System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining employee attendance and departure times; means for obtaining employee schedules; means for analyzing obtained attendance and departure times and schedule data; means for generating feedback and efficiency suggestions based on analysis results; means for notifying a user of the feedback and suggestions; means for generating task reminders based on personality data of the user; and means for aggregating and providing data of all employees to a human resources department.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's business environment, employees must manage a wide variety of tasks and schedules, making it difficult to perform their work efficiently and maintain their health. In particular, overwork and missing tasks are common problems, making it difficult to get enough rest. There is a need for a system that can solve these issues and support employees in performing their work healthily and efficiently. [Means for solving the problem]

[0005] The present invention provides a system including: a means for acquiring employee arrival and departure times; a means for acquiring employee schedules; a means for analyzing the acquired arrival and departure times and schedule data; a means for generating feedback and efficiency suggestions based on the analysis results; a means for notifying the user of the feedback and suggestions; a means for generating task reminders based on the user's personality data; and a means for aggregating data on all employees and providing it to the human resources department. The system further includes a means for calculating employee working hours based on the acquired arrival and departure times and schedule data, and for generating alerts for employees showing signs of overwork based on the calculated working hours. The system also includes a means for analyzing the frequency of employee meetings, detecting excessive meeting time, and suggesting reductions in meeting time and other communication methods based on the detected excessive meeting time. This allows for work efficiency to be improved while maintaining employee health.

[0006] "Employee" refers to a person who belongs to an organization and performs work based on a labor contract.

[0007] "Attendance time" refers to data that records the time an employee starts work.

[0008] "Leaving work time" refers to data that records the time an employee finishes work.

[0009] "Schedule data" refers to data containing information about an employee's work schedule.

[0010] "API" stands for Application Programming Interface, a set of protocols that allows data exchange between software programs.

[0011] "Analysis" refers to the act of processing collected data and extracting meaningful information and trends.

[0012] "Feedback" refers to the response or evaluation provided to the outcome of an action or situation.

[0013] "Efficiency proposals" refer to specific improvement plans to improve business efficiency.

[0014] "Task reminders" refer to notifications or reminders that remind you to perform a specific task or action.

[0015] "Users" refers to employees and human resources personnel who use this system.

[0016] "Personality data" refers to data that contains information about each employee's personality and behavioral patterns.

[0017] "Working hours" refers to the total number of hours an employee actually works in a day or week.

[0018] "Overwork" refers to a state of mental and physical fatigue caused by long working hours and excessive stress.

[0019] "Alert" refers to a notification or warning to call attention or caution.

[0020] "Meeting time" refers to the time spent participating in a meeting.

[0021] "Data aggregation" refers to the act of bringing together information collected from different data sources in a form that is easy to analyze and review.

[0022] The "human resources department" refers to the part of an organization responsible for employee recruitment, evaluation, payroll, attendance management, etc. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0024] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0025] First, the terms used in the following description will be explained.

[0026] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0027] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0028] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0029] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0034] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0036] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0043] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0044] overview

[0045] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. It collects and analyzes users' arrival and departure times and schedule data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality to prevent tasks from being overlooked. It also has the function of aggregating and providing data on all employees to the human resources department.

[0046] Program processing

[0047] Data collection

[0048] server:

[0049] To obtain employee clock-in and clock-out times, data is collected from the time management system via API.

[0050] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook).

[0051] User:

[0052] Enter your arrival and departure times into a time management system and add your work schedule to a scheduling app.

[0053] Examples:

[0054] If an employee clocks in at 9am, clocks out at 5pm, and has a one-hour meeting at 1pm that day, that information is collected from time management systems and scheduling apps.

[0055] Data analysis

[0056] server:

[0057] Calculate employee working hours based on the collected arrival and departure times. For example, calculate the total working hours for each employee per day and calculate the total working hours for the week.

[0058] Analyze schedule data to detect meeting frequency and overlapping tasks.

[0059] Examples:

[0060] If an employee's total weekly working hours exceed 45 hours, an alert is generated indicating possible overwork. It also detects that an employee's schedule includes five meetings per week.

[0061] Feedback and Suggestions

[0062] server:

[0063] Based on the analysis results, feedback on working hours is generated for employees. For example, if there are signs of overwork, an alert is generated to encourage them to take a break.

[0064] Detects unnecessary meetings and duplicate tasks from schedule data and generates suggestions for improving efficiency.

[0065] Device:

[0066] Display feedback and suggestions to users as notifications.

[0067] Examples:

[0068] Notifications will appear saying, "You have worked more than 45 hours this week. We recommend you take some rest," and "You have five meetings scheduled for next week. Please handle less important meetings via email."

[0069] Task Remind

[0070] server:

[0071] Based on the user's personality data, the system sets optimal task reminders. For example, if a user tends to forget things, the system will set reminders to be sent more frequently.

[0072] Generate and send reminders for task deadlines.

[0073] Device:

[0074] Display a reminder notification to the user.

[0075] User:

[0076] Check reminders and perform tasks.

[0077] Examples:

[0078] A timely reminder will be sent saying, "You have a task due in an hour."

[0079] Data aggregation and HR interface

[0080] server:

[0081] Data from all employees is aggregated and provided to the HR department in the form of a dashboard, allowing HR personnel to grasp each employee's working status at a glance.

[0082] Device (e.g., HR person's PC):

[0083] Access the dashboard to see your employees' work status.

[0084] Human resources person:

[0085] Based on the dashboard, we will devise ways to care for employees and revise rules and systems as necessary.

[0086] Examples:

[0087] A human resources manager checks the dashboard for signs of overwork in Employee A, schedules an interview, and considers countermeasures. At this time, it is possible to identify the distribution of the employer's overall working hours and identify departments that frequently suffer from overwork.

[0088] In this way, the present invention provides a system that supports improving work efficiency and maintaining employee health by collecting and analyzing employee data and providing feedback and suggestions for improving efficiency and health management.

[0089] The processing flow will be explained below.

[0090] Step 1: Data collection

[0091] server:

[0092] Call the API endpoint that collects employee clock-in and clock-out times from the time management system, and obtain the employee ID, clock-in time, and clock-out time.

[0093] Employee schedule data is obtained from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and event information (start time, end time, title, participants) is obtained.

[0094] User:

[0095] Enter your daily clock-in and clock-out times into a timekeeping system manually or use an automatic clock-in system.

[0096] Manually enter work schedules and meeting schedules into a scheduling app.

[0097] Step 2: Data integration and storage

[0098] server:

[0099] The acquired attendance and departure data and schedule data are integrated to create a timeline for each employee.

[0100] The integrated data is stored in a database and prepared for analysis.

[0101] Step 3: Data analysis

[0102] server:

[0103] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[0104] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[0105] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[0106] Step 4: Feedback generation

[0107] server:

[0108] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[0109] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[0110] Step 5: Notifications and Display

[0111] server:

[0112] Prepare to notify the user of the generated feedback and efficiency suggestions.

[0113] Device:

[0114] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[0115] User:

[0116] Review the feedback and suggestions you receive and review your work progress, for example, taking breaks or cutting out unnecessary meetings.

[0117] Step 6: Generate task reminders

[0118] server:

[0119] Personality data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[0120] Schedule and send timely reminders for task deadlines.

[0121] Device:

[0122] Receive reminder notifications and display them to the user.

[0123] User:

[0124] Check reminders and perform assigned tasks.

[0125] Step 7: Data aggregation and HR dashboards

[0126] server:

[0127] It aggregates and visualizes work data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, and task completion rates.

[0128] Provide a dedicated interface for easy access by the HR department.

[0129] Device (HR personnel's PC, tablet, etc.):

[0130] Access the dashboard to check each employee's work status.

[0131] Review employee care plans based on established alerts and recommendations.

[0132] Human resources person:

[0133] Use the dashboard to create care plans and take action for employees who show signs of overwork.

[0134] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[0135] Example 1

[0136] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0137] Managing employee arrival and departure times and schedules is an important issue for many companies, but the current system involves a lot of manual input and confirmation, which is inefficient and makes it difficult to understand employee working hours and health status. Furthermore, a lack of appropriate feedback on work efficiency and task management creates the risk of employee overwork and missing tasks. Furthermore, it is difficult for the HR department to centrally manage the working status of all employees.

[0138] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0139] In this invention, the server includes a means for acquiring employee arrival and departure times, a means for acquiring employee schedules, and a means for analyzing the acquired arrival and departure times and schedule data. This makes it possible to automatically collect and analyze employee working hours and schedules, detect signs of overwork and unnecessary meetings, and provide appropriate feedback and suggestions for improving efficiency.

[0140] "Means for obtaining employee arrival and departure times" refers to a system for automatically collecting data registered by employees when they start and finish their shifts.

[0141] The "means for obtaining employee schedules" is a system for obtaining information about appointments and meetings from the schedule management application used by employees.

[0142] "Means for analyzing the acquired arrival and departure times and schedule data" refers to a system for analyzing collected data on working hours and schedules, and calculating and evaluating working hours, frequency of meetings, etc.

[0143] The "means for generating feedback and efficiency suggestions" is a system for notifying users of suggestions and improvements regarding work efficiency and health management based on the analysis results.

[0144] The "means for notifying the user of the feedback and suggestions" is a system for displaying the generated feedback and suggestions on the user's terminal and notifying the user.

[0145] The "means for generating task reminders based on the user's personality data" is a system that individually optimizes task reminders according to the user's personality and behavioral patterns and notifies them at the appropriate time.

[0146] "A means of aggregating data from all employees and providing it to the human resources department" refers to a system that compiles each employee's work status and schedule data, centrally manages it, and provides it to the human resources department.

[0147] "A means of compiling employee work data and providing it to human resources personnel as a dashboard" refers to a system that visualizes employees' working hours and signs of overwork, and provides information in dashboard format so that human resources personnel can easily manage it.

[0148] The "means for generating alerts" refers to a system that generates warnings regarding excessive work hours and health risks based on calculated working hours and analysis results.

[0149] The "means for analyzing the frequency of meetings and detecting excessive meeting time" is a system that monitors schedule data and measures and evaluates the frequency and duration of meetings in which employees participate.

[0150] "Means for suggesting alternative communication methods" is a system that proposes alternative communication methods, such as email or chat, as an alternative to meetings, in order to improve work efficiency.

[0151] The "means for generating reminder notifications" is a system for generating and sending reminder notifications in a timely manner according to the deadlines and importance of the user's tasks.

[0152] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. The system automatically collects employee arrival and departure times and schedule data, and analyzes this data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality, preventing missed tasks. Furthermore, it has the function of aggregating data on all employees and providing it to the human resources department.

[0153] System Configuration

[0154] This system mainly consists of a server, user terminals, and a terminal in the human resources department. Details of each component are shown below.

[0155] server:

[0156] The server collects data via API from time management systems such as "TimePro" and "King of Time" to obtain employee arrival and departure times.

[0157] The server retrieves employee schedule data from scheduling apps such as Google Calendar and Microsoft Outlook, using a mechanism that allows API access through OAuth authentication.

[0158] The server calculates the employee's working hours based on the acquired arrival and departure times and schedule data. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, the working hours are calculated as 8 hours.

[0159] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[0160] Based on the analysis results, the server generates feedback and suggestions for efficiency improvements for employees. For example, if there are signs of overwork, it generates an alert such as, "Working more than 45 hours per week has been detected. We recommend that you take a break."

[0161] The server sets optimal task reminders based on the user's personality data and generates reminder notifications. For example, it sets up frequent reminders for users who tend to forget tasks.

[0162] The server aggregates all employee work data and provides it to the human resources department in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[0163] Device:

[0164] The user's device displays feedback, suggestions, and reminder notifications sent from the server to the user.

[0165] The terminal of the human resources officer is used to access the dashboard generated by the server and check the work status of employees.

[0166] User:

[0167] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[0168] Users add work schedules to the schedule app, and the information is synchronized with the server.

[0169] The user checks the reminder notification displayed on the terminal and performs the task.

[0170] Specific examples

[0171] For example, if an employee arrives at work at 9:00 AM, leaves at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, this information is collected from the time management system and schedule app. The collected information is analyzed on the server, and the employee's working hours and frequency of meetings are calculated and evaluated. If signs of overwork or unnecessary meetings are detected, appropriate feedback and suggestions are generated and sent to the user's device. In addition, based on the user's personality data, reminders are sent at appropriate times to coincide with task deadlines.

[0172] For example, a reminder message such as "You have a task due in one hour" will pop up on the user's device. This will prevent tasks from being overlooked and support work efficiency and health management. Furthermore, a dashboard compiling the work data of all employees will be displayed on the HR department's device, making it easy to provide care to employees showing signs of overwork and revise rules.

[0173] In this way, the present invention is a system that automatically collects and analyzes employee data and generates feedback, suggestions, and reminder notifications to support work efficiency and employee health maintenance.

[0174] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0175] Step 1: Data collection

[0176] server:

[0177] The server obtains employee arrival and departure times from a time management system (e.g., TimePro, King of Time) via API. The obtained data is received in JSON format and stored in a database.

[0178] Input: Incoming clock-in / clock-out API request

[0179] Output: Clock-in / clock-out time data saved in the database

[0180] Specific operation: "The server retrieves User1's attendance data from TimePro at 9:00 AM and saves it in the database."

[0181] server:

[0182] The server uses OAuth authentication to retrieve employee schedule data from Google Calendar and Microsoft Outlook. The retrieved data is organized for each employee and stored in a database.

[0183] Input: Request for schedule data via API

[0184] Output: Schedule data stored in the database

[0185] Specific behavior: "The server retrieves User1's scheduled meetings from Google Calendar starting at 1 PM and saves them in the database."

[0186] User:

[0187] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[0188] Input: Manual entry of clock-in and clock-out times

[0189] Output: Work clock-in and work clock-out data recorded in a database

[0190] Specific behavior: "When User1 clocks in at 9:00 AM, the data is sent to the server through the time management system."

[0191] User:

[0192] The user adds a work schedule to the schedule application.

[0193] Input: Manually input work schedule

[0194] Output: Schedule data recorded in the database

[0195] Specific behavior: "When User1 adds a meeting to Google Calendar starting at 1 PM, the information is synchronized to the server."

[0196] Step 2: Data analysis

[0197] server:

[0198] The server calculates the employee's working hours based on the arrival and departure times stored in the database. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, their working hours are calculated as 8 hours.

[0199] Input: Clock-in / clock-out time data stored in the database

[0200] Output: Calculated working hours data

[0201] Specific operation: "The server calculates the working hours for one day as 8 hours based on User1's clock-in and clock-out data."

[0202] server:

[0203] The server aggregates each employee's total working hours on a weekly basis and detects signs of overwork (e.g., working more than 45 hours a week).

[0204] Input: Calculated working time data

[0205] Output: Overwork alert data

[0206] Specific behavior: "The server detects that User1's total working hours per week is 48 hours and generates an alert as a sign of overwork."

[0207] server:

[0208] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[0209] Input: Schedule data stored in the database

[0210] Output: Meeting frequency and overlapping task data

[0211] Specific behavior: "The server detects from User1's schedule that there are five meetings scheduled for the week."

[0212] Step 3: Generate feedback and suggestions

[0213] server:

[0214] The server generates feedback to employees based on the analysis results. For example, if there are signs of overwork, it generates an alert saying, "Working more than 45 hours per week has been detected. We recommend you take a break."

[0215] Input: Results of data analysis

[0216] Output: Feedback message

[0217] Specific behavior: "The server generates an alert to User1 saying, 'Your work hours this week have exceeded 45 hours. We recommend that you take some rest.'"

[0218] server:

[0219] The server detects unnecessary meetings and duplicated tasks and generates suggestions for improving efficiency, such as "There are more than five meetings scheduled per week. Let's handle less important meetings by email."

[0220] Input: Results of data analysis

[0221] Output: Proposal message

[0222] Specific behavior: "The server generates a suggestion for User1: 'You have five meetings scheduled for next week. Let's handle the less important meetings via email.'"

[0223] Device:

[0224] The device displays feedback and suggestions sent from the server to the user as notifications.

[0225] Input: Feedback and suggestions sent by the server

[0226] Output: Displayed as a popup notification

[0227] Specific behavior: "The device displays the feedback sent from the server as a popup notification to User1."

[0228] Step 4: Generate task reminders

[0229] server:

[0230] The server sets optimal task reminders based on the user's personality data. For example, it sets more frequent reminders for users who tend to forget things.

[0231] Input: User personality data

[0232] Output: Reminder settings

[0233] Specific operation: "The server sets the frequency of reminders based on User1's personality data."

[0234] server:

[0235] The server generates and sends a reminder notification when the task is due, for example, "The task is due in one hour."

[0236] Input: Task deadline data

[0237] Output: Reminder notification message

[0238] Specific behavior: "The server generates a reminder notification for User1 saying, 'You have a task due in one hour,' and sends it to the device."

[0239] Device:

[0240] The terminal displays the reminder notification sent from the server to the user.

[0241] Input: Reminder notification sent from the server

[0242] Output: Displayed as a popup notification

[0243] Specific behavior: "The device displays the reminder notification sent from the server as a popup to User1."

[0244] User:

[0245] The user checks the reminder notification and performs the task.

[0246] Input: Reminder

[0247] Output: Completed tasks

[0248] Specific action: "User1 checks the reminder notification and completes the task according to the deadline."

[0249] Step 5: Aggregate data and provide it to HR

[0250] server:

[0251] The server aggregates all employee work data and provides it in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[0252] Input: Individual employee work data

[0253] Output: Dashboard display data

[0254] Specific operation: "The server aggregates the working time data of all employees and provides it to the HR manager as a dashboard."

[0255] Device (e.g., HR person's PC):

[0256] The device accesses a dashboard to check employee work status.

[0257] Input: Dashboard URL and login information

[0258] Output: Dashboard display

[0259] Specific operation: "The HR person's device accesses the dashboard and checks for signs of overwork for Employee A."

[0260] Human resources person:

[0261] Human resources personnel use the information on the dashboard to plan employee care and revise rules and systems as necessary.

[0262] Input: Dashboard information

[0263] Output: Employee care plan and system revision proposal

[0264] Specific actions: "The HR person checks for signs of overwork in Employee A, schedules a meeting to consider countermeasures, and considers improving the rules by looking at the distribution of working hours across the entire department."

[0265] As described above, the present invention is a system that effectively manages employees' arrival and departure times and schedule data through each step, and supports work efficiency and health management.

[0266] (Application example 1)

[0267] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0268] In modern factory environments, improving worker efficiency and managing their health are important issues. In particular, factors such as excessive work, overlapping tasks, and increasing frequency of meetings reduce production efficiency and have a negative impact on worker health. There is a need for a system that can effectively resolve these issues and support workers in performing their work efficiently and healthily.

[0269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0270] In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for monitoring the work status of factory workers and displaying schedules and task progress status through smart glasses, means for analyzing the acquired arrival and departure times and schedule data, means for displaying reminder notifications on the smart glasses when task deadlines are approaching, means for generating feedback and efficiency suggestions based on the analysis results, means for notifying the user of the feedback and suggestions, means for generating task reminders based on the user's personality data, and means for aggregating data on all employees and providing it to the human resources department. This makes it possible to monitor the work status and health status of each worker in real time and provide appropriate feedback and reminders.

[0271] "Employee arrival and departure times" refers to the time an employee starts and finishes work, and is the basic data for calculating working hours.

[0272] "Employee schedule" is data that includes information about employee plans, scheduled tasks, meetings, etc.

[0273] "Smart glasses" are devices worn by workers that can display information directly in their field of vision.

[0274] "Work status of factory workers" is information about the type of work that workers currently perform at the factory.

[0275] "Task progress status" is data that indicates the progress of a currently ongoing task.

[0276] A "task deadline" is information that indicates the final time or date by which a particular task should be completed.

[0277] "Reminder notification" is a function that notifies the user of task deadlines and matters requiring attention.

[0278] "Analysis results" are the results of analysis based on collected data, and are information that is useful for improving work efficiency and health management.

[0279] "User personality data" is information about the user's personality and behavioral characteristics, and is basic data for providing individual support.

[0280] "Task Remind" is a reminder function that reminds you to perform specific tasks based on the user's personality data.

[0281] "Data of all employees" refers to information including business data and health data relating to all employees belonging to a particular organization.

[0282] The "human resources department" is the department within an organization that manages employees and improves their working environment.

[0283] overview

[0284] This invention is an AI system that supports the work efficiency and health management of factory workers. This system monitors workers' arrival and departure times, schedules, and work status in real time through smart glasses, and provides feedback and reminders to improve work efficiency and health management. It also contributes to improving the working environment by aggregating data on all workers and providing it to the factory management department.

[0285] Hardware

[0286] Smart glasses (e.g. Google Glass)

[0287] Servers (for data processing and analysis)

[0288] Client terminal (such as PC in the factory management department)

[0289] software

[0290] HTTP request library for Python: requests

[0291] SMTP library for Python: smtplib

[0292] Scheduling and Time Management API: REST API Endpoints

[0293] Embodiment

[0294] Data collection

[0295] The server collects the arrival and departure times of factory workers from the time management system via an API, obtains worker schedule data from a scheduling app, and monitors their work status in real time through smart glasses.

[0296] Examples:

[0297] If a worker clocks in at 8am, clocks out at 6pm, and has a scheduled one-hour meeting that day at 2pm, that information is collected from time management systems and scheduling apps.

[0298] Data analysis

[0299] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. It then analyzes the schedule data to detect meeting frequency and overlapping tasks. It also monitors the work status of workers and checks task progress in real time.

