system

Abstract

Provide a system. 【Solution means】 Work information acquisition means, Employee opinion input means, Health status acquisition means, Means for automatically calculating the degree of personnel involvement based on the work information, employee opinions, and health status, Means for issuing a warning according to the calculated degree of involvement, Means for presenting improvement measures based on the warning, Means for collecting the health status of the employees from wearable devices, Means for analyzing the collected data and proposing task improvements, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern workplace environment, appropriately managing and maintaining employee engagement is essential for the success of an organization. However, with the spread of remote work, it has become difficult to grasp the extent to which employees are engaged in the organization. With conventional methods, it is not possible to timely detect a decrease in engagement, and countermeasures are often taken only at the stage when the problem has become apparent. Therefore, it is an issue to prevent a decrease in engagement and improve employee satisfaction and productivity.

Means for Solving the Problems

[0005] This invention provides a system that automatically calculates employee engagement levels in real time using employee work information, opinions, and health status. Specifically, it combines data collection from internal systems as a means of acquiring work information, feedback forms as a means of inputting employee opinions, and data reception from wearable devices as a means of acquiring health status, and uses artificial intelligence to calculate engagement levels based on this data. Furthermore, if the engagement level falls below a certain threshold, it automatically issues a warning and presents specific improvement measures generated by artificial intelligence, enabling early detection and rapid response to problems.

[0006] "Means for acquiring work information" refers to a device or system that has the function of collecting data on employees' arrival and departure times, as well as data related to their work.

[0007] An "employee feedback input method" is a system that provides an interface for employees to input their work status, mood, and feedback.

[0008] A "means for acquiring health status" refers to a device or system that measures and records health-related data such as employees' heart rate and exercise levels.

[0009] "Engagement level" is an indicator that shows how actively employees participate in and are committed to an organization.

[0010] A "means of issuing warnings" is a system that sends notifications to administrators or employees to draw their attention when certain conditions are met.

[0011] A "means of presenting improvement measures" refers to a system that shows users specific action plans or suggestions to solve problems that have arisen. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0015] In the following embodiments, a processor with a reference numeral (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.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral 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.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

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

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0027] 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.

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

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system that calculates an engagement score using employee work information, opinions, and health status, enabling early detection of problems and the suggestion of improvement measures. This system is primarily implemented through data transmission and analysis between a server, terminals, and users.

[0034] The server integrates with various systems within the company to continuously acquire work information such as employee arrival and departure times and break times. The server also receives feedback and health data transmitted from terminals. This data is obtained through employee comments provided via terminals and aggregated on the server side as feedback.

[0035] The terminal plays a role in collecting employee feedback through a user interface. This interface allows users to answer questions about their work situation and feelings, and this data is sent to the server. The terminal also has the function of directly acquiring health-related information from wearable devices and sending it to the server.

[0036] The server calculates an engagement score in real time based on the received data. This process uses machine learning models to analyze work time trends, feedback content, and health parameters to generate the score. During this process, it compares the score with past data to detect outliers and sudden changes, and generates warnings.

[0037] For example, if a user provides feedback stating, "I'm tired because I've had too many meetings lately," the server will consider this emotional data and compile data on the tendency towards long working hours. If an increase in heart rate is detected based on health data, the engagement score will decrease, and the server will automatically suggest improvements. This system will notify the user and their manager via their terminal with specific action suggestions, such as "re-evaluate work priorities" or "encourage taking time off."

[0038] In this way, this system promotes company-wide productivity and employee well-being by having the server, terminal, and user work together to quantitatively evaluate employee engagement and quickly provide necessary countermeasures.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The terminal collects feedback from employees through its user interface. When a user enters their work situation and the level of stress they are experiencing into a feedback form and presses submit, that data is sent from the terminal to the server.

[0042] Step 2:

[0043] The server stores feedback data received from terminals and simultaneously retrieves work data, such as employee attendance and departure times, from the work management system. The server then organizes this data and prepares it for analysis.

[0044] Step 3:

[0045] The device periodically acquires the user's health-related data, such as heart rate and sleep patterns, through a wearable device. This data is also sent to a server.

[0046] Step 4:

[0047] The server standardizes the collected work data, feedback, and health data according to company regulations. If there are missing or outlier data values, it corrects or removes them appropriately.

[0048] Step 5:

[0049] The server uses a generative AI model to calculate each employee's engagement score from pre-processed data. The AI ​​model utilizes keywords included in feedback, patterns of work hour fluctuations, and trends in health data for analysis.

[0050] Step 6:

[0051] The server monitors the calculated engagement score and activates a mechanism to issue a warning if it falls below a certain threshold. This warning is sent to the user's and manager's terminals.

[0052] Step 7:

[0053] The server generates improvement suggestions based on an AI model predicting a decline in engagement scores. These suggestions include specific actions for the user, such as "taking a vacation" or "changing task priorities."

[0054] Step 8:

[0055] The terminal displays improvement suggestions sent from the server to the user. The user can review these suggestions and, if necessary, consult with their manager to implement them.

[0056] Step 9:

[0057] The server updates a dashboard that aggregates and visualizes overall engagement data. Administrators use this dashboard to identify trends across the organization and utilize it for strategic decision-making.

[0058] (Example 1)

[0059] 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."

[0060] In modern businesses, employee productivity and health management are critical issues. However, many organizations find it difficult to comprehensively understand employees' work performance, opinions, and health status, which can delay problem identification and the provision of appropriate solutions. In such situations, solutions that effectively improve employee engagement are needed.

[0061] 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.

[0062] In this invention, the server includes means for acquiring time data, means for inputting opinion data, and means for acquiring health data. This makes it possible to centrally collect and analyze employee work status, feedback, and health information. Furthermore, by calculating an engagement score based on the analyzed information and automatically generating improvement suggestions, the aim is to improve the productivity of the entire organization and maintain employee health.

[0063] "Time data acquisition means" refers to methods or devices for automatically collecting information related to employees' working hours, such as their arrival and departure times and break times.

[0064] "Opinion data input means" refers to an interface or device that allows employees to input feedback regarding their work content and feelings, and a mechanism for collecting that data.

[0065] "Health data acquisition means" refers to devices or systems for directly acquiring data related to employees' health status, such as heart rate and sleep duration.

[0066] "Means for automatically calculating numerical values" refers to methods and devices for analyzing collected time data, opinion data, and health data, and calculating employee engagement scores based on that analysis.

[0067] "Means of issuing notifications" refers to methods or devices for communicating warnings or information to employees and managers based on calculated figures.

[0068] "Means of presenting suggestions" refers to methods or devices for visually or audibly displaying automatically generated improvement measures to encourage employees to take appropriate action.

[0069] An "artificial intelligence model for analyzing data" is a model based on machine learning and data mining techniques used to analyze various types of collected data.

[0070] "Comparison means for detecting outliers and fluctuations" refers to methods or devices for identifying abnormal patterns or sudden changes by comparing past data with current data.

[0071] This invention is a data collection and analysis system for improving employee engagement, and is realized through the coordinated operation of servers, terminals, and users.

[0072] The server integrates with various systems within the company and automatically acquires work information such as employee clock-in, clock-out, and break times using time data acquisition methods. The software used is designed to receive data in real time via APIs. The server also uses AI models (for example, TENSORFLOW® or PyTorch) to analyze the collected data and generate an engagement score by quantifying it.

[0073] The terminal receives feedback data from employees via a user interface. Employees provide feedback by answering questions about their work situation and feelings. The terminal is equipped with a means for inputting feedback data, and a system is in place to allow users to easily input data. In addition, as a means of acquiring health data, data from wearable devices is automatically acquired using Bluetooth, etc., and transmitted to the server.

[0074] Users receive improvement suggestions generated based on their work status and health data. For example, if a user provides feedback such as "I'm tired because I've had too many meetings lately," the server uses a machine learning model to analyze that data. As a result, if the engagement score decreases, the server generates suggestions such as "re-evaluate your work priorities" or "take a vacation" and notifies the user through their device.

[0075] An example of a prompt message for running a generative AI model might be: "Input data: I've had a lot of meetings recently and I'm tired. Health data: My heart rate is higher than normal. Output: Engagement score and improvement suggestions."

[0076] Thus, this invention enables the integrated handling of various data within an organization, allowing for real-time feedback and the presentation of improvement suggestions. This facilitates efficient improvement of overall organizational productivity and management of employee health.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server retrieves time data via the company's internal system API. Inputs include data such as clock-in, clock-out, and break times, linked to employee IDs. The server stores this data in a dedicated database for future analysis. Outputs are work data organized in an appropriate format.

[0080] Step 2:

[0081] The terminal collects opinion data through a user interface. The input here consists of prompts in which employees provide feedback on their daily work and emotions. The terminal automatically sends this feedback to the server. The output is an organized dataset of employee opinions.

[0082] Step 3:

[0083] The terminal acquires health data from wearable devices. Inputs include physiological indicators such as heart rate and sleep duration, collected using Bluetooth or other connection methods. The terminal transfers the acquired health data to a server. The output is formatted health data.

[0084] Step 4:

[0085] The server integrates and analyzes time data, opinion data, and health data stored in the database. The input is all the data collected in steps 1 through 3 described above. The server uses a generative AI model to analyze the data and calculate employee engagement scores. The output is the numerical engagement score.

[0086] Step 5:

[0087] The server generates warnings to detect anomalies and sudden fluctuations based on the calculated engagement score, comparing it with historical data. Inputs include the current engagement score, historical data, and a default threshold. Output is a warning message for employees or administrators.

[0088] Step 6:

[0089] The server uses AI to generate improvement suggestions based on engagement scores and warnings. Inputs include generated scores, employee feedback, and health information. The generating AI model then produces specific action suggestions. The output is a list of improvement suggestions.

[0090] Step 7:

[0091] The server sends the generated improvement suggestions to the terminal, providing the information in a visually easy-to-understand format. The input is a list of improvement suggestions. The terminal notifies the user of these suggestions. The output is the visualized information and notification message.

[0092] Through these steps, the system enables comprehensive evaluation and feedback based on employee work information, opinions, and health status, contributing to improved organizational engagement.

[0093] (Application Example 1)

[0094] 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."

[0095] In the field of elderly care, it is crucial to properly manage the health and working conditions of staff. However, in a busy work environment, staff may suffer from overwork and health problems, which is a concern as it could affect the quality of care services. To address this issue, a system is needed that appropriately monitors staff involvement and promptly implements necessary improvement measures.

[0096] 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.

[0097] In this invention, the server includes means for acquiring work information, means for inputting employee opinions, and means for acquiring health status. This makes it possible to constantly monitor employees' work status and health status and automatically calculate their level of involvement. Based on this, warnings can be issued and improvement measures can be suggested, thereby achieving both improved employee health and increased work efficiency.

[0098] A "means for acquiring work information" refers to a method for automatically recording and collecting data related to employees' work, such as their arrival and departure times and break times.

[0099] "Employee feedback input method" refers to a means of providing an interface for employees to input opinions and feedback regarding their work situation and feelings.

[0100] "Means of acquiring health status" refers to methods for collecting health data of employees using wearable devices, etc.

[0101] "Methods for automatically calculating involvement levels" refer to methods for quantitatively calculating the degree of employee involvement in their work based on work information, employee opinions, and health data.

[0102] "Means of issuing warnings" refer to means of alerting staff and managers based on the calculated level of involvement.

[0103] "Means of proposing improvement measures" refers to methods for proposing specific improvement measures, such as reviewing work processes or taking leave, depending on the employee's level of involvement and health condition.

[0104] A "wearable device" is a device that employees can wear on a daily basis to monitor their health status.

[0105] A "Generative AI Module" is a program that uses artificial intelligence to automatically generate improvement measures from collected data.

[0106] This invention is a system that collects employee work information, opinions, and health status, and calculates their level of involvement. In this system, a server first interacts with various systems within the company to acquire work information such as employee arrival and departure times and break times. Furthermore, terminals provide an interface for collecting feedback from employees regarding their work situation and feelings. Health status is transmitted directly to the terminal via a wearable device and aggregated on the server.

[0107] The server stores this data in AWS® S3 and analyzes it using a machine learning model with AWS SageMaker. This makes it possible to calculate employee engagement levels in real time. If unusual values ​​or sudden fluctuations are detected, the server issues a warning and uses a generated AI module to suggest specific improvement measures, such as changing work priorities or recommending leave.

[0108] For example, if an employee inputs feedback stating, "My recent shifts have been too long and I'm exhausted," the server considers this feedback along with data indicating increased heart rate and evaluates their level of engagement as decreased. Using a generative AI model, it then suggests improvement measures such as "Consider taking weekends off." These improvement measures are generated by the generative AI model and sent as notifications to the employee's smartphone.

[0109] An example of a prompt might be: "Based on recent feedback and health data from care staff, calculate an engagement score and propose appropriate improvement measures."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server integrates with various systems within the company to automatically retrieve employee work information, such as arrival and departure times and break times. Input data comes from the company's internal attendance management system, and output is work data stored on the server. This data is later used to calculate employee engagement levels.

[0113] Step 2:

[0114] The terminal provides employees with an interface for collecting feedback. Employees input their opinions on work conditions and feelings, and this information is sent from the terminal to the server. The input is employee response data, and the output is opinion data stored on the server. This data is used for feedback analysis.

