmental data, and machine state data, means for preprocessing the collected data, and a generative AI module for evaluating the operating state of the machine using the preprocessed data. Thereby, the operating state of the machine can be analyzed in real-time, enabling prompt response.

[0310] "Operation information" is specific data indicating the operating status of a machine or device.

[0311] [[ID=第十九]] "Environmental data" is information indicating the physical conditions of the place where the machine is operating.

[0312] "Machine state data" is information representing the internal and external conditions of the machine.

[0313] "Means for collecting" refers to methods and devices for acquiring data.

[0314] "Means for preprocessing" refers to methods and devices for processing the collected data into a form suitable for analysis and utilization.

[0315] A "generative AI module" is a component used to analyze data and derive results using artificial intelligence.

[0316] "Evaluating the operating state" means determining whether a machine is functioning normally or abnormally, and whether it is operating efficiently.

[0317] "Means of issuing warnings" refers to mechanisms or functions that draw attention when standards are not met.

[0318] "Means of proposing improvement measures" refers to components that show specific methods or actions to resolve the problem.

[0319] "Means of visualization" refer to methods and devices for displaying information and data in a way that is easy for people to understand.

[0320] To implement this invention, three elements—a server, a terminal, and a user—work together to constitute a system.

[0321] The server uses IoT gateways and sensors to collect operational information, environmental data, and machine status data from various machines operating within the factory. The collected data is preprocessed on the server, including data cleaning and normalization. The preprocessed data is then input into a generative AI model to evaluate the machine's operating status in real time. The generative AI model uses a model trained on a large amount of historical data to analyze abnormalities in operation and identify areas for improvement. If an abnormality is detected, the server issues a warning and proposes corrective measures to the user. These corrective measures include readjusting the operating load and suggesting maintenance.

[0322] The terminal functions as a dashboard easily accessible to factory managers and operators. This dashboard provides real-time visualization of machine operating status and improvement suggestions. The software used includes an application structure designed to provide a user-friendly UI interface.

[0323] This dashboard allows users to monitor the situation within the factory and take quick action when necessary. By acting on the suggested improvements, users can optimize machine performance and achieve efficient factory operations.

[0324] For example, if abnormal vibrations are detected in an assembly machine on a particular line, the system will analyze the cause and suggest that there is wear on a part of the machine. Based on this, the user will be advised to replace the part, thereby maintaining the factory's operational efficiency.

[0325] An example of a prompt for a generative AI is, "Based on the latest system data, please suggest the cause of the anomaly and the best course of action." By using this prompt, the generative AI model can perform appropriate analysis and provide effective solutions.

[0326] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0327] Step 1:

[0328] The server collects operational information, environmental data, and machine status data from each machine in the factory using sensors and an IoT gateway. It receives real-time data from machine sensors as input and stores it in cloud storage.

[0329] Step 2:

[0330] The server cleans and normalizes the collected data. This includes denoising the data and imputing missing values. Using the raw data obtained in step 1 as input, it produces well-formed data suitable for analysis as output.

[0331] Step 3:

[0332] The server inputs pre-processed data into a generating AI model. This model is trained on historical data and evaluates the current operating state of the machine. The input is well-formed data, and the output is a machine operation evaluation score and the likelihood of anomalies occurring.

[0333] Step 4:

[0334] The server uses the output of the generated AI model to issue a warning if the machine's operating status falls below a certain threshold. This warning indicates that an anomaly has been detected and that improvement is necessary. The operation evaluation score is used as input, and a warning message is generated as output.

[0335] Step 5:

[0336] The server generates corrective actions based on the warnings. These actions include suggestions for adjusting the operating load and performing component maintenance. The input is the result of the anomaly detection, and the output is a specific corrective action plan.

[0337] Step 6:

[0338] The terminal visualizes the machine's operating status and improvement measures received from the server on a dashboard. This allows administrators to understand the machine's status at a glance. The input is the improvement action plan, and the output is a visual dashboard display.

[0339] Step 7:

[0340] Users can quickly adjust and maintain machinery based on reports and suggestions from the dashboard. This helps maintain the factory's operational efficiency. The input is dashboard information, and the output is the stabilization of machine operation.

[0341] 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.

[0342] In this embodiment of the invention, a system for managing the level of employee engagement operates on a cloud-based platform and consists of three elements: a server, a terminal, and a user.

[0343] The server connects with relevant corporate systems via various APIs to collect employee work information, opinion data, and health information. It also features an emotion engine that uses natural language processing to analyze collected opinion data and recognize employee emotions. This allows for the scoring of emotions, such as positive or negative, and is used to calculate the level of engagement.

[0344] Next, the server inputs the pre-processed data and emotional information obtained from the emotion engine into the generating AI module, which then uses this information to calculate the level of involvement for each employee. In this process, the emotional information is used in particular to weight the opinion data, improving the accuracy of the involvement level calculation.

[0345] If the calculated level of involvement falls below a certain threshold, the server sends an automatically generated warning to HR personnel and managers. The warning then suggests corrective actions such as workload redistribution, vacation suggestions, and improved health management. These corrective actions are individually optimized based on the identified emotional information.

[0346] The device provides an administrator dashboard that displays engagement levels, emotional trends, and suggested improvements in real time. The dashboard is graphically designed, allowing users to intuitively understand the situation and make quick decisions.

[0347] Users (administrators and HR personnel) can leverage the terminal's dashboard to make data-driven decisions and direct specific actions for improvement. Accessing detailed information about each employee, including emotional data, helps provide effective communication and support.

[0348] For example, if negative emotions are frequently detected in an employee's opinion data, indicating a decrease in their level of engagement, the server will detect this and suggest implementing a stress reduction program or individual counseling to that employee. This allows users to quickly understand the problem and take appropriate action.

[0349] Thus, the system of the present invention can accurately evaluate the degree of employee engagement by combining data and emotion recognition, and can support the improvement of the workplace environment.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The server continuously collects data via APIs from the work management system, feedback collection tools, and health tracking applications. This data includes each employee's work information, submitted feedback, and health indicators. The server ingests this data into a centralized data store.

[0353] Step 2:

[0354] The server performs data cleaning on the collected data. This cleaning includes interpolating missing values, removing invalid data entries, and normalizing the data format. This preprocessing enables analysis with high accuracy.

[0355] Step 3:

[0356] The server activates an emotion engine on the opinion data and uses natural language processing to analyze the sentiment of each comment. The sentiment is scored as positive, negative, or neutral and stored in the data store. This provides a quantitative representation of employees' emotional tendencies.

[0357] Step 4:

[0358] The server inputs pre-processed work information, health information, and scored sentiment information into a generating AI module to calculate each employee's level of involvement. This generating AI module learns from past data and performs precise scoring by evaluating the level of involvement in a multidimensional way.

[0359] Step 5:

[0360] The calculated level of involvement is compared to a baseline value. If the level of involvement falls below the baseline value, the server detects this as an anomaly and issues a warning. The warning includes an analysis of the cause of the decrease in involvement, and immediate action is required to take countermeasures.

[0361] Step 6:

[0362] The server automatically generates suggested improvements based on identified emotional information and the reasons for decreased engagement. These improvements may include, for example, adjusting workload, recommending vacations, and implementing health programs. The generated improvements are automatically notified to the responsible person.

[0363] Step 7:

[0364] The device provides a dashboard accessible to administrators and HR personnel, visually displaying engagement levels, sentiment information, alerts, and suggested improvements. The graphs and charts are concise and easy to understand, facilitating quick decision-making by users.

[0365] Step 8:

[0366] Users (administrators or HR personnel) use the information provided on the dashboard to plan interviews and feedback sessions with employees and strive to improve their level of engagement in the workplace by implementing specific improvement measures.

[0367] This processing flow allows the system of the present invention to analyze the degree of employee involvement in detail and to present effective improvement measures at the appropriate time.

[0368] (Example 2)

[0369] 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".

[0370] Accurately assessing the level of employee and individual involvement, and promptly providing appropriate improvement measures as needed, is crucial for improving the workplace environment and overall organizational efficiency. However, conventional systems have struggled to accurately analyze emotions, preprocess data, and integrate various types of information for effective evaluation, making it difficult to identify rapid and effective improvement measures.

[0371] 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.

[0372] In this invention, the server includes a function for acquiring information, a function for analyzing emotions using language processing technology, and a function for preprocessing data using the analysis results. This enables precise evaluation of the degree of involvement of employees or individuals, and the immediate presentation of appropriate improvement measures.

[0373] The "function for acquiring information" refers to the means of collecting necessary information from external systems or databases.

[0374] The "function to analyze emotions using language processing technology" refers to a method of identifying and analyzing emotions from text data using natural language processing technology.

[0375] A "data preprocessing function" is a means of preparing raw data into a format suitable for analysis and input to models.

[0376] A "generative model" refers to a machine learning algorithm used to calculate the characteristics and level of involvement of employees or individuals based on specific input data.

[0377] The "warning function" is a means of sending an alert to relevant parties when the results do not meet predetermined criteria.

[0378] The "function that proposes improvement measures" is a means of automatically generating and presenting appropriate countermeasures for a problem based on the calculated results.

[0379] A "visualization function" is a means of visualizing acquired data and analysis results on a graphical user interface, allowing stakeholders to intuitively understand the information.

[0380] This invention is a highly automated system for evaluating the level of involvement within companies and organizations and proposing improvement measures. Its main components are a server, terminals, and users, which work together to function.