[0300] Examples:

[0301] If a worker's total work week exceeds 50 hours, an alert is generated indicating possible overwork. It also detects that the worker has three overlapping tasks on a Monday afternoon.

[0302] Feedback and Suggestions

[0303] The server generates feedback to workers based on the analysis results. If there are signs of overwork, it generates an alert to encourage rest and suggests ways to streamline tasks such as overlapping tasks and excessive meetings. These notifications are displayed to the worker through the smart glasses.

[0304] Examples:

[0305] Notifications will appear saying, "You have worked over 50 hours this week. We recommend you take some rest," and "You have four meetings scheduled for Monday. Please handle less important meetings via email."

[0306] Task Remind

[0307] The server sets optimal task reminders based on the worker's personality data, and generates reminder notifications according to the task deadline and displays them on the smart glasses.

[0308] Examples:

[0309] A timely reminder will be sent saying, "You have a task due in an hour."

[0310] Data aggregation and interface for factory management

[0311] The server aggregates all worker data and provides it to the factory management department in the form of a dashboard, allowing managers to grasp the working status of each worker at a glance.

[0312] Examples:

[0313] The manager can check the dashboard for signs of overwork in Worker B, schedule an interview, and consider countermeasures. At this time, it is possible to identify the overall distribution of working hours and departments that frequently suffer from overwork.

[0314] Example prompts for generative AI models

[0315] "I have five meetings scheduled for next week. I'll handle the less important ones via email."

[0316] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0317] Step 1:

[0318] Data collection

[0319] The server uses APIs to collect the arrival and departure times and schedule data of factory workers. For example, it obtains "entrance and exit data" from a time management system and "schedule data" from a scheduling application. This makes it possible to understand each worker's daily working hours and schedule for that day. The input is data from the API, and the output is the arrival and departure times and schedule data stored on the server.

[0320] Step 2:

[0321] Data analysis

[0322] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. Specifically, working hours are calculated by subtracting departure times from arrival times. It also detects the frequency of meetings and overlapping tasks based on schedule data. The input is the collected arrival and departure times and schedule data, and the output is the calculated working hours and analysis results.

[0323] Step 3:

[0324] Feedback Generation

[0325] The server generates feedback based on the results of data analysis. For example, if the total working hours per week exceed 50 hours, it generates an alert to encourage rest as a sign of overwork. It also makes suggestions for improving efficiency by addressing duplicate tasks and unnecessary meetings. The input is the results of data analysis, and the output is a feedback message.

[0326] Step 4:

[0327] Feedback Notifications

[0328] The device attached to the smart glasses notifies the worker of the generated feedback. The feedback is displayed visually and can be viewed by the worker in real time. The input is the feedback message, and the output is a notification displayed on the smart glasses display.

[0329] Step 5:

[0330] Reminder generation

[0331] The server generates task reminders based on the worker's personality data. For example, it sets more frequent reminders for workers who tend to forget tasks. The input is personality data and task data, and the output is a reminder message.

[0332] Step 6:

[0333] Reminder notifications

[0334] The smart glasses equipped device displays the generated reminder notification to the worker. The notification is displayed at an appropriate time for tasks with an approaching deadline. The input is the reminder message, and the output is the notification displayed on the smart glasses display.

[0335] Step 7:

[0336] Data aggregation and provision

[0337] The server aggregates data on all workers and provides it to the factory management department in dashboard format. This allows managers to understand the working conditions of workers at a glance and take necessary measures. The input is data on all workers, and the output is displayed data in dashboard format.

[0338] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0339] overview

[0340] This invention combines an AI system that supports businesspeople in improving work efficiency and managing their health with an emotion engine that recognizes the user's emotions. It collects and analyzes the user's arrival and departure times, schedule data, and emotional data to provide feedback and efficiency suggestions. It also generates task reminders based on the user's personality and emotions to prevent missed tasks and stress. It also has the function of aggregating and providing data on all employees to the human resources department.

[0341] Program processing

[0342] Data collection

[0343] server:

[0344] Employee arrival and departure times are collected from the time management system via API.

[0345] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication.

[0346] An emotion engine is used to collect user emotion data (e.g., facial expressions, voice, text).

[0347] User:

[0348] Enter your clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[0349] Manually enter work schedules and meeting schedules into a scheduling app.

[0350] Emotional data is provided to the system through cameras, microphones and other sensors.

[0351] Examples:

[0352] If an employee clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day, that data is collected from time management systems and scheduling apps. At the same time, if the employee feels stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[0353] Data Integration and Storage

[0354] server:

[0355] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[0356] The consolidated data is stored in a database for subsequent analysis.

[0357] Data analysis

[0358] server:

[0359] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[0360] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[0361] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[0362] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation.

[0363] Feedback Generation

[0364] server:

[0365] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[0366] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[0367] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[0368] Notifications and Displays

[0369] server:

[0370] Prepare to notify the user of the generated feedback and efficiency suggestions.

[0371] Device:

[0372] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[0373] User:

[0374] Review the feedback and suggestions you receive and reassess your work progress, for example, by taking breaks or cutting out unnecessary meetings.

[0375] Task reminder generation

[0376] server:

[0377] Personality and emotional data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[0378] Schedule and send timely reminders for task deadlines.

[0379] Device:

[0380] Receive reminder notifications and display them to the user.

[0381] User:

[0382] Check reminders and perform assigned tasks.

[0383] Data aggregation and HR dashboards

[0384] server:

[0385] It aggregates and visualizes work and emotional data from all employees to generate a dashboard, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[0386] Provide a dedicated interface for easy access by the HR department.

[0387] Device (HR personnel's PC, tablet, etc.):

[0388] Access a dashboard to see each employee's work status and emotional state.

[0389] Review employee care plans based on established alerts and recommendations.

[0390] Human resources person:

[0391] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork, and take action.

[0392] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[0393] In this way, the present invention provides a system that collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving efficiency and health management. This provides comprehensive support for employees' working conditions and mental health, improving work efficiency and maintaining their health.

[0394] The processing flow will be explained below.

[0395] Step 1: Data collection

[0396] server:

[0397] Employee clock-in and clock-out times are obtained by calling an API endpoint from the time management system. Specifically, employee ID, clock-in time, and clock-out time are obtained.

[0398] Retrieve employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and obtain event information (start time, end time, title, participants).

[0399] The emotion engine is used to collect emotion data (e.g., facial expression recognition, voice analysis, text analysis) from sensors such as cameras and microphones.

[0400] User:

[0401] Enter your daily clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[0402] Manually add work appointments and scheduled meetings to your scheduling app.

[0403] Emotional data is provided to the system via a camera or microphone. For example, the camera captures facial expressions as emotional data, and voice analysis detects stress levels.

[0404] Step 2: Data integration and storage

[0405] server:

[0406] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[0407] The consolidated data is stored in a database for subsequent analysis, and the database is protected by security measures.

[0408] Step 3: Data analysis

[0409] server:

[0410] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[0411] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[0412] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[0413] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation, for example by using facial recognition technology to determine whether an employee is feeling stressed.

[0414] Step 4: Feedback generation

[0415] server:

[0416] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[0417] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[0418] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[0419] Step 5: Notifications and Display

[0420] server:

[0421] Prepare to notify the user of the generated feedback and efficiency suggestions.

[0422] Device:

[0423] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[0424] User:

[0425] Review the feedback and suggestions you receive and review your work progress, for example, by taking breaks or cutting down on unnecessary meetings.

[0426] Step 6: Generate task reminders

[0427] server:

[0428] The system uses personality and emotional data for each user to determine the optimal reminder format (email, chat, push notification) and timing. For example, users who forget things easily will be reminded more frequently.

[0429] Schedule reminders for task deadlines and send them at the times you specify.

[0430] Device:

[0431] Receive reminder notifications and display them to the user.

[0432] User:

[0433] Check reminders and perform assigned tasks.

[0434] Step 7: Data aggregation and HR dashboards

[0435] server:

[0436] It aggregates and visualizes work and emotional data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[0437] Provide a dedicated interface for easy access by the HR department.

[0438] Device (HR personnel's PC, tablet, etc.):

[0439] Access a dashboard to see each employee's work status and emotional state.

[0440] Review employee care plans based on established alerts and recommendations.

[0441] Human resources person:

[0442] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork or are under high stress, and take appropriate action.

[0443] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[0444] Example 2

[0445] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0446] Conventional labor management systems only collected data on employee arrival and departure times and schedules, but were unable to provide feedback that took into account employees' emotional state or stress levels. This made it difficult to comprehensively support employees' work efficiency and mental health. Furthermore, they failed to detect excessive meetings based on schedule data or provide sufficient task reminders, leading to problems such as decreased work efficiency and increased stress.

[0447] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for acquiring employee emotion data, means for integrating and saving the acquired arrival and departure times, schedules, and emotion data, means for analyzing the integrated data, means for generating feedback and efficiency suggestions for each employee based on the analysis results, means for notifying the user of the feedback and suggestions, means for displaying the notified feedback and suggestions, means for generating task reminders based on the user's personality data and emotion data, and means for aggregating data for all employees and providing it to the human resources department. This makes it possible to comprehensively manage employees' working conditions and emotional states and provide an efficient and healthy working environment.

[0448] "Employee arrival and departure times" refers to the time an employee starts and finishes work.

[0449] "Schedule data" refers to information including the time and content of meetings, tasks, etc. that an employee is scheduled to participate in during working hours.

[0450] "Emotional data" refers to data that represents an employee's emotional state, collected from facial expressions, voice, text, etc.

[0451] An "API" is an interface that allows different software components to communicate with each other.

[0452] "OAuth 2.0 Authentication" is a standardized authentication protocol for securely delegating resource owner authorization to other applications.

[0453] An "emotion engine" is software or algorithm that analyzes and determines a user's emotions from collected data.

[0454] A "timeline" is a chronological representation of a series of events or data points over a specific period of time.

[0455] A "database" is a system for efficiently and securely storing and managing large amounts of data.

[0456] "Feedback" refers to the evaluation and advice the system provides to the user based on the analysis results.

[0457] "Efficiency suggestions" are specific advice and instructions for optimizing business processes.

[0458] A "notification" is a means by which a system communicates information to a user, and can take the form of an email, a pop-up, or the like.

[0459] "Task Remind" is a reminder that helps users remember to perform scheduled tasks.

[0460] "Data aggregation" is the process of centralizing and integrating data collected from different sources.

[0461] A "dashboard" is an interface that visually displays data and enables real-time monitoring and analysis.

[0462] A "care plan" is a specific plan or measure to maintain and improve employee health and work efficiency.

[0463] "Overwork symptoms" are signs or data that indicate that an employee is working too much.

[0464] A "non-important meeting" refers to a meeting that is deemed to have low priority and low importance in business.

[0465] A "reminder notification" is a notification that notifies the user of the task execution time or deadline.

[0466] A "dedicated interface" is a user interface designed to be accessible to a specific user or department.

[0467] "All employee data" refers to information about working hours, schedules, emotions, and so on for all employees in an organization.

[0468] MODE FOR CARRYING OUT THE INVENTION

[0469] overview

[0470] This invention combines an AI system that supports employee work efficiency and health management with an emotion engine that recognizes user emotions. It collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving work efficiency. It also generates task reminders based on the user's personality and emotional data to prevent missed tasks and stress. It also has a function to aggregate and provide data on all employees to the human resources department.

[0471] Data collection

[0472] server:

[0473] The server collects employee arrival and departure times from the time management system via an API. It also obtains employee schedule data from schedule apps (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication. It also uses an emotion engine to collect emotion data from facial expressions, voice, and text data.

[0474] User:

[0475] Users manually enter their arrival and departure times into a time management system or use an automatic clock-in / clock-out system. They also manually enter their work schedules and meeting schedules into a scheduling app. They also provide emotional data via sensors such as cameras and microphones.

[0476] Examples:

[0477] An employee who clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day enters their data into a time management system and scheduling app, and if they feel stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[0478] Data Integration and Storage

[0479] server:

[0480] The collected attendance data, schedule data, and emotion data are integrated to create a timeline for each employee. The integrated data is then stored in a database for subsequent analysis.

[0481] Data analysis

[0482] server:

[0483] The server uses the stored data to calculate each employee's daily working hours. For example, it calculates the difference between the time they arrive and leave work. It also tallies the total number of hours worked in a week and determines whether it exceeds 40 hours. It analyzes the frequency of meetings and overlapping tasks based on schedule data to identify inefficiencies. It uses an emotion engine to analyze the collected emotional data and evaluate stress levels and motivation.

[0484] Feedback Generation

[0485] server:

[0486] Based on the results of work hours aggregation, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week exceed 45 hours. We recommend that you take a rest" is generated. Based on schedule analysis results, suggestions for improving efficiency (e.g., completing non-essential meetings via email) are generated. Based on emotional data, feedback to reduce stress and increase motivation is generated. For example, a suggestion such as "You seem to be feeling stressed during the meeting. It might be a good idea to take a short rest."

[0487] Notifications and Displays

[0488] server:

[0489] Prepare to notify users of the feedback and suggestions you generate.

[0490] Device:

[0491] The device receives feedback and suggestions from the server and displays them to the user in pop-up notifications and emails.

[0492] Task reminder generation

[0493] server:

[0494] The server determines the optimal reminder format (email, chat, push notification) and timing based on the user's personality and emotional data. It schedules reminder notifications according to task deadlines and sends them in a timely manner.

[0495] Device:

[0496] The device receives the reminder notification, displays it to the user, checks the reminder notification, and executes the specified task.

[0497] Data aggregation and HR dashboards

[0498] server:

[0499] The server aggregates all employee work and emotional data and generates a visual dashboard containing indicators such as working hours, meeting frequency, task completion rate, and stress level. A dedicated interface is provided for easy access by the HR department.

[0500] Device (HR personnel's PC, tablet, etc.):

[0501] Access a dashboard to view each employee's work status and emotional state, and develop a care plan for each employee based on configured alerts and recommendations.

[0502] Prompt Sentence Examples

[0503] Examples of prompts to be input to a generative AI model include:

[0504] "Analyze current working conditions and stress levels based on employee arrival and departure times, schedule data, and emotional data, and suggest areas for improvement."

[0505] "Generate specific feedback for employees who show signs of overwork based on weekly work hour aggregates and sentiment data."

[0506] The above describes an embodiment of the present invention. The present invention provides an efficient and healthy working environment by comprehensively managing the working conditions and emotional states of employees, thereby improving work efficiency and managing their health.

[0507] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0508] Step 1: Data collection

[0509] server:

[0510] The server retrieves employee arrival and departure time data from a time management system via an API. It also retrieves schedule data from schedule apps (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication. It uses an emotion engine to collect emotion data from facial expressions, voice, and text data.

[0511] input:

[0512] Arrival and departure time data

[0513] Schedule Data

[0514] Emotional Data

[0515] output:

[0516] Obtained data on arrival and departure times

[0517] Retrieved schedule data

[0518] Acquired emotion data

[0519] Specific behavior:

[0520] For example, if an employee clocks in at 9 a.m. and clocks out at 5 p.m., this data is automatically collected from the time management system. Similarly, a one-hour meeting scheduled for 1 p.m. on Google Calendar is also collected. If the employee feels stressed during the meeting, emotional data is collected using a camera and microphone.

[0521] Step 2: Data integration and storage

[0522] server:

[0523] The server integrates the collected attendance data, schedule data, and emotion data to create a timeline for each employee, and then stores the integrated data in a database.

[0524] input:

[0525] Obtained data on arrival and departure times

[0526] Retrieved schedule data

[0527] Acquired emotion data

[0528] output:

[0529] Integrated Timeline Data

[0530] Data stored in a database

[0531] Specific behavior:

[0532] Arrival and departure times, schedule data, and emotion data are compiled in chronological order to create a timeline of one day. This timeline is saved in a database for subsequent analysis.

[0533] Step 3: Data analysis

[0534] server:

[0535] The server calculates each employee's daily working hours based on the stored data. It also tallies the total working hours for the week and determines whether they exceed a set standard (e.g., 40 hours). It also analyzes the frequency of meetings and overlapping tasks from schedule data to identify inefficiencies. At the same time, it analyzes the emotional data collected by the emotion engine to evaluate stress levels and motivation.

[0536] input:

[0537] Integrated Timeline Data

[0538] Data stored in a database

[0539] output:

[0540] Calculation results of working hours

[0541] Identifying inefficient schedules

[0542] Emotion data analysis results

[0543] Specific behavior:

[0544] If an employee starts work at 9:00 and finishes work at 17:00, the working hours for that day are calculated as 8 hours. The total working hours for the week are calculated to determine whether they exceed 40 hours. At the same time, Google Calendar data is analyzed to identify unnecessary meetings and duplicate tasks. Emotional data is analyzed to quantify stress levels during meetings.

[0545] Step 4: Feedback generation

[0546] server:

[0547] Based on the aggregated results, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours have exceeded 45 hours this week. We recommend that you take a rest" is generated. Based on the schedule analysis results, efficiency suggestions are generated, such as conducting non-important meetings by email. Based on the results of emotional data, feedback is generated to reduce stress and improve motivation.

[0548] input:

[0549] Calculation results of working hours

[0550] Identifying inefficient schedules

[0551] Emotion data analysis results

[0552] output:

[0553] Overwork alert feedback

[0554] Efficiency proposals

[0555] Feedback about emotional state

[0556] Specific behavior:

[0557] Automatically generate and send messages recommending rest to employees whose working hours exceed the standard. Analyze schedule data to suggest replacing inefficient meetings with text chat. Based on emotional data, send feedback suggesting relaxation methods to employees in high-stress situations.

[0558] Step 5: Notifications and Display

[0559] server:

[0560] Prepare to notify users of generated feedback and suggestions.

[0561] Device:

[0562] The device receives feedback and suggestions from the server and displays them to the user via pop-up notifications or emails.

[0563] input:

[0564] Feedback and Suggestion Data

[0565] output:

[0566] User Notification and Display

[0567] Specific behavior:

[0568] A message pops up on the user's PC or smartphone saying, "Your working hours this week have exceeded the standard. We recommend you take a break." An email with suggestions for improvement arrives in the user's inbox, and the user can view it and cancel or reschedule the meeting.

[0569] Step 6: Generate task reminders

[0570] server:

[0571] The server determines the optimal reminder format (email, chat, push notification) and timing based on the user's personality and emotional data. It schedules reminders to match task deadlines and sends them in a timely manner.

[0572] Device:

[0573] The device receives the reminder notification, displays it to the user, confirms the reminder notification, and performs the specified task.

[0574] input:

[0575] Personality Data

[0576] Emotional Data

[0577] Task Deadline Data

[0578] output:

[0579] Task Reminder Notifications

[0580] Specific behavior:

[0581] Reminders for specific tasks will appear on the smartphone as push notifications before the deadline, and reminder emails will arrive in the user's inbox, allowing the user to check the email and complete the task.

[0582] Step 7: Data aggregation and HR dashboards

[0583] server:

[0584] The server aggregates all employee work and emotional data and generates a visual dashboard containing indicators such as working hours, meeting frequency, task completion rate, and stress level. A dedicated interface is provided for easy access by the HR department.

[0585] Device (HR personnel's PC, tablet, etc.):

[0586] The device accesses a dashboard to check each employee's work status and emotional state, and considers care plans for employees based on set alerts and recommendations.

[0587] input:

[0588] Labor Data

[0589] Emotional Data

[0590] output:

[0591] Dashboard

[0592] Care plan proposal

[0593] Specific behavior:

[0594] The dashboard visualizes working hours and emotional data, allowing HR personnel to check the status of each employee at a glance. Care plans are then created for highly stressed employees, offering specific rest plans and stress reduction measures.

[0595] (Application example 2)

[0596] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0597] Conventional employee work efficiency and health management systems are limited to collecting and analyzing data such as arrival and departure times and schedules, making it difficult to comprehensively evaluate employees' performance, including emotional data. Furthermore, feedback and suggestions are only provided to a single device, preventing flexible responses based on user attributes and circumstances, resulting in insufficient support for on-site workers and managers. This makes it difficult to detect and address declines in work efficiency and health risks early on.

[0598] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0599] In this invention, the server includes a means for collecting and analyzing emotion data using an emotion engine, a means for integrating and storing attendance data, schedule data, and emotion data, and a means for notifying and displaying the data on smart glasses or a robot. This enables support for on-site workers and managers by comprehensively analyzing employees' attendance times, schedule data, and emotion data, and generating feedback and suggestions for improving efficiency and health management.

[0600] 1. "Working hours" refers to the time an employee starts and finishes work.

[0601] 2. "Schedule data" refers to data that includes employee meetings, tasks, and other schedules.

[0602] 3. "Emotional data" refers to emotional information obtained from employees' facial expressions, voice, text, etc.

[0603] 4. An "emotion engine" is a system that analyzes emotional data and evaluates employees' emotional states.

[0604] 5. "Feedback" refers to instructions or advice given to employees based on the results of analysis.

[0605] 6. "Efficiency Proposals" are notifications proposing specific means or methods for improving business efficiency.

[0606] 7. "Task Remind" is a task reminder generated based on employee personality data.

[0607] 8. "Data integration" refers to the bringing together of data obtained from different sources into a single data set.

[0608] 9. "Smart glasses" are glasses-type devices that provide visual information to users when worn.

[0609] 10. "Robot" means a mechanical device that performs work automatically based on a program.

[0610] 11. "Stress level" is a numerical representation of an employee's mental burden and tension.

[0611] 12. "Motivation" refers to an employee's enthusiasm and enthusiasm for work.

[0612] 13. "Push Notification" means a form of notification that instantly sends specific information to a Device.