[0115] Step 3:

[0116] The server acquires data on employees' health status from wearable devices. Information such as heart rate and steps taken is input from the sensors of the wearable devices, aggregated and stored on the server. The output is data indicating health status, which is used as part of the involvement level calculation process.

[0117] Step 4:

[0118] The server uses all data stored in AWS S3 to perform analysis using machine learning models on AWS SageMaker. Inputs include work data, opinion data, and health status data, and the output is the calculated employee engagement level. This analysis makes it possible to evaluate employee status in real time.

[0119] Step 5:

[0120] The server detects anomalies and sudden fluctuations based on the calculation of involvement levels and issues warnings as needed. Warnings are generated using a generative AI model, and relevant information is notified to staff and administrators.

[0121] Step 6:

[0122] The server uses a generative AI model to generate specific improvement measures, such as changing task priorities or recommending leave, from the collected data. The input is involvement data indicating outliers, and the output is the text of the improvement measures. The generated improvement measures are notified to the employee's terminal and implemented.

[0123] Step 7:

[0124] The user's terminal receives improvement suggestions sent from the server and notifies the staff. Staff can then review the notification and take appropriate action. The input is the improvement suggestion message, and the output is instructions to prompt staff action. This feedback loop helps the system support staff well-being and improved work efficiency.

[0125] 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.

[0126] This invention is a system that calculates an engagement score based on employee work information, opinions, and health status, and further combines this with an emotion engine to recognize employees' emotions and stress, providing more precise analysis and countermeasures. This system operates in cooperation with servers, terminals, and users to manage the level of engagement of target employees in real time.

[0127] The server collects work information from data sources within the company and receives feedback data from users via terminals. The server also receives health data transmitted from terminals. This health data includes information related to the user's physical condition, such as heart rate and stress level.

[0128] The device provides an interface for receiving user feedback and has the functionality to send collected data to a server. Users regularly input their work status and emotions, which form the basis of the analysis. The device also acquires health information from wearable devices based on the user's permission and updates this information in real time.

[0129] The emotion engine is integrated into the server and analyzes received feedback data and health data to recognize the user's emotional state. This analysis includes sentiment analysis of feedback documents using natural language processing techniques and stress assessment based on vital data. The emotion engine identifies emotions from the user's opinions and calculates a precise stress level based on health data.

[0130] The server incorporates the analysis results from the emotion engine and uses the obtained data to calculate each employee's engagement score. This score is a comprehensive one that incorporates negative emotions captured by natural language processing and stress levels estimated from vital signs. For example, if a user writes in feedback that "My workload has increased recently and I'm feeling stressed," the emotion engine analyzes the sentence and recognizes the emotion of "stress," and also confirms a high-load state from health data. If this state continues for a long period, the user's engagement score will decrease, and the server will automatically issue a warning.

[0131] Furthermore, the server uses artificial intelligence to present specific improvement suggestions to the terminal based on this data. These suggestions include "revising work hours" and "suggesting short-term activities for relaxation." The terminal can notify the user of these suggestions and, if necessary, coordinate with the manager.

[0132] This system is expected to enhance overall organizational engagement by accurately understanding users' emotional states and stress fluctuations and providing immediate support.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The device periodically provides users with a feedback form. Users input data into the device by freely describing their current work situation and feelings in this form and submitting it.

[0136] Step 2:

[0137] The device acquires health data such as heart rate and activity levels from wearable devices via Bluetooth. This information is updated in real time and transmitted to the server.

[0138] Step 3:

[0139] The server collects and stores feedback data and health data received from the terminals in an integrated database.

[0140] Step 4:

[0141] The emotion engine initiates natural language processing of feedback within the server. It analyzes the input opinion data and identifies emotions such as positive, negative, and neutral.

[0142] Step 5:

[0143] Simultaneously, the emotion engine analyzes health data, particularly heart rate and activity levels, to assess stress levels. This assessment also includes comparisons with past health data.

[0144] Step 6:

[0145] The server calculates employee engagement scores based on emotional evaluations and stress levels, which are outputs from the emotion engine. A machine learning model then uses this data to perform the scoring.

[0146] Step 7:

[0147] The server monitors the engagement scores of all employees and issues a warning if the score falls below a certain threshold. The warning is notified to the terminal and displayed to the user and their administrator.

[0148] Step 8:

[0149] The server uses artificial intelligence to generate solutions to address the problems associated with the score decline. These solutions are adjusted based on the factors that affected the score.

[0150] Step 9:

[0151] The device presents the generated improvement plans to the user and guides them through the process to easily implement them. The user can review the improvement plans, consult with their manager if necessary, and then put them into action.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0154] In modern organizations, accurately understanding the level of engagement of individual users and responding to stress and emotional changes in real time is challenging. Traditional systems lack the ability to comprehensively analyze user biometric data and opinions and automatically suggest improvement measures. Furthermore, systems that provide appropriate feedback based on user engagement levels are limited.

[0155] 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.

[0156] In this invention, the server includes data acquisition means, user input means, and biometric information acquisition means. This enables comprehensive and real-time collection of user work status and biometric data, and allows for sentiment analysis and engagement level calculation based on this data. Furthermore, by automatically suggesting improvement measures using a generative AI model, it is possible to improve the level of engagement throughout the organization.

[0157] "Data acquisition means" refers to methods and devices for collecting diverse data related to users.

[0158] A "user input means" is an interface or device for receiving information or opinions from a user.

[0159] "Means for acquiring biometric information" refers to methods or devices for acquiring physical data such as a user's heart rate and stress level.

[0160] "Level of involvement" is an indicator that shows the degree to which a user is involved in the business or organization.

[0161] "Warning mechanisms" refer to methods or devices that notify users of a warning when their level of engagement falls below a certain threshold.

[0162] "Means of proposing improvement measures" refers to methods or devices that propose specific improvement plans based on the user's situation.

[0163] "Natural language processing technology" is a technology used to analyze user opinions and feedback to identify emotions.

[0164] A "generative AI model" is a technology that uses artificial intelligence to make suggestions and perform analyses based on user data.

[0165] This invention is a system that grasps the user's work status and emotional state in real time, calculates their level of involvement, and provides necessary improvement measures.

[0166] The server retrieves data from internal corporate sources via databases and internet connectivity. This includes data such as working hours and job descriptions. The server is equipped with natural language processing technology and AI models to analyze feedback received from users through their devices. The feedback data is analyzed using natural language processing technology to identify the user's emotions.

[0167] The device provides an interface for users to input their opinions and feelings, and sends that information to a server. Furthermore, based on user permission, it acquires biometric information such as heart rate and stress level from the wearable device and updates it in real time.

[0168] This system identifies the user's emotional state and stress levels and calculates their level of involvement based on that. Based on the calculated involvement level, the server uses an AI model to generate improvement suggestions, which are then presented to the user via their terminal. These suggestions may include "revising work hours" or "proposing short-term stress-relieving activities."

[0169] For example, if a user enters feedback stating, "My workload has increased recently, and I'm feeling stressed," the server's emotion engine analyzes the sentence and recognizes the emotion "stress." If this condition is determined to persist in conjunction with health data, the engagement score decreases. In this case, the server uses an AI model to generate improvement measures such as "reviewing work hours," and the terminal notifies the user of these measures.

[0170] An example of a prompt to input into the generating AI model would be: "Analyze the feedback sentences that users input daily, and use the emotion engine to recognize the user's emotional state. Based on the analysis results, calculate an engagement score and, if necessary, generate improvement measures to reduce stress."

[0171] In this way, providing optimized feedback and improvement measures is expected to enhance engagement across the entire organization.

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

[0173] Step 1:

[0174] The server retrieves work information from within the company via a database and internet connection. This information includes working hours and job duties. After receiving the work information as input, the server integrates this data and preprocesses it for analysis. Preprocessing includes deduplication of data and detection and correction of outliers. As output, the cleaned work information is used in the next step.

[0175] Step 2:

[0176] The terminal provides users with an interface for inputting feedback on work performance and emotions. Users periodically input feedback, and this data is sent from the terminal to the server. After receiving the feedback data as input, the server analyzes this data using natural language processing techniques to identify the emotional state. The data calculations performed here include sentiment analysis of the feedback document. As output, the emotional state is identified and used in the next step.

[0177] Step 3:

[0178] Based on user permission, the terminal acquires biometric information such as heart rate and stress level from the wearable device. This information is transmitted to the server in real time. After receiving the biometric information as input, the server performs a stress assessment. The data calculation is performed by analyzing heart rate fluctuations and quantifying the stress level. The quantified stress level is then used in the next step as output.

[0179] Step 4:

[0180] The server integrates the emotional state and stress level obtained in the previous step to calculate the user's engagement level. The input includes the emotional state and stress level. The data calculation is performed by combining these values ​​and quantifying them as an engagement level. The output is the calculated engagement level, which is used in the next step.

[0181] Step 5:

[0182] The server determines whether a warning needs to be issued based on the calculated involvement level. If the level falls below the threshold, a warning is generated. The input includes the involvement level. The output is a warning message, which is used in the next step.

[0183] Step 6:

[0184] The server uses a generative AI model to generate corrective actions based on warnings. Input includes warning messages and related data. The generated corrective actions may include suggestions for reviewing work hours or taking breaks. The output consists of specific corrective actions, which are then notified to the user via their terminal.

[0185] Step 7:

[0186] The terminal notifies the user of improvement measures sent from the server. The user can then adjust their daily work based on this information. The input includes improvement measures from the server. The output is a notification to the user, completing the system's processing.

[0187] (Application Example 2)

[0188] 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".

[0189] Managing staff stress and improving work efficiency are crucial issues in caregiving settings. In particular, it is necessary to understand staff emotional states and health information in real time and respond appropriately, but this is difficult to do effectively with conventional methods. Therefore, it is necessary to simultaneously reduce the burden on staff and improve the quality of care.

[0190] 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.

[0191] In this invention, the server includes means for acquiring work data, means for inputting employee opinions, and means for acquiring health information. This makes it possible to automatically calculate the level of employee involvement in real time based on their work data, opinions, and health information, and to provide appropriate warnings and corrective measures.

[0192] "Means for acquiring work data" refers to the means of collecting information related to employees' work and storing it in a database.

[0193] "Methods for inputting employee feedback" refers to providing an interface for employees to input feedback and opinions.

[0194] "Means of acquiring health information" refers to methods for acquiring health-related data of employees from wearable devices, etc.

[0195] "Engagement level" is an indicator that shows how actively employees are involved in their work, and is calculated based on work data, opinions, and health information.

[0196] "Natural language processing technology" is a technology that uses human language to allow computers to analyze data.

[0197] Artificial intelligence is a technology that gives computer systems the ability to learn and adapt knowledge by mimicking human intelligence.

[0198] A "generative AI model" is an artificial intelligence model trained to generate new information or results based on data.

[0199] To implement this system, a server first acquires and manages work data, employee opinions, and health information. A cloud-based database system is used to acquire work data. For employee opinion input, an interface is provided that allows employees to input their opinions via smartphone or PC. The data collected through this interface is analyzed for sentiment using natural language processing technology such as Google Cloud Natural Language. For health information acquisition, data is acquired via wearable devices such as smartwatches and transmitted to the server via Bluetooth connection.

[0200] The terminal receives this information and sends it to the server for analysis. The terminal is equipped with a function to display user data that is updated in real time and to notify staff of warnings and improvement suggestions as needed. Based on feedback from staff and health data, the server performs analysis using artificial intelligence libraries such as TensorFlow, and the generated AI model proposes improvement measures. These improvement measures include "suggestions for short breaks" and "adjustments to workload," and these are notified to staff.

[0201] For example, if an employee reports in feedback that they are "tired from working consecutive shifts recently," the server's emotion engine will recognize this information as the emotion of "fatigue" and determine that the stress level is high. Based on these analysis results, the system may suggest to the employee that they "consider adjusting their next shift."

[0202] An example of a prompt message is a "prompt to suggest a short break to manage the stress levels of care staff." The purpose is to support staff health management and work efficiency by presenting appropriate improvement measures based on staff feedback and health information.

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server retrieves employee work data from a cloud-based database. It receives work records from the database as input, converts them into a data format for internal processing, and then processes them into a format suitable for transmission to terminals. The output is the processed work data.

[0206] Step 2:

[0207] Users input their opinions through a smartphone or PC interface. The input, in text format, is received and sent to the server via the terminal. The terminal then parses this opinion and converts it into a well-formed format for processing.

[0208] Step 3:

[0209] The terminal acquires health information from wearable devices such as smartwatches via Bluetooth connection. Inputs include heart rate and stress levels, and this data is updated every second. As output, real-time health information is sent to a server and stored for each employee.

[0210] Step 4:

[0211] The server uses natural language processing technology to analyze the sentiment of employee opinions sent from terminals. It uses text data of employee opinions as input and quantifies the sentiment using APIs such as Google Cloud Natural Language. The output is a sentiment score.

[0212] Step 5:

[0213] The server uses TensorFlow to evaluate employee stress levels and engagement levels via a generative AI model, based on analyzed sentiment scores and health information. It accepts sentiment scores and health data as input and outputs the analysis results as a numerical engagement level.

[0214] Step 6:

[0215] The server uses a generated AI model to formulate specific improvement measures and create prompt messages to present to employees. The inputs are quantified levels of involvement and analyzed stress indicators, and the output are prompt messages such as "Suggest a short break" or "Adjust workload."