[0381] The server operates on a cloud-based platform and collects work information, opinion data, and health information using various APIs. For example, it retrieves data from attendance management systems and opinion collection tools. The collected data is analyzed by an emotion analysis engine using natural language processing technology and converted into emotion scores such as positive and negative. This data is then used by generative models to calculate the degree of involvement.

[0382] Next, the server calculates the level of involvement of each employee or individual by inputting prompt messages into a generating AI model based on pre-processed data and sentiment information. A specific example of a prompt message is, "Analyze employee A's latest opinion data and provide sentiment score and level of involvement." As a result, if the server detects an involvement level below a certain threshold, it automatically generates a warning and sends it to managers or HR personnel.

[0383] The device receives data from the server and displays engagement levels, sentiment trends, and suggested improvements in real time on an administrator dashboard. This allows the device to function as a support tool for users to intuitively understand the data, quickly grasp the situation, and make decisions.

[0384] Users (administrators and HR personnel) can utilize the terminal's dashboard to access detailed information about each employee and provide effective communication and support. For example, they can suggest stress reduction programs or individual counseling to employees who frequently exhibit negative emotions and have decreased engagement.

[0385] Thus, the embodiment of the present invention achieves effective human resource management within an organization by using integrated technology, from data collection, sentiment analysis, and calculation of involvement levels to the proposal of improvement measures.

[0386] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0387] Step 1:

[0388] The server retrieves work information, opinion data, and health information from external systems via APIs. This input data is stored in a database and prepared as material for pre-processing and relationship building. Specifically, the process involves sending data retrieval requests to the API endpoint, receiving responses, and storing them.

[0389] Step 2:

[0390] The server uses a natural language processing engine to analyze emotions from acquired opinion data. Here, text data is taken as input, and positive or negative emotion scores are output. Specifically, it applies a text analysis algorithm and processes the data through an emotion classification model.

[0391] Step 3:

[0392] The server integrates the sentiment analysis results with other data and performs preprocessing. This generates a normalized dataset, which is then prepared as input for the generative AI model. Specifically, it performs data processing such as data cleaning, normalization, and feature selection.

[0393] Step 4:

[0394] The server inputs pre-processed data using prompts into a generative AI model to calculate the level of involvement for each employee. For example, it might send a prompt such as, "Analyze employee A's latest opinion data and provide a sentiment score and level of involvement." The output is the individual level of involvement score.

[0395] Step 5:

[0396] The server sends an automatically generated warning to HR personnel or managers if the calculated level of involvement falls below a certain threshold. Here, it receives a low involvement score as input and sends a warning message as output. Specific actions include distributing warnings via email or notification systems.

[0397] Step 6:

[0398] The terminal displays data received from the server on a dashboard. Input data includes involvement scores and related sentiment tendency information, while output is displayed as visually easy-to-understand graphs and charts. Specifically, it generates real-time graphics using a data visualization library.

[0399] Step 7:

[0400] Users (administrators and HR personnel) implement specific improvement measures based on the information displayed on the dashboard. Here, users receive information from the dashboard as input and decide on and execute improvement actions as output. Specific examples of actions include arranging face-to-face consultations with employees and proposing stress reduction programs.

[0401] (Application Example 2)

[0402] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0403] In an aging society, it is crucial for family members and caregivers to appropriately understand the emotional state of individuals and provide appropriate interventions as needed. However, current systems and devices are insufficient in recognizing emotions through everyday conversations and behaviors, and in automatically suggesting appropriate improvement measures based on the situation, making it difficult to respond effectively.

[0404] 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.

[0405] In this invention, the server includes means for collecting work information, opinion data, and health information; means for preprocessing the collected data; and a generative AI module that calculates the degree of involvement of individuals using the preprocessed data. This makes it possible to accurately grasp the emotions and degree of involvement of individuals in real time and to propose and support improvement measures as needed.

[0406] "Work information" refers to information related to an employee's working hours and job duties.

[0407] "Opinion data" refers to the thoughts and feelings expressed by individuals, collected as text data.

[0408] "Health information" refers to information about an individual's physical or mental health status.

[0409] "Preprocessing" refers to the process of organizing and processing collected data before analysis or training.

[0410] A "generative AI module" is a program module that uses artificial intelligence technology to generate specific results from data.

[0411] "Degree of involvement" is an indicator that shows how actively a person is involved in an activity or organization.

[0412] A "warning" refers to a notification that alerts you to a situation that deviates from the established criteria.

[0413] "Improvement measures" refer to specific means or suggestions for solving a problem and improving the situation.

[0414] "Visualization" is a technique that helps understand data and information by displaying them visually.

[0415] "Means of collecting opinion data from conversations and actions" refers to methods of collecting information through individuals' statements and actions.

[0416] "Means of recognizing emotions" refers to the processes and techniques for analyzing and evaluating a person's emotional state.

[0417] "Means of providing improvement measures based on emotional scores through assistive devices" refers to methods of providing feedback and countermeasures based on emotional analysis using assistive devices.

[0418] The system for implementing this invention centers around three elements: a server, a terminal, and a user. The server is responsible for collecting and managing individual work information, opinion data, and health information. Data collection is performed on a cloud platform using various APIs. Furthermore, the server is equipped with an emotion recognition engine and performs text analysis on the collected opinion data using natural language processing technology. This recognizes emotions and scores them as positive or negative.

[0419] Next, the generating AI module calculates an individual's level of involvement based on emotional information and other pre-processed data. Emotional information is particularly important for weighting opinion data, contributing to improved evaluation accuracy. If the calculated level of involvement falls below a certain threshold, the server automatically issues a warning and suggests improvement measures. These suggestions include workload reallocation, vacation suggestions, and improvements to health management, all optimized based on individual emotional information.

[0420] The device provides an interactive dashboard accessible to administrators, displaying individual engagement levels, emotional tendencies, and suggested improvements in real time. The dashboard is graphically designed, allowing administrators and stakeholders to intuitively understand the situation.

[0421] Users, or administrators and staff, can utilize the device's dashboard to make data-driven decisions and provide specific instructions for improvement. This enables effective communication and support, reducing the need for user intervention. Furthermore, access to detailed information, including emotional data, allows for appropriate responses tailored to the situation.

[0422] As a concrete example, in a home equipped with assistive devices, a robot analyzes speech and behavior, and if negative emotions are detected, it provides stress reduction measures and activity suggestions. Furthermore, the generating AI model uses prompts such as, "Generate a report that evaluates the level of engagement based on the user's recent emotions and opinions, and suggests improvement measures." This system enables efficient support that improves the quality of life for the elderly and individuals.

[0423] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0424] Step 1:

[0425] The server collects work information, opinion data, and health information using APIs. This input data includes digital information on each employee's working hours, daily opinion records, and health status. This forms the basis for data collection.

[0426] Step 2:

[0427] The server preprocesses the collected data. Specifically, it removes unnecessary information, standardizes the format, and performs word segmentation and normalization on text data. The input is the digital data collected in step 1, and the output is cleaned data suitable for analysis.

[0428] Step 3:

[0429] The server uses an emotion recognition engine to analyze pre-processed opinion data and score the emotions. The input for this step is pre-processed text data, which is classified as positive or negative using natural language processing techniques and outputs an emotion score.

[0430] Step 4:

[0431] The server uses a generation AI module to calculate the degree of involvement based on sentiment scores and other data. Sentiment scores are used to weight opinion data, contributing to improved accuracy of the involvement level. Inputs here are sentiment scores and health / work information, and output is the individual's involvement level.

[0432] Step 5:

[0433] The server checks if the calculated level of involvement falls below a certain threshold and issues a warning if it does. The input is the level of involvement data from step 4, and the output is the necessary warning message. The warning message is sent to the person in charge or the administrator.

[0434] Step 6:

[0435] The server suggests appropriate corrective actions based on the warning message. In this step, it utilizes involvement levels, emotional scores, and health data to automatically generate corrective actions such as workload redistribution, stress management, and vacation suggestions. The input is the warning information from step 5, and the output is the personalized corrective actions.

[0436] Step 7:

[0437] On the dashboard provided by the terminal, users can view individual levels of involvement, emotional tendencies, and suggested improvement measures in real time. With data visualization and interactive elements, this dashboard is intuitive to operate and understand, enabling users to make quick decisions. Inputs consist of various data from the system, and output is visually organized information.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] [Third Embodiment]

[0442] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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).

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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".

[0454] In this embodiment of the invention, the system for managing employee engagement levels operates on a cloud-based platform. The system primarily consists of servers, terminals, and users.

[0455] First, the server automatically collects data from related systems through APIs for aggregating work information, opinion data, and health information. The server then performs preprocessing on this collected data, such as data cleaning and normalization, to convert it into a format suitable for analysis.

[0456] Next, the server inputs the pre-processed data into the generating AI module, which calculates the level of involvement of each employee in real time. Based on a model derived from past data, the generating AI module analyzes the employee's work patterns, feedback content, health status, etc., and dynamically evaluates the level of involvement.

[0457] Furthermore, if the calculated level of involvement falls below a pre-set threshold, the server immediately issues a warning and suggests optimal improvement measures. These include suggestions for task redistribution, vacation time, and introductions to health management support programs. This information is automatically generated and provides specific strategies to mitigate the decline in involvement.

[0458] The device provides a dashboard accessible to staff and administrators. The dashboard on the device visually displays changes in engagement levels, deviations from baseline values, and suggested improvement measures, making it easy for users to intuitively understand the situation.

[0459] Finally, users (primarily HR personnel and managers) can use the device's dashboard to monitor the level of engagement of the entire team or individual employees in real time, plan feedback sessions as needed, and enhance communication with employees.