[0613] 14. A "visual dashboard" is an interface that visually displays data using graphs and charts.

[0614] 15. "Overwork" refers to a condition in which an employee's health is harmed due to excessive working hours or workload.

[0615] Server Processing

[0616] In the system for realizing this application example, first, a server executes a program using the following hardware and software.

[0617] 1. Data Collection:

[0618] The server collects employee arrival and departure times from the time management system via an API, obtains employee schedule data from schedule apps (e.g., Google Calendar or Microsoft Outlook) using OAuth 2.0 authentication, and uses an emotion engine to collect employee emotion data from sensors such as cameras and microphones.

[0619] 2. Data integration and storage:

[0620] The server integrates the acquired attendance data, schedule data, and emotion data to create a timeline for each employee and saves it in a database. For this purpose, an SQL database (e.g., SQLite) is used.

[0621] 3. Data Analysis:

[0622] The server calculates each employee's daily working hours and aggregates their total weekly working hours based on the stored data. It also analyzes schedule data to identify inefficiencies, such as meeting frequency and overlapping tasks, and uses an emotion engine to evaluate stress levels and motivation based on emotional data. This is done using the Pandas library.

[0623] 4. Feedback Generation:

[0624] The server generates alerts for employees who show signs of overwork based on the results of work hours aggregation, and also generates feedback to users to suggest ways to improve efficiency and reduce stress.

[0625] 5. Notices and Displays:

[0626] The server notifies the generated feedback and suggestions for efficiency improvement to devices such as smart glasses and robots via push notifications and emails.

[0627] 6. Task reminder generation:

[0628] The server refers to the personality and emotional data of each user, sets the optimal reminder format and timing, and schedules the reminder notification to match the task deadline.

[0629] 7. Data aggregation and dashboard generation:

[0630] The server aggregates work and emotional data from all employees and generates a visual dashboard for the HR department, visualizing indicators such as working hours, meeting frequency, task completion rate, and stress level.

[0631] User Action

[0632] 1. Data Entry:

[0633] Users manually enter their arrival and departure times into a time management system or use an automatic time-stamping system, and also manually enter their work schedules and meeting schedules into a scheduling app.

[0634] 2. Emotion data provision:

[0635] Users provide emotional data to the system through cameras, microphones, and other sensors.

[0636] 3. Feedback confirmation:

[0637] Users can review their work progress by checking the feedback and suggestions for efficiency displayed on the smart glasses or robot's display.

[0638] 4. Reminder confirmation:

[0639] The user checks the reminder notification and performs the specified task.

[0640] Examples of prompt statements

[0641] For example, here is a concrete example of a prompt statement to calculate working hours using the Pandas library:

[0642] "Using Python's Pandas library, write code to calculate the number of hours worked each day in a week and check whether the total number of hours worked exceeds 40. The data is given in the following format: a DataFrame with columns 'start_time' and 'end_time'."

[0643] Adding specific examples

[0644] If an employee clocks in at 9:00 AM, clocks out at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, that data will be collected from the time management system and schedule app. At the same time, if the employee feels stressed during the meeting, emotional data will be collected through facial recognition and voice analysis. Based on this, the server will generate feedback such as "We recommend you take a short break" and send it to the smart glasses. The user can then check the notification and take an appropriate rest.

[0645] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0646] Step 1:

[0647] Data collection

[0648] The server obtains employee arrival and departure times through the time management system's API. Additionally, the server collects employee schedule data from a scheduling app using OAuth 2.0 authentication. This data is received in JSON format, after which it is formatted and filtered. An emotion engine is used to collect employee emotional data (facial expressions, voice, text, etc.) in real time from sensors such as cameras and microphones. The input for data collection is the API responses from the time management system and scheduling app, as well as the emotional data from the sensors, and the output is the integrated initial dataset.

[0649] Step 2:

[0650] Data Integration and Storage

[0651] The server integrates the acquired attendance / leave data, schedule data, and emotion data to create a timeline for each employee. To do this, a database (e.g., SQLite) is used to store the data. The input for the integrated data is the various datasets output from Step 1, and the output is the integrated data stored in the SQL database. Specifically, each data field is matched and saved as a record in a standardized timeline format.

[0652] Step 3:

[0653] Data analysis

[0654] The server uses the integrated data to calculate the daily working hours of each employee. Using the Pandas library, it calculates the difference between the arrival time and departure time to calculate the working hours for that day. It also aggregates the total working hours by week and determines whether they exceed the set standard. The input is the integrated data, and the output is the analysis results of each employee's working hours. Specifically, daily and weekly working hours are calculated through data frame operations.

[0655] Step 4:

[0656] Emotional Data Evaluation

[0657] The server uses an emotion engine to analyze the emotional data and evaluate employees' stress levels and motivation. Specifically, it analyzes the collected voice and facial expression data and calculates emotional parameters. The input is emotional data, and the output is the evaluation results (stress level, motivation score).

[0658] Step 5:

[0659] Feedback Generation

[0660] The server generates alerts for employees showing signs of overwork or stress based on the results of the work time analysis and the emotional data evaluation. It also generates feedback to suggest efficiency improvements and reduce stress. The input is the results of the work time analysis and the emotional data evaluation, and the output is the generated feedback or alert message.

[0661] Step 6:

[0662] Notifications and Displays

[0663] The server sends the generated feedback and suggestions to the smart glasses or robot device via push notification or email. The input is the feedback message, and the output is a notification displayed on the user device. Specifically, the message is sent to the device through a dedicated API, and the user can view it.

[0664] Step 7:

[0665] Task reminder generation

[0666] The server determines the optimal reminder format (e.g., email, chat, or push notification) and timing based on each user's personality and emotional data. It schedules reminder notifications to match task deadlines and sends them at the appropriate time. The input is the user's personality and emotional data, and the output is the scheduled reminder notification.

[0667] Step 8:

[0668] Data aggregation and dashboard generation

[0669] The server aggregates the work and emotion data of all employees and generates a visual dashboard for the HR department, visualizing indicators such as working hours, meeting frequency, task completion rate, and stress level. The input is the aggregated data, and the output is the visual dashboard. Specifically, the data is displayed visually using graphs and charts, and organized into a format that is easy for HR personnel to understand.

[0670] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0671] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0672] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0673] [Second embodiment]

[0674] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0675] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0676] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0677] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0678] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0679] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0680] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0681] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0682] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0683] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0684] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0685] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0686] overview

[0687] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. It collects and analyzes users' arrival and departure times and schedule data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality to prevent tasks from being overlooked. It also has the function of aggregating and providing data on all employees to the human resources department.

[0688] Program processing

[0689] Data collection

[0690] server:

[0691] To obtain employee clock-in and clock-out times, data is collected from the time management system via API.

[0692] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook).

[0693] User:

[0694] Enter your arrival and departure times into a time management system and add your work schedule to a scheduling app.

[0695] Examples:

[0696] If an employee clocks in at 9am, clocks out at 5pm, and has a one-hour meeting at 1pm that day, that information is collected from time management systems and scheduling apps.

[0697] Data analysis

[0698] server:

[0699] Calculate employee working hours based on the collected arrival and departure times. For example, calculate the total working hours for each employee per day and calculate the total working hours for the week.

[0700] Analyze schedule data to detect meeting frequency and overlapping tasks.

[0701] Examples:

[0702] If an employee's total weekly working hours exceed 45 hours, an alert is generated indicating possible overwork. It also detects that an employee's schedule includes five meetings per week.

[0703] Feedback and Suggestions

[0704] server:

[0705] Based on the analysis results, feedback on working hours is generated for employees. For example, if there are signs of overwork, an alert is generated to encourage them to take a break.

[0706] Detects unnecessary meetings and duplicate tasks from schedule data and generates suggestions for improving efficiency.

[0707] Device:

[0708] Display feedback and suggestions to users as notifications.

[0709] Examples:

[0710] Notifications will appear saying, "You have worked more than 45 hours this week. We recommend you take some rest," and "You have five meetings scheduled for next week. Please handle less important meetings via email."

[0711] Task Remind

[0712] server:

[0713] Based on the user's personality data, the system sets optimal task reminders. For example, if a user tends to forget things, the system will set reminders to be sent more frequently.

[0714] Generate and send reminders for task deadlines.

[0715] Device:

[0716] Display a reminder notification to the user.

[0717] User:

[0718] Check reminders and perform tasks.

[0719] Examples:

[0720] A timely reminder will be sent saying, "You have a task due in an hour."

[0721] Data aggregation and HR interface

[0722] server:

[0723] Data from all employees is aggregated and provided to the HR department in the form of a dashboard, allowing HR personnel to grasp each employee's working status at a glance.

[0724] Device (e.g., HR person's PC):

[0725] Access the dashboard to see your employees' work status.

[0726] Human resources person:

[0727] Based on the dashboard, we will devise ways to care for employees and revise rules and systems as necessary.

[0728] Examples:

[0729] A human resources manager checks the dashboard for signs of overwork in Employee A, schedules an interview, and considers countermeasures. At this time, it is possible to identify the distribution of the employer's overall working hours and identify departments that frequently suffer from overwork.

[0730] In this way, the present invention provides a system that supports improving work efficiency and maintaining employee health by collecting and analyzing employee data and providing feedback and suggestions for improving efficiency and health management.

[0731] The processing flow will be explained below.

[0732] Step 1: Data collection

[0733] server:

[0734] Call the API endpoint that collects employee clock-in and clock-out times from the time management system, and obtain the employee ID, clock-in time, and clock-out time.

[0735] Employee schedule data is obtained from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and event information (start time, end time, title, participants) is obtained.

[0736] User:

[0737] Enter your daily clock-in and clock-out times into a timekeeping system manually or use an automatic clock-in system.

[0738] Manually enter work schedules and meeting schedules into a scheduling app.

[0739] Step 2: Data integration and storage

[0740] server:

[0741] The acquired attendance and departure data and schedule data are integrated to create a timeline for each employee.

[0742] The integrated data is stored in a database and prepared for analysis.

[0743] Step 3: Data analysis

[0744] server:

[0745] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[0746] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[0747] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[0748] Step 4: Feedback generation

[0749] server:

[0750] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[0751] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[0752] Step 5: Notifications and Display

[0753] server:

[0754] Prepare to notify the user of the generated feedback and efficiency suggestions.

[0755] Device:

[0756] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[0757] User:

[0758] Review the feedback and suggestions you receive and review your work progress, for example, taking breaks or cutting out unnecessary meetings.

[0759] Step 6: Generate task reminders

[0760] server:

[0761] Personality data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[0762] Schedule and send timely reminders for task deadlines.

[0763] Device:

[0764] Receive reminder notifications and display them to the user.

[0765] User:

[0766] Check reminders and perform assigned tasks.

[0767] Step 7: Data aggregation and HR dashboards

[0768] server:

[0769] It aggregates and visualizes work data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, and task completion rates.

[0770] Provide a dedicated interface for easy access by the HR department.

[0771] Device (HR personnel's PC, tablet, etc.):

[0772] Access the dashboard to check each employee's work status.

[0773] Review employee care plans based on established alerts and recommendations.

[0774] Human resources person:

[0775] Use the dashboard to create care plans and take action for employees who show signs of overwork.

[0776] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[0777] Example 1

[0778] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0779] Managing employee arrival and departure times and schedules is an important issue for many companies, but the current system involves a lot of manual input and confirmation, which is inefficient and makes it difficult to understand employee working hours and health status. Furthermore, a lack of appropriate feedback on work efficiency and task management creates the risk of employee overwork and missing tasks. Furthermore, it is difficult for the HR department to centrally manage the working status of all employees.

[0780] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0781] In this invention, the server includes a means for acquiring employee arrival and departure times, a means for acquiring employee schedules, and a means for analyzing the acquired arrival and departure times and schedule data. This makes it possible to automatically collect and analyze employee working hours and schedules, detect signs of overwork and unnecessary meetings, and provide appropriate feedback and suggestions for improving efficiency.

[0782] "Means for obtaining employee arrival and departure times" refers to a system for automatically collecting data registered by employees when they start and finish their shifts.

[0783] The "means for obtaining employee schedules" is a system for obtaining information about appointments and meetings from the schedule management application used by employees.

[0784] "Means for analyzing the acquired arrival and departure times and schedule data" refers to a system for analyzing collected data on working hours and schedules, and calculating and evaluating working hours, frequency of meetings, etc.

[0785] The "means for generating feedback and efficiency suggestions" is a system for notifying users of suggestions and improvements regarding work efficiency and health management based on the analysis results.

[0786] The "means for notifying the user of the feedback and suggestions" is a system for displaying the generated feedback and suggestions on the user's terminal and notifying the user.

[0787] The "means for generating task reminders based on the user's personality data" is a system that individually optimizes task reminders according to the user's personality and behavioral patterns and notifies them at the appropriate time.

[0788] "A means of aggregating data from all employees and providing it to the human resources department" refers to a system that compiles each employee's work status and schedule data, centrally manages it, and provides it to the human resources department.

[0789] "A means of compiling employee work data and providing it to human resources personnel as a dashboard" refers to a system that visualizes employees' working hours and signs of overwork, and provides information in dashboard format so that human resources personnel can easily manage it.

[0790] The "means for generating alerts" refers to a system that generates warnings regarding excessive work hours and health risks based on calculated working hours and analysis results.

[0791] The "means for analyzing the frequency of meetings and detecting excessive meeting time" is a system that monitors schedule data and measures and evaluates the frequency and duration of meetings in which employees participate.

[0792] "Means for suggesting alternative communication methods" is a system that proposes alternative communication methods, such as email or chat, as an alternative to meetings, in order to improve work efficiency.

[0793] The "means for generating reminder notifications" is a system for generating and sending reminder notifications in a timely manner according to the deadlines and importance of the user's tasks.

[0794] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. The system automatically collects employee arrival and departure times and schedule data, and analyzes this data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality, preventing missed tasks. Furthermore, it has the function of aggregating data on all employees and providing it to the human resources department.

[0795] System Configuration

[0796] This system mainly consists of a server, user terminals, and a terminal in the human resources department. Details of each component are shown below.

[0797] server:

[0798] The server collects data via API from time management systems such as "TimePro" and "King of Time" to obtain employee arrival and departure times.

[0799] The server retrieves employee schedule data from scheduling apps such as Google Calendar and Microsoft Outlook, using a mechanism that allows API access through OAuth authentication.

[0800] The server calculates the employee's working hours based on the acquired arrival and departure times and schedule data. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, the working hours are calculated as 8 hours.

[0801] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[0802] Based on the analysis results, the server generates feedback and suggestions for efficiency improvements for employees. For example, if there are signs of overwork, it generates an alert such as, "Working more than 45 hours per week has been detected. We recommend that you take a break."

[0803] The server sets optimal task reminders based on the user's personality data and generates reminder notifications. For example, it sets up frequent reminders for users who tend to forget tasks.

[0804] The server aggregates all employee work data and provides it to the human resources department in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[0805] Device:

[0806] The user's device displays feedback, suggestions, and reminder notifications sent from the server to the user.

[0807] The terminal of the human resources officer is used to access the dashboard generated by the server and check the work status of employees.

[0808] User:

[0809] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[0810] Users add work schedules to the schedule app, and the information is synchronized with the server.

[0811] The user checks the reminder notification displayed on the terminal and performs the task.

[0812] Specific examples

[0813] For example, if an employee arrives at work at 9:00 AM, leaves at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, this information is collected from the time management system and schedule app. The collected information is analyzed on the server, and the employee's working hours and frequency of meetings are calculated and evaluated. If signs of overwork or unnecessary meetings are detected, appropriate feedback and suggestions are generated and sent to the user's device. In addition, based on the user's personality data, reminders are sent at appropriate times to coincide with task deadlines.

[0814] For example, a reminder message such as "You have a task due in one hour" will pop up on the user's device. This will prevent tasks from being overlooked and support work efficiency and health management. Furthermore, a dashboard compiling the work data of all employees will be displayed on the HR department's device, making it easy to provide care to employees showing signs of overwork and revise rules.

[0815] In this way, the present invention is a system that automatically collects and analyzes employee data and generates feedback, suggestions, and reminder notifications to support work efficiency and employee health maintenance.

[0816] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0817] Step 1: Data collection

[0818] server:

[0819] The server obtains employee arrival and departure times from a time management system (e.g., TimePro, King of Time) via API. The obtained data is received in JSON format and stored in a database.

[0820] Input: Incoming clock-in / clock-out API request

[0821] Output: Clock-in / clock-out time data saved in the database

[0822] Specific operation: "The server retrieves User1's attendance data from TimePro at 9:00 AM and saves it in the database."

[0823] server:

[0824] The server uses OAuth authentication to retrieve employee schedule data from Google Calendar and Microsoft Outlook. The retrieved data is organized for each employee and stored in a database.

[0825] Input: Request for schedule data via API

[0826] Output: Schedule data stored in the database

[0827] Specific behavior: "The server retrieves User1's scheduled meetings from Google Calendar starting at 1 PM and saves them in the database."

[0828] User:

[0829] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[0830] Input: Manual entry of clock-in and clock-out times

[0831] Output: Work clock-in and work clock-out data recorded in a database

[0832] Specific behavior: "When User1 clocks in at 9:00 AM, the data is sent to the server through the time management system."

[0833] User:

[0834] The user adds a work schedule to the schedule application.

[0835] Input: Manually input work schedule

[0836] Output: Schedule data recorded in the database

[0837] Specific behavior: "When User1 adds a meeting to Google Calendar starting at 1 PM, the information is synchronized to the server."

[0838] Step 2: Data analysis

[0839] server:

[0840] The server calculates the employee's working hours based on the arrival and departure times stored in the database. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, their working hours are calculated as 8 hours.

[0841] Input: Clock-in / clock-out time data stored in the database

[0842] Output: Calculated working hours data

[0843] Specific operation: "The server calculates the working hours for one day as 8 hours based on User1's clock-in and clock-out data."

[0844] server:

[0845] The server aggregates each employee's total working hours on a weekly basis and detects signs of overwork (e.g., working more than 45 hours a week).

[0846] Input: Calculated working time data

[0847] Output: Overwork alert data

[0848] Specific behavior: "The server detects that User1's total working hours per week is 48 hours and generates an alert as a sign of overwork."

[0849] server:

[0850] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[0851] Input: Schedule data stored in the database

[0852] Output: Meeting frequency and overlapping task data

[0853] Specific behavior: "The server detects from User1's schedule that there are five meetings scheduled for the week."

[0854] Step 3: Generate feedback and suggestions

[0855] server:

[0856] The server generates feedback to employees based on the analysis results. For example, if there are signs of overwork, it generates an alert saying, "Working more than 45 hours per week has been detected. We recommend you take a break."

[0857] Input: Results of data analysis

[0858] Output: Feedback message

[0859] Specific behavior: "The server generates an alert to User1 saying, 'Your work hours this week have exceeded 45 hours. We recommend that you take some rest.'"

[0860] server:

[0861] The server detects unnecessary meetings and duplicated tasks and generates suggestions for improving efficiency, such as "There are more than five meetings scheduled per week. Let's handle less important meetings by email."

[0862] Input: Results of data analysis

[0863] Output: Proposal message

[0864] Specific behavior: "The server generates a suggestion for User1: 'You have five meetings scheduled for next week. Let's handle the less important meetings via email.'"

[0865] Device:

[0866] The device displays feedback and suggestions sent from the server to the user as notifications.

[0867] Input: Feedback and suggestions sent by the server

[0868] Output: Displayed as a popup notification

[0869] Specific behavior: "The device displays the feedback sent from the server as a popup notification to User1."

[0870] Step 4: Generate task reminders

[0871] server:

[0872] The server sets optimal task reminders based on the user's personality data. For example, it sets more frequent reminders for users who tend to forget things.

[0873] Input: User personality data

[0874] Output: Reminder settings

[0875] Specific operation: "The server sets the frequency of reminders based on User1's personality data."

[0876] server:

[0877] The server generates and sends a reminder notification when the task is due, for example, "The task is due in one hour."

[0878] Input: Task deadline data

[0879] Output: Reminder notification message

[0880] Specific behavior: "The server generates a reminder notification for User1 saying, 'You have a task due in one hour,' and sends it to the device."

[0881] Device:

[0882] The terminal displays the reminder notification sent from the server to the user.

[0883] Input: Reminder notification sent from the server

[0884] Output: Displayed as a popup notification

[0885] Specific behavior: "The device displays the reminder notification sent from the server as a popup to User1."

[0886] User:

[0887] The user checks the reminder notification and performs the task.

[0888] Input: Reminder

[0889] Output: Completed tasks

[0890] Specific action: "User1 checks the reminder notification and completes the task according to the deadline."

[0891] Step 5: Aggregate data and provide it to HR

[0892] server:

[0893] The server aggregates all employee work data and provides it in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[0894] Input: Individual employee work data

[0895] Output: Dashboard display data

[0896] Specific operation: "The server aggregates the working time data of all employees and provides it to the HR manager as a dashboard."

[0897] Device (e.g., HR person's PC):

[0898] The device accesses a dashboard to check employee work status.

[0899] Input: Dashboard URL and login information

[0900] Output: Dashboard display

[0901] Specific operation: "The HR person's device accesses the dashboard and checks for signs of overwork for Employee A."

[0902] Human resources person:

[0903] Human resources personnel use the information on the dashboard to plan employee care and revise rules and systems as necessary.

[0904] Input: Dashboard information

[0905] Output: Employee care plan and system revision proposal

[0906] Specific actions: "The HR person checks for signs of overwork in Employee A, schedules a meeting to consider countermeasures, and considers improving the rules by looking at the distribution of working hours across the entire department."