[0216] Step 7:

[0217] The terminal notifies the staff of the prompt message received from the server. The input is a prompt message presenting a solution, and the output is displayed as a notification on the staff member's smartphone or computer screen. The staff member adjusts their actions based on this information.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] 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.

[0224] 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).

[0225] 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.

[0226] 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.

[0227] 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).

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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".

[0234] This invention is a system that calculates an engagement score using employee work information, opinions, and health status, enabling early detection of problems and the suggestion of improvement measures. This system is primarily implemented through data transmission and analysis between a server, terminals, and users.

[0235] The server integrates with various systems within the company to continuously acquire work information such as employee arrival and departure times and break times. The server also receives feedback and health data transmitted from terminals. This data is obtained through employee comments provided via terminals and aggregated on the server side as feedback.

[0236] The terminal plays a role in collecting employee feedback through a user interface. This interface allows users to answer questions about their work situation and feelings, and this data is sent to the server. The terminal also has the function of directly acquiring health-related information from wearable devices and sending it to the server.

[0237] The server calculates an engagement score in real time based on the received data. This process uses machine learning models to analyze work time trends, feedback content, and health parameters to generate the score. During this process, it compares the score with past data to detect outliers and sudden changes, and generates warnings.

[0238] For example, if a user provides feedback stating, "I'm tired because I've had too many meetings lately," the server will consider this emotional data and compile data on the tendency towards long working hours. If an increase in heart rate is detected based on health data, the engagement score will decrease, and the server will automatically suggest improvements. This system will notify the user and their manager via their terminal with specific action suggestions, such as "re-evaluate work priorities" or "encourage taking time off."

[0239] In this way, this system promotes company-wide productivity and employee well-being by having the server, terminal, and user work together to quantitatively evaluate employee engagement and quickly provide necessary countermeasures.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The terminal collects feedback from employees through its user interface. When a user enters their work situation and the level of stress they are experiencing into a feedback form and presses submit, that data is sent from the terminal to the server.

[0243] Step 2:

[0244] The server stores feedback data received from terminals and simultaneously retrieves work data, such as employee attendance and departure times, from the work management system. The server then organizes this data and prepares it for analysis.

[0245] Step 3:

[0246] The device periodically acquires the user's health-related data, such as heart rate and sleep patterns, through a wearable device. This data is also sent to a server.

[0247] Step 4:

[0248] The server standardizes the collected work data, feedback, and health data according to company regulations. If there are missing or outlier data values, it corrects or removes them appropriately.

[0249] Step 5:

[0250] The server uses a generative AI model to calculate each employee's engagement score from pre-processed data. The AI ​​model utilizes keywords included in feedback, patterns of work hour fluctuations, and trends in health data for analysis.

[0251] Step 6:

[0252] The server monitors the calculated engagement score and activates a mechanism to issue a warning if it falls below a certain threshold. This warning is sent to the user's and manager's terminals.

[0253] Step 7:

[0254] The server generates improvement suggestions based on an AI model predicting a decline in engagement scores. These suggestions include specific actions for the user, such as "taking a vacation" or "changing task priorities."

[0255] Step 8:

[0256] The terminal displays improvement suggestions sent from the server to the user. The user can review these suggestions and, if necessary, consult with their manager to implement them.

[0257] Step 9:

[0258] The server updates a dashboard that aggregates and visualizes overall engagement data. Administrators use this dashboard to identify trends across the organization and utilize it for strategic decision-making.

[0259] (Example 1)

[0260] 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".

[0261] In modern businesses, employee productivity and health management are critical issues. However, many organizations find it difficult to comprehensively understand employees' work performance, opinions, and health status, which can delay problem identification and the provision of appropriate solutions. In such situations, solutions that effectively improve employee engagement are needed.

[0262] 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.

[0263] In this invention, the server includes means for acquiring time data, means for inputting opinion data, and means for acquiring health data. This makes it possible to centrally collect and analyze employee work status, feedback, and health information. Furthermore, by calculating an engagement score based on the analyzed information and automatically generating improvement suggestions, the aim is to improve the productivity of the entire organization and maintain employee health.

[0264] "Time data acquisition means" refers to methods or devices for automatically collecting information related to employees' working hours, such as their arrival and departure times and break times.

[0265] "Opinion data input means" refers to an interface or device that allows employees to input feedback regarding their work content and feelings, and a mechanism for collecting that data.

[0266] "Health data acquisition means" refers to devices or systems for directly acquiring data related to employees' health status, such as heart rate and sleep duration.

[0267] "Means for automatically calculating numerical values" refers to methods and devices for analyzing collected time data, opinion data, and health data, and calculating employee engagement scores based on that analysis.

[0268] "Means of issuing notifications" refers to methods or devices for communicating warnings or information to employees and managers based on calculated figures.

[0269] "Means of presenting suggestions" refers to methods or devices for visually or audibly displaying automatically generated improvement measures to encourage employees to take appropriate action.

[0270] An "artificial intelligence model for analyzing data" is a model based on machine learning and data mining techniques used to analyze various types of collected data.

[0271] "Comparison means for detecting outliers and fluctuations" refers to methods or devices for identifying abnormal patterns or sudden changes by comparing past data with current data.

[0272] This invention is a data collection and analysis system for improving employee engagement, and is realized through the coordinated operation of servers, terminals, and users.

[0273] The server integrates with various systems within the company and automatically acquires work information such as employee clock-in, clock-out, and break times using time data acquisition methods. The software used is designed to receive data in real time via APIs. The server also uses AI models (such as TensorFlow or PyTorch) to analyze the collected data and generate an engagement score by quantifying it.

[0274] The terminal receives feedback data from employees via a user interface. Employees provide feedback by answering questions about their work situation and feelings. The terminal is equipped with a means for inputting feedback data, and a system is in place to allow users to easily input data. In addition, as a means of acquiring health data, data from wearable devices is automatically acquired using Bluetooth, etc., and transmitted to the server.

[0275] Users receive improvement suggestions generated based on their work status and health data. For example, if a user provides feedback such as "I'm tired because I've had too many meetings lately," the server uses a machine learning model to analyze that data. As a result, if the engagement score decreases, the server generates suggestions such as "re-evaluate your work priorities" or "take a vacation" and notifies the user through their device.

[0276] An example of a prompt message for running a generative AI model might be: "Input data: I've had a lot of meetings recently and I'm tired. Health data: My heart rate is higher than normal. Output: Engagement score and improvement suggestions."

[0277] Thus, this invention enables the integrated handling of various data within an organization, allowing for real-time feedback and the presentation of improvement suggestions. This facilitates efficient improvement of overall organizational productivity and management of employee health.

[0278] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0279] Step 1:

[0280] The server obtains time data via the API of the enterprise internal system. The input is data such as attendance, leaving work, and break times associated with the employee ID. The server stores these data in a dedicated database for future analysis. The output is work data organized in an appropriate format.

[0281] Step 2:

[0282] The terminal collects opinion data through the user interface. The input here is the prompt text for employees to input feedback on daily work and feelings. The terminal automatically sends this feedback to the server. The output is an organized dataset regarding the opinions of employees.

[0283] Step 3:

[0284] The terminal obtains health data from the wearable device. The input includes physiological indicators such as heart rate and sleep time collected using Bluetooth or other connection means. The terminal transfers the obtained health data to the server. The output is formatted health data.

[0285] Step 4:

[0286] The server integrates and analyzes the time data, opinion data, and health data accumulated in the database. The input is all the data collected in Steps 1 to 3 above. The server uses a generated AI model for analysis and calculates the employee engagement score. The output is a quantified engagement score.

[0287] Step 5:

[0288] The server generates warnings to detect anomalies and sudden fluctuations based on the calculated engagement score, comparing it with historical data. Inputs include the current engagement score, historical data, and a default threshold. Output is a warning message for employees or administrators.

[0289] Step 6:

[0290] The server uses AI to generate improvement suggestions based on engagement scores and warnings. Inputs include generated scores, employee feedback, and health information. The generating AI model then produces specific action suggestions. The output is a list of improvement suggestions.

[0291] Step 7:

[0292] The server sends the generated improvement suggestions to the terminal, providing the information in a visually easy-to-understand format. The input is a list of improvement suggestions. The terminal notifies the user of these suggestions. The output is the visualized information and notification message.

[0293] Through these steps, the system enables comprehensive evaluation and feedback based on employee work information, opinions, and health status, contributing to improved organizational engagement.

[0294] (Application Example 1)

[0295] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0296] In the field of elderly care, it is crucial to properly manage the health and working conditions of staff. However, in a busy work environment, staff may suffer from overwork and health problems, which is a concern as it could affect the quality of care services. To address this issue, a system is needed that appropriately monitors staff involvement and promptly implements necessary improvement measures.

[0297] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0298] In this invention, the server includes means for acquiring work information, means for inputting employee opinions, and means for acquiring health status. This makes it possible to constantly monitor employees' work status and health status and automatically calculate their level of involvement. Based on this, warnings can be issued and improvement measures can be suggested, thereby achieving both improved employee health and increased work efficiency.

[0299] A "means for acquiring work information" refers to a method for automatically recording and collecting data related to employees' work, such as their arrival and departure times and break times.

[0300] "Employee feedback input method" refers to a means of providing an interface for employees to input opinions and feedback regarding their work situation and feelings.

[0301] "Means of acquiring health status" refers to methods for collecting health data of employees using wearable devices, etc.

[0302] "Methods for automatically calculating involvement levels" refer to methods for quantitatively calculating the degree of employee involvement in their work based on work information, employee opinions, and health data.

[0303] "Means of issuing warnings" refer to means of alerting staff and managers based on the calculated level of involvement.

[0304] "Means of proposing improvement measures" refers to methods for proposing specific improvement measures, such as reviewing work processes or taking leave, depending on the employee's level of involvement and health condition.

[0305] A "wearable device" is a device that employees can wear on a daily basis to monitor their health status.

[0306] The "Generative AI Module" is a program that uses artificial intelligence to automatically generate improvement measures from the collected data.

[0307] This invention is a system that collects employees' work information, opinions, and health status and calculates their engagement. In this system, first, the server cooperates with each system within the company to obtain work information such as employees' arrival and departure times and break times. Furthermore, the terminal provides an interface for collecting feedback from employees regarding their work situation and feelings. The health status is directly transmitted to the terminal via a wearable device and aggregated on the server.

[0308] The server stores these data in AWS S3 and performs analysis using a machine learning model with AWS SageMaker. This makes it possible to calculate employees' engagement in real time. When specific values or sudden fluctuations are detected, the server issues a warning and uses the Generative AI Module to propose specific improvement measures such as changing the business priority or recommending vacations.

[0309] As a specific example, when an employee inputs "The recent shift is too long and I'm tired" as feedback, the server considers this opinion and the rising heart rate data and evaluates the engagement as decreased. It presents improvement measures such as "Consider taking a vacation on the weekend" using the Generative AI model. This improvement measure is generated by the Generative AI model and notified to the employee's smartphone.

[0310] As an example of a prompt sentence, the text "Based on the recent feedback and health data of the care staff, calculate the engagement score and propose appropriate improvement measures." is used.

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

[0312] Step 1:

[0313] The server integrates with various systems within the company to automatically retrieve employee work information, such as arrival and departure times and break times. Input data comes from the company's internal attendance management system, and output is work data stored on the server. This data is later used to calculate employee engagement levels.

[0314] Step 2:

[0315] The terminal provides employees with an interface for collecting feedback. Employees input their opinions on work conditions and feelings, and this information is sent from the terminal to the server. The input is employee response data, and the output is opinion data stored on the server. This data is used for feedback analysis.

[0316] Step 3:

[0317] The server acquires data on employees' health status from wearable devices. Information such as heart rate and steps taken is input from the sensors of the wearable devices, aggregated and stored on the server. The output is data indicating health status, which is used as part of the involvement level calculation process.

[0318] Step 4:

[0319] The server uses all data stored in AWS S3 to perform analysis using machine learning models on AWS SageMaker. Inputs include work data, opinion data, and health status data, and the output is the calculated employee engagement level. This analysis makes it possible to evaluate employee status in real time.

[0320] Step 5:

[0321] The server detects anomalies and sudden fluctuations based on the calculation of involvement levels and issues warnings as needed. Warnings are generated using a generative AI model, and relevant information is notified to staff and administrators.

[0322] Step 6:

[0323] The server uses a generative AI model to generate specific improvement measures, such as changing task priorities or recommending leave, from the collected data. The input is involvement data indicating outliers, and the output is the text of the improvement measures. The generated improvement measures are notified to the employee's terminal and implemented.

[0324] Step 7:

[0325] The user's terminal receives improvement suggestions sent from the server and notifies the staff. Staff can then review the notification and take appropriate action. The input is the improvement suggestion message, and the output is instructions to prompt staff action. This feedback loop helps the system support staff well-being and improved work efficiency.

[0326] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0327] This invention is a system that calculates an engagement score based on employee work information, opinions, and health status, and further combines this with an emotion engine to recognize employees' emotions and stress, providing more precise analysis and countermeasures. This system operates in cooperation with servers, terminals, and users to manage the level of engagement of target employees in real time.