[0460] As a concrete example, suppose a team member working on a project is detected to have decreased engagement based on recent work data. Based on the relevant data, the server suggests reducing the employee's task load and conducting weekly one-on-one meetings. These suggestions and the engagement score are prominently displayed on the terminal's dashboard, allowing the user to take quick action based on them.

[0461] Thus, the system of the present invention can improve employee engagement through a data-driven approach and support the creation of a more comfortable working environment within an organization.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server automatically collects data via APIs from systems such as work management systems, project management tools, feedback platforms, and health management systems. This allows for centralized collection of daily work hours, project progress, employee feedback, and health-related data.

[0465] Step 2:

[0466] The server performs data cleaning on the collected raw data. This involves imputing missing values, detecting and removing outliers, and normalizing the data into an analyzable format to generate a high-quality dataset.

[0467] Step 3:

[0468] The server inputs pre-processed data into a generating AI module. The AI ​​module, having learned from past data, calculates the level of involvement for each employee. This process runs in real time, and the score is constantly updated based on the latest information.

[0469] Step 4:

[0470] The server compares the calculated involvement score to a baseline value. If the score falls below the baseline, it predicts a problem and triggers an early warning. At the same time, a detailed analysis is performed to identify the cause of the score drop.

[0471] Step 5:

[0472] The server automatically generates effective improvement measures based on the cause of the performance degradation. These measures may include adjusting workloads, suggesting vacation time, and implementing health programs. This information is compiled into a proposal document and immediately notified to HR personnel and managers.

[0473] Step 6:

[0474] The terminal visually displays changes in involvement levels, warnings, and suggested improvements via a dashboard used by staff and managers. This information is presented clearly using graphs and charts, enabling users to make quick decisions.

[0475] Step 7:

[0476] Users (HR personnel, administrators) can utilize the dashboard on their devices to view real-time data and, if necessary, schedule meetings or feedback sessions with employees to quickly implement corrective measures.

[0477] (Example 1)

[0478] 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."

[0479] There is a growing need to improve productivity and a better work environment within organizations by appropriately evaluating employee engagement and proposing improvement measures early on. However, traditional methods often involve manual data collection and analysis, making real-time responses difficult. Furthermore, the evaluation of engagement may not be sufficiently precise, sometimes resulting in the inability to propose appropriate improvement measures.

[0480] 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.

[0481] In this invention, the server includes means for collecting activity data, means for organizing the collected information, and a generating AI module that calculates the degree of worker involvement using the organized information. This makes it possible to evaluate the degree of involvement within an organization in real time and to quickly propose appropriate improvement measures.

[0482] "Activity data" refers to information related to work, such as employee work status, feedback, and health information.

[0483] "Preparation" refers to the process of performing preprocessing such as data cleaning and normalization on collected information and converting it into an analyzable format.

[0484] The "Generative AI Module" refers to a function that uses AI technology modeled based on past data to evaluate and calculate the degree of employee involvement.

[0485] A "benchmark value" refers to a standard or target value used when evaluating the degree of employee engagement, and this value is used to determine whether improvement is necessary.

[0486] "Means of notification" refers to a system for sending warnings to managers or responsible persons when the level of involvement falls below a certain threshold.

[0487] "Improvement measures" refer to specific actions taken to increase employee engagement.

[0488] "Means of presentation" refers to methods of visually displaying the degree of involvement and improvement measures so that managers and staff can review them.

[0489] The term "administration screen" refers to an interface that displays collected data and analysis results, allowing administrators to easily access and review them.

[0490] "Means of planning dialogue" refers to how users can set up feedback sessions and meetings to enhance communication with employees.

[0491] This invention is an information processing system for managing employee engagement levels, and it operates in a cloud-based environment. The system mainly consists of servers, terminals, and users.

[0492] The server has the functionality to collect activity data from internal and external data sources within the company, obtaining work status, feedback, and health information via APIs. This data collection process is automated, primarily using digital communication technology, and is performed regularly every day.

[0493] Next, the server organizes the collected information. Specifically, it uses the Python Pandas library to perform data cleaning and normalization, and converts the data into a format suitable for analysis.

[0494] The server then inputs the compiled information into a generative AI model, which evaluates each employee's level of involvement in real time. This generative AI module is built using TensorFlow and leverages a model based on historical data to calculate involvement levels based on employee work patterns and feedback content.

[0495] If the calculated level of involvement falls below a predetermined threshold, the server has a function to immediately notify the responsible person, for example, using the Slack API. Furthermore, it also has a means of suggesting improvement measures, and the server will present individually tailored improvement plans.

[0496] The device provides a user-accessible administration screen. Using React.js, a visual interface is built to visually display involvement levels and improvement suggestions. This administration screen is designed to be intuitively understandable to users.

[0497] Finally, users (primarily HR personnel and managers) can monitor employee engagement levels through the terminal display and plan interactions as needed. For example, prompts can be used with the generated AI model to evaluate engagement levels and suggest appropriate improvement measures. For instance, inputting a prompt such as, "Evaluate employee engagement levels based on the latest work data and suggest appropriate improvement measures if the level falls below the threshold," can yield appropriate output.

[0498] This system makes it easier to increase engagement within the organization and strengthen communication with employees.

[0499] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0500] Step 1:

[0501] The server collects activity data, including various types of data such as work information, feedback, and health information. As input, the server retrieves necessary data from relevant systems via APIs. The output is the collected raw data, which is stored in a dedicated database. Specifically, the server calls the API at a designated time each day to automatically retrieve new information.

[0502] Step 2:

[0503] The server preprocesses the collected data. It uses the raw data obtained in Step 1 as input. Here, data cleaning and normalization are performed to prepare the data for analysis. The output is a clean and consistent dataset. Specifically, the Python Pandas library is used to handle missing and outlier values ​​and to format the data frame.

[0504] Step 3:

[0505] The server inputs the prepared data into a generating AI model to calculate the level of involvement. The input is the data preprocessed in step 2. As part of the process, the AI ​​model analyzes the data and evaluates the level of involvement for each employee in real time. The output is the level of involvement score for each employee. Specifically, a model trained using TensorFlow calculates these scores and generates the results in JSON format.

[0506] Step 4:

[0507] The server will issue a warning to the person in charge if the calculated level of involvement falls below a certain threshold. The involvement score from step 3 is used as input. The process will trigger an alert if the level falls below a specific threshold. The output is a notification message. Specifically, the warning is sent in real time via the Slack API.

[0508] Step 5:

[0509] The server proposes the optimal improvement measures based on the involvement score. It references the evaluation data from Step 3 as input. During processing, the AI ​​generates appropriate countermeasures and presents feasible improvements. The output is the specific improvement measures. In terms of action, the server sends the generated improvements to the terminal and provides actionable instructions.

[0510] Step 6:

[0511] The terminal provides visualization through the management screen. The input is the information generated in steps 4 and 5. Here, the engagement score and suggested improvement measures are displayed on the dashboard. The output is a visually organized management screen. Specifically, an interface using React.js is used to update and display information to the user in real time.

[0512] Step 7:

[0513] Users monitor data through the administration panel and plan interactions as needed. They refer to the information displayed in step 6 as input. During processing, they plan communication with employees based on the displayed improvement suggestions. The output is an action plan, such as a specific feedback session. As concrete action, users schedule meetings in Google Calendar based on the information and implement feedback and improvement suggestions.

[0514] (Application Example 1)

[0515] 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."

[0516] Machine malfunctions and inefficient operation in production facilities reduce the overall efficiency of the manufacturing process, ultimately undermining a company's competitiveness. To address these problems, it is necessary to accurately and in real time evaluate the operating status of machinery and to quickly implement necessary improvements. However, conventional systems have the problem of taking too long to monitor the state of machinery and detect abnormalities, resulting in a lack of appropriate corrective measures.

[0517] 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.

[0518] In this invention, the server includes means for collecting operational information, environmental data, and machine status data; means for preprocessing the collected data; and a generating AI module for evaluating the machine's operational status using the preprocessed data. This enables real-time analysis of the machine's operational status and allows for rapid response.

[0519] "Operational information" refers to specific data that indicates the operating status of machinery and equipment.

[0520] "Environmental data" refers to information that describes the physical conditions of the environment in which a machine is operating.

[0521] "Machine condition data" refers to information that describes the internal and external condition of a machine.

[0522] "Means of collection" refers to the methods and equipment used to acquire data.

[0523] "Preprocessing means" refers to methods and devices for processing collected data into a format suitable for analysis and use.

[0524] A "generative AI module" is a component used to analyze data and derive results using artificial intelligence.

[0525] "Evaluating the operating state" means determining whether a machine is functioning normally or abnormally, and whether it is operating efficiently.

[0526] "Means of issuing warnings" refers to mechanisms or functions that draw attention when standards are not met.

[0527] "Means of proposing improvement measures" refers to components that show specific methods or actions to resolve the problem.

[0528] "Means of visualization" refer to methods and devices for displaying information and data in a way that is easy for people to understand.

[0529] To implement this invention, three elements—a server, a terminal, and a user—work together to constitute a system.

[0530] The server uses IoT gateways and sensors to collect operational information, environmental data, and machine status data from various machines operating within the factory. The collected data is preprocessed on the server, including data cleaning and normalization. The preprocessed data is then input into a generative AI model to evaluate the machine's operating status in real time. The generative AI model uses a model trained on a large amount of historical data to analyze abnormalities in operation and identify areas for improvement. If an abnormality is detected, the server issues a warning and proposes corrective measures to the user. These corrective measures include readjusting the operating load and suggesting maintenance.