[0907] As described above, the present invention is a system that effectively manages employees' arrival and departure times and schedule data through each step, and supports work efficiency and health management.

[0908] (Application example 1)

[0909] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0910] In modern factory environments, improving worker efficiency and managing their health are important issues. In particular, factors such as excessive work, overlapping tasks, and increasing frequency of meetings reduce production efficiency and have a negative impact on worker health. There is a need for a system that can effectively resolve these issues and support workers in performing their work efficiently and healthily.

[0911] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0912] In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for monitoring the work status of factory workers and displaying schedules and task progress status through smart glasses, means for analyzing the acquired arrival and departure times and schedule data, means for displaying reminder notifications on the smart glasses when task deadlines are approaching, means for generating feedback and efficiency suggestions based on the analysis results, means for notifying the user of the feedback and suggestions, means for generating task reminders based on the user's personality data, and means for aggregating data on all employees and providing it to the human resources department. This makes it possible to monitor the work status and health status of each worker in real time and provide appropriate feedback and reminders.

[0913] "Employee arrival and departure times" refers to the time an employee starts and finishes work, and is the basic data for calculating working hours.

[0914] "Employee schedule" is data that includes information about employee plans, scheduled tasks, meetings, etc.

[0915] "Smart glasses" are devices worn by workers that can display information directly in their field of vision.

[0916] "Work status of factory workers" is information about the type of work that workers currently perform at the factory.

[0917] "Task progress status" is data that indicates the progress of a currently ongoing task.

[0918] A "task deadline" is information that indicates the final time or date by which a particular task should be completed.

[0919] "Reminder notification" is a function that notifies the user of task deadlines and matters requiring attention.

[0920] "Analysis results" are the results of analysis based on collected data, and are information that is useful for improving work efficiency and health management.

[0921] "User personality data" is information about the user's personality and behavioral characteristics, and is basic data for providing individual support.

[0922] "Task Remind" is a reminder function that reminds you to perform specific tasks based on the user's personality data.

[0923] "Data of all employees" refers to information including business data and health data relating to all employees belonging to a particular organization.

[0924] The "human resources department" is the department within an organization that manages employees and improves their working environment.

[0925] overview

[0926] This invention is an AI system that supports the work efficiency and health management of factory workers. This system monitors workers' arrival and departure times, schedules, and work status in real time through smart glasses, and provides feedback and reminders to improve work efficiency and health management. It also contributes to improving the working environment by aggregating data on all workers and providing it to the factory management department.

[0927] Hardware

[0928] Smart glasses (e.g. Google Glass)

[0929] Servers (for data processing and analysis)

[0930] Client terminal (such as PC in the factory management department)

[0931] software

[0932] HTTP request library for Python: requests

[0933] SMTP library for Python: smtplib

[0934] Scheduling and Time Management API: REST API Endpoints

[0935] Embodiment

[0936] Data collection

[0937] The server collects the arrival and departure times of factory workers from the time management system via an API, obtains worker schedule data from a scheduling app, and monitors their work status in real time through smart glasses.

[0938] Examples:

[0939] If a worker clocks in at 8am, clocks out at 6pm, and has a scheduled one-hour meeting that day at 2pm, that information is collected from time management systems and scheduling apps.

[0940] Data analysis

[0941] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. It then analyzes the schedule data to detect meeting frequency and overlapping tasks. It also monitors the work status of workers and checks task progress in real time.

[0942] Examples:

[0943] If a worker's total work week exceeds 50 hours, an alert is generated indicating possible overwork. It also detects that the worker has three overlapping tasks on a Monday afternoon.

[0944] Feedback and Suggestions

[0945] The server generates feedback to workers based on the analysis results. If there are signs of overwork, it generates an alert to encourage rest and suggests ways to streamline tasks such as overlapping tasks and excessive meetings. These notifications are displayed to the worker through the smart glasses.

[0946] Examples:

[0947] Notifications will appear saying, "You have worked over 50 hours this week. We recommend you take some rest," and "You have four meetings scheduled for Monday. Please handle less important meetings via email."

[0948] Task Remind

[0949] The server sets optimal task reminders based on the worker's personality data, and generates reminder notifications according to the task deadline and displays them on the smart glasses.

[0950] Examples:

[0951] A timely reminder will be sent saying, "You have a task due in an hour."

[0952] Data aggregation and interface for factory management

[0953] The server aggregates all worker data and provides it to the factory management department in the form of a dashboard, allowing managers to grasp the working status of each worker at a glance.

[0954] Examples:

[0955] The manager can check the dashboard for signs of overwork in Worker B, schedule an interview, and consider countermeasures. At this time, it is possible to identify the overall distribution of working hours and departments that frequently suffer from overwork.

[0956] Example prompts for generative AI models

[0957] "I have five meetings scheduled for next week. I'll handle the less important ones via email."

[0958] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0959] Step 1:

[0960] Data collection

[0961] The server uses APIs to collect the arrival and departure times and schedule data of factory workers. For example, it obtains "entrance and exit data" from a time management system and "schedule data" from a scheduling application. This makes it possible to understand each worker's daily working hours and schedule for that day. The input is data from the API, and the output is the arrival and departure times and schedule data stored on the server.

[0962] Step 2:

[0963] Data analysis

[0964] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. Specifically, working hours are calculated by subtracting departure times from arrival times. It also detects the frequency of meetings and overlapping tasks based on schedule data. The input is the collected arrival and departure times and schedule data, and the output is the calculated working hours and analysis results.

[0965] Step 3:

[0966] Feedback Generation

[0967] The server generates feedback based on the results of data analysis. For example, if the total working hours per week exceed 50 hours, it generates an alert to encourage rest as a sign of overwork. It also makes suggestions for improving efficiency by addressing duplicate tasks and unnecessary meetings. The input is the results of data analysis, and the output is a feedback message.

[0968] Step 4:

[0969] Feedback Notifications

[0970] The device attached to the smart glasses notifies the worker of the generated feedback. The feedback is displayed visually and can be viewed by the worker in real time. The input is the feedback message, and the output is a notification displayed on the smart glasses display.

[0971] Step 5:

[0972] Reminder generation

[0973] The server generates task reminders based on the worker's personality data. For example, it sets more frequent reminders for workers who tend to forget tasks. The input is personality data and task data, and the output is a reminder message.

[0974] Step 6:

[0975] Reminder notifications

[0976] The smart glasses equipped device displays the generated reminder notification to the worker. The notification is displayed at an appropriate time for tasks with an approaching deadline. The input is the reminder message, and the output is the notification displayed on the smart glasses display.

[0977] Step 7:

[0978] Data aggregation and provision

[0979] The server aggregates data on all workers and provides it to the factory management department in dashboard format. This allows managers to understand the working conditions of workers at a glance and take necessary measures. The input is data on all workers, and the output is displayed data in dashboard format.

[0980] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0981] overview

[0982] This invention combines an AI system that supports businesspeople in improving work efficiency and managing their health with an emotion engine that recognizes the user's emotions. It collects and analyzes the user's arrival and departure times, schedule data, and emotional data to provide feedback and efficiency suggestions. It also generates task reminders based on the user's personality and emotions to prevent missed tasks and stress. It also has the function of aggregating and providing data on all employees to the human resources department.

[0983] Program processing

[0984] Data collection

[0985] server:

[0986] Employee arrival and departure times are collected from the time management system via API.

[0987] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication.

[0988] An emotion engine is used to collect user emotion data (e.g., facial expressions, voice, text).

[0989] User:

[0990] Enter your clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[0991] Manually enter work schedules and meeting schedules into a scheduling app.

[0992] Emotional data is provided to the system through cameras, microphones and other sensors.

[0993] Examples:

[0994] If an employee clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day, that data is collected from time management systems and scheduling apps. At the same time, if the employee feels stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[0995] Data Integration and Storage

[0996] server:

[0997] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[0998] The consolidated data is stored in a database for subsequent analysis.

[0999] Data analysis

[1000] server:

[1001] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[1002] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[1003] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[1004] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation.

[1005] Feedback Generation

[1006] server:

[1007] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[1008] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[1009] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[1010] Notifications and Displays

[1011] server:

[1012] Prepare to notify the user of the generated feedback and efficiency suggestions.

[1013] Device:

[1014] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[1015] User:

[1016] Review the feedback and suggestions you receive and reassess your work progress, for example, by taking breaks or cutting out unnecessary meetings.

[1017] Task reminder generation

[1018] server:

[1019] Personality and emotional data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[1020] Schedule and send timely reminders for task deadlines.

[1021] Device:

[1022] Receive reminder notifications and display them to the user.

[1023] User:

[1024] Check reminders and perform assigned tasks.

[1025] Data aggregation and HR dashboards

[1026] server:

[1027] It aggregates and visualizes work and emotional data from all employees to generate a dashboard, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[1028] Provide a dedicated interface for easy access by the HR department.

[1029] Device (HR personnel's PC, tablet, etc.):

[1030] Access a dashboard to see each employee's work status and emotional state.

[1031] Review employee care plans based on established alerts and recommendations.

[1032] Human resources person:

[1033] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork, and take action.

[1034] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[1035] In this way, the present invention provides a system that collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving efficiency and health management. This provides comprehensive support for employees' working conditions and mental health, improving work efficiency and maintaining their health.

[1036] The processing flow will be explained below.

[1037] Step 1: Data collection

[1038] server:

[1039] Employee clock-in and clock-out times are obtained by calling an API endpoint from the time management system. Specifically, employee ID, clock-in time, and clock-out time are obtained.

[1040] Retrieve employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and obtain event information (start time, end time, title, participants).

[1041] The emotion engine is used to collect emotion data (e.g., facial expression recognition, voice analysis, text analysis) from sensors such as cameras and microphones.

[1042] User:

[1043] Enter your daily clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[1044] Manually add work appointments and scheduled meetings to your scheduling app.

[1045] Emotional data is provided to the system via a camera or microphone. For example, the camera captures facial expressions as emotional data, and voice analysis detects stress levels.

[1046] Step 2: Data integration and storage

[1047] server:

[1048] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[1049] The consolidated data is stored in a database for subsequent analysis, and the database is protected by security measures.

[1050] Step 3: Data analysis

[1051] server:

[1052] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[1053] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[1054] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[1055] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation, for example by using facial recognition technology to determine whether an employee is feeling stressed.

[1056] Step 4: Feedback generation

[1057] server:

[1058] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[1059] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[1060] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[1061] Step 5: Notifications and Display

[1062] server:

[1063] Prepare to notify the user of the generated feedback and efficiency suggestions.

[1064] Device:

[1065] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[1066] User:

[1067] Review the feedback and suggestions you receive and review your work progress, for example, by taking breaks or cutting down on unnecessary meetings.

[1068] Step 6: Generate task reminders

[1069] server:

[1070] The system uses personality and emotional data for each user to determine the optimal reminder format (email, chat, push notification) and timing. For example, users who forget things easily will be reminded more frequently.

[1071] Schedule reminders for task deadlines and send them at the times you specify.

[1072] Device:

[1073] Receive reminder notifications and display them to the user.

[1074] User:

[1075] Check reminders and perform assigned tasks.

[1076] Step 7: Data aggregation and HR dashboards

[1077] server:

[1078] It aggregates and visualizes work and emotional data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[1079] Provide a dedicated interface for easy access by the HR department.

[1080] Device (HR personnel's PC, tablet, etc.):

[1081] Access a dashboard to see each employee's work status and emotional state.

[1082] Review employee care plans based on established alerts and recommendations.

[1083] Human resources person:

[1084] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork or are under high stress, and take appropriate action.

[1085] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[1086] Example 2

[1087] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1088] Conventional labor management systems only collected data on employee arrival and departure times and schedules, but were unable to provide feedback that took into account employees' emotional state or stress levels. This made it difficult to comprehensively support employees' work efficiency and mental health. Furthermore, they failed to detect excessive meetings based on schedule data or provide sufficient task reminders, leading to problems such as decreased work efficiency and increased stress.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for acquiring employee emotion data, means for integrating and saving the acquired arrival and departure times, schedules, and emotion data, means for analyzing the integrated data, means for generating feedback and efficiency suggestions for each employee based on the analysis results, means for notifying the user of the feedback and suggestions, means for displaying the notified feedback and suggestions, means for generating task reminders based on the user's personality data and emotion data, and means for aggregating data for all employees and providing it to the human resources department. This makes it possible to comprehensively manage employees' working conditions and emotional states and provide an efficient and healthy working environment.

[1090] "Employee arrival and departure times" refers to the time an employee starts and finishes work.

[1091] "Schedule data" refers to information including the time and content of meetings, tasks, etc. that an employee is scheduled to participate in during working hours.

[1092] "Emotional data" refers to data that represents an employee's emotional state, collected from facial expressions, voice, text, etc.

[1093] An "API" is an interface that allows different software components to communicate with each other.

[1094] "OAuth 2.0 Authentication" is a standardized authentication protocol for securely delegating resource owner authorization to other applications.

[1095] An "emotion engine" is software or algorithm that analyzes and determines a user's emotions from collected data.

[1096] A "timeline" is a chronological representation of a series of events or data points over a specific period of time.

[1097] A "database" is a system for efficiently and securely storing and managing large amounts of data.

[1098] "Feedback" refers to the evaluation and advice the system provides to the user based on the analysis results.

[1099] "Efficiency suggestions" are specific advice and instructions for optimizing business processes.

[1100] A "notification" is a means by which a system communicates information to a user, and can take the form of an email, a pop-up, or the like.

[1101] "Task Remind" is a reminder that helps users remember to perform scheduled tasks.

[1102] "Data aggregation" is the process of centralizing and integrating data collected from different sources.

[1103] A "dashboard" is an interface that visually displays data and enables real-time monitoring and analysis.

[1104] A "care plan" is a specific plan or measure to maintain and improve employee health and work efficiency.

[1105] "Overwork symptoms" are signs or data that indicate that an employee is working too much.

[1106] A "non-important meeting" refers to a meeting that is deemed to have low priority and low importance in business.

[1107] A "reminder notification" is a notification that notifies the user of the task execution time or deadline.

[1108] A "dedicated interface" is a user interface designed to be accessible to a specific user or department.

[1109] "All employee data" refers to information about working hours, schedules, emotions, and so on for all employees in an organization.

[1110] MODE FOR CARRYING OUT THE INVENTION

[1111] overview

[1112] This invention combines an AI system that supports employee work efficiency and health management with an emotion engine that recognizes user emotions. It collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving work efficiency. It also generates task reminders based on the user's personality and emotional data to prevent missed tasks and stress. It also has a function to aggregate and provide data on all employees to the human resources department.

[1113] Data collection

[1114] server:

[1115] The server collects employee arrival and departure times from the time management system via an API. It also obtains employee schedule data from schedule apps (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication. It also uses an emotion engine to collect emotion data from facial expressions, voice, and text data.

[1116] User:

[1117] Users manually enter their arrival and departure times into a time management system or use an automatic clock-in / clock-out system. They also manually enter their work schedules and meeting schedules into a scheduling app. They also provide emotional data via sensors such as cameras and microphones.

[1118] Examples:

[1119] An employee who clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day enters their data into a time management system and scheduling app, and if they feel stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[1120] Data Integration and Storage

[1121] server:

[1122] The collected attendance data, schedule data, and emotion data are integrated to create a timeline for each employee. The integrated data is then stored in a database for subsequent analysis.

[1123] Data analysis

[1124] server:

[1125] The server uses the stored data to calculate each employee's daily working hours. For example, it calculates the difference between the time they arrive and leave work. It also tallies the total number of hours worked in a week and determines whether it exceeds 40 hours. It analyzes the frequency of meetings and overlapping tasks based on schedule data to identify inefficiencies. It uses an emotion engine to analyze the collected emotional data and evaluate stress levels and motivation.

[1126] Feedback Generation

[1127] server:

[1128] Based on the results of work hours aggregation, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week exceed 45 hours. We recommend that you take a rest" is generated. Based on schedule analysis results, suggestions for improving efficiency (e.g., completing non-essential meetings via email) are generated. Based on emotional data, feedback to reduce stress and increase motivation is generated. For example, a suggestion such as "You seem to be feeling stressed during the meeting. It might be a good idea to take a short rest."

[1129] Notifications and Displays

[1130] server:

[1131] Prepare to notify users of the feedback and suggestions you generate.

[1132] Device:

[1133] The device receives feedback and suggestions from the server and displays them to the user in pop-up notifications and emails.

[1134] Task reminder generation

[1135] server:

[1136] The server determines the optimal reminder format (email, chat, push notification) and timing based on the user's personality and emotional data. It schedules reminder notifications according to task deadlines and sends them in a timely manner.

[1137] Device:

[1138] The device receives the reminder notification, displays it to the user, checks the reminder notification, and executes the specified task.

[1139] Data aggregation and HR dashboards

[1140] server:

[1141] The server aggregates all employee work and emotional data and generates a visual dashboard containing indicators such as working hours, meeting frequency, task completion rate, and stress level. A dedicated interface is provided for easy access by the HR department.

[1142] Device (HR personnel's PC, tablet, etc.):

[1143] Access a dashboard to view each employee's work status and emotional state, and develop a care plan for each employee based on configured alerts and recommendations.

[1144] Prompt Sentence Examples

[1145] Examples of prompts to be input to a generative AI model include:

[1146] "Analyze current working conditions and stress levels based on employee arrival and departure times, schedule data, and emotional data, and suggest areas for improvement."

[1147] "Generate specific feedback for employees who show signs of overwork based on weekly work hour aggregates and sentiment data."

[1148] The above describes an embodiment of the present invention. The present invention provides an efficient and healthy working environment by comprehensively managing the working conditions and emotional states of employees, thereby improving work efficiency and managing their health.

[1149] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1150] Step 1: Data collection

[1151] server:

[1152] The server retrieves employee arrival and departure time data from a time management system via an API. It also retrieves schedule data from schedule apps (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication. It uses an emotion engine to collect emotion data from facial expressions, voice, and text data.

[1153] input:

[1154] Arrival and departure time data

[1155] Schedule Data

[1156] Emotional Data

[1157] output:

[1158] Obtained data on arrival and departure times

[1159] Retrieved schedule data

[1160] Acquired emotion data

[1161] Specific behavior:

[1162] For example, if an employee clocks in at 9 a.m. and clocks out at 5 p.m., this data is automatically collected from the time management system. Similarly, a one-hour meeting scheduled for 1 p.m. on Google Calendar is also collected. If the employee feels stressed during the meeting, emotional data is collected using a camera and microphone.

[1163] Step 2: Data integration and storage

[1164] server:

[1165] The server integrates the collected attendance data, schedule data, and emotion data to create a timeline for each employee, and then stores the integrated data in a database.

[1166] input:

[1167] Obtained data on arrival and departure times

[1168] Retrieved schedule data

[1169] Acquired emotion data

[1170] output:

[1171] Integrated Timeline Data

[1172] Data stored in a database

[1173] Specific behavior:

[1174] Arrival and departure times, schedule data, and emotion data are compiled in chronological order to create a timeline of one day. This timeline is saved in a database for subsequent analysis.

[1175] Step 3: Data analysis

[1176] server:

[1177] The server calculates each employee's daily working hours based on the stored data. It also tallies the total working hours for the week and determines whether they exceed a set standard (e.g., 40 hours). It also analyzes the frequency of meetings and overlapping tasks from schedule data to identify inefficiencies. At the same time, it analyzes the emotional data collected by the emotion engine to evaluate stress levels and motivation.

[1178] input:

[1179] Integrated Timeline Data

[1180] Data stored in a database

[1181] output:

[1182] Calculation results of working hours

[1183] Identifying inefficient schedules

[1184] Emotion data analysis results

[1185] Specific behavior:

[1186] If an employee starts work at 9:00 and finishes work at 17:00, the working hours for that day are calculated as 8 hours. The total working hours for the week are calculated to determine whether they exceed 40 hours. At the same time, Google Calendar data is analyzed to identify unnecessary meetings and duplicate tasks. Emotional data is analyzed to quantify stress levels during meetings.

[1187] Step 4: Feedback generation

[1188] server:

[1189] Based on the aggregated results, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours have exceeded 45 hours this week. We recommend that you take a rest" is generated. Based on the schedule analysis results, efficiency suggestions are generated, such as conducting non-important meetings by email. Based on the results of emotional data, feedback is generated to reduce stress and improve motivation.

[1190] input:

[1191] Calculation results of working hours

[1192] Identifying inefficient schedules

[1193] Emotion data analysis results

[1194] output:

[1195] Overwork alert feedback

[1196] Efficiency proposals

[1197] Feedback about emotional state

[1198] Specific behavior:

[1199] Automatically generate and send messages recommending rest to employees whose working hours exceed the standard. Analyze schedule data to suggest replacing inefficient meetings with text chat. Based on emotional data, send feedback suggesting relaxation methods to employees in high-stress situations.

[1200] Step 5: Notifications and Display

[1201] server:

[1202] Prepare to notify users of generated feedback and suggestions.

[1203] Device:

[1204] The device receives feedback and suggestions from the server and displays them to the user via pop-up notifications or emails.

[1205] input:

[1206] Feedback and Suggestion Data

[1207] output:

[1208] User Notification and Display

[1209] Specific behavior:

[1210] A message pops up on the user's PC or smartphone saying, "Your working hours this week have exceeded the standard. We recommend you take a break." An email with suggestions for improvement arrives in the user's inbox, and the user can view it and cancel or reschedule the meeting.