[0328] The server collects work information from data sources within the company and receives feedback data from users via terminals. The server also receives health data transmitted from terminals. This health data includes information related to the user's physical condition, such as heart rate and stress level.

[0329] The device provides an interface for receiving user feedback and has the functionality to send collected data to a server. Users regularly input their work status and emotions, which form the basis of the analysis. The device also acquires health information from wearable devices based on the user's permission and updates this information in real time.

[0330] The emotion engine is integrated into the server and analyzes received feedback data and health data to recognize the user's emotional state. This analysis includes sentiment analysis of feedback documents using natural language processing techniques and stress assessment based on vital data. The emotion engine identifies emotions from the user's opinions and calculates a precise stress level based on health data.

[0331] The server incorporates the analysis results from the emotion engine and uses the obtained data to calculate each employee's engagement score. This score is a comprehensive one that incorporates negative emotions captured by natural language processing and stress levels estimated from vital signs. For example, if a user writes in feedback that "My workload has increased recently and I'm feeling stressed," the emotion engine analyzes the sentence and recognizes the emotion of "stress," and also confirms a high-load state from health data. If this state continues for a long period, the user's engagement score will decrease, and the server will automatically issue a warning.

[0332] Furthermore, the server uses artificial intelligence to present specific improvement suggestions to the terminal based on this data. These suggestions include "revising work hours" and "suggesting short-term activities for relaxation." The terminal can notify the user of these suggestions and, if necessary, coordinate with the manager.

[0333] This system is expected to enhance overall organizational engagement by accurately understanding users' emotional states and stress fluctuations and providing immediate support.

[0334] The following describes the processing flow.

[0335] Step 1:

[0336] The device periodically provides users with a feedback form. Users input data into the device by freely describing their current work situation and feelings in this form and submitting it.

[0337] Step 2:

[0338] The device acquires health data such as heart rate and activity levels from wearable devices via Bluetooth. This information is updated in real time and transmitted to the server.

[0339] Step 3:

[0340] The server collects and stores feedback data and health data received from the terminals in an integrated database.

[0341] Step 4:

[0342] The emotion engine initiates natural language processing of feedback within the server. It analyzes the input opinion data and identifies emotions such as positive, negative, and neutral.

[0343] Step 5:

[0344] Simultaneously, the emotion engine analyzes health data, particularly heart rate and activity levels, to assess stress levels. This assessment also includes comparisons with past health data.

[0345] Step 6:

[0346] The server calculates employee engagement scores based on emotional evaluations and stress levels, which are outputs from the emotion engine. A machine learning model then uses this data to perform the scoring.

[0347] Step 7:

[0348] The server monitors the engagement scores of all employees and issues a warning if the score falls below a certain threshold. The warning is notified to the terminal and displayed to the user and their administrator.

[0349] Step 8:

[0350] The server uses artificial intelligence to generate solutions to address the problems associated with the score decline. These solutions are adjusted based on the factors that affected the score.

[0351] Step 9:

[0352] The device presents the generated improvement plans to the user and guides them through the process to easily implement them. The user can review the improvement plans, consult with their manager if necessary, and then put them into action.

[0353] (Example 2)

[0354] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0355] In modern organizations, accurately understanding the level of engagement of individual users and responding to stress and emotional changes in real time is challenging. Traditional systems lack the ability to comprehensively analyze user biometric data and opinions and automatically suggest improvement measures. Furthermore, systems that provide appropriate feedback based on user engagement levels are limited.

[0356] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0357] In this invention, the server includes data acquisition means, user input means, and biometric information acquisition means. This enables comprehensive and real-time collection of user work status and biometric data, and allows for sentiment analysis and engagement level calculation based on this data. Furthermore, by automatically suggesting improvement measures using a generative AI model, it is possible to improve the level of engagement throughout the organization.

[0358] "Data acquisition means" refers to methods and devices for collecting diverse data related to users.

[0359] A "user input means" is an interface or device for receiving information or opinions from a user.

[0360] "Means for acquiring biometric information" refers to methods or devices for acquiring physical data such as a user's heart rate and stress level.

[0361] "Level of involvement" is an indicator that shows the degree to which a user is involved in the business or organization.

[0362] "Warning mechanisms" refer to methods or devices that notify users of a warning when their level of engagement falls below a certain threshold.

[0363] "Means of proposing improvement measures" refers to methods or devices that propose specific improvement plans based on the user's situation.

[0364] "Natural language processing technology" is a technology used to analyze user opinions and feedback to identify emotions.

[0365] A "generative AI model" is a technology that uses artificial intelligence to make suggestions and perform analyses based on user data.

[0366] This invention is a system that grasps the user's work status and emotional state in real time, calculates their level of involvement, and provides necessary improvement measures.

[0367] The server retrieves data from internal corporate sources via databases and internet connectivity. This includes data such as working hours and job descriptions. The server is equipped with natural language processing technology and AI models to analyze feedback received from users through their devices. The feedback data is analyzed using natural language processing technology to identify the user's emotions.

[0368] The device provides an interface for users to input their opinions and feelings, and sends that information to a server. Furthermore, based on user permission, it acquires biometric information such as heart rate and stress level from the wearable device and updates it in real time.

[0369] This system identifies the user's emotional state and stress levels and calculates their level of involvement based on that. Based on the calculated involvement level, the server uses an AI model to generate improvement suggestions, which are then presented to the user via their terminal. These suggestions may include "revising work hours" or "proposing short-term stress-relieving activities."

[0370] For example, if a user enters feedback stating, "My workload has increased recently, and I'm feeling stressed," the server's emotion engine analyzes the sentence and recognizes the emotion "stress." If this condition is determined to persist in conjunction with health data, the engagement score decreases. In this case, the server uses an AI model to generate improvement measures such as "reviewing work hours," and the terminal notifies the user of these measures.

[0371] An example of a prompt to input into the generating AI model would be: "Analyze the feedback sentences that users input daily, and use the emotion engine to recognize the user's emotional state. Based on the analysis results, calculate an engagement score and, if necessary, generate improvement measures to reduce stress."

[0372] In this way, providing optimized feedback and improvement measures is expected to enhance engagement across the entire organization.

[0373] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0374] Step 1:

[0375] The server retrieves work information from within the company via a database and internet connection. This information includes working hours and job duties. After receiving the work information as input, the server integrates this data and preprocesses it for analysis. Preprocessing includes deduplication of data and detection and correction of outliers. As output, the cleaned work information is used in the next step.

[0376] Step 2:

[0377] The terminal provides users with an interface for inputting feedback on work performance and emotions. Users periodically input feedback, and this data is sent from the terminal to the server. After receiving the feedback data as input, the server analyzes this data using natural language processing techniques to identify the emotional state. The data calculations performed here include sentiment analysis of the feedback document. As output, the emotional state is identified and used in the next step.

[0378] Step 3:

[0379] Based on user permission, the terminal acquires biometric information such as heart rate and stress level from the wearable device. This information is transmitted to the server in real time. After receiving the biometric information as input, the server performs a stress assessment. The data calculation is performed by analyzing heart rate fluctuations and quantifying the stress level. The quantified stress level is then used in the next step as output.

[0380] Step 4:

[0381] The server integrates the emotional state and stress level obtained in the previous step to calculate the user's engagement level. The input includes the emotional state and stress level. The data calculation is performed by combining these values ​​and quantifying them as an engagement level. The output is the calculated engagement level, which is used in the next step.

[0382] Step 5:

[0383] The server determines whether a warning needs to be issued based on the calculated involvement level. If the level falls below the threshold, a warning is generated. The input includes the involvement level. The output is a warning message, which is used in the next step.

[0384] Step 6:

[0385] The server uses a generative AI model to generate corrective actions based on warnings. Input includes warning messages and related data. The generated corrective actions may include suggestions for reviewing work hours or taking breaks. The output consists of specific corrective actions, which are then notified to the user via their terminal.

[0386] Step 7:

[0387] The terminal notifies the user of improvement measures sent from the server. The user can then adjust their daily work based on this information. The input includes improvement measures from the server. The output is a notification to the user, completing the system's processing.

[0388] (Application Example 2)

[0389] 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."

[0390] Managing staff stress and improving work efficiency are crucial issues in caregiving settings. In particular, it is necessary to understand staff emotional states and health information in real time and respond appropriately, but this is difficult to do effectively with conventional methods. Therefore, it is necessary to simultaneously reduce the burden on staff and improve the quality of care.

[0391] 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.

[0392] In this invention, the server includes means for acquiring work data, means for inputting employee opinions, and means for acquiring health information. This makes it possible to automatically calculate the level of employee involvement in real time based on their work data, opinions, and health information, and to provide appropriate warnings and corrective measures.

[0393] "Means for acquiring work data" refers to the means of collecting information related to employees' work and storing it in a database.

[0394] "Methods for inputting employee feedback" refers to providing an interface for employees to input feedback and opinions.

[0395] "Means of acquiring health information" refers to methods for acquiring health-related data of employees from wearable devices, etc.

[0396] "Engagement level" is an indicator that shows how actively employees are involved in their work, and is calculated based on work data, opinions, and health information.

[0397] "Natural language processing technology" is a technology that uses human language to allow computers to analyze data.

[0398] Artificial intelligence is a technology that gives computer systems the ability to learn and adapt knowledge by mimicking human intelligence.

[0399] A "generative AI model" is an artificial intelligence model trained to generate new information or results based on data.

[0400] To implement this system, a server first acquires and manages work data, employee feedback, and health information. A cloud-based database system is used to acquire work data. For employee feedback input, an interface is provided that allows employees to input their opinions via smartphone or PC. The data collected through this interface is analyzed for sentiment using natural language processing technology such as Google Cloud Natural Language. For health information acquisition, data is acquired via wearable devices such as smartwatches and transmitted to the server via Bluetooth connection.

[0401] The terminal receives this information and sends it to the server for analysis. The terminal is equipped with a function to display user data that is updated in real time and to notify staff of warnings and improvement suggestions as needed. Based on feedback from staff and health data, the server performs analysis using artificial intelligence libraries such as TensorFlow, and the generated AI model proposes improvement measures. These improvement measures include "suggestions for short breaks" and "adjustments to workload," and these are notified to staff.

[0402] For example, if an employee reports in feedback that they are "tired from working consecutive shifts recently," the server's emotion engine will recognize this information as the emotion of "fatigue" and determine that the stress level is high. Based on these analysis results, the system may suggest to the employee that they "consider adjusting their next shift."

[0403] An example of a prompt message is a "prompt to suggest a short break to manage the stress levels of care staff." The purpose is to support staff health management and work efficiency by presenting appropriate improvement measures based on staff feedback and health information.

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The server retrieves employee work data from a cloud-based database. It receives work records from the database as input, converts them into a data format for internal processing, and then processes them into a format suitable for transmission to terminals. The output is the processed work data.

[0407] Step 2:

[0408] Users input their opinions through a smartphone or PC interface. The input, in text format, is received and sent to the server via the terminal. The terminal then parses this opinion and converts it into a well-formed format for processing.

[0409] Step 3:

[0410] The terminal acquires health information from wearable devices such as smartwatches via Bluetooth connection. Inputs include heart rate and stress levels, and this data is updated every second. As output, real-time health information is sent to a server and stored for each employee.

[0411] Step 4:

[0412] The server uses natural language processing technology to analyze the sentiment of employee opinions sent from terminals. It uses text data of employee opinions as input and quantifies the sentiment using APIs such as Google Cloud Natural Language. The output is a sentiment score.

[0413] Step 5:

[0414] The server uses TensorFlow to evaluate employee stress levels and engagement levels via a generative AI model, based on analyzed sentiment scores and health information. It accepts sentiment scores and health data as input and outputs the analysis results as a numerical engagement level.

[0415] Step 6:

[0416] The server uses a generated AI model to formulate specific improvement measures and create prompt messages to present to employees. The inputs are quantified levels of involvement and analyzed stress indicators, and the output are prompt messages such as "Suggest a short break" or "Adjust workload."

[0417] Step 7:

[0418] The terminal notifies the staff of the prompt message received from the server. The input is a prompt message presenting a solution, and the output is displayed as a notification on the staff member's smartphone or computer screen. The staff member adjusts their actions based on this information.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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).

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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".

[0435] This invention is a system that calculates an engagement score using employee work information, opinions, and health status, enabling early detection of problems and the suggestion of improvement measures. This system is primarily implemented through data transmission and analysis between a server, terminals, and users.

[0436] The server integrates with various systems within the company to continuously acquire work information such as employee arrival and departure times and break times. The server also receives feedback and health data transmitted from terminals. This data is obtained through employee comments provided via terminals and aggregated on the server side as feedback.

[0437] The terminal plays a role in collecting employee feedback through a user interface. This interface allows users to answer questions about their work situation and feelings, and this data is sent to the server. The terminal also has the function of directly acquiring health-related information from wearable devices and sending it to the server.

[0438] The server calculates an engagement score in real time based on the received data. This process uses machine learning models to analyze work time trends, feedback content, and health parameters to generate the score. During this process, it compares the score with past data to detect outliers and sudden changes, and generates warnings.

[0439] For example, if a user provides feedback stating, "I'm tired because I've had too many meetings lately," the server will consider this emotional data and compile data on the tendency towards long working hours. If an increase in heart rate is detected based on health data, the engagement score will decrease, and the server will automatically suggest improvements. This system will notify the user and their manager via their terminal with specific action suggestions, such as "re-evaluate work priorities" or "encourage taking time off."