[0531] The terminal functions as a dashboard easily accessible to factory managers and operators. This dashboard provides real-time visualization of machine operating status and improvement suggestions. The software used includes an application structure designed to provide a user-friendly UI interface.

[0532] This dashboard allows users to monitor the situation within the factory and take quick action when necessary. By acting on the suggested improvements, users can optimize machine performance and achieve efficient factory operations.

[0533] For example, if abnormal vibrations are detected in an assembly machine on a particular line, the system will analyze the cause and suggest that there is wear on a part of the machine. Based on this, the user will be advised to replace the part, thereby maintaining the factory's operational efficiency.

[0534] An example of a prompt for a generative AI is, "Based on the latest system data, please suggest the cause of the anomaly and the best course of action." By using this prompt, the generative AI model can perform appropriate analysis and provide effective solutions.

[0535] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0536] Step 1:

[0537] The server collects operational information, environmental data, and machine status data from each machine in the factory using sensors and an IoT gateway. It receives real-time data from machine sensors as input and stores it in cloud storage.

[0538] Step 2:

[0539] The server cleans and normalizes the collected data. This includes denoising the data and imputing missing values. Using the raw data obtained in step 1 as input, it produces well-formed data suitable for analysis as output.

[0540] Step 3:

[0541] The server inputs pre-processed data into a generating AI model. This model is trained on historical data and evaluates the current operating state of the machine. The input is well-formed data, and the output is a machine operation evaluation score and the likelihood of anomalies occurring.

[0542] Step 4:

[0543] The server uses the output of the generated AI model to issue a warning if the machine's operating status falls below a certain threshold. This warning indicates that an anomaly has been detected and that improvement is necessary. The operation evaluation score is used as input, and a warning message is generated as output.

[0544] Step 5:

[0545] The server generates corrective actions based on the warnings. These actions include suggestions for adjusting the operating load and performing component maintenance. The input is the result of the anomaly detection, and the output is a specific corrective action plan.

[0546] Step 6:

[0547] The terminal visualizes the machine's operating status and improvement measures received from the server on a dashboard. This allows administrators to understand the machine's status at a glance. The input is the improvement action plan, and the output is a visual dashboard display.

[0548] Step 7:

[0549] Users can quickly adjust and maintain machinery based on reports and suggestions from the dashboard. This helps maintain the factory's operational efficiency. The input is dashboard information, and the output is the stabilization of machine operation.

[0550] 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.

[0551] In this embodiment of the invention, a system for managing the level of employee engagement operates on a cloud-based platform and consists of three elements: a server, a terminal, and a user.

[0552] The server connects with relevant corporate systems via various APIs to collect employee work information, opinion data, and health information. It also features an emotion engine that uses natural language processing to analyze collected opinion data and recognize employee emotions. This allows for the scoring of emotions, such as positive or negative, and is used to calculate the level of engagement.

[0553] Next, the server inputs the pre-processed data and emotional information obtained from the emotion engine into the generating AI module, which then uses this information to calculate the level of involvement for each employee. In this process, the emotional information is used in particular to weight the opinion data, improving the accuracy of the involvement level calculation.

[0554] If the calculated level of involvement falls below a certain threshold, the server sends an automatically generated warning to HR personnel and managers. The warning then suggests corrective actions such as workload redistribution, vacation suggestions, and improved health management. These corrective actions are individually optimized based on the identified emotional information.

[0555] The device provides an administrator dashboard that displays engagement levels, emotional trends, and suggested improvements in real time. The dashboard is graphically designed, allowing users to intuitively understand the situation and make quick decisions.

[0556] Users (administrators and HR personnel) can leverage the terminal's dashboard to make data-driven decisions and direct specific actions for improvement. Accessing detailed information about each employee, including emotional data, helps provide effective communication and support.

[0557] For example, if negative emotions are frequently detected in an employee's opinion data, indicating a decrease in their level of engagement, the server will detect this and suggest implementing a stress reduction program or individual counseling to that employee. This allows users to quickly understand the problem and take appropriate action.

[0558] Thus, the system of the present invention can accurately evaluate the degree of employee engagement by combining data and emotion recognition, and can support the improvement of the workplace environment.

[0559] The following describes the processing flow.

[0560] Step 1:

[0561] The server continuously collects data via APIs from the work management system, feedback collection tools, and health tracking applications. This data includes each employee's work information, submitted feedback, and health indicators. The server ingests this data into a centralized data store.

[0562] Step 2:

[0563] The server performs data cleaning on the collected data. This cleaning includes interpolating missing values, removing invalid data entries, and normalizing the data format. This preprocessing enables analysis with high accuracy.

[0564] Step 3:

[0565] The server activates an emotion engine on the opinion data and uses natural language processing to analyze the sentiment of each comment. The sentiment is scored as positive, negative, or neutral and stored in the data store. This provides a quantitative representation of employees' emotional tendencies.

[0566] Step 4:

[0567] The server inputs pre-processed work information, health information, and scored sentiment information into a generating AI module to calculate each employee's level of involvement. This generating AI module learns from past data and performs precise scoring by evaluating the level of involvement in a multidimensional way.

[0568] Step 5:

[0569] The calculated level of involvement is compared to a baseline value. If the level of involvement falls below the baseline value, the server detects this as an anomaly and issues a warning. The warning includes an analysis of the cause of the decrease in involvement, and immediate action is required to take countermeasures.

[0570] Step 6:

[0571] The server automatically generates suggested improvements based on identified emotional information and the reasons for decreased engagement. These improvements may include, for example, adjusting workload, recommending vacations, and implementing health programs. The generated improvements are automatically notified to the responsible person.

[0572] Step 7:

[0573] The device provides a dashboard accessible to administrators and HR personnel, visually displaying engagement levels, sentiment information, alerts, and suggested improvements. The graphs and charts are concise and easy to understand, facilitating quick decision-making by users.

[0574] Step 8:

[0575] Users (administrators or HR personnel) use the information provided on the dashboard to plan interviews and feedback sessions with employees and strive to improve their level of engagement in the workplace by implementing specific improvement measures.

[0576] This processing flow allows the system of the present invention to analyze the degree of employee involvement in detail and to present effective improvement measures at the appropriate time.

[0577] (Example 2)

[0578] 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."

[0579] Accurately assessing the level of employee and individual involvement, and promptly providing appropriate improvement measures as needed, is crucial for improving the workplace environment and overall organizational efficiency. However, conventional systems have struggled to accurately analyze emotions, preprocess data, and integrate various types of information for effective evaluation, making it difficult to identify rapid and effective improvement measures.

[0580] 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.

[0581] In this invention, the server includes a function for acquiring information, a function for analyzing emotions using language processing technology, and a function for preprocessing data using the analysis results. This enables precise evaluation of the degree of involvement of employees or individuals, and the immediate presentation of appropriate improvement measures.

[0582] The "function for acquiring information" refers to the means of collecting necessary information from external systems or databases.

[0583] The "function to analyze emotions using language processing technology" refers to a method of identifying and analyzing emotions from text data using natural language processing technology.

[0584] A "data preprocessing function" is a means of preparing raw data into a format suitable for analysis and input to models.

[0585] A "generative model" refers to a machine learning algorithm used to calculate the characteristics and level of involvement of employees or individuals based on specific input data.

[0586] The "warning function" is a means of sending an alert to relevant parties when the results do not meet predetermined criteria.

[0587] The "function that proposes improvement measures" is a means of automatically generating and presenting appropriate countermeasures for a problem based on the calculated results.

[0588] A "visualization function" is a means of visualizing acquired data and analysis results on a graphical user interface, allowing stakeholders to intuitively understand the information.

[0589] This invention is a highly automated system for evaluating the level of involvement within companies and organizations and proposing improvement measures. Its main components are a server, terminals, and users, which work together to function.

[0590] The server operates on a cloud-based platform and collects work information, opinion data, and health information using various APIs. For example, it retrieves data from attendance management systems and opinion collection tools. The collected data is analyzed by an emotion analysis engine using natural language processing technology and converted into emotion scores such as positive and negative. This data is then used by generative models to calculate the degree of involvement.

[0591] Next, the server calculates the level of involvement of each employee or individual by inputting prompt messages into a generating AI model based on pre-processed data and sentiment information. A specific example of a prompt message is, "Analyze employee A's latest opinion data and provide sentiment score and level of involvement." As a result, if the server detects an involvement level below a certain threshold, it automatically generates a warning and sends it to managers or HR personnel.

[0592] The device receives data from the server and displays engagement levels, sentiment trends, and suggested improvements in real time on an administrator dashboard. This allows the device to function as a support tool for users to intuitively understand the data, quickly grasp the situation, and make decisions.

[0593] Users (administrators and HR personnel) can utilize the terminal's dashboard to access detailed information about each employee and provide effective communication and support. For example, they can suggest stress reduction programs or individual counseling to employees who frequently exhibit negative emotions and have decreased engagement.

[0594] Thus, the embodiment of the present invention achieves effective human resource management within an organization by using integrated technology, from data collection, sentiment analysis, and calculation of involvement levels to the proposal of improvement measures.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The server retrieves work information, opinion data, and health information from external systems via APIs. This input data is stored in a database and prepared as material for pre-processing and relationship building. Specifically, the process involves sending data retrieval requests to the API endpoint, receiving responses, and storing them.

[0598] Step 2:

[0599] The server uses a natural language processing engine to analyze emotions from acquired opinion data. Here, text data is taken as input, and positive or negative emotion scores are output. Specifically, it applies a text analysis algorithm and processes the data through an emotion classification model.