[1211] Step 6: Generate task reminders

[1212] server:

[1213] The server determines the optimal reminder format (email, chat, push notification) and timing based on the user's personality and emotional data. It schedules reminders to match task deadlines and sends them in a timely manner.

[1214] Device:

[1215] The device receives the reminder notification, displays it to the user, confirms the reminder notification, and performs the specified task.

[1216] input:

[1217] Personality Data

[1218] Emotional Data

[1219] Task Deadline Data

[1220] output:

[1221] Task Reminder Notifications

[1222] Specific behavior:

[1223] Reminders for specific tasks will appear on the smartphone as push notifications before the deadline, and reminder emails will arrive in the user's inbox, allowing the user to check the email and complete the task.

[1224] Step 7: Data aggregation and HR dashboards

[1225] server:

[1226] The server aggregates all employee work and emotional data and generates a visual dashboard containing indicators such as working hours, meeting frequency, task completion rate, and stress level. A dedicated interface is provided for easy access by the HR department.

[1227] Device (HR personnel's PC, tablet, etc.):

[1228] The device accesses a dashboard to check each employee's work status and emotional state, and considers care plans for employees based on set alerts and recommendations.

[1229] input:

[1230] Labor Data

[1231] Emotional Data

[1232] output:

[1233] Dashboard

[1234] Care plan proposal

[1235] Specific behavior:

[1236] The dashboard visualizes working hours and emotional data, allowing HR personnel to check the status of each employee at a glance. Care plans are then created for highly stressed employees, offering specific rest plans and stress reduction measures.

[1237] (Application example 2)

[1238] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1239] Conventional employee work efficiency and health management systems are limited to collecting and analyzing data such as arrival and departure times and schedules, making it difficult to comprehensively evaluate employees' performance, including emotional data. Furthermore, feedback and suggestions are only provided to a single device, preventing flexible responses based on user attributes and circumstances, resulting in insufficient support for on-site workers and managers. This makes it difficult to detect and address declines in work efficiency and health risks early on.

[1240] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1241] In this invention, the server includes a means for collecting and analyzing emotion data using an emotion engine, a means for integrating and storing attendance data, schedule data, and emotion data, and a means for notifying and displaying the data on smart glasses or a robot. This enables support for on-site workers and managers by comprehensively analyzing employees' attendance times, schedule data, and emotion data, and generating feedback and suggestions for improving efficiency and health management.

[1242] 1. "Working hours" refers to the time an employee starts and finishes work.

[1243] 2. "Schedule data" refers to data that includes employee meetings, tasks, and other schedules.

[1244] 3. "Emotional data" refers to emotional information obtained from employees' facial expressions, voice, text, etc.

[1245] 4. An "emotion engine" is a system that analyzes emotional data and evaluates employees' emotional states.

[1246] 5. "Feedback" refers to instructions or advice given to employees based on the results of analysis.

[1247] 6. "Efficiency Proposals" are notifications proposing specific means or methods for improving business efficiency.

[1248] 7. "Task Remind" is a task reminder generated based on employee personality data.

[1249] 8. "Data integration" refers to the bringing together of data obtained from different sources into a single data set.

[1250] 9. "Smart glasses" are glasses-type devices that provide visual information to users when worn.

[1251] 10. "Robot" means a mechanical device that performs work automatically based on a program.

[1252] 11. "Stress level" is a numerical representation of an employee's mental burden and tension.

[1253] 12. "Motivation" refers to an employee's enthusiasm and enthusiasm for work.

[1254] 13. "Push Notification" means a form of notification that instantly sends specific information to a Device.

[1255] 14. A "visual dashboard" is an interface that visually displays data using graphs and charts.

[1256] 15. "Overwork" refers to a condition in which an employee's health is harmed due to excessive working hours or workload.

[1257] Server Processing

[1258] In the system for realizing this application example, first, a server executes a program using the following hardware and software.

[1259] 1. Data Collection:

[1260] The server collects employee arrival and departure times from the time management system via an API, obtains employee schedule data from schedule apps (e.g., Google Calendar or Microsoft Outlook) using OAuth 2.0 authentication, and uses an emotion engine to collect employee emotion data from sensors such as cameras and microphones.

[1261] 2. Data integration and storage:

[1262] The server integrates the acquired attendance data, schedule data, and emotion data to create a timeline for each employee and saves it in a database. For this purpose, an SQL database (e.g., SQLite) is used.

[1263] 3. Data Analysis:

[1264] The server calculates each employee's daily working hours and aggregates their total weekly working hours based on the stored data. It also analyzes schedule data to identify inefficiencies, such as meeting frequency and overlapping tasks, and uses an emotion engine to evaluate stress levels and motivation based on emotional data. This is done using the Pandas library.

[1265] 4. Feedback Generation:

[1266] The server generates alerts for employees who show signs of overwork based on the results of work hours aggregation, and also generates feedback to users to suggest ways to improve efficiency and reduce stress.

[1267] 5. Notices and Displays:

[1268] The server notifies the generated feedback and suggestions for efficiency improvement to devices such as smart glasses and robots via push notifications and emails.

[1269] 6. Task reminder generation:

[1270] The server refers to the personality and emotional data of each user, sets the optimal reminder format and timing, and schedules the reminder notification to match the task deadline.

[1271] 7. Data aggregation and dashboard generation:

[1272] The server aggregates work and emotional data from all employees and generates a visual dashboard for the HR department, visualizing indicators such as working hours, meeting frequency, task completion rate, and stress level.

[1273] User Action

[1274] 1. Data Entry:

[1275] Users manually enter their arrival and departure times into a time management system or use an automatic time-stamping system, and also manually enter their work schedules and meeting schedules into a scheduling app.

[1276] 2. Emotion data provision:

[1277] Users provide emotional data to the system through cameras, microphones, and other sensors.

[1278] 3. Feedback confirmation:

[1279] Users can review their work progress by checking the feedback and suggestions for efficiency displayed on the smart glasses or robot's display.

[1280] 4. Reminder confirmation:

[1281] The user checks the reminder notification and performs the specified task.

[1282] Examples of prompt statements

[1283] For example, here is a concrete example of a prompt statement to calculate working hours using the Pandas library:

[1284] "Using Python's Pandas library, write code to calculate the number of hours worked each day in a week and check whether the total number of hours worked exceeds 40. The data is given in the following format: a DataFrame with columns 'start_time' and 'end_time'."

[1285] Adding specific examples

[1286] If an employee clocks in at 9:00 AM, clocks out at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, that data will be collected from the time management system and schedule app. At the same time, if the employee feels stressed during the meeting, emotional data will be collected through facial recognition and voice analysis. Based on this, the server will generate feedback such as "We recommend you take a short break" and send it to the smart glasses. The user can then check the notification and take an appropriate rest.

[1287] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1288] Step 1:

[1289] Data collection

[1290] The server obtains employee arrival and departure times through the time management system's API. Additionally, the server collects employee schedule data from a scheduling app using OAuth 2.0 authentication. This data is received in JSON format, after which it is formatted and filtered. An emotion engine is used to collect employee emotional data (facial expressions, voice, text, etc.) in real time from sensors such as cameras and microphones. The input for data collection is the API responses from the time management system and scheduling app, as well as the emotional data from the sensors, and the output is the integrated initial dataset.

[1291] Step 2:

[1292] Data Integration and Storage

[1293] The server integrates the acquired attendance / leave data, schedule data, and emotion data to create a timeline for each employee. To do this, a database (e.g., SQLite) is used to store the data. The input for the integrated data is the various datasets output from Step 1, and the output is the integrated data stored in the SQL database. Specifically, each data field is matched and saved as a record in a standardized timeline format.

[1294] Step 3:

[1295] Data analysis

[1296] The server uses the integrated data to calculate the daily working hours of each employee. Using the Pandas library, it calculates the difference between the arrival time and departure time to calculate the working hours for that day. It also aggregates the total working hours by week and determines whether they exceed the set standard. The input is the integrated data, and the output is the analysis results of each employee's working hours. Specifically, daily and weekly working hours are calculated through data frame operations.

[1297] Step 4:

[1298] Emotional Data Evaluation

[1299] The server uses an emotion engine to analyze the emotional data and evaluate employees' stress levels and motivation. Specifically, it analyzes the collected voice and facial expression data and calculates emotional parameters. The input is emotional data, and the output is the evaluation results (stress level, motivation score).

[1300] Step 5:

[1301] Feedback Generation

[1302] The server generates alerts for employees showing signs of overwork or stress based on the results of the work time analysis and the emotional data evaluation. It also generates feedback to suggest efficiency improvements and reduce stress. The input is the results of the work time analysis and the emotional data evaluation, and the output is the generated feedback or alert message.

[1303] Step 6:

[1304] Notifications and Displays

[1305] The server sends the generated feedback and suggestions to the smart glasses or robot device via push notification or email. The input is the feedback message, and the output is a notification displayed on the user device. Specifically, the message is sent to the device through a dedicated API, and the user can view it.

[1306] Step 7:

[1307] Task reminder generation

[1308] The server determines the optimal reminder format (e.g., email, chat, or push notification) and timing based on each user's personality and emotional data. It schedules reminder notifications to match task deadlines and sends them at the appropriate time. The input is the user's personality and emotional data, and the output is the scheduled reminder notification.

[1309] Step 8:

[1310] Data aggregation and dashboard generation

[1311] The server aggregates the work and emotion data of all employees and generates a visual dashboard for the HR department, visualizing indicators such as working hours, meeting frequency, task completion rate, and stress level. The input is the aggregated data, and the output is the visual dashboard. Specifically, the data is displayed visually using graphs and charts, and organized into a format that is easy for HR personnel to understand.

[1312] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1313] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1314] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1315] [Third embodiment]

[1316] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1317] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1318] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1319] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1320] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1321] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1322] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1323] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1324] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1325] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1326] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1327] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1328] overview

[1329] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. It collects and analyzes users' arrival and departure times and schedule data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality to prevent tasks from being overlooked. It also has the function of aggregating and providing data on all employees to the human resources department.

[1330] Program processing

[1331] Data collection

[1332] server:

[1333] To obtain employee clock-in and clock-out times, data is collected from the time management system via API.

[1334] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook).

[1335] User:

[1336] Enter your arrival and departure times into a time management system and add your work schedule to a scheduling app.

[1337] Examples:

[1338] If an employee clocks in at 9am, clocks out at 5pm, and has a one-hour meeting at 1pm that day, that information is collected from time management systems and scheduling apps.

[1339] Data analysis

[1340] server:

[1341] Calculate employee working hours based on the collected arrival and departure times. For example, calculate the total working hours for each employee per day and calculate the total working hours for the week.

[1342] Analyze schedule data to detect meeting frequency and overlapping tasks.

[1343] Examples:

[1344] If an employee's total weekly working hours exceed 45 hours, an alert is generated indicating possible overwork. It also detects that an employee's schedule includes five meetings per week.

[1345] Feedback and Suggestions

[1346] server:

[1347] Based on the analysis results, feedback on working hours is generated for employees. For example, if there are signs of overwork, an alert is generated to encourage them to take a break.

[1348] Detects unnecessary meetings and duplicate tasks from schedule data and generates suggestions for improving efficiency.

[1349] Device:

[1350] Display feedback and suggestions to users as notifications.

[1351] Examples:

[1352] Notifications will appear saying, "You have worked more than 45 hours this week. We recommend you take some rest," and "You have five meetings scheduled for next week. Please handle less important meetings via email."

[1353] Task Remind

[1354] server:

[1355] Based on the user's personality data, the system sets optimal task reminders. For example, if a user tends to forget things, the system will set reminders to be sent more frequently.

[1356] Generate and send reminders for task deadlines.

[1357] Device:

[1358] Display a reminder notification to the user.

[1359] User:

[1360] Check reminders and perform tasks.

[1361] Examples:

[1362] A timely reminder will be sent saying, "You have a task due in an hour."

[1363] Data aggregation and HR interface

[1364] server:

[1365] Data from all employees is aggregated and provided to the HR department in the form of a dashboard, allowing HR personnel to grasp each employee's working status at a glance.

[1366] Device (e.g., HR person's PC):

[1367] Access the dashboard to see your employees' work status.

[1368] Human resources person:

[1369] Based on the dashboard, we will devise ways to care for employees and revise rules and systems as necessary.

[1370] Examples:

[1371] A human resources manager checks the dashboard for signs of overwork in Employee A, schedules an interview, and considers countermeasures. At this time, it is possible to identify the distribution of the employer's overall working hours and identify departments that frequently suffer from overwork.

[1372] In this way, the present invention provides a system that supports improving work efficiency and maintaining employee health by collecting and analyzing employee data and providing feedback and suggestions for improving efficiency and health management.

[1373] The processing flow will be explained below.

[1374] Step 1: Data collection

[1375] server:

[1376] Call the API endpoint that collects employee clock-in and clock-out times from the time management system, and obtain the employee ID, clock-in time, and clock-out time.

[1377] Employee schedule data is obtained from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and event information (start time, end time, title, participants) is obtained.

[1378] User:

[1379] Enter your daily clock-in and clock-out times into a timekeeping system manually or use an automatic clock-in system.

[1380] Manually enter work schedules and meeting schedules into a scheduling app.

[1381] Step 2: Data integration and storage

[1382] server:

[1383] The acquired attendance and departure data and schedule data are integrated to create a timeline for each employee.

[1384] The integrated data is stored in a database and prepared for analysis.

[1385] Step 3: Data analysis

[1386] server:

[1387] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[1388] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[1389] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[1390] Step 4: Feedback generation

[1391] server:

[1392] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[1393] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[1394] Step 5: Notifications and Display

[1395] server:

[1396] Prepare to notify the user of the generated feedback and efficiency suggestions.

[1397] Device:

[1398] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[1399] User:

[1400] Review the feedback and suggestions you receive and review your work progress, for example, taking breaks or cutting out unnecessary meetings.

[1401] Step 6: Generate task reminders

[1402] server:

[1403] Personality data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[1404] Schedule and send timely reminders for task deadlines.

[1405] Device:

[1406] Receive reminder notifications and display them to the user.

[1407] User:

[1408] Check reminders and perform assigned tasks.

[1409] Step 7: Data aggregation and HR dashboards

[1410] server:

[1411] It aggregates and visualizes work data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, and task completion rates.

[1412] Provide a dedicated interface for easy access by the HR department.

[1413] Device (HR personnel's PC, tablet, etc.):

[1414] Access the dashboard to check each employee's work status.

[1415] Review employee care plans based on established alerts and recommendations.

[1416] Human resources person:

[1417] Use the dashboard to create care plans and take action for employees who show signs of overwork.

[1418] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[1419] Example 1

[1420] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1421] Managing employee arrival and departure times and schedules is an important issue for many companies, but the current system involves a lot of manual input and confirmation, which is inefficient and makes it difficult to understand employee working hours and health status. Furthermore, a lack of appropriate feedback on work efficiency and task management creates the risk of employee overwork and missing tasks. Furthermore, it is difficult for the HR department to centrally manage the working status of all employees.

[1422] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1423] In this invention, the server includes a means for acquiring employee arrival and departure times, a means for acquiring employee schedules, and a means for analyzing the acquired arrival and departure times and schedule data. This makes it possible to automatically collect and analyze employee working hours and schedules, detect signs of overwork and unnecessary meetings, and provide appropriate feedback and suggestions for improving efficiency.

[1424] "Means for obtaining employee arrival and departure times" refers to a system for automatically collecting data registered by employees when they start and finish their shifts.

[1425] The "means for obtaining employee schedules" is a system for obtaining information about appointments and meetings from the schedule management application used by employees.

[1426] "Means for analyzing the acquired arrival and departure times and schedule data" refers to a system for analyzing collected data on working hours and schedules, and calculating and evaluating working hours, frequency of meetings, etc.

[1427] The "means for generating feedback and efficiency suggestions" is a system for notifying users of suggestions and improvements regarding work efficiency and health management based on the analysis results.

[1428] The "means for notifying the user of the feedback and suggestions" is a system for displaying the generated feedback and suggestions on the user's terminal and notifying the user.

[1429] The "means for generating task reminders based on the user's personality data" is a system that individually optimizes task reminders according to the user's personality and behavioral patterns and notifies them at the appropriate time.

[1430] "A means of aggregating data from all employees and providing it to the human resources department" refers to a system that compiles each employee's work status and schedule data, centrally manages it, and provides it to the human resources department.

[1431] "A means of compiling employee work data and providing it to human resources personnel as a dashboard" refers to a system that visualizes employees' working hours and signs of overwork, and provides information in dashboard format so that human resources personnel can easily manage it.

[1432] The "means for generating alerts" refers to a system that generates warnings regarding excessive work hours and health risks based on calculated working hours and analysis results.

[1433] The "means for analyzing the frequency of meetings and detecting excessive meeting time" is a system that monitors schedule data and measures and evaluates the frequency and duration of meetings in which employees participate.

[1434] "Means for suggesting alternative communication methods" is a system that proposes alternative communication methods, such as email or chat, as an alternative to meetings, in order to improve work efficiency.

[1435] The "means for generating reminder notifications" is a system for generating and sending reminder notifications in a timely manner according to the deadlines and importance of the user's tasks.

[1436] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. The system automatically collects employee arrival and departure times and schedule data, and analyzes this data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality, preventing missed tasks. Furthermore, it has the function of aggregating data on all employees and providing it to the human resources department.

[1437] System Configuration

[1438] This system mainly consists of a server, user terminals, and a terminal in the human resources department. Details of each component are shown below.

[1439] server:

[1440] The server collects data via API from time management systems such as "TimePro" and "King of Time" to obtain employee arrival and departure times.

[1441] The server retrieves employee schedule data from scheduling apps such as Google Calendar and Microsoft Outlook, using a mechanism that allows API access through OAuth authentication.

[1442] The server calculates the employee's working hours based on the acquired arrival and departure times and schedule data. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, the working hours are calculated as 8 hours.

[1443] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[1444] Based on the analysis results, the server generates feedback and suggestions for efficiency improvements for employees. For example, if there are signs of overwork, it generates an alert such as, "Working more than 45 hours per week has been detected. We recommend that you take a break."

[1445] The server sets optimal task reminders based on the user's personality data and generates reminder notifications. For example, it sets up frequent reminders for users who tend to forget tasks.

[1446] The server aggregates all employee work data and provides it to the human resources department in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[1447] Device:

[1448] The user's device displays feedback, suggestions, and reminder notifications sent from the server to the user.

[1449] The terminal of the human resources officer is used to access the dashboard generated by the server and check the work status of employees.

[1450] User:

[1451] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[1452] Users add work schedules to the schedule app, and the information is synchronized with the server.

[1453] The user checks the reminder notification displayed on the terminal and performs the task.

[1454] Specific examples

[1455] For example, if an employee arrives at work at 9:00 AM, leaves at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, this information is collected from the time management system and schedule app. The collected information is analyzed on the server, and the employee's working hours and frequency of meetings are calculated and evaluated. If signs of overwork or unnecessary meetings are detected, appropriate feedback and suggestions are generated and sent to the user's device. In addition, based on the user's personality data, reminders are sent at appropriate times to coincide with task deadlines.

[1456] For example, a reminder message such as "You have a task due in one hour" will pop up on the user's device. This will prevent tasks from being overlooked and support work efficiency and health management. Furthermore, a dashboard compiling the work data of all employees will be displayed on the HR department's device, making it easy to provide care to employees showing signs of overwork and revise rules.

[1457] In this way, the present invention is a system that automatically collects and analyzes employee data and generates feedback, suggestions, and reminder notifications to support work efficiency and employee health maintenance.

[1458] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1459] Step 1: Data collection

[1460] server:

[1461] The server obtains employee arrival and departure times from a time management system (e.g., TimePro, King of Time) via API. The obtained data is received in JSON format and stored in a database.

[1462] Input: Incoming clock-in / clock-out API request

[1463] Output: Clock-in / clock-out time data saved in the database

[1464] Specific operation: "The server retrieves User1's attendance data from TimePro at 9:00 AM and saves it in the database."

[1465] server:

[1466] The server uses OAuth authentication to retrieve employee schedule data from Google Calendar and Microsoft Outlook. The retrieved data is organized for each employee and stored in a database.

[1467] Input: Request for schedule data via API

[1468] Output: Schedule data stored in the database

[1469] Specific behavior: "The server retrieves User1's scheduled meetings from Google Calendar starting at 1 PM and saves them in the database."

[1470] User:

[1471] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[1472] Input: Manual entry of clock-in and clock-out times

[1473] Output: Work clock-in and work clock-out data recorded in a database

[1474] Specific behavior: "When User1 clocks in at 9:00 AM, the data is sent to the server through the time management system."

[1475] User:

[1476] The user adds a work schedule to the schedule application.

[1477] Input: Manually input work schedule

[1478] Output: Schedule data recorded in the database

[1479] Specific behavior: "When User1 adds a meeting to Google Calendar starting at 1 PM, the information is synchronized to the server."

[1480] Step 2: Data analysis

[1481] server:

[1482] The server calculates the employee's working hours based on the arrival and departure times stored in the database. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, their working hours are calculated as 8 hours.

[1483] Input: Clock-in / clock-out time data stored in the database

[1484] Output: Calculated working hours data

[1485] Specific operation: "The server calculates the working hours for one day as 8 hours based on User1's clock-in and clock-out data."

[1486] server:

[1487] The server aggregates each employee's total working hours on a weekly basis and detects signs of overwork (e.g., working more than 45 hours a week).

[1488] Input: Calculated working time data

[1489] Output: Overwork alert data

[1490] Specific behavior: "The server detects that User1's total working hours per week is 48 hours and generates an alert as a sign of overwork."