[0440] In this way, this system promotes company-wide productivity and employee well-being by having the server, terminal, and user work together to quantitatively evaluate employee engagement and quickly provide necessary countermeasures.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The terminal collects feedback from employees through its user interface. When a user enters their work situation and the level of stress they are experiencing into a feedback form and presses submit, that data is sent from the terminal to the server.

[0444] Step 2:

[0445] The server stores feedback data received from terminals and simultaneously retrieves work data, such as employee attendance and departure times, from the work management system. The server then organizes this data and prepares it for analysis.

[0446] Step 3:

[0447] The device periodically acquires the user's health-related data, such as heart rate and sleep patterns, through a wearable device. This data is also sent to a server.

[0448] Step 4:

[0449] The server standardizes the collected work data, feedback, and health data according to company regulations. If there are missing or outlier data values, it corrects or removes them appropriately.

[0450] Step 5:

[0451] The server uses a generative AI model to calculate each employee's engagement score from pre-processed data. The AI ​​model utilizes keywords included in feedback, patterns of work hour fluctuations, and trends in health data for analysis.

[0452] Step 6:

[0453] The server monitors the calculated engagement score and activates a mechanism to issue a warning if it falls below a certain threshold. This warning is sent to the user's and manager's terminals.

[0454] Step 7:

[0455] The server generates improvement suggestions based on an AI model predicting a decline in engagement scores. These suggestions include specific actions for the user, such as "taking a vacation" or "changing task priorities."

[0456] Step 8:

[0457] The terminal displays improvement suggestions sent from the server to the user. The user can review these suggestions and, if necessary, consult with their manager to implement them.

[0458] Step 9:

[0459] The server updates a dashboard that aggregates and visualizes overall engagement data. Administrators use this dashboard to identify trends across the organization and utilize it for strategic decision-making.

[0460] (Example 1)

[0461] 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."

[0462] In modern businesses, employee productivity and health management are critical issues. However, many organizations find it difficult to comprehensively understand employees' work performance, opinions, and health status, which can delay problem identification and the provision of appropriate solutions. In such situations, solutions that effectively improve employee engagement are needed.

[0463] 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.

[0464] In this invention, the server includes means for acquiring time data, means for inputting opinion data, and means for acquiring health data. This makes it possible to centrally collect and analyze employee work status, feedback, and health information. Furthermore, by calculating an engagement score based on the analyzed information and automatically generating improvement suggestions, the aim is to improve the productivity of the entire organization and maintain employee health.

[0465] "Time data acquisition means" refers to methods or devices for automatically collecting information related to employees' working hours, such as their arrival and departure times and break times.

[0466] "Opinion data input means" refers to an interface or device that allows employees to input feedback regarding their work content and feelings, and a mechanism for collecting that data.

[0467] "Health data acquisition means" refers to devices or systems for directly acquiring data related to employees' health status, such as heart rate and sleep duration.

[0468] "Means for automatically calculating numerical values" refers to methods and devices for analyzing collected time data, opinion data, and health data, and calculating employee engagement scores based on that analysis.

[0469] "Means of issuing notifications" refers to methods or devices for communicating warnings or information to employees and managers based on calculated figures.

[0470] "Means of presenting suggestions" refers to methods or devices for visually or audibly displaying automatically generated improvement measures to encourage employees to take appropriate action.

[0471] An "artificial intelligence model for analyzing data" is a model based on machine learning and data mining techniques used to analyze various types of collected data.

[0472] "Comparison means for detecting outliers and fluctuations" refers to methods or devices for identifying abnormal patterns or sudden changes by comparing past data with current data.

[0473] This invention is a data collection and analysis system for improving employee engagement, and is realized through the coordinated operation of servers, terminals, and users.

[0474] The server integrates with various systems within the company and automatically acquires work information such as employee clock-in, clock-out, and break times using time data acquisition methods. The software used is designed to receive data in real time via APIs. The server also uses AI models (such as TensorFlow or PyTorch) to analyze the collected data and generate an engagement score by quantifying it.

[0475] The terminal receives feedback data from employees via a user interface. Employees provide feedback by answering questions about their work situation and feelings. The terminal is equipped with a means for inputting feedback data, and a system is in place to allow users to easily input data. In addition, as a means of acquiring health data, data from wearable devices is automatically acquired using Bluetooth, etc., and transmitted to the server.

[0476] Users receive improvement suggestions generated based on their work status and health data. For example, if a user provides feedback such as "I'm tired because I've had too many meetings lately," the server uses a machine learning model to analyze that data. As a result, if the engagement score decreases, the server generates suggestions such as "re-evaluate your work priorities" or "take a vacation" and notifies the user through their device.

[0477] An example of a prompt message for running a generative AI model might be: "Input data: I've had a lot of meetings recently and I'm tired. Health data: My heart rate is higher than normal. Output: Engagement score and improvement suggestions."

[0478] Thus, this invention enables the integrated handling of various data within an organization, allowing for real-time feedback and the presentation of improvement suggestions. This facilitates efficient improvement of overall organizational productivity and management of employee health.

[0479] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0480] Step 1:

[0481] The server retrieves time data via the company's internal system API. Inputs include data such as clock-in, clock-out, and break times, linked to employee IDs. The server stores this data in a dedicated database for future analysis. Outputs are work data organized in an appropriate format.

[0482] Step 2:

[0483] The terminal collects opinion data through a user interface. The input here consists of prompts in which employees provide feedback on their daily work and emotions. The terminal automatically sends this feedback to the server. The output is an organized dataset of employee opinions.

[0484] Step 3:

[0485] The terminal acquires health data from wearable devices. Inputs include physiological indicators such as heart rate and sleep duration, collected using Bluetooth or other connection methods. The terminal transfers the acquired health data to a server. The output is formatted health data.

[0486] Step 4:

[0487] The server integrates and analyzes time data, opinion data, and health data stored in the database. The input is all the data collected in steps 1 through 3 described above. The server uses a generative AI model to analyze the data and calculate employee engagement scores. The output is the numerical engagement score.

[0488] Step 5:

[0489] The server generates warnings to detect anomalies and sudden fluctuations based on the calculated engagement score, comparing it with historical data. Inputs include the current engagement score, historical data, and a default threshold. Output is a warning message for employees or administrators.

[0490] Step 6:

[0491] The server uses AI to generate improvement suggestions based on engagement scores and warnings. Inputs include generated scores, employee feedback, and health information. The generating AI model then produces specific action suggestions. The output is a list of improvement suggestions.

[0492] Step 7:

[0493] The server sends the generated improvement suggestions to the terminal, providing the information in a visually easy-to-understand format. The input is a list of improvement suggestions. The terminal notifies the user of these suggestions. The output is the visualized information and notification message.

[0494] Through these steps, the system enables comprehensive evaluation and feedback based on employee work information, opinions, and health status, contributing to improved organizational engagement.

[0495] (Application Example 1)

[0496] 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."

[0497] In the field of elderly care, it is crucial to properly manage the health and working conditions of staff. However, in a busy work environment, staff may suffer from overwork and health problems, which is a concern as it could affect the quality of care services. To address this issue, a system is needed that appropriately monitors staff involvement and promptly implements necessary improvement measures.

[0498] 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.

[0499] In this invention, the server includes means for acquiring work information, means for inputting employee opinions, and means for acquiring health status. This makes it possible to constantly monitor employees' work status and health status and automatically calculate their level of involvement. Based on this, warnings can be issued and improvement measures can be suggested, thereby achieving both improved employee health and increased work efficiency.

[0500] A "means for acquiring work information" refers to a method for automatically recording and collecting data related to employees' work, such as their arrival and departure times and break times.

[0501] "Employee feedback input method" refers to a means of providing an interface for employees to input opinions and feedback regarding their work situation and feelings.

[0502] "Means of acquiring health status" refers to methods for collecting health data of employees using wearable devices, etc.

[0503] "Methods for automatically calculating involvement levels" refer to methods for quantitatively calculating the degree of employee involvement in their work based on work information, employee opinions, and health data.

[0504] "Means of issuing warnings" refer to means of alerting staff and managers based on the calculated level of involvement.

[0505] "Means of proposing improvement measures" refers to methods for proposing specific improvement measures, such as reviewing work processes or taking leave, depending on the employee's level of involvement and health condition.

[0506] A "wearable device" is a device that employees can wear on a daily basis to monitor their health status.

[0507] A "Generative AI Module" is a program that uses artificial intelligence to automatically generate improvement measures from collected data.

[0508] This invention is a system that collects employee work information, opinions, and health status, and calculates their level of involvement. In this system, a server first interacts with various systems within the company to acquire work information such as employee arrival and departure times and break times. Furthermore, terminals provide an interface for collecting feedback from employees regarding their work situation and feelings. Health status is transmitted directly to the terminal via a wearable device and aggregated on the server.

[0509] The server stores this data in AWS S3 and analyzes it using a machine learning model with AWS SageMaker. This makes it possible to calculate employee engagement levels in real time. If unusual values ​​or sudden fluctuations are detected, the server issues a warning and uses a generated AI module to suggest specific improvement measures, such as changing work priorities or recommending leave.

[0510] For example, if an employee inputs feedback stating, "My recent shifts have been too long and I'm exhausted," the server considers this feedback along with data indicating increased heart rate and evaluates their level of engagement as decreased. Using a generative AI model, it then suggests improvement measures such as "Consider taking weekends off." These improvement measures are generated by the generative AI model and sent as notifications to the employee's smartphone.

[0511] An example of a prompt might be: "Based on recent feedback and health data from care staff, calculate an engagement score and propose appropriate improvement measures."

[0512] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0513] Step 1:

[0514] The server integrates with various systems within the company to automatically retrieve employee work information, such as arrival and departure times and break times. Input data comes from the company's internal attendance management system, and output is work data stored on the server. This data is later used to calculate employee engagement levels.

[0515] Step 2:

[0516] The terminal provides employees with an interface for collecting feedback. Employees input their opinions on work conditions and feelings, and this information is sent from the terminal to the server. The input is employee response data, and the output is opinion data stored on the server. This data is used for feedback analysis.

[0517] Step 3:

[0518] The server acquires data on employees' health status from wearable devices. Information such as heart rate and steps taken is input from the sensors of the wearable devices, aggregated and stored on the server. The output is data indicating health status, which is used as part of the involvement level calculation process.

[0519] Step 4:

[0520] The server uses all data stored in AWS S3 to perform analysis using machine learning models on AWS SageMaker. Inputs include work data, opinion data, and health status data, and the output is the calculated employee engagement level. This analysis makes it possible to evaluate employee status in real time.

[0521] Step 5:

[0522] The server detects anomalies and sudden fluctuations based on the calculation of involvement levels and issues warnings as needed. Warnings are generated using a generative AI model, and relevant information is notified to staff and administrators.

[0523] Step 6:

[0524] The server uses a generative AI model to generate specific improvement measures, such as changing task priorities or recommending leave, from the collected data. The input is involvement data indicating outliers, and the output is the text of the improvement measures. The generated improvement measures are notified to the employee's terminal and implemented.

[0525] Step 7:

[0526] The user's terminal receives improvement suggestions sent from the server and notifies the staff. Staff can then review the notification and take appropriate action. The input is the improvement suggestion message, and the output is instructions to prompt staff action. This feedback loop helps the system support staff well-being and improved work efficiency.

[0527] 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.

[0528] This invention is a system that calculates an engagement score based on employee work information, opinions, and health status, and further combines this with an emotion engine to recognize employees' emotions and stress, providing more precise analysis and countermeasures. This system operates in cooperation with servers, terminals, and users to manage the level of engagement of target employees in real time.

[0529] The server collects work information from data sources within the company and receives feedback data from users via terminals. The server also receives health data transmitted from terminals. This health data includes information related to the user's physical condition, such as heart rate and stress level.

[0530] The device provides an interface for receiving user feedback and has the functionality to send collected data to a server. Users regularly input their work status and emotions, which form the basis of the analysis. The device also acquires health information from wearable devices based on the user's permission and updates this information in real time.

[0531] The emotion engine is integrated into the server and analyzes received feedback data and health data to recognize the user's emotional state. This analysis includes sentiment analysis of feedback documents using natural language processing techniques and stress assessment based on vital data. The emotion engine identifies emotions from the user's opinions and calculates a precise stress level based on health data.

[0532] The server incorporates the analysis results from the emotion engine and uses the obtained data to calculate each employee's engagement score. This score is a comprehensive one that incorporates negative emotions captured by natural language processing and stress levels estimated from vital signs. For example, if a user writes in feedback that "My workload has increased recently and I'm feeling stressed," the emotion engine analyzes the sentence and recognizes the emotion of "stress," and also confirms a high-load state from health data. If this state continues for a long period, the user's engagement score will decrease, and the server will automatically issue a warning.

[0533] Furthermore, the server uses artificial intelligence to present specific improvement suggestions to the terminal based on this data. These suggestions include "revising work hours" and "suggesting short-term activities for relaxation." The terminal can notify the user of these suggestions and, if necessary, coordinate with the manager.

[0534] This system is expected to enhance overall organizational engagement by accurately understanding users' emotional states and stress fluctuations and providing immediate support.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The device periodically provides users with a feedback form. Users input data into the device by freely describing their current work situation and feelings in this form and submitting it.