[0600] Step 3:

[0601] The server integrates the sentiment analysis results with other data and performs preprocessing. This generates a normalized dataset, which is then prepared as input for the generative AI model. Specifically, it performs data processing such as data cleaning, normalization, and feature selection.

[0602] Step 4:

[0603] The server inputs pre-processed data using prompts into a generative AI model to calculate the level of involvement for each employee. For example, it might send a prompt such as, "Analyze employee A's latest opinion data and provide a sentiment score and level of involvement." The output is the individual level of involvement score.

[0604] Step 5:

[0605] The server sends an automatically generated warning to HR personnel or managers if the calculated level of involvement falls below a certain threshold. Here, it receives a low involvement score as input and sends a warning message as output. Specific actions include distributing warnings via email or notification systems.

[0606] Step 6:

[0607] The terminal displays data received from the server on a dashboard. Input data includes involvement scores and related sentiment tendency information, while output is displayed as visually easy-to-understand graphs and charts. Specifically, it generates real-time graphics using a data visualization library.

[0608] Step 7:

[0609] Users (administrators and HR personnel) implement specific improvement measures based on the information displayed on the dashboard. Here, users receive information from the dashboard as input and decide on and execute improvement actions as output. Specific examples of actions include arranging face-to-face consultations with employees and proposing stress reduction programs.

[0610] (Application Example 2)

[0611] 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."

[0612] In an aging society, it is crucial for family members and caregivers to appropriately understand the emotional state of individuals and provide appropriate interventions as needed. However, current systems and devices are insufficient in recognizing emotions through everyday conversations and behaviors, and in automatically suggesting appropriate improvement measures based on the situation, making it difficult to respond effectively.

[0613] 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.

[0614] In this invention, the server includes means for collecting work information, opinion data, and health information; means for preprocessing the collected data; and a generative AI module that calculates the degree of involvement of individuals using the preprocessed data. This makes it possible to accurately grasp the emotions and degree of involvement of individuals in real time and to propose and support improvement measures as needed.

[0615] "Work information" refers to information related to an employee's working hours and job duties.

[0616] "Opinion data" refers to the thoughts and feelings expressed by individuals, collected as text data.

[0617] "Health information" refers to information about an individual's physical or mental health status.

[0618] "Preprocessing" refers to the process of organizing and processing collected data before analysis or training.

[0619] A "generative AI module" is a program module that uses artificial intelligence technology to generate specific results from data.

[0620] "Degree of involvement" is an indicator that shows how actively a person is involved in an activity or organization.

[0621] A "warning" refers to a notification that alerts you to a situation that deviates from the established criteria.

[0622] "Improvement measures" refer to specific means or suggestions for solving a problem and improving the situation.

[0623] "Visualization" is a technique that helps understand data and information by displaying them visually.

[0624] "Means of collecting opinion data from conversations and actions" refers to methods of collecting information through individuals' statements and actions.

[0625] "Means of recognizing emotions" refers to the processes and techniques for analyzing and evaluating a person's emotional state.

[0626] "Means of providing improvement measures based on emotional scores through assistive devices" refers to methods of providing feedback and countermeasures based on emotional analysis using assistive devices.

[0627] The system for implementing this invention centers around three elements: a server, a terminal, and a user. The server is responsible for collecting and managing individual work information, opinion data, and health information. Data collection is performed on a cloud platform using various APIs. Furthermore, the server is equipped with an emotion recognition engine and performs text analysis on the collected opinion data using natural language processing technology. This recognizes emotions and scores them as positive or negative.

[0628] Next, the generating AI module calculates an individual's level of involvement based on emotional information and other pre-processed data. Emotional information is particularly important for weighting opinion data, contributing to improved evaluation accuracy. If the calculated level of involvement falls below a certain threshold, the server automatically issues a warning and suggests improvement measures. These suggestions include workload reallocation, vacation suggestions, and improvements to health management, all optimized based on individual emotional information.

[0629] The device provides an interactive dashboard accessible to administrators, displaying individual engagement levels, emotional tendencies, and suggested improvements in real time. The dashboard is graphically designed, allowing administrators and stakeholders to intuitively understand the situation.

[0630] Users, or administrators and staff, can utilize the device's dashboard to make data-driven decisions and provide specific instructions for improvement. This enables effective communication and support, reducing the need for user intervention. Furthermore, access to detailed information, including emotional data, allows for appropriate responses tailored to the situation.

[0631] As a concrete example, in a home equipped with assistive devices, a robot analyzes speech and behavior, and if negative emotions are detected, it provides stress reduction measures and activity suggestions. Furthermore, the generating AI model uses prompts such as, "Generate a report that evaluates the level of engagement based on the user's recent emotions and opinions, and suggests improvement measures." This system enables efficient support that improves the quality of life for the elderly and individuals.

[0632] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0633] Step 1:

[0634] The server collects work information, opinion data, and health information using APIs. This input data includes digital information on each employee's working hours, daily opinion records, and health status. This forms the basis for data collection.

[0635] Step 2:

[0636] The server preprocesses the collected data. Specifically, it removes unnecessary information, standardizes the format, and performs word segmentation and normalization on text data. The input is the digital data collected in step 1, and the output is cleaned data suitable for analysis.

[0637] Step 3:

[0638] The server uses an emotion recognition engine to analyze pre-processed opinion data and score the emotions. The input for this step is pre-processed text data, which is classified as positive or negative using natural language processing techniques and outputs an emotion score.

[0639] Step 4:

[0640] The server uses a generation AI module to calculate the degree of involvement based on sentiment scores and other data. Sentiment scores are used to weight opinion data, contributing to improved accuracy of the involvement level. Inputs here are sentiment scores and health / work information, and output is the individual's involvement level.

[0641] Step 5:

[0642] The server checks if the calculated level of involvement falls below a certain threshold and issues a warning if it does. The input is the level of involvement data from step 4, and the output is the necessary warning message. The warning message is sent to the person in charge or the administrator.

[0643] Step 6:

[0644] The server suggests appropriate corrective actions based on the warning message. In this step, it utilizes involvement levels, emotional scores, and health data to automatically generate corrective actions such as workload redistribution, stress management, and vacation suggestions. The input is the warning information from step 5, and the output is the personalized corrective actions.

[0645] Step 7:

[0646] On the dashboard provided by the terminal, users can view individual levels of involvement, emotional tendencies, and suggested improvement measures in real time. With data visualization and interactive elements, this dashboard is intuitive to operate and understand, enabling users to make quick decisions. Inputs consist of various data from the system, and output is visually organized information.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] [Fourth Embodiment]

[0651] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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".

[0664] In this embodiment of the invention, the system for managing employee engagement levels operates on a cloud-based platform. The system primarily consists of servers, terminals, and users.

[0665] First, the server automatically collects data from related systems through APIs for aggregating work information, opinion data, and health information. The server then performs preprocessing on this collected data, such as data cleaning and normalization, to convert it into a format suitable for analysis.

[0666] Next, the server inputs the pre-processed data into the generating AI module, which calculates the level of involvement of each employee in real time. Based on a model derived from past data, the generating AI module analyzes the employee's work patterns, feedback content, health status, etc., and dynamically evaluates the level of involvement.

[0667] Furthermore, if the calculated level of involvement falls below a pre-set threshold, the server immediately issues a warning and suggests optimal improvement measures. These include suggestions for task redistribution, vacation time, and introductions to health management support programs. This information is automatically generated and provides specific strategies to mitigate the decline in involvement.

[0668] The device provides a dashboard accessible to staff and administrators. The dashboard on the device visually displays changes in engagement levels, deviations from baseline values, and suggested improvement measures, making it easy for users to intuitively understand the situation.

[0669] Finally, users (primarily HR personnel and managers) can use the device's dashboard to monitor the level of engagement of the entire team or individual employees in real time, plan feedback sessions as needed, and enhance communication with employees.

[0670] As a concrete example, suppose a team member working on a project is detected to have decreased engagement based on recent work data. Based on the relevant data, the server suggests reducing the employee's task load and conducting weekly one-on-one meetings. These suggestions and the engagement score are prominently displayed on the terminal's dashboard, allowing the user to take quick action based on them.

[0671] Thus, the system of the present invention can improve employee engagement through a data-driven approach and support the creation of a more comfortable working environment within an organization.

[0672] The following describes the processing flow.

[0673] Step 1:

[0674] The server automatically collects data via APIs from systems such as work management systems, project management tools, feedback platforms, and health management systems. This allows for centralized collection of daily work hours, project progress, employee feedback, and health-related data.

[0675] Step 2:

[0676] The server performs data cleaning on the collected raw data. This involves imputing missing values, detecting and removing outliers, and normalizing the data into an analyzable format to generate a high-quality dataset.

[0677] Step 3:

[0678] The server inputs pre-processed data into a generating AI module. The AI ​​module, having learned from past data, calculates the level of involvement for each employee. This process runs in real time, and the score is constantly updated based on the latest information.

[0679] Step 4:

[0680] The server compares the calculated involvement score to a baseline value. If the score falls below the baseline, it predicts a problem and triggers an early warning. At the same time, a detailed analysis is performed to identify the cause of the score drop.

[0681] Step 5:

[0682] The server automatically generates effective improvement measures based on the cause of the performance degradation. These measures may include adjusting workloads, suggesting vacation time, and implementing health programs. This information is compiled into a proposal document and immediately notified to HR personnel and managers.

[0683] Step 6:

[0684] The terminal visually displays changes in involvement levels, warnings, and suggested improvements via a dashboard used by staff and managers. This information is presented clearly using graphs and charts, enabling users to make quick decisions.