[1491] server:

[1492] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[1493] Input: Schedule data stored in the database

[1494] Output: Meeting frequency and overlapping task data

[1495] Specific behavior: "The server detects from User1's schedule that there are five meetings scheduled for the week."

[1496] Step 3: Generate feedback and suggestions

[1497] server:

[1498] The server generates feedback to employees based on the analysis results. For example, if there are signs of overwork, it generates an alert saying, "Working more than 45 hours per week has been detected. We recommend you take a break."

[1499] Input: Results of data analysis

[1500] Output: Feedback message

[1501] Specific behavior: "The server generates an alert to User1 saying, 'Your work hours this week have exceeded 45 hours. We recommend that you take some rest.'"

[1502] server:

[1503] The server detects unnecessary meetings and duplicated tasks and generates suggestions for improving efficiency, such as "There are more than five meetings scheduled per week. Let's handle less important meetings by email."

[1504] Input: Results of data analysis

[1505] Output: Proposal message

[1506] Specific behavior: "The server generates a suggestion for User1: 'You have five meetings scheduled for next week. Let's handle the less important meetings via email.'"

[1507] Device:

[1508] The device displays feedback and suggestions sent from the server to the user as notifications.

[1509] Input: Feedback and suggestions sent by the server

[1510] Output: Displayed as a popup notification

[1511] Specific behavior: "The device displays the feedback sent from the server as a popup notification to User1."

[1512] Step 4: Generate task reminders

[1513] server:

[1514] The server sets optimal task reminders based on the user's personality data. For example, it sets more frequent reminders for users who tend to forget things.

[1515] Input: User personality data

[1516] Output: Reminder settings

[1517] Specific operation: "The server sets the frequency of reminders based on User1's personality data."

[1518] server:

[1519] The server generates and sends a reminder notification when the task is due, for example, "The task is due in one hour."

[1520] Input: Task deadline data

[1521] Output: Reminder notification message

[1522] Specific behavior: "The server generates a reminder notification for User1 saying, 'You have a task due in one hour,' and sends it to the device."

[1523] Device:

[1524] The terminal displays the reminder notification sent from the server to the user.

[1525] Input: Reminder notification sent from the server

[1526] Output: Displayed as a popup notification

[1527] Specific behavior: "The device displays the reminder notification sent from the server as a popup to User1."

[1528] User:

[1529] The user checks the reminder notification and performs the task.

[1530] Input: Reminder

[1531] Output: Completed tasks

[1532] Specific action: "User1 checks the reminder notification and completes the task according to the deadline."

[1533] Step 5: Aggregate data and provide it to HR

[1534] server:

[1535] The server aggregates all employee work data and provides it in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[1536] Input: Individual employee work data

[1537] Output: Dashboard display data

[1538] Specific operation: "The server aggregates the working time data of all employees and provides it to the HR manager as a dashboard."

[1539] Device (e.g., HR person's PC):

[1540] The device accesses a dashboard to check employee work status.

[1541] Input: Dashboard URL and login information

[1542] Output: Dashboard display

[1543] Specific operation: "The HR person's device accesses the dashboard and checks for signs of overwork for Employee A."

[1544] Human resources person:

[1545] Human resources personnel use the information on the dashboard to plan employee care and revise rules and systems as necessary.

[1546] Input: Dashboard information

[1547] Output: Employee care plan and system revision proposal

[1548] Specific actions: "The HR person checks for signs of overwork in Employee A, schedules a meeting to consider countermeasures, and considers improving the rules by looking at the distribution of working hours across the entire department."

[1549] As described above, the present invention is a system that effectively manages employees' arrival and departure times and schedule data through each step, and supports work efficiency and health management.

[1550] (Application example 1)

[1551] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1552] In modern factory environments, improving worker efficiency and managing their health are important issues. In particular, factors such as excessive work, overlapping tasks, and increasing frequency of meetings reduce production efficiency and have a negative impact on worker health. There is a need for a system that can effectively resolve these issues and support workers in performing their work efficiently and healthily.

[1553] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1554] In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for monitoring the work status of factory workers and displaying schedules and task progress status through smart glasses, means for analyzing the acquired arrival and departure times and schedule data, means for displaying reminder notifications on the smart glasses when task deadlines are approaching, means for generating feedback and efficiency suggestions based on the analysis results, means for notifying the user of the feedback and suggestions, means for generating task reminders based on the user's personality data, and means for aggregating data on all employees and providing it to the human resources department. This makes it possible to monitor the work status and health status of each worker in real time and provide appropriate feedback and reminders.

[1555] "Employee arrival and departure times" refers to the time an employee starts and finishes work, and is the basic data for calculating working hours.

[1556] "Employee schedule" is data that includes information about employee plans, scheduled tasks, meetings, etc.

[1557] "Smart glasses" are devices worn by workers that can display information directly in their field of vision.

[1558] "Work status of factory workers" is information about the type of work that workers currently perform at the factory.

[1559] "Task progress status" is data that indicates the progress of a currently ongoing task.

[1560] A "task deadline" is information that indicates the final time or date by which a particular task should be completed.

[1561] "Reminder notification" is a function that notifies the user of task deadlines and matters requiring attention.

[1562] "Analysis results" are the results of analysis based on collected data, and are information that is useful for improving work efficiency and health management.

[1563] "User personality data" is information about the user's personality and behavioral characteristics, and is basic data for providing individual support.

[1564] "Task Remind" is a reminder function that reminds you to perform specific tasks based on the user's personality data.

[1565] "Data of all employees" refers to information including business data and health data relating to all employees belonging to a particular organization.

[1566] The "human resources department" is the department within an organization that manages employees and improves their working environment.

[1567] overview

[1568] This invention is an AI system that supports the work efficiency and health management of factory workers. This system monitors workers' arrival and departure times, schedules, and work status in real time through smart glasses, and provides feedback and reminders to improve work efficiency and health management. It also contributes to improving the working environment by aggregating data on all workers and providing it to the factory management department.

[1569] Hardware

[1570] Smart glasses (e.g. Google Glass)

[1571] Servers (for data processing and analysis)

[1572] Client terminal (such as PC in the factory management department)

[1573] software

[1574] HTTP request library for Python: requests

[1575] SMTP library for Python: smtplib

[1576] Scheduling and Time Management API: REST API Endpoints

[1577] Embodiment

[1578] Data collection

[1579] The server collects the arrival and departure times of factory workers from the time management system via an API, obtains worker schedule data from a scheduling app, and monitors their work status in real time through smart glasses.

[1580] Examples:

[1581] If a worker clocks in at 8am, clocks out at 6pm, and has a scheduled one-hour meeting that day at 2pm, that information is collected from time management systems and scheduling apps.

[1582] Data analysis

[1583] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. It then analyzes the schedule data to detect meeting frequency and overlapping tasks. It also monitors the work status of workers and checks task progress in real time.

[1584] Examples:

[1585] If a worker's total work week exceeds 50 hours, an alert is generated indicating possible overwork. It also detects that the worker has three overlapping tasks on a Monday afternoon.

[1586] Feedback and Suggestions

[1587] The server generates feedback to workers based on the analysis results. If there are signs of overwork, it generates an alert to encourage rest and suggests ways to streamline tasks such as overlapping tasks and excessive meetings. These notifications are displayed to the worker through the smart glasses.

[1588] Examples:

[1589] Notifications will appear saying, "You have worked over 50 hours this week. We recommend you take some rest," and "You have four meetings scheduled for Monday. Please handle less important meetings via email."

[1590] Task Remind

[1591] The server sets optimal task reminders based on the worker's personality data, and generates reminder notifications according to the task deadline and displays them on the smart glasses.

[1592] Examples:

[1593] A timely reminder will be sent saying, "You have a task due in an hour."

[1594] Data aggregation and interface for factory management

[1595] The server aggregates all worker data and provides it to the factory management department in the form of a dashboard, allowing managers to grasp the working status of each worker at a glance.

[1596] Examples:

[1597] The manager can check the dashboard for signs of overwork in Worker B, schedule an interview, and consider countermeasures. At this time, it is possible to identify the overall distribution of working hours and departments that frequently suffer from overwork.

[1598] Example prompts for generative AI models

[1599] "I have five meetings scheduled for next week. I'll handle the less important ones via email."

[1600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1601] Step 1:

[1602] Data collection

[1603] The server uses APIs to collect the arrival and departure times and schedule data of factory workers. For example, it obtains "entrance and exit data" from a time management system and "schedule data" from a scheduling application. This makes it possible to understand each worker's daily working hours and schedule for that day. The input is data from the API, and the output is the arrival and departure times and schedule data stored on the server.

[1604] Step 2:

[1605] Data analysis

[1606] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. Specifically, working hours are calculated by subtracting departure times from arrival times. It also detects the frequency of meetings and overlapping tasks based on schedule data. The input is the collected arrival and departure times and schedule data, and the output is the calculated working hours and analysis results.

[1607] Step 3:

[1608] Feedback Generation

[1609] The server generates feedback based on the results of data analysis. For example, if the total working hours per week exceed 50 hours, it generates an alert to encourage rest as a sign of overwork. It also makes suggestions for improving efficiency by addressing duplicate tasks and unnecessary meetings. The input is the results of data analysis, and the output is a feedback message.

[1610] Step 4:

[1611] Feedback Notifications

[1612] The device attached to the smart glasses notifies the worker of the generated feedback. The feedback is displayed visually and can be viewed by the worker in real time. The input is the feedback message, and the output is a notification displayed on the smart glasses display.

[1613] Step 5:

[1614] Reminder generation

[1615] The server generates task reminders based on the worker's personality data. For example, it sets more frequent reminders for workers who tend to forget tasks. The input is personality data and task data, and the output is a reminder message.

[1616] Step 6:

[1617] Reminder notifications

[1618] The smart glasses equipped device displays the generated reminder notification to the worker. The notification is displayed at an appropriate time for tasks with an approaching deadline. The input is the reminder message, and the output is the notification displayed on the smart glasses display.

[1619] Step 7:

[1620] Data aggregation and provision

[1621] The server aggregates data on all workers and provides it to the factory management department in dashboard format. This allows managers to understand the working conditions of workers at a glance and take necessary measures. The input is data on all workers, and the output is displayed data in dashboard format.

[1622] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1623] overview

[1624] This invention combines an AI system that supports businesspeople in improving work efficiency and managing their health with an emotion engine that recognizes the user's emotions. It collects and analyzes the user's arrival and departure times, schedule data, and emotional data to provide feedback and efficiency suggestions. It also generates task reminders based on the user's personality and emotions to prevent missed tasks and stress. It also has the function of aggregating and providing data on all employees to the human resources department.

[1625] Program processing

[1626] Data collection

[1627] server:

[1628] Employee arrival and departure times are collected from the time management system via API.

[1629] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication.

[1630] An emotion engine is used to collect user emotion data (e.g., facial expressions, voice, text).

[1631] User:

[1632] Enter your clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[1633] Manually enter work schedules and meeting schedules into a scheduling app.

[1634] Emotional data is provided to the system through cameras, microphones and other sensors.

[1635] Examples:

[1636] If an employee clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day, that data is collected from time management systems and scheduling apps. At the same time, if the employee feels stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[1637] Data Integration and Storage

[1638] server:

[1639] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[1640] The consolidated data is stored in a database for subsequent analysis.

[1641] Data analysis

[1642] server:

[1643] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[1644] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[1645] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[1646] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation.

[1647] Feedback Generation

[1648] server:

[1649] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[1650] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[1651] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[1652] Notifications and Displays

[1653] server:

[1654] Prepare to notify the user of the generated feedback and efficiency suggestions.

[1655] Device:

[1656] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[1657] User:

[1658] Review the feedback and suggestions you receive and reassess your work progress, for example, by taking breaks or cutting out unnecessary meetings.

[1659] Task reminder generation

[1660] server:

[1661] Personality and emotional data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[1662] Schedule and send timely reminders for task deadlines.

[1663] Device:

[1664] Receive reminder notifications and display them to the user.

[1665] User:

[1666] Check reminders and perform assigned tasks.

[1667] Data aggregation and HR dashboards

[1668] server:

[1669] It aggregates and visualizes work and emotional data from all employees to generate a dashboard, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[1670] Provide a dedicated interface for easy access by the HR department.

[1671] Device (HR personnel's PC, tablet, etc.):

[1672] Access a dashboard to see each employee's work status and emotional state.

[1673] Review employee care plans based on established alerts and recommendations.

[1674] Human resources person:

[1675] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork, and take action.

[1676] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[1677] In this way, the present invention provides a system that collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving efficiency and health management. This provides comprehensive support for employees' working conditions and mental health, improving work efficiency and maintaining their health.

[1678] The processing flow will be explained below.

[1679] Step 1: Data collection

[1680] server:

[1681] Employee clock-in and clock-out times are obtained by calling an API endpoint from the time management system. Specifically, employee ID, clock-in time, and clock-out time are obtained.

[1682] Retrieve employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and obtain event information (start time, end time, title, participants).

[1683] The emotion engine is used to collect emotion data (e.g., facial expression recognition, voice analysis, text analysis) from sensors such as cameras and microphones.

[1684] User:

[1685] Enter your daily clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[1686] Manually add work appointments and scheduled meetings to your scheduling app.

[1687] Emotional data is provided to the system via a camera or microphone. For example, the camera captures facial expressions as emotional data, and voice analysis detects stress levels.

[1688] Step 2: Data integration and storage

[1689] server:

[1690] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[1691] The consolidated data is stored in a database for subsequent analysis, and the database is protected by security measures.

[1692] Step 3: Data analysis

[1693] server:

[1694] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[1695] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[1696] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[1697] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation, for example by using facial recognition technology to determine whether an employee is feeling stressed.

[1698] Step 4: Feedback generation

[1699] server:

[1700] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[1701] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[1702] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[1703] Step 5: Notifications and Display

[1704] server:

[1705] Prepare to notify the user of the generated feedback and efficiency suggestions.

[1706] Device:

[1707] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[1708] User:

[1709] Review the feedback and suggestions you receive and review your work progress, for example, by taking breaks or cutting down on unnecessary meetings.

[1710] Step 6: Generate task reminders

[1711] server:

[1712] The system uses personality and emotional data for each user to determine the optimal reminder format (email, chat, push notification) and timing. For example, users who forget things easily will be reminded more frequently.

[1713] Schedule reminders for task deadlines and send them at the times you specify.

[1714] Device:

[1715] Receive reminder notifications and display them to the user.

[1716] User:

[1717] Check reminders and perform assigned tasks.

[1718] Step 7: Data aggregation and HR dashboards

[1719] server:

[1720] It aggregates and visualizes work and emotional data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[1721] Provide a dedicated interface for easy access by the HR department.

[1722] Device (HR personnel's PC, tablet, etc.):

[1723] Access a dashboard to see each employee's work status and emotional state.

[1724] Review employee care plans based on established alerts and recommendations.

[1725] Human resources person:

[1726] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork or are under high stress, and take appropriate action.

[1727] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[1728] Example 2

[1729] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1730] Conventional labor management systems only collected data on employee arrival and departure times and schedules, but were unable to provide feedback that took into account employees' emotional state or stress levels. This made it difficult to comprehensively support employees' work efficiency and mental health. Furthermore, they failed to detect excessive meetings based on schedule data or provide sufficient task reminders, leading to problems such as decreased work efficiency and increased stress.

[1731] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for acquiring employee emotion data, means for integrating and saving the acquired arrival and departure times, schedules, and emotion data, means for analyzing the integrated data, means for generating feedback and efficiency suggestions for each employee based on the analysis results, means for notifying the user of the feedback and suggestions, means for displaying the notified feedback and suggestions, means for generating task reminders based on the user's personality data and emotion data, and means for aggregating data for all employees and providing it to the human resources department. This makes it possible to comprehensively manage employees' working conditions and emotional states and provide an efficient and healthy working environment.

[1732] "Employee arrival and departure times" refers to the time an employee starts and finishes work.

[1733] "Schedule data" refers to information including the time and content of meetings, tasks, etc. that an employee is scheduled to participate in during working hours.

[1734] "Emotional data" refers to data that represents an employee's emotional state, collected from facial expressions, voice, text, etc.

[1735] An "API" is an interface that allows different software components to communicate with each other.

[1736] "OAuth 2.0 Authentication" is a standardized authentication protocol for securely delegating resource owner authorization to other applications.

[1737] An "emotion engine" is software or algorithm that analyzes and determines a user's emotions from collected data.

[1738] A "timeline" is a chronological representation of a series of events or data points over a specific period of time.

[1739] A "database" is a system for efficiently and securely storing and managing large amounts of data.

[1740] "Feedback" refers to the evaluation and advice the system provides to the user based on the analysis results.

[1741] "Efficiency suggestions" are specific advice and instructions for optimizing business processes.

[1742] A "notification" is a means by which a system communicates information to a user, and can take the form of an email, a pop-up, or the like.

[1743] "Task Remind" is a reminder that helps users remember to perform scheduled tasks.

[1744] "Data aggregation" is the process of centralizing and integrating data collected from different sources.

[1745] A "dashboard" is an interface that visually displays data and enables real-time monitoring and analysis.

[1746] A "care plan" is a specific plan or measure to maintain and improve employee health and work efficiency.

[1747] "Overwork symptoms" are signs or data that indicate that an employee is working too much.

[1748] A "non-important meeting" refers to a meeting that is deemed to have low priority and low importance in business.

[1749] A "reminder notification" is a notification that notifies the user of the task execution time or deadline.

[1750] A "dedicated interface" is a user interface designed to be accessible to a specific user or department.

[1751] "All employee data" refers to information about working hours, schedules, emotions, and so on for all employees in an organization.

[1752] MODE FOR CARRYING OUT THE INVENTION

[1753] overview

[1754] This invention combines an AI system that supports employee work efficiency and health management with an emotion engine that recognizes user emotions. It collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving work efficiency. It also generates task reminders based on the user's personality and emotional data to prevent missed tasks and stress. It also has a function to aggregate and provide data on all employees to the human resources department.

[1755] Data collection

[1756] server:

[1757] The server collects employee arrival and departure times from the time management system via an API. It also obtains employee schedule data from schedule apps (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication. It also uses an emotion engine to collect emotion data from facial expressions, voice, and text data.

[1758] User:

[1759] Users manually enter their arrival and departure times into a time management system or use an automatic clock-in / clock-out system. They also manually enter their work schedules and meeting schedules into a scheduling app. They also provide emotional data via sensors such as cameras and microphones.

[1760] Examples:

[1761] An employee who clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day enters their data into a time management system and scheduling app, and if they feel stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[1762] Data Integration and Storage

[1763] server:

[1764] The collected attendance data, schedule data, and emotion data are integrated to create a timeline for each employee. The integrated data is then stored in a database for subsequent analysis.

[1765] Data analysis

[1766] server:

[1767] The server uses the stored data to calculate each employee's daily working hours. For example, it calculates the difference between the time they arrive and leave work. It also tallies the total number of hours worked in a week and determines whether it exceeds 40 hours. It analyzes the frequency of meetings and overlapping tasks based on schedule data to identify inefficiencies. It uses an emotion engine to analyze the collected emotional data and evaluate stress levels and motivation.

[1768] Feedback Generation

[1769] server:

[1770] Based on the results of work hours aggregation, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week exceed 45 hours. We recommend that you take a rest" is generated. Based on schedule analysis results, suggestions for improving efficiency (e.g., completing non-essential meetings via email) are generated. Based on emotional data, feedback to reduce stress and increase motivation is generated. For example, a suggestion such as "You seem to be feeling stressed during the meeting. It might be a good idea to take a short rest."

[1771] Notifications and Displays

[1772] server:

[1773] Prepare to notify users of the feedback and suggestions you generate.

[1774] Device:

[1775] The device receives feedback and suggestions from the server and displays them to the user in pop-up notifications and emails.

[1776] Task reminder generation

[1777] server:

[1778] The server determines the optimal reminder format (email, chat, push notification) and timing based on the user's personality and emotional data. It schedules reminder notifications according to task deadlines and sends them in a timely manner.

[1779] Device:

[1780] The device receives the reminder notification, displays it to the user, checks the reminder notification, and executes the specified task.

[1781] Data aggregation and HR dashboards

[1782] server:

[1783] The server aggregates all employee work and emotional data and generates a visual dashboard containing indicators such as working hours, meeting frequency, task completion rate, and stress level. A dedicated interface is provided for easy access by the HR department.

[1784] Device (HR personnel's PC, tablet, etc.):

[1785] Access a dashboard to view each employee's work status and emotional state, and develop a care plan for each employee based on configured alerts and recommendations.

[1786] Prompt Sentence Examples

[1787] Examples of prompts to be input to a generative AI model include:

[1788] "Analyze current working conditions and stress levels based on employee arrival and departure times, schedule data, and emotional data, and suggest areas for improvement."

[1789] "Generate specific feedback for employees who show signs of overwork based on weekly work hour aggregates and sentiment data."

[1790] The above describes an embodiment of the present invention. The present invention provides an efficient and healthy working environment by comprehensively managing the working conditions and emotional states of employees, thereby improving work efficiency and managing their health.

[1791] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1792] Step 1: Data collection

[1793] server:

[1794] The server retrieves employee arrival and departure time data from a time management system via an API. It also retrieves schedule data from schedule apps (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication. It uses an emotion engine to collect emotion data from facial expressions, voice, and text data.