[0538] Step 2:

[0539] The device acquires health data such as heart rate and activity levels from wearable devices via Bluetooth. This information is updated in real time and transmitted to the server.

[0540] Step 3:

[0541] The server collects and stores feedback data and health data received from the terminals in an integrated database.

[0542] Step 4:

[0543] The emotion engine initiates natural language processing of feedback within the server. It analyzes the input opinion data and identifies emotions such as positive, negative, and neutral.

[0544] Step 5:

[0545] Simultaneously, the emotion engine analyzes health data, particularly heart rate and activity levels, to assess stress levels. This assessment also includes comparisons with past health data.

[0546] Step 6:

[0547] The server calculates employee engagement scores based on emotional evaluations and stress levels, which are outputs from the emotion engine. A machine learning model then uses this data to perform the scoring.

[0548] Step 7:

[0549] The server monitors the engagement scores of all employees and issues a warning if the score falls below a certain threshold. The warning is notified to the terminal and displayed to the user and their administrator.

[0550] Step 8:

[0551] The server uses artificial intelligence to generate solutions to address the problems associated with the score decline. These solutions are adjusted based on the factors that affected the score.

[0552] Step 9:

[0553] The device presents the generated improvement plans to the user and guides them through the process to easily implement them. The user can review the improvement plans, consult with their manager if necessary, and then put them into action.

[0554] (Example 2)

[0555] 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."

[0556] In modern organizations, accurately understanding the level of engagement of individual users and responding to stress and emotional changes in real time is challenging. Traditional systems lack the ability to comprehensively analyze user biometric data and opinions and automatically suggest improvement measures. Furthermore, systems that provide appropriate feedback based on user engagement levels are limited.

[0557] 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.

[0558] In this invention, the server includes data acquisition means, user input means, and biometric information acquisition means. This enables comprehensive and real-time collection of user work status and biometric data, and allows for sentiment analysis and engagement level calculation based on this data. Furthermore, by automatically suggesting improvement measures using a generative AI model, it is possible to improve the level of engagement throughout the organization.

[0559] "Data acquisition means" refers to methods and devices for collecting diverse data related to users.

[0560] A "user input means" is an interface or device for receiving information or opinions from a user.

[0561] "Means for acquiring biometric information" refers to methods or devices for acquiring physical data such as a user's heart rate and stress level.

[0562] "Level of involvement" is an indicator that shows the degree to which a user is involved in the business or organization.

[0563] "Warning mechanisms" refer to methods or devices that notify users of a warning when their level of engagement falls below a certain threshold.

[0564] "Means of proposing improvement measures" refers to methods or devices that propose specific improvement plans based on the user's situation.

[0565] "Natural language processing technology" is a technology used to analyze user opinions and feedback to identify emotions.

[0566] A "generative AI model" is a technology that uses artificial intelligence to make suggestions and perform analyses based on user data.

[0567] This invention is a system that grasps the user's work status and emotional state in real time, calculates their level of involvement, and provides necessary improvement measures.

[0568] The server retrieves data from internal corporate sources via databases and internet connectivity. This includes data such as working hours and job descriptions. The server is equipped with natural language processing technology and AI models to analyze feedback received from users through their devices. The feedback data is analyzed using natural language processing technology to identify the user's emotions.

[0569] The device provides an interface for users to input their opinions and feelings, and sends that information to a server. Furthermore, based on user permission, it acquires biometric information such as heart rate and stress level from the wearable device and updates it in real time.

[0570] This system identifies the user's emotional state and stress levels and calculates their level of involvement based on that. Based on the calculated involvement level, the server uses an AI model to generate improvement suggestions, which are then presented to the user via their terminal. These suggestions may include "revising work hours" or "proposing short-term stress-relieving activities."

[0571] For example, if a user enters feedback stating, "My workload has increased recently, and I'm feeling stressed," the server's emotion engine analyzes the sentence and recognizes the emotion "stress." If this condition is determined to persist in conjunction with health data, the engagement score decreases. In this case, the server uses an AI model to generate improvement measures such as "reviewing work hours," and the terminal notifies the user of these measures.

[0572] An example of a prompt to input into the generating AI model would be: "Analyze the feedback sentences that users input daily, and use the emotion engine to recognize the user's emotional state. Based on the analysis results, calculate an engagement score and, if necessary, generate improvement measures to reduce stress."

[0573] In this way, providing optimized feedback and improvement measures is expected to enhance engagement across the entire organization.

[0574] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0575] Step 1:

[0576] The server retrieves work information from within the company via a database and internet connection. This information includes working hours and job duties. After receiving the work information as input, the server integrates this data and preprocesses it for analysis. Preprocessing includes deduplication of data and detection and correction of outliers. As output, the cleaned work information is used in the next step.

[0577] Step 2:

[0578] The terminal provides users with an interface for inputting feedback on work performance and emotions. Users periodically input feedback, and this data is sent from the terminal to the server. After receiving the feedback data as input, the server analyzes this data using natural language processing techniques to identify the emotional state. The data calculations performed here include sentiment analysis of the feedback document. As output, the emotional state is identified and used in the next step.

[0579] Step 3:

[0580] Based on user permission, the terminal acquires biometric information such as heart rate and stress level from the wearable device. This information is transmitted to the server in real time. After receiving the biometric information as input, the server performs a stress assessment. The data calculation is performed by analyzing heart rate fluctuations and quantifying the stress level. The quantified stress level is then used in the next step as output.

[0581] Step 4:

[0582] The server integrates the emotional state and stress level obtained in the previous step to calculate the user's engagement level. The input includes the emotional state and stress level. The data calculation is performed by combining these values ​​and quantifying them as an engagement level. The output is the calculated engagement level, which is used in the next step.

[0583] Step 5:

[0584] The server determines whether a warning needs to be issued based on the calculated involvement level. If the level falls below the threshold, a warning is generated. The input includes the involvement level. The output is a warning message, which is used in the next step.

[0585] Step 6:

[0586] The server uses a generative AI model to generate corrective actions based on warnings. Input includes warning messages and related data. The generated corrective actions may include suggestions for reviewing work hours or taking breaks. The output consists of specific corrective actions, which are then notified to the user via their terminal.

[0587] Step 7:

[0588] The terminal notifies the user of improvement measures sent from the server. The user can then adjust their daily work based on this information. The input includes improvement measures from the server. The output is a notification to the user, completing the system's processing.

[0589] (Application Example 2)

[0590] 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."

[0591] Managing staff stress and improving work efficiency are crucial issues in caregiving settings. In particular, it is necessary to understand staff emotional states and health information in real time and respond appropriately, but this is difficult to do effectively with conventional methods. Therefore, it is necessary to simultaneously reduce the burden on staff and improve the quality of care.

[0592] 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.

[0593] In this invention, the server includes means for acquiring work data, means for inputting employee opinions, and means for acquiring health information. This makes it possible to automatically calculate the level of employee involvement in real time based on their work data, opinions, and health information, and to provide appropriate warnings and corrective measures.

[0594] "Means for acquiring work data" refers to the means of collecting information related to employees' work and storing it in a database.

[0595] "Methods for inputting employee feedback" refers to providing an interface for employees to input feedback and opinions.

[0596] "Means of acquiring health information" refers to methods for acquiring health-related data of employees from wearable devices, etc.

[0597] "Engagement level" is an indicator that shows how actively employees are involved in their work, and is calculated based on work data, opinions, and health information.

[0598] "Natural language processing technology" is a technology that uses human language to allow computers to analyze data.

[0599] Artificial intelligence is a technology that gives computer systems the ability to learn and adapt knowledge by mimicking human intelligence.

[0600] A "generative AI model" is an artificial intelligence model trained to generate new information or results based on data.

[0601] To implement this system, a server first acquires and manages work data, employee feedback, and health information. A cloud-based database system is used to acquire work data. For employee feedback input, an interface is provided that allows employees to input their opinions via smartphone or PC. The data collected through this interface is analyzed for sentiment using natural language processing technology such as Google Cloud Natural Language. For health information acquisition, data is acquired via wearable devices such as smartwatches and transmitted to the server via Bluetooth connection.

[0602] The terminal receives this information and sends it to the server for analysis. The terminal is equipped with a function to display user data that is updated in real time and to notify staff of warnings and improvement suggestions as needed. Based on feedback from staff and health data, the server performs analysis using artificial intelligence libraries such as TensorFlow, and the generated AI model proposes improvement measures. These improvement measures include "suggestions for short breaks" and "adjustments to workload," and these are notified to staff.

[0603] For example, if an employee reports in feedback that they are "tired from working consecutive shifts recently," the server's emotion engine will recognize this information as the emotion of "fatigue" and determine that the stress level is high. Based on these analysis results, the system may suggest to the employee that they "consider adjusting their next shift."

[0604] An example of a prompt message is a "prompt to suggest a short break to manage the stress levels of care staff." The purpose is to support staff health management and work efficiency by presenting appropriate improvement measures based on staff feedback and health information.

[0605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0606] Step 1:

[0607] The server retrieves employee work data from a cloud-based database. It receives work records from the database as input, converts them into a data format for internal processing, and then processes them into a format suitable for transmission to terminals. The output is the processed work data.

[0608] Step 2:

[0609] Users input their opinions through a smartphone or PC interface. The input, in text format, is received and sent to the server via the terminal. The terminal then parses this opinion and converts it into a well-formed format for processing.

[0610] Step 3:

[0611] The terminal acquires health information from wearable devices such as smartwatches via Bluetooth connection. Inputs include heart rate and stress levels, and this data is updated every second. As output, real-time health information is sent to a server and stored for each employee.

[0612] Step 4:

[0613] The server uses natural language processing technology to analyze the sentiment of employee opinions sent from terminals. It uses text data of employee opinions as input and quantifies the sentiment using APIs such as Google Cloud Natural Language. The output is a sentiment score.

[0614] Step 5:

[0615] The server uses TensorFlow to evaluate employee stress levels and engagement levels via a generative AI model, based on analyzed sentiment scores and health information. It accepts sentiment scores and health data as input and outputs the analysis results as a numerical engagement level.

[0616] Step 6:

[0617] The server uses a generated AI model to formulate specific improvement measures and create prompt messages to present to employees. The inputs are quantified levels of involvement and analyzed stress indicators, and the output are prompt messages such as "Suggest a short break" or "Adjust workload."

[0618] Step 7:

[0619] The terminal notifies the staff of the prompt message received from the server. The input is a prompt message presenting a solution, and the output is displayed as a notification on the staff member's smartphone or computer screen. The staff member adjusts their actions based on this information.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] [Fourth Embodiment]

[0624] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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).

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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".

[0637] This invention is a system that calculates an engagement score using employee work information, opinions, and health status, enabling early detection of problems and the suggestion of improvement measures. This system is primarily implemented through data transmission and analysis between a server, terminals, and users.

[0638] The server integrates with various systems within the company to continuously acquire work information such as employee arrival and departure times and break times. The server also receives feedback and health data transmitted from terminals. This data is obtained through employee comments provided via terminals and aggregated on the server side as feedback.

[0639] The terminal plays a role in collecting employee feedback through a user interface. This interface allows users to answer questions about their work situation and feelings, and this data is sent to the server. The terminal also has the function of directly acquiring health-related information from wearable devices and sending it to the server.

[0640] The server calculates an engagement score in real time based on the received data. This process uses machine learning models to analyze work time trends, feedback content, and health parameters to generate the score. During this process, it compares the score with past data to detect outliers and sudden changes, and generates warnings.

[0641] For example, if a user provides feedback stating, "I'm tired because I've had too many meetings lately," the server will consider this emotional data and compile data on the tendency towards long working hours. If an increase in heart rate is detected based on health data, the engagement score will decrease, and the server will automatically suggest improvements. This system will notify the user and their manager via their terminal with specific action suggestions, such as "re-evaluate work priorities" or "encourage taking time off."

[0642] In this way, this system promotes company-wide productivity and employee well-being by having the server, terminal, and user work together to quantitatively evaluate employee engagement and quickly provide necessary countermeasures.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] The terminal collects feedback from employees through its user interface. When a user enters their work situation and the level of stress they are experiencing into a feedback form and presses submit, that data is sent from the terminal to the server.

[0646] Step 2:

[0647] The server stores feedback data received from terminals and simultaneously retrieves work data, such as employee attendance and departure times, from the work management system. The server then organizes this data and prepares it for analysis.

[0648] Step 3:

[0649] The device periodically acquires the user's health-related data, such as heart rate and sleep patterns, through a wearable device. This data is also sent to a server.

[0650] Step 4:

[0651] The server standardizes the collected work data, feedback, and health data according to company regulations. If there are missing or outlier data values, it corrects or removes them appropriately.

[0652] Step 5:

[0653] The server uses a generative AI model to calculate each employee's engagement score from pre-processed data. The AI ​​model utilizes keywords included in feedback, patterns of work hour fluctuations, and trends in health data for analysis.

[0654] Step 6:

[0655] The server monitors the calculated engagement score and activates a mechanism to issue a warning if it falls below a certain threshold. This warning is sent to the user's and manager's terminals.

[0656] Step 7:

[0657] The server generates improvement suggestions based on an AI model predicting a decline in engagement scores. These suggestions include specific actions for the user, such as "taking a vacation" or "changing task priorities."