[0685] Step 7:

[0686] Users (HR personnel, administrators) can utilize the dashboard on their devices to view real-time data and, if necessary, schedule meetings or feedback sessions with employees to quickly implement corrective measures.

[0687] (Example 1)

[0688] 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".

[0689] There is a growing need to improve productivity and a better work environment within organizations by appropriately evaluating employee engagement and proposing improvement measures early on. However, traditional methods often involve manual data collection and analysis, making real-time responses difficult. Furthermore, the evaluation of engagement may not be sufficiently precise, sometimes resulting in the inability to propose appropriate improvement measures.

[0690] 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.

[0691] In this invention, the server includes means for collecting activity data, means for organizing the collected information, and a generating AI module that calculates the degree of worker involvement using the organized information. This makes it possible to evaluate the degree of involvement within an organization in real time and to quickly propose appropriate improvement measures.

[0692] "Activity data" refers to information related to work, such as employee work status, feedback, and health information.

[0693] "Preparation" refers to the process of performing preprocessing such as data cleaning and normalization on collected information and converting it into an analyzable format.

[0694] The "Generative AI Module" refers to a function that uses AI technology modeled based on past data to evaluate and calculate the degree of employee involvement.

[0695] A "benchmark value" refers to a standard or target value used when evaluating the degree of employee engagement, and this value is used to determine whether improvement is necessary.

[0696] "Means of notification" refers to a system for sending warnings to managers or responsible persons when the level of involvement falls below a certain threshold.

[0697] "Improvement measures" refer to specific actions taken to increase employee engagement.

[0698] "Means of presentation" refers to methods of visually displaying the degree of involvement and improvement measures so that managers and staff can review them.

[0699] The term "administration screen" refers to an interface that displays collected data and analysis results, allowing administrators to easily access and review them.

[0700] "Means of planning dialogue" refers to how users can set up feedback sessions and meetings to enhance communication with employees.

[0701] This invention is an information processing system for managing employee engagement levels, and it operates in a cloud-based environment. The system mainly consists of servers, terminals, and users.

[0702] The server has the functionality to collect activity data from internal and external data sources within the company, obtaining work status, feedback, and health information via APIs. This data collection process is automated, primarily using digital communication technology, and is performed regularly every day.

[0703] Next, the server organizes the collected information. Specifically, it uses the Python Pandas library to perform data cleaning and normalization, and converts the data into a format suitable for analysis.

[0704] The server then inputs the compiled information into a generative AI model, which evaluates each employee's level of involvement in real time. This generative AI module is built using TensorFlow and leverages a model based on historical data to calculate involvement levels based on employee work patterns and feedback content.

[0705] If the calculated level of involvement falls below a predetermined threshold, the server has a function to immediately notify the responsible person, for example, using the Slack API. Furthermore, it also has a means of suggesting improvement measures, and the server will present individually tailored improvement plans.

[0706] The device provides a user-accessible administration screen. Using React.js, a visual interface is built to visually display involvement levels and improvement suggestions. This administration screen is designed to be intuitively understandable to users.

[0707] Finally, users (primarily HR personnel and managers) can monitor employee engagement levels through the terminal display and plan interactions as needed. For example, prompts can be used with the generated AI model to evaluate engagement levels and suggest appropriate improvement measures. For instance, inputting a prompt such as, "Evaluate employee engagement levels based on the latest work data and suggest appropriate improvement measures if the level falls below the threshold," can yield appropriate output.

[0708] This system makes it easier to increase engagement within the organization and strengthen communication with employees.

[0709] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0710] Step 1:

[0711] The server collects activity data, including various types of data such as work information, feedback, and health information. As input, the server retrieves necessary data from relevant systems via APIs. The output is the collected raw data, which is stored in a dedicated database. Specifically, the server calls the API at a designated time each day to automatically retrieve new information.

[0712] Step 2:

[0713] The server preprocesses the collected data. It uses the raw data obtained in Step 1 as input. Here, data cleaning and normalization are performed to prepare the data for analysis. The output is a clean and consistent dataset. Specifically, the Python Pandas library is used to handle missing and outlier values ​​and to format the data frame.

[0714] Step 3:

[0715] The server inputs the prepared data into a generating AI model to calculate the level of involvement. The input is the data preprocessed in step 2. As part of the process, the AI ​​model analyzes the data and evaluates the level of involvement for each employee in real time. The output is the level of involvement score for each employee. Specifically, a model trained using TensorFlow calculates these scores and generates the results in JSON format.

[0716] Step 4:

[0717] The server will issue a warning to the person in charge if the calculated level of involvement falls below a certain threshold. The involvement score from step 3 is used as input. The process will trigger an alert if the level falls below a specific threshold. The output is a notification message. Specifically, the warning is sent in real time via the Slack API.

[0718] Step 5:

[0719] The server proposes the optimal improvement measures based on the involvement score. It references the evaluation data from Step 3 as input. During processing, the AI ​​generates appropriate countermeasures and presents feasible improvements. The output is the specific improvement measures. In terms of action, the server sends the generated improvements to the terminal and provides actionable instructions.

[0720] Step 6:

[0721] The terminal provides visualization through the management screen. The input is the information generated in steps 4 and 5. Here, the engagement score and suggested improvement measures are displayed on the dashboard. The output is a visually organized management screen. Specifically, an interface using React.js is used to update and display information to the user in real time.

[0722] Step 7:

[0723] Users monitor data through the administration panel and plan interactions as needed. They refer to the information displayed in step 6 as input. During processing, they plan communication with employees based on the displayed improvement suggestions. The output is an action plan, such as a specific feedback session. As concrete action, users schedule meetings in Google Calendar based on the information and implement feedback and improvement suggestions.

[0724] (Application Example 1)

[0725] 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".

[0726] Machine malfunctions and inefficient operation in production facilities reduce the overall efficiency of the manufacturing process, ultimately undermining a company's competitiveness. To address these problems, it is necessary to accurately and in real time evaluate the operating status of machinery and to quickly implement necessary improvements. However, conventional systems have the problem of taking too long to monitor the state of machinery and detect abnormalities, resulting in a lack of appropriate corrective measures.

[0727] 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.

[0728] In this invention, the server includes means for collecting operational information, environmental data, and machine status data; means for preprocessing the collected data; and a generating AI module for evaluating the machine's operational status using the preprocessed data. This enables real-time analysis of the machine's operational status and allows for rapid response.

[0729] "Operational information" refers to specific data that indicates the operating status of machinery and equipment.

[0730] "Environmental data" refers to information that describes the physical conditions of the environment in which a machine is operating.

[0731] "Machine condition data" refers to information that describes the internal and external condition of a machine.

[0732] "Means of collection" refers to the methods and equipment used to acquire data.

[0733] "Preprocessing means" refers to methods and devices for processing collected data into a format suitable for analysis and use.

[0734] A "generative AI module" is a component used to analyze data and derive results using artificial intelligence.

[0735] "Evaluating the operating state" means determining whether a machine is functioning normally or abnormally, and whether it is operating efficiently.

[0736] "Means of issuing warnings" refers to mechanisms or functions that draw attention when standards are not met.

[0737] "Means of proposing improvement measures" refers to components that show specific methods or actions to resolve the problem.

[0738] "Means of visualization" refer to methods and devices for displaying information and data in a way that is easy for people to understand.

[0739] To implement this invention, three elements—a server, a terminal, and a user—work together to constitute a system.

[0740] The server uses IoT gateways and sensors to collect operational information, environmental data, and machine status data from various machines operating within the factory. The collected data is preprocessed on the server, including data cleaning and normalization. The preprocessed data is then input into a generative AI model to evaluate the machine's operating status in real time. The generative AI model uses a model trained on a large amount of historical data to analyze abnormalities in operation and identify areas for improvement. If an abnormality is detected, the server issues a warning and proposes corrective measures to the user. These corrective measures include readjusting the operating load and suggesting maintenance.

[0741] The terminal functions as a dashboard easily accessible to factory managers and operators. This dashboard provides real-time visualization of machine operating status and improvement suggestions. The software used includes an application structure designed to provide a user-friendly UI interface.

[0742] This dashboard allows users to monitor the situation within the factory and take quick action when necessary. By acting on the suggested improvements, users can optimize machine performance and achieve efficient factory operations.

[0743] For example, if abnormal vibrations are detected in an assembly machine on a particular line, the system will analyze the cause and suggest that there is wear on a part of the machine. Based on this, the user will be advised to replace the part, thereby maintaining the factory's operational efficiency.

[0744] An example of a prompt for a generative AI is, "Based on the latest system data, please suggest the cause of the anomaly and the best course of action." By using this prompt, the generative AI model can perform appropriate analysis and provide effective solutions.

[0745] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0746] Step 1:

[0747] The server collects operational information, environmental data, and machine status data from each machine in the factory using sensors and an IoT gateway. It receives real-time data from machine sensors as input and stores it in cloud storage.

[0748] Step 2:

[0749] The server cleans and normalizes the collected data. This includes denoising the data and imputing missing values. Using the raw data obtained in step 1 as input, it produces well-formed data suitable for analysis as output.

[0750] Step 3:

[0751] The server inputs pre-processed data into a generating AI model. This model is trained on historical data and evaluates the current operating state of the machine. The input is well-formed data, and the output is a machine operation evaluation score and the likelihood of anomalies occurring.

[0752] Step 4:

[0753] The server uses the output of the generated AI model to issue a warning if the machine's operating status falls below a certain threshold. This warning indicates that an anomaly has been detected and that improvement is necessary. The operation evaluation score is used as input, and a warning message is generated as output.