[1795] input:

[1796] Arrival and departure time data

[1797] Schedule Data

[1798] Emotional Data

[1799] output:

[1800] Obtained data on arrival and departure times

[1801] Retrieved schedule data

[1802] Acquired emotion data

[1803] Specific behavior:

[1804] For example, if an employee clocks in at 9 a.m. and clocks out at 5 p.m., this data is automatically collected from the time management system. Similarly, a one-hour meeting scheduled for 1 p.m. on Google Calendar is also collected. If the employee feels stressed during the meeting, emotional data is collected using a camera and microphone.

[1805] Step 2: Data integration and storage

[1806] server:

[1807] The server integrates the collected attendance data, schedule data, and emotion data to create a timeline for each employee, and then stores the integrated data in a database.

[1808] input:

[1809] Obtained data on arrival and departure times

[1810] Retrieved schedule data

[1811] Acquired emotion data

[1812] output:

[1813] Integrated Timeline Data

[1814] Data stored in a database

[1815] Specific behavior:

[1816] Arrival and departure times, schedule data, and emotion data are compiled in chronological order to create a timeline of one day. This timeline is saved in a database for subsequent analysis.

[1817] Step 3: Data analysis

[1818] server:

[1819] The server calculates each employee's daily working hours based on the stored data. It also tallies the total working hours for the week and determines whether they exceed a set standard (e.g., 40 hours). It also analyzes the frequency of meetings and overlapping tasks from schedule data to identify inefficiencies. At the same time, it analyzes the emotional data collected by the emotion engine to evaluate stress levels and motivation.

[1820] input:

[1821] Integrated Timeline Data

[1822] Data stored in a database

[1823] output:

[1824] Calculation results of working hours

[1825] Identifying inefficient schedules

[1826] Emotion data analysis results

[1827] Specific behavior:

[1828] If an employee starts work at 9:00 and finishes work at 17:00, the working hours for that day are calculated as 8 hours. The total working hours for the week are calculated to determine whether they exceed 40 hours. At the same time, Google Calendar data is analyzed to identify unnecessary meetings and duplicate tasks. Emotional data is analyzed to quantify stress levels during meetings.

[1829] Step 4: Feedback generation

[1830] server:

[1831] Based on the aggregated results, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours have exceeded 45 hours this week. We recommend that you take a rest" is generated. Based on the schedule analysis results, efficiency suggestions are generated, such as conducting non-important meetings by email. Based on the results of emotional data, feedback is generated to reduce stress and improve motivation.

[1832] input:

[1833] Calculation results of working hours

[1834] Identifying inefficient schedules

[1835] Emotion data analysis results

[1836] output:

[1837] Overwork alert feedback

[1838] Efficiency proposals

[1839] Feedback about emotional state

[1840] Specific behavior:

[1841] Automatically generate and send messages recommending rest to employees whose working hours exceed the standard. Analyze schedule data to suggest replacing inefficient meetings with text chat. Based on emotional data, send feedback suggesting relaxation methods to employees in high-stress situations.

[1842] Step 5: Notifications and Display

[1843] server:

[1844] Prepare to notify users of generated feedback and suggestions.

[1845] Device:

[1846] The device receives feedback and suggestions from the server and displays them to the user via pop-up notifications or emails.

[1847] input:

[1848] Feedback and Suggestion Data

[1849] output:

[1850] User Notification and Display

[1851] Specific behavior:

[1852] A message pops up on the user's PC or smartphone saying, "Your working hours this week have exceeded the standard. We recommend you take a break." An email with suggestions for improvement arrives in the user's inbox, and the user can view it and cancel or reschedule the meeting.

[1853] Step 6: Generate task reminders

[1854] server:

[1855] The server determines the optimal reminder format (email, chat, push notification) and timing based on the user's personality and emotional data. It schedules reminders to match task deadlines and sends them in a timely manner.

[1856] Device:

[1857] The device receives the reminder notification, displays it to the user, confirms the reminder notification, and performs the specified task.

[1858] input:

[1859] Personality Data

[1860] Emotional Data

[1861] Task Deadline Data

[1862] output:

[1863] Task Reminder Notifications

[1864] Specific behavior:

[1865] Reminders for specific tasks will appear on the smartphone as push notifications before the deadline, and reminder emails will arrive in the user's inbox, allowing the user to check the email and complete the task.

[1866] Step 7: Data aggregation and HR dashboards

[1867] server:

[1868] The server aggregates all employee work and emotional data and generates a visual dashboard containing indicators such as working hours, meeting frequency, task completion rate, and stress level. A dedicated interface is provided for easy access by the HR department.

[1869] Device (HR personnel's PC, tablet, etc.):

[1870] The device accesses a dashboard to check each employee's work status and emotional state, and considers care plans for employees based on set alerts and recommendations.

[1871] input:

[1872] Labor Data

[1873] Emotional Data

[1874] output:

[1875] Dashboard

[1876] Care plan proposal

[1877] Specific behavior:

[1878] The dashboard visualizes working hours and emotional data, allowing HR personnel to check the status of each employee at a glance. Care plans are then created for highly stressed employees, offering specific rest plans and stress reduction measures.

[1879] (Application example 2)

[1880] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1881] Conventional employee work efficiency and health management systems are limited to collecting and analyzing data such as arrival and departure times and schedules, making it difficult to comprehensively evaluate employees' performance, including emotional data. Furthermore, feedback and suggestions are only provided to a single device, preventing flexible responses based on user attributes and circumstances, resulting in insufficient support for on-site workers and managers. This makes it difficult to detect and address declines in work efficiency and health risks early on.

[1882] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1883] In this invention, the server includes a means for collecting and analyzing emotion data using an emotion engine, a means for integrating and storing attendance data, schedule data, and emotion data, and a means for notifying and displaying the data on smart glasses or a robot. This enables support for on-site workers and managers by comprehensively analyzing employees' attendance times, schedule data, and emotion data, and generating feedback and suggestions for improving efficiency and health management.

[1884] 1. "Working hours" refers to the time an employee starts and finishes work.

[1885] 2. "Schedule data" refers to data that includes employee meetings, tasks, and other schedules.

[1886] 3. "Emotional data" refers to emotional information obtained from employees' facial expressions, voice, text, etc.

[1887] 4. An "emotion engine" is a system that analyzes emotional data and evaluates employees' emotional states.

[1888] 5. "Feedback" refers to instructions or advice given to employees based on the results of analysis.

[1889] 6. "Efficiency Proposals" are notifications proposing specific means or methods for improving business efficiency.

[1890] 7. "Task Remind" is a task reminder generated based on employee personality data.

[1891] 8. "Data integration" refers to the bringing together of data obtained from different sources into a single data set.

[1892] 9. "Smart glasses" are glasses-type devices that provide visual information to users when worn.

[1893] 10. "Robot" means a mechanical device that performs work automatically based on a program.

[1894] 11. "Stress level" is a numerical representation of an employee's mental burden and tension.

[1895] 12. "Motivation" refers to an employee's enthusiasm and enthusiasm for work.

[1896] 13. "Push Notification" means a form of notification that instantly sends specific information to a Device.

[1897] 14. A "visual dashboard" is an interface that visually displays data using graphs and charts.

[1898] 15. "Overwork" refers to a condition in which an employee's health is harmed due to excessive working hours or workload.

[1899] Server Processing

[1900] In the system for realizing this application example, first, a server executes a program using the following hardware and software.

[1901] 1. Data Collection:

[1902] The server collects employee arrival and departure times from the time management system via an API, obtains employee schedule data from schedule apps (e.g., Google Calendar or Microsoft Outlook) using OAuth 2.0 authentication, and uses an emotion engine to collect employee emotion data from sensors such as cameras and microphones.

[1903] 2. Data integration and storage:

[1904] The server integrates the acquired attendance data, schedule data, and emotion data to create a timeline for each employee and saves it in a database. For this purpose, an SQL database (e.g., SQLite) is used.

[1905] 3. Data Analysis:

[1906] The server calculates each employee's daily working hours and aggregates their total weekly working hours based on the stored data. It also analyzes schedule data to identify inefficiencies, such as meeting frequency and overlapping tasks, and uses an emotion engine to evaluate stress levels and motivation based on emotional data. This is done using the Pandas library.

[1907] 4. Feedback Generation:

[1908] The server generates alerts for employees who show signs of overwork based on the results of work hours aggregation, and also generates feedback to users to suggest ways to improve efficiency and reduce stress.

[1909] 5. Notices and Displays:

[1910] The server notifies the generated feedback and suggestions for efficiency improvement to devices such as smart glasses and robots via push notifications and emails.

[1911] 6. Task reminder generation:

[1912] The server refers to the personality and emotional data of each user, sets the optimal reminder format and timing, and schedules the reminder notification to match the task deadline.

[1913] 7. Data aggregation and dashboard generation:

[1914] The server aggregates work and emotional data from all employees and generates a visual dashboard for the HR department, visualizing indicators such as working hours, meeting frequency, task completion rate, and stress level.

[1915] User Action

[1916] 1. Data Entry:

[1917] Users manually enter their arrival and departure times into a time management system or use an automatic time-stamping system, and also manually enter their work schedules and meeting schedules into a scheduling app.

[1918] 2. Emotion data provision:

[1919] Users provide emotional data to the system through cameras, microphones, and other sensors.

[1920] 3. Feedback confirmation:

[1921] Users can review their work progress by checking the feedback and suggestions for efficiency displayed on the smart glasses or robot's display.

[1922] 4. Reminder confirmation:

[1923] The user checks the reminder notification and performs the specified task.

[1924] Examples of prompt statements

[1925] For example, here is a concrete example of a prompt statement to calculate working hours using the Pandas library:

[1926] "Using Python's Pandas library, write code to calculate the number of hours worked each day in a week and check whether the total number of hours worked exceeds 40. The data is given in the following format: a DataFrame with columns 'start_time' and 'end_time'."

[1927] Adding specific examples

[1928] If an employee clocks in at 9:00 AM, clocks out at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, that data will be collected from the time management system and schedule app. At the same time, if the employee feels stressed during the meeting, emotional data will be collected through facial recognition and voice analysis. Based on this, the server will generate feedback such as "We recommend you take a short break" and send it to the smart glasses. The user can then check the notification and take an appropriate rest.

[1929] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1930] Step 1:

[1931] Data collection

[1932] The server obtains employee arrival and departure times through the time management system's API. Additionally, the server collects employee schedule data from a scheduling app using OAuth 2.0 authentication. This data is received in JSON format, after which it is formatted and filtered. An emotion engine is used to collect employee emotional data (facial expressions, voice, text, etc.) in real time from sensors such as cameras and microphones. The input for data collection is the API responses from the time management system and scheduling app, as well as the emotional data from the sensors, and the output is the integrated initial dataset.

[1933] Step 2:

[1934] Data Integration and Storage

[1935] The server integrates the acquired attendance / leave data, schedule data, and emotion data to create a timeline for each employee. To do this, a database (e.g., SQLite) is used to store the data. The input for the integrated data is the various datasets output from Step 1, and the output is the integrated data stored in the SQL database. Specifically, each data field is matched and saved as a record in a standardized timeline format.

[1936] Step 3:

[1937] Data analysis

[1938] The server uses the integrated data to calculate the daily working hours of each employee. Using the Pandas library, it calculates the difference between the arrival time and departure time to calculate the working hours for that day. It also aggregates the total working hours by week and determines whether they exceed the set standard. The input is the integrated data, and the output is the analysis results of each employee's working hours. Specifically, daily and weekly working hours are calculated through data frame operations.

[1939] Step 4:

[1940] Emotional Data Evaluation

[1941] The server uses an emotion engine to analyze the emotional data and evaluate employees' stress levels and motivation. Specifically, it analyzes the collected voice and facial expression data and calculates emotional parameters. The input is emotional data, and the output is the evaluation results (stress level, motivation score).

[1942] Step 5:

[1943] Feedback Generation

[1944] The server generates alerts for employees showing signs of overwork or stress based on the results of the work time analysis and the emotional data evaluation. It also generates feedback to suggest efficiency improvements and reduce stress. The input is the results of the work time analysis and the emotional data evaluation, and the output is the generated feedback or alert message.

[1945] Step 6:

[1946] Notifications and Displays

[1947] The server sends the generated feedback and suggestions to the smart glasses or robot device via push notification or email. The input is the feedback message, and the output is a notification displayed on the user device. Specifically, the message is sent to the device through a dedicated API, and the user can view it.

[1948] Step 7:

[1949] Task reminder generation

[1950] The server determines the optimal reminder format (e.g., email, chat, or push notification) and timing based on each user's personality and emotional data. It schedules reminder notifications to match task deadlines and sends them at the appropriate time. The input is the user's personality and emotional data, and the output is the scheduled reminder notification.

[1951] Step 8:

[1952] Data aggregation and dashboard generation

[1953] The server aggregates the work and emotion data of all employees and generates a visual dashboard for the HR department, visualizing indicators such as working hours, meeting frequency, task completion rate, and stress level. The input is the aggregated data, and the output is the visual dashboard. Specifically, the data is displayed visually using graphs and charts, and organized into a format that is easy for HR personnel to understand.

[1954] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1955] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1956] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1957] [Fourth embodiment]

[1958] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1959] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1960] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1961] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1962] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1963] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1964] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1965] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1966] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1967] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1968] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1969] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1970] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1971] overview

[1972] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. It collects and analyzes users' arrival and departure times and schedule data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality to prevent tasks from being overlooked. It also has the function of aggregating and providing data on all employees to the human resources department.

[1973] Program processing

[1974] Data collection

[1975] server:

[1976] To obtain employee clock-in and clock-out times, data is collected from the time management system via API.

[1977] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook).

[1978] User:

[1979] Enter your arrival and departure times into a time management system and add your work schedule to a scheduling app.

[1980] Examples:

[1981] If an employee clocks in at 9am, clocks out at 5pm, and has a one-hour meeting at 1pm that day, that information is collected from time management systems and scheduling apps.

[1982] Data analysis

[1983] server:

[1984] Calculate employee working hours based on the collected arrival and departure times. For example, calculate the total working hours for each employee per day and calculate the total working hours for the week.

[1985] Analyze schedule data to detect meeting frequency and overlapping tasks.

[1986] Examples:

[1987] If an employee's total weekly working hours exceed 45 hours, an alert is generated indicating possible overwork. It also detects that an employee's schedule includes five meetings per week.

[1988] Feedback and Suggestions

[1989] server:

[1990] Based on the analysis results, feedback on working hours is generated for employees. For example, if there are signs of overwork, an alert is generated to encourage them to take a break.

[1991] Detects unnecessary meetings and duplicate tasks from schedule data and generates suggestions for improving efficiency.

[1992] Device:

[1993] Display feedback and suggestions to users as notifications.

[1994] Examples:

[1995] Notifications will appear saying, "You have worked more than 45 hours this week. We recommend you take some rest," and "You have five meetings scheduled for next week. Please handle less important meetings via email."

[1996] Task Remind

[1997] server:

[1998] Based on the user's personality data, the system sets optimal task reminders. For example, if a user tends to forget things, the system will set reminders to be sent more frequently.

[1999] Generate and send reminders for task deadlines.

[2000] Device:

[2001] Display a reminder notification to the user.

[2002] User:

[2003] Check reminders and perform tasks.

[2004] Examples:

[2005] A timely reminder will be sent saying, "You have a task due in an hour."

[2006] Data aggregation and HR interface

[2007] server:

[2008] Data from all employees is aggregated and provided to the HR department in the form of a dashboard, allowing HR personnel to grasp each employee's working status at a glance.

[2009] Device (e.g., HR person's PC):

[2010] Access the dashboard to see your employees' work status.

[2011] Human resources person:

[2012] Based on the dashboard, we will devise ways to care for employees and revise rules and systems as necessary.

[2013] Examples:

[2014] A human resources manager checks the dashboard for signs of overwork in Employee A, schedules an interview, and considers countermeasures. At this time, it is possible to identify the distribution of the employer's overall working hours and identify departments that frequently suffer from overwork.

[2015] In this way, the present invention provides a system that supports improving work efficiency and maintaining employee health by collecting and analyzing employee data and providing feedback and suggestions for improving efficiency and health management.

[2016] The processing flow will be explained below.

[2017] Step 1: Data collection

[2018] server:

[2019] Call the API endpoint that collects employee clock-in and clock-out times from the time management system, and obtain the employee ID, clock-in time, and clock-out time.

[2020] Employee schedule data is obtained from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and event information (start time, end time, title, participants) is obtained.

[2021] User:

[2022] Enter your daily clock-in and clock-out times into a timekeeping system manually or use an automatic clock-in system.

[2023] Manually enter work schedules and meeting schedules into a scheduling app.

[2024] Step 2: Data integration and storage

[2025] server:

[2026] The acquired attendance and departure data and schedule data are integrated to create a timeline for each employee.

[2027] The integrated data is stored in a database and prepared for analysis.

[2028] Step 3: Data analysis

[2029] server:

[2030] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[2031] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[2032] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[2033] Step 4: Feedback generation

[2034] server:

[2035] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[2036] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[2037] Step 5: Notifications and Display

[2038] server:

[2039] Prepare to notify the user of the generated feedback and efficiency suggestions.

[2040] Device:

[2041] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[2042] User:

[2043] Review the feedback and suggestions you receive and review your work progress, for example, taking breaks or cutting out unnecessary meetings.

[2044] Step 6: Generate task reminders

[2045] server:

[2046] Personality data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[2047] Schedule and send timely reminders for task deadlines.

[2048] Device:

[2049] Receive reminder notifications and display them to the user.

[2050] User:

[2051] Check reminders and perform assigned tasks.

[2052] Step 7: Data aggregation and HR dashboards

[2053] server:

[2054] It aggregates and visualizes work data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, and task completion rates.

[2055] Provide a dedicated interface for easy access by the HR department.

[2056] Device (HR personnel's PC, tablet, etc.):

[2057] Access the dashboard to check each employee's work status.

[2058] Review employee care plans based on established alerts and recommendations.

[2059] Human resources person:

[2060] Use the dashboard to create care plans and take action for employees who show signs of overwork.

[2061] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[2062] Example 1

[2063] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2064] Managing employee arrival and departure times and schedules is an important issue for many companies, but the current system involves a lot of manual input and confirmation, which is inefficient and makes it difficult to understand employee working hours and health status. Furthermore, a lack of appropriate feedback on work efficiency and task management creates the risk of employee overwork and missing tasks. Furthermore, it is difficult for the HR department to centrally manage the working status of all employees.

[2065] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2066] In this invention, the server includes a means for acquiring employee arrival and departure times, a means for acquiring employee schedules, and a means for analyzing the acquired arrival and departure times and schedule data. This makes it possible to automatically collect and analyze employee working hours and schedules, detect signs of overwork and unnecessary meetings, and provide appropriate feedback and suggestions for improving efficiency.

[2067] "Means for obtaining employee arrival and departure times" refers to a system for automatically collecting data registered by employees when they start and finish their shifts.

[2068] The "means for obtaining employee schedules" is a system for obtaining information about appointments and meetings from the schedule management application used by employees.

[2069] "Means for analyzing the acquired arrival and departure times and schedule data" refers to a system for analyzing collected data on working hours and schedules, and calculating and evaluating working hours, frequency of meetings, etc.

[2070] The "means for generating feedback and efficiency suggestions" is a system for notifying users of suggestions and improvements regarding work efficiency and health management based on the analysis results.

[2071] The "means for notifying the user of the feedback and suggestions" is a system for displaying the generated feedback and suggestions on the user's terminal and notifying the user.

[2072] The "means for generating task reminders based on the user's personality data" is a system that individually optimizes task reminders according to the user's personality and behavioral patterns and notifies them at the appropriate time.

[2073] "A means of aggregating data from all employees and providing it to the human resources department" refers to a system that compiles each employee's work status and schedule data, centrally manages it, and provides it to the human resources department.

[2074] "A means of compiling employee work data and providing it to human resources personnel as a dashboard" refers to a system that visualizes employees' working hours and signs of overwork, and provides information in dashboard format so that human resources personnel can easily manage it.

[2075] The "means for generating alerts" refers to a system that generates warnings regarding excessive work hours and health risks based on calculated working hours and analysis results.

[2076] The "means for analyzing the frequency of meetings and detecting excessive meeting time" is a system that monitors schedule data and measures and evaluates the frequency and duration of meetings in which employees participate.

[2077] "Means for suggesting alternative communication methods" is a system that proposes alternative communication methods, such as email or chat, as an alternative to meetings, in order to improve work efficiency.

[2078] The "means for generating reminder notifications" is a system for generating and sending reminder notifications in a timely manner according to the deadlines and importance of the user's tasks.

[2079] This invention is an AI system that supports businesspeople in improving work efficiency and managing their health. The system automatically collects employee arrival and departure times and schedule data, and analyzes this data to provide feedback and suggestions for improving efficiency. It also generates task reminders based on the user's personality, preventing missed tasks. Furthermore, it has the function of aggregating data on all employees and providing it to the human resources department.

[2080] System Configuration

[2081] This system mainly consists of a server, user terminals, and a terminal in the human resources department. Details of each component are shown below.

[2082] server:

[2083] The server collects data via API from time management systems such as "TimePro" and "King of Time" to obtain employee arrival and departure times.

[2084] The server retrieves employee schedule data from scheduling apps such as Google Calendar and Microsoft Outlook, using a mechanism that allows API access through OAuth authentication.

[2085] The server calculates the employee's working hours based on the acquired arrival and departure times and schedule data. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, the working hours are calculated as 8 hours.

[2086] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[2087] Based on the analysis results, the server generates feedback and suggestions for efficiency improvements for employees. For example, if there are signs of overwork, it generates an alert such as, "Working more than 45 hours per week has been detected. We recommend that you take a break."