[0658] Step 8:

[0659] The terminal displays improvement suggestions sent from the server to the user. The user can review these suggestions and, if necessary, consult with their manager to implement them.

[0660] Step 9:

[0661] The server updates a dashboard that aggregates and visualizes overall engagement data. Administrators use this dashboard to identify trends across the organization and utilize it for strategic decision-making.

[0662] (Example 1)

[0663] 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".

[0664] In modern businesses, employee productivity and health management are critical issues. However, many organizations find it difficult to comprehensively understand employees' work performance, opinions, and health status, which can delay problem identification and the provision of appropriate solutions. In such situations, solutions that effectively improve employee engagement are needed.

[0665] 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.

[0666] In this invention, the server includes means for acquiring time data, means for inputting opinion data, and means for acquiring health data. This makes it possible to centrally collect and analyze employee work status, feedback, and health information. Furthermore, by calculating an engagement score based on the analyzed information and automatically generating improvement suggestions, the aim is to improve the productivity of the entire organization and maintain employee health.

[0667] "Time data acquisition means" refers to methods or devices for automatically collecting information related to employees' working hours, such as their arrival and departure times and break times.

[0668] "Opinion data input means" refers to an interface or device that allows employees to input feedback regarding their work content and feelings, and a mechanism for collecting that data.

[0669] "Health data acquisition means" refers to devices or systems for directly acquiring data related to employees' health status, such as heart rate and sleep duration.

[0670] "Means for automatically calculating numerical values" refers to methods and devices for analyzing collected time data, opinion data, and health data, and calculating employee engagement scores based on that analysis.

[0671] "Means of issuing notifications" refers to methods or devices for communicating warnings or information to employees and managers based on calculated figures.

[0672] "Means of presenting suggestions" refers to methods or devices for visually or audibly displaying automatically generated improvement measures to encourage employees to take appropriate action.

[0673] An "artificial intelligence model for analyzing data" is a model based on machine learning and data mining techniques used to analyze various types of collected data.

[0674] "Comparison means for detecting outliers and fluctuations" refers to methods or devices for identifying abnormal patterns or sudden changes by comparing past data with current data.

[0675] This invention is a data collection and analysis system for improving employee engagement, and is realized through the coordinated operation of servers, terminals, and users.

[0676] The server integrates with various systems within the company and automatically acquires work information such as employee clock-in, clock-out, and break times using time data acquisition methods. The software used is designed to receive data in real time via APIs. The server also uses AI models (such as TensorFlow or PyTorch) to analyze the collected data and generate an engagement score by quantifying it.

[0677] The terminal receives feedback data from employees via a user interface. Employees provide feedback by answering questions about their work situation and feelings. The terminal is equipped with a means for inputting feedback data, and a system is in place to allow users to easily input data. In addition, as a means of acquiring health data, data from wearable devices is automatically acquired using Bluetooth, etc., and transmitted to the server.

[0678] Users receive improvement suggestions generated based on their work status and health data. For example, if a user provides feedback such as "I'm tired because I've had too many meetings lately," the server uses a machine learning model to analyze that data. As a result, if the engagement score decreases, the server generates suggestions such as "re-evaluate your work priorities" or "take a vacation" and notifies the user through their device.

[0679] An example of a prompt message for running a generative AI model might be: "Input data: I've had a lot of meetings recently and I'm tired. Health data: My heart rate is higher than normal. Output: Engagement score and improvement suggestions."

[0680] Thus, this invention enables the integrated handling of various data within an organization, allowing for real-time feedback and the presentation of improvement suggestions. This facilitates efficient improvement of overall organizational productivity and management of employee health.

[0681] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0682] Step 1:

[0683] The server retrieves time data via the company's internal system API. Inputs include data such as clock-in, clock-out, and break times, linked to employee IDs. The server stores this data in a dedicated database for future analysis. Outputs are work data organized in an appropriate format.

[0684] Step 2:

[0685] The terminal collects opinion data through a user interface. The input here consists of prompts in which employees provide feedback on their daily work and emotions. The terminal automatically sends this feedback to the server. The output is an organized dataset of employee opinions.

[0686] Step 3:

[0687] The terminal acquires health data from wearable devices. Inputs include physiological indicators such as heart rate and sleep duration, collected using Bluetooth or other connection methods. The terminal transfers the acquired health data to a server. The output is formatted health data.

[0688] Step 4:

[0689] The server integrates and analyzes time data, opinion data, and health data stored in the database. The input is all the data collected in steps 1 through 3 described above. The server uses a generative AI model to analyze the data and calculate employee engagement scores. The output is the numerical engagement score.

[0690] Step 5:

[0691] The server generates warnings to detect anomalies and sudden fluctuations based on the calculated engagement score, comparing it with historical data. Inputs include the current engagement score, historical data, and a default threshold. Output is a warning message for employees or administrators.

[0692] Step 6:

[0693] The server uses AI to generate improvement suggestions based on engagement scores and warnings. Inputs include generated scores, employee feedback, and health information. The generating AI model then produces specific action suggestions. The output is a list of improvement suggestions.

[0694] Step 7:

[0695] The server sends the generated improvement suggestions to the terminal, providing the information in a visually easy-to-understand format. The input is a list of improvement suggestions. The terminal notifies the user of these suggestions. The output is the visualized information and notification message.

[0696] Through these steps, the system enables comprehensive evaluation and feedback based on employee work information, opinions, and health status, contributing to improved organizational engagement.

[0697] (Application Example 1)

[0698] 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".

[0699] In the field of elderly care, it is crucial to properly manage the health and working conditions of staff. However, in a busy work environment, staff may suffer from overwork and health problems, which is a concern as it could affect the quality of care services. To address this issue, a system is needed that appropriately monitors staff involvement and promptly implements necessary improvement measures.

[0700] 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.

[0701] In this invention, the server includes means for acquiring work information, means for inputting employee opinions, and means for acquiring health status. This makes it possible to constantly monitor employees' work status and health status and automatically calculate their level of involvement. Based on this, warnings can be issued and improvement measures can be suggested, thereby achieving both improved employee health and increased work efficiency.

[0702] A "means for acquiring work information" refers to a method for automatically recording and collecting data related to employees' work, such as their arrival and departure times and break times.

[0703] "Employee feedback input method" refers to a means of providing an interface for employees to input opinions and feedback regarding their work situation and feelings.

[0704] "Means of acquiring health status" refers to methods for collecting health data of employees using wearable devices, etc.

[0705] "Methods for automatically calculating involvement levels" refer to methods for quantitatively calculating the degree of employee involvement in their work based on work information, employee opinions, and health data.

[0706] "Means of issuing warnings" refer to means of alerting staff and managers based on the calculated level of involvement.

[0707] "Means of proposing improvement measures" refers to methods for proposing specific improvement measures, such as reviewing work processes or taking leave, depending on the employee's level of involvement and health condition.

[0708] A "wearable device" is a device that employees can wear on a daily basis to monitor their health status.

[0709] A "Generative AI Module" is a program that uses artificial intelligence to automatically generate improvement measures from collected data.

[0710] This invention is a system that collects employee work information, opinions, and health status, and calculates their level of involvement. In this system, a server first interacts with various systems within the company to acquire work information such as employee arrival and departure times and break times. Furthermore, terminals provide an interface for collecting feedback from employees regarding their work situation and feelings. Health status is transmitted directly to the terminal via a wearable device and aggregated on the server.

[0711] The server stores this data in AWS S3 and analyzes it using a machine learning model with AWS SageMaker. This makes it possible to calculate employee engagement levels in real time. If unusual values ​​or sudden fluctuations are detected, the server issues a warning and uses a generated AI module to suggest specific improvement measures, such as changing work priorities or recommending leave.

[0712] For example, if an employee inputs feedback stating, "My recent shifts have been too long and I'm exhausted," the server considers this feedback along with data indicating increased heart rate and evaluates their level of engagement as decreased. Using a generative AI model, it then suggests improvement measures such as "Consider taking weekends off." These improvement measures are generated by the generative AI model and sent as notifications to the employee's smartphone.

[0713] An example of a prompt might be: "Based on recent feedback and health data from care staff, calculate an engagement score and propose appropriate improvement measures."

[0714] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0715] Step 1:

[0716] The server integrates with various systems within the company to automatically retrieve employee work information, such as arrival and departure times and break times. Input data comes from the company's internal attendance management system, and output is work data stored on the server. This data is later used to calculate employee engagement levels.

[0717] Step 2:

[0718] The terminal provides employees with an interface for collecting feedback. Employees input their opinions on work conditions and feelings, and this information is sent from the terminal to the server. The input is employee response data, and the output is opinion data stored on the server. This data is used for feedback analysis.

[0719] Step 3:

[0720] The server acquires data on employees' health status from wearable devices. Information such as heart rate and steps taken is input from the sensors of the wearable devices, aggregated and stored on the server. The output is data indicating health status, which is used as part of the involvement level calculation process.

[0721] Step 4:

[0722] The server uses all data stored in AWS S3 to perform analysis using machine learning models on AWS SageMaker. Inputs include work data, opinion data, and health status data, and the output is the calculated employee engagement level. This analysis makes it possible to evaluate employee status in real time.

[0723] Step 5:

[0724] The server detects anomalies and sudden fluctuations based on the calculation of involvement levels and issues warnings as needed. Warnings are generated using a generative AI model, and relevant information is notified to staff and administrators.

[0725] Step 6:

[0726] The server uses a generative AI model to generate specific improvement measures, such as changing task priorities or recommending leave, from the collected data. The input is involvement data indicating outliers, and the output is the text of the improvement measures. The generated improvement measures are notified to the employee's terminal and implemented.

[0727] Step 7:

[0728] The user's terminal receives improvement suggestions sent from the server and notifies the staff. Staff can then review the notification and take appropriate action. The input is the improvement suggestion message, and the output is instructions to prompt staff action. This feedback loop helps the system support staff well-being and improved work efficiency.

[0729] 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.

[0730] This invention is a system that calculates an engagement score based on employee work information, opinions, and health status, and further combines this with an emotion engine to recognize employees' emotions and stress, providing more precise analysis and countermeasures. This system operates in cooperation with servers, terminals, and users to manage the level of engagement of target employees in real time.

[0731] The server collects work information from data sources within the company and receives feedback data from users via terminals. The server also receives health data transmitted from terminals. This health data includes information related to the user's physical condition, such as heart rate and stress level.

[0732] The device provides an interface for receiving user feedback and has the functionality to send collected data to a server. Users regularly input their work status and emotions, which form the basis of the analysis. The device also acquires health information from wearable devices based on the user's permission and updates this information in real time.

[0733] The emotion engine is integrated into the server and analyzes received feedback data and health data to recognize the user's emotional state. This analysis includes sentiment analysis of feedback documents using natural language processing techniques and stress assessment based on vital data. The emotion engine identifies emotions from the user's opinions and calculates a precise stress level based on health data.

[0734] The server incorporates the analysis results from the emotion engine and uses the obtained data to calculate each employee's engagement score. This score is a comprehensive one that incorporates negative emotions captured by natural language processing and stress levels estimated from vital signs. For example, if a user writes in feedback that "My workload has increased recently and I'm feeling stressed," the emotion engine analyzes the sentence and recognizes the emotion of "stress," and also confirms a high-load state from health data. If this state continues for a long period, the user's engagement score will decrease, and the server will automatically issue a warning.

[0735] Furthermore, the server uses artificial intelligence to present specific improvement suggestions to the terminal based on this data. These suggestions include "revising work hours" and "suggesting short-term activities for relaxation." The terminal can notify the user of these suggestions and, if necessary, coordinate with the manager.

[0736] This system is expected to enhance overall organizational engagement by accurately understanding users' emotional states and stress fluctuations and providing immediate support.

[0737] The following describes the processing flow.

[0738] Step 1:

[0739] The device periodically provides users with a feedback form. Users input data into the device by freely describing their current work situation and feelings in this form and submitting it.

[0740] Step 2:

[0741] The device acquires health data such as heart rate and activity levels from wearable devices via Bluetooth. This information is updated in real time and transmitted to the server.

[0742] Step 3:

[0743] The server collects and stores feedback data and health data received from the terminals in an integrated database.

[0744] Step 4:

[0745] The emotion engine initiates natural language processing of feedback within the server. It analyzes the input opinion data and identifies emotions such as positive, negative, and neutral.

[0746] Step 5:

[0747] Simultaneously, the emotion engine analyzes health data, particularly heart rate and activity levels, to assess stress levels. This assessment also includes comparisons with past health data.

[0748] Step 6:

[0749] The server calculates employee engagement scores based on emotional evaluations and stress levels, which are outputs from the emotion engine. A machine learning model then uses this data to perform the scoring.

[0750] Step 7:

[0751] The server monitors the engagement scores of all employees and issues a warning if the score falls below a certain threshold. The warning is notified to the terminal and displayed to the user and their administrator.

[0752] Step 8:

[0753] The server uses artificial intelligence to generate solutions to address the problems associated with the score decline. These solutions are adjusted based on the factors that affected the score.

[0754] Step 9:

[0755] The device presents the generated improvement plans to the user and guides them through the process to easily implement them. The user can review the improvement plans, consult with their manager if necessary, and then put them into action.