[0754] Step 5:

[0755] The server generates corrective actions based on the warnings. These actions include suggestions for adjusting the operating load and performing component maintenance. The input is the result of the anomaly detection, and the output is a specific corrective action plan.

[0756] Step 6:

[0757] The terminal visualizes the machine's operating status and improvement measures received from the server on a dashboard. This allows administrators to understand the machine's status at a glance. The input is the improvement action plan, and the output is a visual dashboard display.

[0758] Step 7:

[0759] Users can quickly adjust and maintain machinery based on reports and suggestions from the dashboard. This helps maintain the factory's operational efficiency. The input is dashboard information, and the output is the stabilization of machine operation.

[0760] 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.

[0761] In this embodiment of the invention, a system for managing the level of employee engagement operates on a cloud-based platform and consists of three elements: a server, a terminal, and a user.

[0762] The server connects with relevant corporate systems via various APIs to collect employee work information, opinion data, and health information. It also features an emotion engine that uses natural language processing to analyze collected opinion data and recognize employee emotions. This allows for the scoring of emotions, such as positive or negative, and is used to calculate the level of engagement.

[0763] Next, the server inputs the pre-processed data and emotional information obtained from the emotion engine into the generating AI module, which then uses this information to calculate the level of involvement for each employee. In this process, the emotional information is used in particular to weight the opinion data, improving the accuracy of the involvement level calculation.

[0764] If the calculated level of involvement falls below a certain threshold, the server sends an automatically generated warning to HR personnel and managers. The warning then suggests corrective actions such as workload redistribution, vacation suggestions, and improved health management. These corrective actions are individually optimized based on the identified emotional information.

[0765] The device provides an administrator dashboard that displays engagement levels, emotional trends, and suggested improvements in real time. The dashboard is graphically designed, allowing users to intuitively understand the situation and make quick decisions.

[0766] Users (administrators and HR personnel) can leverage the terminal's dashboard to make data-driven decisions and direct specific actions for improvement. Accessing detailed information about each employee, including emotional data, helps provide effective communication and support.

[0767] For example, if negative emotions are frequently detected in an employee's opinion data, indicating a decrease in their level of engagement, the server will detect this and suggest implementing a stress reduction program or individual counseling to that employee. This allows users to quickly understand the problem and take appropriate action.

[0768] Thus, the system of the present invention can accurately evaluate the degree of employee engagement by combining data and emotion recognition, and can support the improvement of the workplace environment.

[0769] The following describes the processing flow.

[0770] Step 1:

[0771] The server continuously collects data via APIs from the work management system, feedback collection tools, and health tracking applications. This data includes each employee's work information, submitted feedback, and health indicators. The server ingests this data into a centralized data store.

[0772] Step 2:

[0773] The server performs data cleaning on the collected data. This cleaning includes interpolating missing values, removing invalid data entries, and normalizing the data format. This preprocessing enables analysis with high accuracy.

[0774] Step 3:

[0775] The server activates an emotion engine on the opinion data and uses natural language processing to analyze the sentiment of each comment. The sentiment is scored as positive, negative, or neutral and stored in the data store. This provides a quantitative representation of employees' emotional tendencies.

[0776] Step 4:

[0777] The server inputs pre-processed work information, health information, and scored sentiment information into a generating AI module to calculate each employee's level of involvement. This generating AI module learns from past data and performs precise scoring by evaluating the level of involvement in a multidimensional way.

[0778] Step 5:

[0779] The calculated level of involvement is compared to a baseline value. If the level of involvement falls below the baseline value, the server detects this as an anomaly and issues a warning. The warning includes an analysis of the cause of the decrease in involvement, and immediate action is required to take countermeasures.

[0780] Step 6:

[0781] The server automatically generates suggested improvements based on identified emotional information and the reasons for decreased engagement. These improvements may include, for example, adjusting workload, recommending vacations, and implementing health programs. The generated improvements are automatically notified to the responsible person.

[0782] Step 7:

[0783] The device provides a dashboard accessible to administrators and HR personnel, visually displaying engagement levels, sentiment information, alerts, and suggested improvements. The graphs and charts are concise and easy to understand, facilitating quick decision-making by users.

[0784] Step 8:

[0785] Users (administrators or HR personnel) use the information provided on the dashboard to plan interviews and feedback sessions with employees and strive to improve their level of engagement in the workplace by implementing specific improvement measures.

[0786] This processing flow allows the system of the present invention to analyze the degree of employee involvement in detail and to present effective improvement measures at the appropriate time.

[0787] (Example 2)

[0788] 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".

[0789] Accurately assessing the level of employee and individual involvement, and promptly providing appropriate improvement measures as needed, is crucial for improving the workplace environment and overall organizational efficiency. However, conventional systems have struggled to accurately analyze emotions, preprocess data, and integrate various types of information for effective evaluation, making it difficult to identify rapid and effective improvement measures.

[0790] 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.

[0791] In this invention, the server includes a function for acquiring information, a function for analyzing emotions using language processing technology, and a function for preprocessing data using the analysis results. This enables precise evaluation of the degree of involvement of employees or individuals, and the immediate presentation of appropriate improvement measures.

[0792] The "function for acquiring information" refers to the means of collecting necessary information from external systems or databases.

[0793] The "function to analyze emotions using language processing technology" refers to a method of identifying and analyzing emotions from text data using natural language processing technology.

[0794] A "data preprocessing function" is a means of preparing raw data into a format suitable for analysis and input to models.

[0795] A "generative model" refers to a machine learning algorithm used to calculate the characteristics and level of involvement of employees or individuals based on specific input data.

[0796] The "warning function" is a means of sending an alert to relevant parties when the results do not meet predetermined criteria.

[0797] The "function that proposes improvement measures" is a means of automatically generating and presenting appropriate countermeasures for a problem based on the calculated results.

[0798] A "visualization function" is a means of visualizing acquired data and analysis results on a graphical user interface, allowing stakeholders to intuitively understand the information.

[0799] This invention is a highly automated system for evaluating the level of involvement within companies and organizations and proposing improvement measures. Its main components are a server, terminals, and users, which work together to function.

[0800] The server operates on a cloud-based platform and collects work information, opinion data, and health information using various APIs. For example, it retrieves data from attendance management systems and opinion collection tools. The collected data is analyzed by an emotion analysis engine using natural language processing technology and converted into emotion scores such as positive and negative. This data is then used by generative models to calculate the degree of involvement.

[0801] Next, the server calculates the level of involvement of each employee or individual by inputting prompt messages into a generating AI model based on pre-processed data and sentiment information. A specific example of a prompt message is, "Analyze employee A's latest opinion data and provide sentiment score and level of involvement." As a result, if the server detects an involvement level below a certain threshold, it automatically generates a warning and sends it to managers or HR personnel.

[0802] The device receives data from the server and displays engagement levels, sentiment trends, and suggested improvements in real time on an administrator dashboard. This allows the device to function as a support tool for users to intuitively understand the data, quickly grasp the situation, and make decisions.

[0803] Users (administrators and HR personnel) can utilize the terminal's dashboard to access detailed information about each employee and provide effective communication and support. For example, they can suggest stress reduction programs or individual counseling to employees who frequently exhibit negative emotions and have decreased engagement.

[0804] Thus, the embodiment of the present invention achieves effective human resource management within an organization by using integrated technology, from data collection, sentiment analysis, and calculation of involvement levels to the proposal of improvement measures.

[0805] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0806] Step 1:

[0807] The server retrieves work information, opinion data, and health information from external systems via APIs. This input data is stored in a database and prepared as material for pre-processing and relationship building. Specifically, the process involves sending data retrieval requests to the API endpoint, receiving responses, and storing them.

[0808] Step 2:

[0809] The server uses a natural language processing engine to analyze emotions from acquired opinion data. Here, text data is taken as input, and positive or negative emotion scores are output. Specifically, it applies a text analysis algorithm and processes the data through an emotion classification model.

[0810] Step 3:

[0811] The server integrates the sentiment analysis results with other data and performs preprocessing. This generates a normalized dataset, which is then prepared as input for the generative AI model. Specifically, it performs data processing such as data cleaning, normalization, and feature selection.

[0812] Step 4:

[0813] The server inputs pre-processed data using prompts into a generative AI model to calculate the level of involvement for each employee. For example, it might send a prompt such as, "Analyze employee A's latest opinion data and provide a sentiment score and level of involvement." The output is the individual level of involvement score.

[0814] Step 5:

[0815] The server sends an automatically generated warning to HR personnel or managers if the calculated level of involvement falls below a certain threshold. Here, it receives a low involvement score as input and sends a warning message as output. Specific actions include distributing warnings via email or notification systems.

[0816] Step 6:

[0817] The terminal displays data received from the server on a dashboard. Input data includes involvement scores and related sentiment tendency information, while output is displayed as visually easy-to-understand graphs and charts. Specifically, it generates real-time graphics using a data visualization library.

[0818] Step 7:

[0819] Users (administrators and HR personnel) implement specific improvement measures based on the information displayed on the dashboard. Here, users receive information from the dashboard as input and decide on and execute improvement actions as output. Specific examples of actions include arranging face-to-face consultations with employees and proposing stress reduction programs.

[0820] (Application Example 2)

[0821] 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".

[0822] In an aging society, it is crucial for family members and caregivers to appropriately understand the emotional state of individuals and provide appropriate interventions as needed. However, current systems and devices are insufficient in recognizing emotions through everyday conversations and behaviors, and in automatically suggesting appropriate improvement measures based on the situation, making it difficult to respond effectively.

[0823] 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.