[2088] The server sets optimal task reminders based on the user's personality data and generates reminder notifications. For example, it sets up frequent reminders for users who tend to forget tasks.

[2089] The server aggregates all employee work data and provides it to the human resources department in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[2090] Device:

[2091] The user's device displays feedback, suggestions, and reminder notifications sent from the server to the user.

[2092] The terminal of the human resources officer is used to access the dashboard generated by the server and check the work status of employees.

[2093] User:

[2094] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[2095] Users add work schedules to the schedule app, and the information is synchronized with the server.

[2096] The user checks the reminder notification displayed on the terminal and performs the task.

[2097] Specific examples

[2098] For example, if an employee arrives at work at 9:00 AM, leaves at 5:00 PM, and has a one-hour meeting starting at 1:00 PM that day, this information is collected from the time management system and schedule app. The collected information is analyzed on the server, and the employee's working hours and frequency of meetings are calculated and evaluated. If signs of overwork or unnecessary meetings are detected, appropriate feedback and suggestions are generated and sent to the user's device. In addition, based on the user's personality data, reminders are sent at appropriate times to coincide with task deadlines.

[2099] For example, a reminder message such as "You have a task due in one hour" will pop up on the user's device. This will prevent tasks from being overlooked and support work efficiency and health management. Furthermore, a dashboard compiling the work data of all employees will be displayed on the HR department's device, making it easy to provide care to employees showing signs of overwork and revise rules.

[2100] In this way, the present invention is a system that automatically collects and analyzes employee data and generates feedback, suggestions, and reminder notifications to support work efficiency and employee health maintenance.

[2101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2102] Step 1: Data collection

[2103] server:

[2104] The server obtains employee arrival and departure times from a time management system (e.g., TimePro, King of Time) via API. The obtained data is received in JSON format and stored in a database.

[2105] Input: Incoming clock-in / clock-out API request

[2106] Output: Clock-in / clock-out time data saved in the database

[2107] Specific operation: "The server retrieves User1's attendance data from TimePro at 9:00 AM and saves it in the database."

[2108] server:

[2109] The server uses OAuth authentication to retrieve employee schedule data from Google Calendar and Microsoft Outlook. The retrieved data is organized for each employee and stored in a database.

[2110] Input: Request for schedule data via API

[2111] Output: Schedule data stored in the database

[2112] Specific behavior: "The server retrieves User1's scheduled meetings from Google Calendar starting at 1 PM and saves them in the database."

[2113] User:

[2114] Users enter their arrival and departure times into the time management system, which is then sent to the server.

[2115] Input: Manual entry of clock-in and clock-out times

[2116] Output: Work clock-in and work clock-out data recorded in a database

[2117] Specific behavior: "When User1 clocks in at 9:00 AM, the data is sent to the server through the time management system."

[2118] User:

[2119] The user adds a work schedule to the schedule application.

[2120] Input: Manually input work schedule

[2121] Output: Schedule data recorded in the database

[2122] Specific behavior: "When User1 adds a meeting to Google Calendar starting at 1 PM, the information is synchronized to the server."

[2123] Step 2: Data analysis

[2124] server:

[2125] The server calculates the employee's working hours based on the arrival and departure times stored in the database. For example, if an employee starts work at 9:00 AM and leaves work at 5:00 PM, their working hours are calculated as 8 hours.

[2126] Input: Clock-in / clock-out time data stored in the database

[2127] Output: Calculated working hours data

[2128] Specific operation: "The server calculates the working hours for one day as 8 hours based on User1's clock-in and clock-out data."

[2129] server:

[2130] The server aggregates each employee's total working hours on a weekly basis and detects signs of overwork (e.g., working more than 45 hours a week).

[2131] Input: Calculated working time data

[2132] Output: Overwork alert data

[2133] Specific behavior: "The server detects that User1's total working hours per week is 48 hours and generates an alert as a sign of overwork."

[2134] server:

[2135] The server analyzes the schedule data to detect meeting frequency and overlapping tasks, for example, if there are more than five meetings scheduled in a week.

[2136] Input: Schedule data stored in the database

[2137] Output: Meeting frequency and overlapping task data

[2138] Specific behavior: "The server detects from User1's schedule that there are five meetings scheduled for the week."

[2139] Step 3: Generate feedback and suggestions

[2140] server:

[2141] The server generates feedback to employees based on the analysis results. For example, if there are signs of overwork, it generates an alert saying, "Working more than 45 hours per week has been detected. We recommend you take a break."

[2142] Input: Results of data analysis

[2143] Output: Feedback message

[2144] Specific behavior: "The server generates an alert to User1 saying, 'Your work hours this week have exceeded 45 hours. We recommend that you take some rest.'"

[2145] server:

[2146] The server detects unnecessary meetings and duplicated tasks and generates suggestions for improving efficiency, such as "There are more than five meetings scheduled per week. Let's handle less important meetings by email."

[2147] Input: Results of data analysis

[2148] Output: Proposal message

[2149] Specific behavior: "The server generates a suggestion for User1: 'You have five meetings scheduled for next week. Let's handle the less important meetings via email.'"

[2150] Device:

[2151] The device displays feedback and suggestions sent from the server to the user as notifications.

[2152] Input: Feedback and suggestions sent by the server

[2153] Output: Displayed as a popup notification

[2154] Specific behavior: "The device displays the feedback sent from the server as a popup notification to User1."

[2155] Step 4: Generate task reminders

[2156] server:

[2157] The server sets optimal task reminders based on the user's personality data. For example, it sets more frequent reminders for users who tend to forget things.

[2158] Input: User personality data

[2159] Output: Reminder settings

[2160] Specific operation: "The server sets the frequency of reminders based on User1's personality data."

[2161] server:

[2162] The server generates and sends a reminder notification when the task is due, for example, "The task is due in one hour."

[2163] Input: Task deadline data

[2164] Output: Reminder notification message

[2165] Specific behavior: "The server generates a reminder notification for User1 saying, 'You have a task due in one hour,' and sends it to the device."

[2166] Device:

[2167] The terminal displays the reminder notification sent from the server to the user.

[2168] Input: Reminder notification sent from the server

[2169] Output: Displayed as a popup notification

[2170] Specific behavior: "The device displays the reminder notification sent from the server as a popup to User1."

[2171] User:

[2172] The user checks the reminder notification and performs the task.

[2173] Input: Reminder

[2174] Output: Completed tasks

[2175] Specific action: "User1 checks the reminder notification and completes the task according to the deadline."

[2176] Step 5: Aggregate data and provide it to HR

[2177] server:

[2178] The server aggregates all employee work data and provides it in the form of a dashboard, allowing human resources personnel to grasp each employee's work status at a glance.

[2179] Input: Individual employee work data

[2180] Output: Dashboard display data

[2181] Specific operation: "The server aggregates the working time data of all employees and provides it to the HR manager as a dashboard."

[2182] Device (e.g., HR person's PC):

[2183] The device accesses a dashboard to check employee work status.

[2184] Input: Dashboard URL and login information

[2185] Output: Dashboard display

[2186] Specific operation: "The HR person's device accesses the dashboard and checks for signs of overwork for Employee A."

[2187] Human resources person:

[2188] Human resources personnel use the information on the dashboard to plan employee care and revise rules and systems as necessary.

[2189] Input: Dashboard information

[2190] Output: Employee care plan and system revision proposal

[2191] Specific actions: "The HR person checks for signs of overwork in Employee A, schedules a meeting to consider countermeasures, and considers improving the rules by looking at the distribution of working hours across the entire department."

[2192] As described above, the present invention is a system that effectively manages employees' arrival and departure times and schedule data through each step, and supports work efficiency and health management.

[2193] (Application example 1)

[2194] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2195] In modern factory environments, improving worker efficiency and managing their health are important issues. In particular, factors such as excessive work, overlapping tasks, and increasing frequency of meetings reduce production efficiency and have a negative impact on worker health. There is a need for a system that can effectively resolve these issues and support workers in performing their work efficiently and healthily.

[2196] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2197] In this invention, the server includes means for acquiring employee arrival and departure times, means for acquiring employee schedules, means for monitoring the work status of factory workers and displaying schedules and task progress status through smart glasses, means for analyzing the acquired arrival and departure times and schedule data, means for displaying reminder notifications on the smart glasses when task deadlines are approaching, means for generating feedback and efficiency suggestions based on the analysis results, means for notifying the user of the feedback and suggestions, means for generating task reminders based on the user's personality data, and means for aggregating data on all employees and providing it to the human resources department. This makes it possible to monitor the work status and health status of each worker in real time and provide appropriate feedback and reminders.

[2198] "Employee arrival and departure times" refers to the time an employee starts and finishes work, and is the basic data for calculating working hours.

[2199] "Employee schedule" is data that includes information about employee plans, scheduled tasks, meetings, etc.

[2200] "Smart glasses" are devices worn by workers that can display information directly in their field of vision.

[2201] "Work status of factory workers" is information about the type of work that workers currently perform at the factory.

[2202] "Task progress status" is data that indicates the progress of a currently ongoing task.

[2203] A "task deadline" is information that indicates the final time or date by which a particular task should be completed.

[2204] "Reminder notification" is a function that notifies the user of task deadlines and matters requiring attention.

[2205] "Analysis results" are the results of analysis based on collected data, and are information that is useful for improving work efficiency and health management.

[2206] "User personality data" is information about the user's personality and behavioral characteristics, and is basic data for providing individual support.

[2207] "Task Remind" is a reminder function that reminds you to perform specific tasks based on the user's personality data.

[2208] "Data of all employees" refers to information including business data and health data relating to all employees belonging to a particular organization.

[2209] The "human resources department" is the department within an organization that manages employees and improves their working environment.

[2210] overview

[2211] This invention is an AI system that supports the work efficiency and health management of factory workers. This system monitors workers' arrival and departure times, schedules, and work status in real time through smart glasses, and provides feedback and reminders to improve work efficiency and health management. It also contributes to improving the working environment by aggregating data on all workers and providing it to the factory management department.

[2212] Hardware

[2213] Smart glasses (e.g. Google Glass)

[2214] Servers (for data processing and analysis)

[2215] Client terminal (such as PC in the factory management department)

[2216] software

[2217] HTTP request library for Python: requests

[2218] SMTP library for Python: smtplib

[2219] Scheduling and Time Management API: REST API Endpoints

[2220] Embodiment

[2221] Data collection

[2222] The server collects the arrival and departure times of factory workers from the time management system via an API, obtains worker schedule data from a scheduling app, and monitors their work status in real time through smart glasses.

[2223] Examples:

[2224] If a worker clocks in at 8am, clocks out at 6pm, and has a scheduled one-hour meeting that day at 2pm, that information is collected from time management systems and scheduling apps.

[2225] Data analysis

[2226] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. It then analyzes the schedule data to detect meeting frequency and overlapping tasks. It also monitors the work status of workers and checks task progress in real time.

[2227] Examples:

[2228] If a worker's total work week exceeds 50 hours, an alert is generated indicating possible overwork. It also detects that the worker has three overlapping tasks on a Monday afternoon.

[2229] Feedback and Suggestions

[2230] The server generates feedback to workers based on the analysis results. If there are signs of overwork, it generates an alert to encourage rest and suggests ways to streamline tasks such as overlapping tasks and excessive meetings. These notifications are displayed to the worker through the smart glasses.

[2231] Examples:

[2232] Notifications will appear saying, "You have worked over 50 hours this week. We recommend you take some rest," and "You have four meetings scheduled for Monday. Please handle less important meetings via email."

[2233] Task Remind

[2234] The server sets optimal task reminders based on the worker's personality data, and generates reminder notifications according to the task deadline and displays them on the smart glasses.

[2235] Examples:

[2236] A timely reminder will be sent saying, "You have a task due in an hour."

[2237] Data aggregation and interface for factory management

[2238] The server aggregates all worker data and provides it to the factory management department in the form of a dashboard, allowing managers to grasp the working status of each worker at a glance.

[2239] Examples:

[2240] The manager can check the dashboard for signs of overwork in Worker B, schedule an interview, and consider countermeasures. At this time, it is possible to identify the overall distribution of working hours and departments that frequently suffer from overwork.

[2241] Example prompts for generative AI models

[2242] "I have five meetings scheduled for next week. I'll handle the less important ones via email."

[2243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2244] Step 1:

[2245] Data collection

[2246] The server uses APIs to collect the arrival and departure times and schedule data of factory workers. For example, it obtains "entrance and exit data" from a time management system and "schedule data" from a scheduling application. This makes it possible to understand each worker's daily working hours and schedule for that day. The input is data from the API, and the output is the arrival and departure times and schedule data stored on the server.

[2247] Step 2:

[2248] Data analysis

[2249] The server calculates the working hours of workers based on the collected arrival and departure times and schedule data. Specifically, working hours are calculated by subtracting departure times from arrival times. It also detects the frequency of meetings and overlapping tasks based on schedule data. The input is the collected arrival and departure times and schedule data, and the output is the calculated working hours and analysis results.

[2250] Step 3:

[2251] Feedback Generation

[2252] The server generates feedback based on the results of data analysis. For example, if the total working hours per week exceed 50 hours, it generates an alert to encourage rest as a sign of overwork. It also makes suggestions for improving efficiency by addressing duplicate tasks and unnecessary meetings. The input is the results of data analysis, and the output is a feedback message.

[2253] Step 4:

[2254] Feedback Notifications

[2255] The device attached to the smart glasses notifies the worker of the generated feedback. The feedback is displayed visually and can be viewed by the worker in real time. The input is the feedback message, and the output is a notification displayed on the smart glasses display.

[2256] Step 5:

[2257] Reminder generation

[2258] The server generates task reminders based on the worker's personality data. For example, it sets more frequent reminders for workers who tend to forget tasks. The input is personality data and task data, and the output is a reminder message.

[2259] Step 6:

[2260] Reminder notifications

[2261] The smart glasses equipped device displays the generated reminder notification to the worker. The notification is displayed at an appropriate time for tasks with an approaching deadline. The input is the reminder message, and the output is the notification displayed on the smart glasses display.

[2262] Step 7:

[2263] Data aggregation and provision

[2264] The server aggregates data on all workers and provides it to the factory management department in dashboard format. This allows managers to understand the working conditions of workers at a glance and take necessary measures. The input is data on all workers, and the output is displayed data in dashboard format.

[2265] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2266] overview

[2267] This invention combines an AI system that supports businesspeople in improving work efficiency and managing their health with an emotion engine that recognizes the user's emotions. It collects and analyzes the user's arrival and departure times, schedule data, and emotional data to provide feedback and efficiency suggestions. It also generates task reminders based on the user's personality and emotions to prevent missed tasks and stress. It also has the function of aggregating and providing data on all employees to the human resources department.

[2268] Program processing

[2269] Data collection

[2270] server:

[2271] Employee arrival and departure times are collected from the time management system via API.

[2272] Obtain employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication.

[2273] An emotion engine is used to collect user emotion data (e.g., facial expressions, voice, text).

[2274] User:

[2275] Enter your clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[2276] Manually enter work schedules and meeting schedules into a scheduling app.

[2277] Emotional data is provided to the system through cameras, microphones and other sensors.

[2278] Examples:

[2279] If an employee clocks in at 9 a.m., clocks out at 5 p.m., and has a one-hour meeting at 1 p.m. that day, that data is collected from time management systems and scheduling apps. At the same time, if the employee feels stressed during the meeting, emotional data is collected through facial recognition and voice analysis.

[2280] Data Integration and Storage

[2281] server:

[2282] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[2283] The consolidated data is stored in a database for subsequent analysis.

[2284] Data analysis

[2285] server:

[2286] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[2287] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[2288] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[2289] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation.

[2290] Feedback Generation

[2291] server:

[2292] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[2293] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[2294] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[2295] Notifications and Displays

[2296] server:

[2297] Prepare to notify the user of the generated feedback and efficiency suggestions.

[2298] Device:

[2299] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[2300] User:

[2301] Review the feedback and suggestions you receive and reassess your work progress, for example, by taking breaks or cutting out unnecessary meetings.

[2302] Task reminder generation

[2303] server:

[2304] Personality and emotional data is used to determine the optimal reminder format (email, chat, push notification) and timing for each user.

[2305] Schedule and send timely reminders for task deadlines.

[2306] Device:

[2307] Receive reminder notifications and display them to the user.

[2308] User:

[2309] Check reminders and perform assigned tasks.

[2310] Data aggregation and HR dashboards

[2311] server:

[2312] It aggregates and visualizes work and emotional data from all employees to generate a dashboard, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[2313] Provide a dedicated interface for easy access by the HR department.

[2314] Device (HR personnel's PC, tablet, etc.):

[2315] Access a dashboard to see each employee's work status and emotional state.

[2316] Review employee care plans based on established alerts and recommendations.

[2317] Human resources person:

[2318] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork, and take action.

[2319] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[2320] In this way, the present invention provides a system that collects and analyzes employee arrival and departure times, schedule data, and emotional data to provide feedback and suggestions for improving efficiency and health management. This provides comprehensive support for employees' working conditions and mental health, improving work efficiency and maintaining their health.

[2321] The processing flow will be explained below.

[2322] Step 1: Data collection

[2323] server:

[2324] Employee clock-in and clock-out times are obtained by calling an API endpoint from the time management system. Specifically, employee ID, clock-in time, and clock-out time are obtained.

[2325] Retrieve employee schedule data from a scheduling app (e.g., Google Calendar, Microsoft Outlook) using OAuth 2.0 authentication, and obtain event information (start time, end time, title, participants).

[2326] The emotion engine is used to collect emotion data (e.g., facial expression recognition, voice analysis, text analysis) from sensors such as cameras and microphones.

[2327] User:

[2328] Enter your daily clock-in and clock-out times into the timekeeping system manually or use an automatic clock-in system.

[2329] Manually add work appointments and scheduled meetings to your scheduling app.

[2330] Emotional data is provided to the system via a camera or microphone. For example, the camera captures facial expressions as emotional data, and voice analysis detects stress levels.

[2331] Step 2: Data integration and storage

[2332] server:

[2333] The collected attendance and departure data, schedule data, and emotion data are integrated to create a timeline for each employee.

[2334] The consolidated data is stored in a database for subsequent analysis, and the database is protected by security measures.

[2335] Step 3: Data analysis

[2336] server:

[2337] Based on the saved data, the working hours of each employee per day are calculated. For example, the difference between the time of arrival and the time of departure is calculated to calculate the working hours for that day.

[2338] The total working hours for the week are tallied and a determination is made as to whether they exceed a set standard (for example, 40 hours).

[2339] Based on schedule data, analyze meeting frequency and overlapping tasks to identify inefficiencies.

[2340] An emotion engine is used to analyze collected emotional data and assess stress levels and motivation, for example by using facial recognition technology to determine whether an employee is feeling stressed.

[2341] Step 4: Feedback generation

[2342] server:

[2343] Based on the aggregated results of working hours, an alert is generated for employees who show signs of overwork. For example, feedback such as "Your working hours this week have exceeded 45 hours. We recommend that you take some rest" can be generated.

[2344] Based on the results of schedule analysis, suggestions for efficiency (e.g., conducting non-important meetings via email) are generated.

[2345] Based on the analysis of emotional data, feedback is generated to reduce stress and improve motivation. For example, it may suggest, "You seem to be feeling stressed during meetings recently. Try taking a short break."

[2346] Step 5: Notifications and Display

[2347] server:

[2348] Prepare to notify the user of the generated feedback and efficiency suggestions.

[2349] Device:

[2350] Receives feedback and suggestions from the server and displays them to the user in a pop-up notification or email.

[2351] User:

[2352] Review the feedback and suggestions you receive and review your work progress, for example, by taking breaks or cutting down on unnecessary meetings.

[2353] Step 6: Generate task reminders

[2354] server:

[2355] The system uses personality and emotional data for each user to determine the optimal reminder format (email, chat, push notification) and timing. For example, users who forget things easily will be reminded more frequently.

[2356] Schedule reminders for task deadlines and send them at the times you specify.

[2357] Device:

[2358] Receive reminder notifications and display them to the user.

[2359] User:

[2360] Check reminders and perform assigned tasks.

[2361] Step 7: Data aggregation and HR dashboards

[2362] server:

[2363] It aggregates and visualizes work and emotional data from all employees to generate dashboards, including metrics such as working hours, meeting frequency, task completion rates, and stress levels.

[2364] Provide a dedicated interface for easy access by the HR department.

[2365] Device (HR personnel's PC, tablet, etc.):

[2366] Access a dashboard to see each employee's work status and emotional state.

[2367] Review employee care plans based on established alerts and recommendations.

[2368] Human resources person:

[2369] Use the dashboard to develop care plans and stress reduction measures for employees who show signs of overwork or are under high stress, and take appropriate action.

[2370] Based on the collected data, we will revise our systems to improve work efficiency and maintain health.

[2371] Example 2

[2372] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2373] Conventional labor management syst...

Claims

1. A means of obtaining employee arrival and departure times; A means of obtaining employee schedules; A means for analyzing the acquired arrival and departure time and schedule data; a means for generating feedback and efficiency suggestions based on the analysis results; means for notifying the user of said feedback and suggestions; means for generating a task reminder based on the user's personality data; A means to aggregate data on all employees and provide it to the HR department, A system including:

2. A means for calculating employee working hours based on the acquired arrival and departure times and schedule data; A means of generating alerts for employees showing signs of overwork based on calculated working hours; and The system of claim 1 further comprising:

3. A means to analyze the frequency of employee meetings and detect excessive meeting time; a means for suggesting reduction in meeting time and other communication methods based on the detected excessive meeting time; The system of claim 1 further comprising:

Images