[0756] (Example 2)

[0757] 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".

[0758] In modern organizations, accurately understanding the level of engagement of individual users and responding to stress and emotional changes in real time is challenging. Traditional systems lack the ability to comprehensively analyze user biometric data and opinions and automatically suggest improvement measures. Furthermore, systems that provide appropriate feedback based on user engagement levels are limited.

[0759] 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.

[0760] In this invention, the server includes data acquisition means, user input means, and biometric information acquisition means. This enables comprehensive and real-time collection of user work status and biometric data, and allows for sentiment analysis and engagement level calculation based on this data. Furthermore, by automatically suggesting improvement measures using a generative AI model, it is possible to improve the level of engagement throughout the organization.

[0761] "Data acquisition means" refers to methods and devices for collecting diverse data related to users.

[0762] A "user input means" is an interface or device for receiving information or opinions from a user.

[0763] "Means for acquiring biometric information" refers to methods or devices for acquiring physical data such as a user's heart rate and stress level.

[0764] "Level of involvement" is an indicator that shows the degree to which a user is involved in the business or organization.

[0765] "Warning mechanisms" refer to methods or devices that notify users of a warning when their level of engagement falls below a certain threshold.

[0766] "Means of proposing improvement measures" refers to methods or devices that propose specific improvement plans based on the user's situation.

[0767] "Natural language processing technology" is a technology used to analyze user opinions and feedback to identify emotions.

[0768] A "generative AI model" is a technology that uses artificial intelligence to make suggestions and perform analyses based on user data.

[0769] This invention is a system that grasps the user's work status and emotional state in real time, calculates their level of involvement, and provides necessary improvement measures.

[0770] The server retrieves data from internal corporate sources via databases and internet connectivity. This includes data such as working hours and job descriptions. The server is equipped with natural language processing technology and AI models to analyze feedback received from users through their devices. The feedback data is analyzed using natural language processing technology to identify the user's emotions.

[0771] The device provides an interface for users to input their opinions and feelings, and sends that information to a server. Furthermore, based on user permission, it acquires biometric information such as heart rate and stress level from the wearable device and updates it in real time.

[0772] This system identifies the user's emotional state and stress levels and calculates their level of involvement based on that. Based on the calculated involvement level, the server uses an AI model to generate improvement suggestions, which are then presented to the user via their terminal. These suggestions may include "revising work hours" or "proposing short-term stress-relieving activities."

[0773] For example, if a user enters feedback stating, "My workload has increased recently, and I'm feeling stressed," the server's emotion engine analyzes the sentence and recognizes the emotion "stress." If this condition is determined to persist in conjunction with health data, the engagement score decreases. In this case, the server uses an AI model to generate improvement measures such as "reviewing work hours," and the terminal notifies the user of these measures.

[0774] An example of a prompt to input into the generating AI model would be: "Analyze the feedback sentences that users input daily, and use the emotion engine to recognize the user's emotional state. Based on the analysis results, calculate an engagement score and, if necessary, generate improvement measures to reduce stress."

[0775] In this way, providing optimized feedback and improvement measures is expected to enhance engagement across the entire organization.

[0776] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0777] Step 1:

[0778] The server retrieves work information from within the company via a database and internet connection. This information includes working hours and job duties. After receiving the work information as input, the server integrates this data and preprocesses it for analysis. Preprocessing includes deduplication of data and detection and correction of outliers. As output, the cleaned work information is used in the next step.

[0779] Step 2:

[0780] The terminal provides users with an interface for inputting feedback on work performance and emotions. Users periodically input feedback, and this data is sent from the terminal to the server. After receiving the feedback data as input, the server analyzes this data using natural language processing techniques to identify the emotional state. The data calculations performed here include sentiment analysis of the feedback document. As output, the emotional state is identified and used in the next step.

[0781] Step 3:

[0782] Based on user permission, the terminal acquires biometric information such as heart rate and stress level from the wearable device. This information is transmitted to the server in real time. After receiving the biometric information as input, the server performs a stress assessment. The data calculation is performed by analyzing heart rate fluctuations and quantifying the stress level. The quantified stress level is then used in the next step as output.

[0783] Step 4:

[0784] The server integrates the emotional state and stress level obtained in the previous step to calculate the user's engagement level. The input includes the emotional state and stress level. The data calculation is performed by combining these values ​​and quantifying them as an engagement level. The output is the calculated engagement level, which is used in the next step.

[0785] Step 5:

[0786] The server determines whether a warning needs to be issued based on the calculated involvement level. If the level falls below the threshold, a warning is generated. The input includes the involvement level. The output is a warning message, which is used in the next step.

[0787] Step 6:

[0788] The server uses a generative AI model to generate corrective actions based on warnings. Input includes warning messages and related data. The generated corrective actions may include suggestions for reviewing work hours or taking breaks. The output consists of specific corrective actions, which are then notified to the user via their terminal.

[0789] Step 7:

[0790] The terminal notifies the user of improvement measures sent from the server. The user can then adjust their daily work based on this information. The input includes improvement measures from the server. The output is a notification to the user, completing the system's processing.

[0791] (Application Example 2)

[0792] 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".

[0793] Managing staff stress and improving work efficiency are crucial issues in caregiving settings. In particular, it is necessary to understand staff emotional states and health information in real time and respond appropriately, but this is difficult to do effectively with conventional methods. Therefore, it is necessary to simultaneously reduce the burden on staff and improve the quality of care.

[0794] 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.

[0795] In this invention, the server includes means for acquiring work data, means for inputting employee opinions, and means for acquiring health information. This makes it possible to automatically calculate the level of employee involvement in real time based on their work data, opinions, and health information, and to provide appropriate warnings and corrective measures.

[0796] "Means for acquiring work data" refers to the means of collecting information related to employees' work and storing it in a database.

[0797] "Methods for inputting employee feedback" refers to providing an interface for employees to input feedback and opinions.

[0798] "Means of acquiring health information" refers to methods for acquiring health-related data of employees from wearable devices, etc.

[0799] "Engagement level" is an indicator that shows how actively employees are involved in their work, and is calculated based on work data, opinions, and health information.

[0800] "Natural language processing technology" is a technology that uses human language to allow computers to analyze data.

[0801] Artificial intelligence is a technology that gives computer systems the ability to learn and adapt knowledge by mimicking human intelligence.

[0802] A "generative AI model" is an artificial intelligence model trained to generate new information or results based on data.

[0803] To implement this system, a server first acquires and manages work data, employee feedback, and health information. A cloud-based database system is used to acquire work data. For employee feedback input, an interface is provided that allows employees to input their opinions via smartphone or PC. The data collected through this interface is analyzed for sentiment using natural language processing technology such as Google Cloud Natural Language. For health information acquisition, data is acquired via wearable devices such as smartwatches and transmitted to the server via Bluetooth connection.

[0804] The terminal receives this information and sends it to the server for analysis. The terminal is equipped with a function to display user data that is updated in real time and to notify staff of warnings and improvement suggestions as needed. Based on feedback from staff and health data, the server performs analysis using artificial intelligence libraries such as TensorFlow, and the generated AI model proposes improvement measures. These improvement measures include "suggestions for short breaks" and "adjustments to workload," and these are notified to staff.

[0805] For example, if an employee reports in feedback that they are "tired from working consecutive shifts recently," the server's emotion engine will recognize this information as the emotion of "fatigue" and determine that the stress level is high. Based on these analysis results, the system may suggest to the employee that they "consider adjusting their next shift."

[0806] An example of a prompt message is a "prompt to suggest a short break to manage the stress levels of care staff." The purpose is to support staff health management and work efficiency by presenting appropriate improvement measures based on staff feedback and health information.

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1:

[0809] The server retrieves employee work data from a cloud-based database. It receives work records from the database as input, converts them into a data format for internal processing, and then processes them into a format suitable for transmission to terminals. The output is the processed work data.

[0810] Step 2:

[0811] Users input their opinions through a smartphone or PC interface. The input, in text format, is received and sent to the server via the terminal. The terminal then parses this opinion and converts it into a well-formed format for processing.

[0812] Step 3:

[0813] The terminal acquires health information from wearable devices such as smartwatches via Bluetooth connection. Inputs include heart rate and stress levels, and this data is updated every second. As output, real-time health information is sent to a server and stored for each employee.

[0814] Step 4:

[0815] The server uses natural language processing technology to analyze the sentiment of employee opinions sent from terminals. It uses text data of employee opinions as input and quantifies the sentiment using APIs such as Google Cloud Natural Language. The output is a sentiment score.

[0816] Step 5:

[0817] The server uses TensorFlow to evaluate employee stress levels and engagement levels via a generative AI model, based on analyzed sentiment scores and health information. It accepts sentiment scores and health data as input and outputs the analysis results as a numerical engagement level.

[0818] Step 6:

[0819] The server uses a generated AI model to formulate specific improvement measures and create prompt messages to present to employees. The inputs are quantified levels of involvement and analyzed stress indicators, and the output are prompt messages such as "Suggest a short break" or "Adjust workload."

[0820] Step 7:

[0821] The terminal notifies the staff of the prompt message received from the server. The input is a prompt message presenting a solution, and the output is displayed as a notification on the staff member's smartphone or computer screen. The staff member adjusts their actions based on this information.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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."

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] The following is further disclosed regarding the embodiments described above.

[0844] (Claim 1)

[0845] Means of obtaining work information,

[0846] Employee feedback input methods,

[0847] Means of obtaining health status,

[0848] A means for automatically calculating the degree of employee involvement based on the aforementioned work information, employee opinions, and health status,

[0849] A means of issuing warnings according to the calculated level of involvement,

[0850] A means of providing corrective measures based on the aforementioned warning,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, wherein the opinions of the aforementioned employees are collected periodically.

[0854] (Claim 3)

[0855] The system according to claim 1, wherein the aforementioned improvement measures are generated using artificial intelligence.

[0856] "Example 1"

[0857] (Claim 1)

[0858] A means of acquiring time data,

[0859] A means of inputting opinion data,

[0860] Methods for acquiring health data,

[0861] A means for automatically calculating numerical values ​​based on the aforementioned time data, opinion data, and health data,

[0862] A means of issuing a notification according to the calculated value,

[0863] Means for presenting proposals based on the aforementioned notification,

[0864] A means including an artificial intelligence model for analyzing data,

[0865] Comparison methods for detecting outliers and fluctuations,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, wherein the aforementioned opinion data is collected periodically.

[0869] (Claim 3)

[0870] The system according to claim 1, wherein the above proposal is generated using a generative model.

[0871] "Application Example 1"

[0872] (Claim 1)

[0873] Means of obtaining work information,

[0874] A means for staff to input their opinions,

[0875] Means of obtaining health status,

[0876] A means for automatically calculating the degree of personnel involvement based on the aforementioned work information, employee opinions, and health status,

[0877] A means of issuing warnings according to the calculated level of involvement,

[0878] A means of providing corrective measures based on the aforementioned warning,

[0879] A means for collecting the health status of the aforementioned employee from a wearable device,

[0880] A means of analyzing collected data and proposing task improvements,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, wherein the opinions of the aforementioned staff are collected periodically and the data is continuously acquired from a wearable device.

[0884] (Claim 3)

[0885] The system according to claim 1, wherein the aforementioned improvement measures are generated using a generation AI module.

[0886] "Example 2 of combining an emotion engine"

[0887] (Claim 1)

[0888] Data acquisition method,

[0889] User input means and

[0890] Means for acquiring biometric information,

[0891] A means for automatically calculating the user's level of involvement based on the aforementioned data, user opinions, and biometric information,

[0892] A means of issuing warnings according to the calculated level of involvement,

[0893] A means of providing corrective measures based on the aforementioned warning,

[0894] A method for analyzing emotions using natural language processing technology,

[0895] A means of generating improvement measures using a generative AI model,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, wherein the user's opinions are collected periodically.

[0899] (Claim 3)

[0900] The system according to claim 1, wherein the aforementioned improvement measures are automatically generated and presented to the user via a terminal.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] Means of acquiring work data,

[0904] A means for staff to input their opinions,

[0905] means of obtaining health information,

[0906] A means for automatically calculating the level of involvement in real time based on the aforementioned work data, employee opinions, and health information,

[0907] A means of issuing warnings according to the calculated level of involvement,

[0908] A means of presenting specific corrective measures based on the aforementioned warning,

[0909] A method for analyzing emotional states using natural language processing technology,

[0910] A means for generating improvement measures based on the analysis results using artificial intelligence,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, wherein the opinions of the aforementioned staff are collected periodically.

[0914] (Claim 3)

[0915] The system according to claim 1, wherein the aforementioned improvement measures are generated using a generation AI model. [Explanation of symbols]

[0916] 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 of obtaining work information, A means for staff to input their opinions, Means of obtaining health status, A means for automatically calculating the degree of personnel involvement based on the aforementioned work information, employee opinions, and health status, A means of issuing warnings according to the calculated level of involvement, A means of providing corrective measures based on the aforementioned warning, A means for collecting the health status of the aforementioned employee from a wearable device, A means of analyzing collected data and proposing task improvements, A system that includes this.

2. The system according to claim 1, wherein the opinions of the aforementioned staff are collected periodically and the data is continuously acquired from a wearable device.

3. The system according to claim 1, wherein the aforementioned improvement measures are generated using a generation AI module.

Images