[0824] In this invention, the server includes means for collecting work information, opinion data, and health information; means for preprocessing the collected data; and a generative AI module that calculates the degree of involvement of individuals using the preprocessed data. This makes it possible to accurately grasp the emotions and degree of involvement of individuals in real time and to propose and support improvement measures as needed.

[0825] "Work information" refers to information related to an employee's working hours and job duties.

[0826] "Opinion data" refers to the thoughts and feelings expressed by individuals, collected as text data.

[0827] "Health information" refers to information about an individual's physical or mental health status.

[0828] "Preprocessing" refers to the process of organizing and processing collected data before analysis or training.

[0829] A "generative AI module" is a program module that uses artificial intelligence technology to generate specific results from data.

[0830] "Degree of involvement" is an indicator that shows how actively a person is involved in an activity or organization.

[0831] A "warning" refers to a notification that alerts you to a situation that deviates from the established criteria.

[0832] "Improvement measures" refer to specific means or suggestions for solving a problem and improving the situation.

[0833] "Visualization" is a technique that helps understand data and information by displaying them visually.

[0834] "Means of collecting opinion data from conversations and actions" refers to methods of collecting information through individuals' statements and actions.

[0835] "Means of recognizing emotions" refers to the processes and techniques for analyzing and evaluating a person's emotional state.

[0836] "Means of providing improvement measures based on emotional scores through assistive devices" refers to methods of providing feedback and countermeasures based on emotional analysis using assistive devices.

[0837] The system for implementing this invention centers around three elements: a server, a terminal, and a user. The server is responsible for collecting and managing individual work information, opinion data, and health information. Data collection is performed on a cloud platform using various APIs. Furthermore, the server is equipped with an emotion recognition engine and performs text analysis on the collected opinion data using natural language processing technology. This recognizes emotions and scores them as positive or negative.

[0838] Next, the generating AI module calculates an individual's level of involvement based on emotional information and other pre-processed data. Emotional information is particularly important for weighting opinion data, contributing to improved evaluation accuracy. If the calculated level of involvement falls below a certain threshold, the server automatically issues a warning and suggests improvement measures. These suggestions include workload reallocation, vacation suggestions, and improvements to health management, all optimized based on individual emotional information.

[0839] The device provides an interactive dashboard accessible to administrators, displaying individual engagement levels, emotional tendencies, and suggested improvements in real time. The dashboard is graphically designed, allowing administrators and stakeholders to intuitively understand the situation.

[0840] Users, or administrators and staff, can utilize the device's dashboard to make data-driven decisions and provide specific instructions for improvement. This enables effective communication and support, reducing the need for user intervention. Furthermore, access to detailed information, including emotional data, allows for appropriate responses tailored to the situation.

[0841] As a concrete example, in a home equipped with assistive devices, a robot analyzes speech and behavior, and if negative emotions are detected, it provides stress reduction measures and activity suggestions. Furthermore, the generating AI model uses prompts such as, "Generate a report that evaluates the level of engagement based on the user's recent emotions and opinions, and suggests improvement measures." This system enables efficient support that improves the quality of life for the elderly and individuals.

[0842] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0843] Step 1:

[0844] The server collects work information, opinion data, and health information using APIs. This input data includes digital information on each employee's working hours, daily opinion records, and health status. This forms the basis for data collection.

[0845] Step 2:

[0846] The server preprocesses the collected data. Specifically, it removes unnecessary information, standardizes the format, and performs word segmentation and normalization on text data. The input is the digital data collected in step 1, and the output is cleaned data suitable for analysis.

[0847] Step 3:

[0848] The server uses an emotion recognition engine to analyze pre-processed opinion data and score the emotions. The input for this step is pre-processed text data, which is classified as positive or negative using natural language processing techniques and outputs an emotion score.

[0849] Step 4:

[0850] The server uses a generation AI module to calculate the degree of involvement based on sentiment scores and other data. Sentiment scores are used to weight opinion data, contributing to improved accuracy of the involvement level. Inputs here are sentiment scores and health / work information, and output is the individual's involvement level.

[0851] Step 5:

[0852] The server checks if the calculated level of involvement falls below a certain threshold and issues a warning if it does. The input is the level of involvement data from step 4, and the output is the necessary warning message. The warning message is sent to the person in charge or the administrator.

[0853] Step 6:

[0854] The server suggests appropriate corrective actions based on the warning message. In this step, it utilizes involvement levels, emotional scores, and health data to automatically generate corrective actions such as workload redistribution, stress management, and vacation suggestions. The input is the warning information from step 5, and the output is the personalized corrective actions.

[0855] Step 7:

[0856] On the dashboard provided by the terminal, users can view individual levels of involvement, emotional tendencies, and suggested improvement measures in real time. With data visualization and interactive elements, this dashboard is intuitive to operate and understand, enabling users to make quick decisions. Inputs consist of various data from the system, and output is visually organized information.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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."

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] 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.

[0876] 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.

[0877] 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.

[0878] The following is further disclosed regarding the embodiments described above.

[0879] (Claim 1)

[0880] Means for collecting work information, opinion data, and health information,

[0881] Means for preprocessing the collected data,

[0882] A generative AI module that calculates the degree of employee involvement using the aforementioned preprocessed data,

[0883] A means of issuing a warning when the calculated level of involvement falls below the standard value,

[0884] A means of proposing corrective measures based on the aforementioned warning,

[0885] A means for visualizing the degree of involvement and the proposed improvement measures,

[0886] A system that includes this.

[0887] (Claim 2)

[0888] The system according to claim 1, wherein the improvement measures include reallocating workload, suggesting vacations, and improving health management.

[0889] (Claim 3)

[0890] The system according to claim 1, wherein the aforementioned warning is notified to HR personnel and managers in real time.

[0891]

[0892] "Example 1"

[0893] (Claim 1)

[0894] Means of collecting activity data,

[0895] Means for organizing the collected information,

[0896] A generating AI module that uses the aforementioned compiled information to calculate the degree of worker involvement,

[0897] A means of notifying when the calculated level of involvement falls below the standard value,

[0898] A means of proposing improvement measures based on the aforementioned notification,

[0899] Means for presenting the degree of involvement and proposed improvement measures,

[0900] A means of displaying the analysis results on the management screen,

[0901] Means for planning dialogue with employees,

[0902] An information processing system that includes this.

[0903] (Claim 2)

[0904] The information processing system according to claim 1, wherein the improvement measures include work adjustment, recommendation of vacations, and improvement of public health.

[0905] (Claim 3)

[0906] The information processing system according to claim 1, wherein the aforementioned notification is immediately transmitted to the person in charge of operations and the manager.

[0907] "Application Example 1"

[0908] (Claim 1)

[0909] Means for collecting operational information, environmental data, and machine status data,

[0910] Means for preprocessing the collected data,

[0911] A generation AI module that evaluates the operating state of the machine using the aforementioned preprocessed data,

[0912] A means of issuing a warning when the evaluated operating state falls below a standard value,

[0913] A means of proposing corrective measures based on the aforementioned warning,

[0914] Means for visualizing the aforementioned operating state and proposed improvement measures,

[0915] A system that includes this.

[0916] (Claim 2)

[0917] The system according to claim 1, wherein the improvement measures include adjusting the operating load, suggesting maintenance for parts, and optimizing the operating environment.

[0918] (Claim 3)

[0919] The system according to claim 1, wherein the aforementioned warning is notified to the administrator and operator in real time.

[0920] "Example 2 of combining an emotion engine"

[0921] (Claim 1)

[0922] The function to acquire information,

[0923] A function that analyzes emotions using language processing technology,

[0924] A function to preprocess data using the aforementioned analysis results,

[0925] A generative model that calculates the degree of involvement of the subject using the preprocessed data,

[0926] A function that issues a warning when the calculated level of involvement falls below the standard value,

[0927] A function that suggests corrective measures based on the aforementioned warning,

[0928] A function to visualize the degree of involvement and proposed improvement measures,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, wherein the improvement measures include reallocating workload, suggesting rest, and improving health maintenance.

[0932] (Claim 3)

[0933] The system according to claim 1, wherein the aforementioned warning is immediately notified to the person in charge and the operator.

[0934] "Application example 2 when combining with an emotional engine"

[0935] (Claim 1)

[0936] Means for collecting work information, opinion data, and health information,

[0937] Means for preprocessing the collected data,

[0938] A generative AI module that calculates the degree of involvement of individuals using the aforementioned preprocessed data,

[0939] A means of issuing a warning when the calculated level of involvement falls below the standard value,

[0940] A means of proposing corrective measures based on the aforementioned warning,

[0941] A means for visualizing the degree of involvement and the proposed improvement measures,

[0942] A means of collecting opinion data from conversations and actions and recognizing emotions,

[0943] A means of presenting improvement measures based on emotional scores through life support devices,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, wherein the improvement measures include work reallocation, vacation suggestions, improved health management, and suggestions for individualized measures.

[0947] (Claim 3)

[0948] The system according to claim 1, wherein the aforementioned warning notifies relevant parties and administrators of the situation. [Explanation of symbols]

[0949] 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. Means for collecting work information, opinion data, and health information, Means for preprocessing the collected data, A generative AI module that calculates the degree of employee involvement using the aforementioned preprocessed data, A means of issuing a warning when the calculated level of involvement falls below the standard value, A means of proposing corrective measures based on the aforementioned warning, A means for visualizing the degree of involvement and the proposed improvement measures, A system that includes this.

2. The system according to claim 1, wherein the improvement measures include reallocating workload, suggesting vacations, and improving health management.

3. The system according to claim 1, wherein the aforementioned warning is notified to HR personnel and managers in real time.

Images