system

Abstract

Provide a system. 【Solution means】 Means for acquiring workers' activity data in real time, Means for analyzing activity data to detect anomalies, Means for immediately notifying the administrator and the corresponding actor when an anomaly is detected, Means for analyzing machine usage records to confirm deficiencies in activity input, Means for sending notifications and reminders, Means for generating proposals for improving health management and the harmony of active life, Means for providing health promotion feedback to actors through visual displays, Means for monitoring the physical condition using sensors and comprehensively analyzing it with activity data, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern workplace environment, appropriately managing the working conditions of workers has become a major issue for personnel officers and managers. In particular, it is difficult to monitor the attendance status and working hours of employees in real time and immediately grasp abnormalities. In addition, manual attendance management is prone to errors, and there is a possibility of input omission and incorrect recording of working hours. Moreover, although it is required to detect in advance the health risks caused by long working hours and conduct labor management, the dispersion of information has become an obstacle.

Means for Solving the Problems

[0005] This invention provides a system for detecting abnormal work conditions by acquiring and analyzing employee work data in real time. Specifically, it collects employee work data using data collection means and analyzes that data using analysis means to detect abnormalities. When an abnormality is detected, it has a notification means for immediately notifying the manager and the employee concerned. It also includes means for analyzing computer usage records to detect deficiencies in work input and sending reminders to the employee concerned. Furthermore, it provides a suggestion means for generating suggestions to improve health management and work-life balance based on the collected and analyzed data. This makes it possible to centrally and efficiently manage the work conditions of employees.

[0006] "Labor data" is a general term for information related to employees' work, including their arrival and departure times, break times, working hours, and leave information.

[0007] "Means of acquiring data in real time" refers to hardware or software functions that allow for the immediate acquisition of employee work status at the present moment.

[0008] "Means for analyzing and detecting anomalies" refers to algorithms or programs that analyze collected labor data to identify work patterns or irregular trends that differ from normal conditions.

[0009] "Means of notifying administrators and workers" refers to notification functions such as email or message informing them when an anomaly is detected.

[0010] "Computer usage records" refer to information about the operation history and activity logs of computers used by employees for work purposes.

[0011] "Methods for checking for errors in labor data entry" refers to a checking function to verify whether there are any omissions or errors in the daily work data.

[0012] The "means of sending reminders" refers to a function that automatically sends notifications to employees to draw their attention when errors in work data entry are detected.

[0013] "Suggestions for improving health management and work-life balance" are advice and improvement plans based on employee work data to promote healthy and sustainable work practices. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention provides a labor management system that collects employee attendance data and computer usage records in real time and immediately notifies relevant managers and employees when abnormal work patterns are detected. This system primarily operates via a server.

[0036] The server first automatically retrieves information such as working hours and leave status from the employee attendance database, and simultaneously collects computer usage records from the terminals used by employees for work. All data is integrated within the server and organized in a format that allows for analysis.

[0037] The server uses AI to analyze the acquired data. Specifically, it detects abnormal events that deviate from normal work patterns (for example, long working hours or repeated tardiness), and also analyzes PC usage logs to check for errors such as missing entries.

[0038] If an anomaly is detected, the server immediately notifies the relevant administrator. The notification is sent via email or internal messaging tools, allowing for swift action. Additionally, the affected employee receives a reminder or notification tailored to the nature of the anomaly, encouraging proactive response.

[0039] For example, if an employee works more than 50 hours continuously in a week, the server will detect this as an anomaly and send an alert to the administrator stating "Possible employee overwork." The employee will also receive a notification recommending that they take appropriate breaks.

[0040] Furthermore, the server is equipped with a function that provides suggestions for improving health management and work-life balance. Based on analysis of past attendance data and thought patterns, it provides improvement suggestions tailored to each employee's situation, supporting the maintenance of a sustainable work-life balance.

[0041] Thus, this invention enables real-time attendance management, allows for a rapid response in the event of an anomaly, and aims to improve employee health and motivation.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server automatically retrieves the latest data from employee attendance databases and computer usage databases periodically (for example, every 5 minutes). This enables real-time data collection, ensuring that the most up-to-date information is always available.

[0045] Step 2:

[0046] The server performs data preprocessing on the acquired data as input. This includes formatting the data, imputing missing values, and filtering outliers. If necessary, it standardizes the data format and prepares it for analysis.

[0047] Step 3:

[0048] The server uses an AI analysis module to analyze the formatted data. Here, it checks whether there are deviations from normal attendance patterns and whether working hours exceed the regulations. It also checks for inconsistencies between computer usage records and attendance data.

[0049] Step 4:

[0050] The server identifies anomalies based on the analysis results. Anomalies include, for example, consecutive long working hours, failure to enter attendance records, and consecutive lateness. In this case, the server determines the next course of action based on the severity of the anomaly.

[0051] Step 5:

[0052] If an anomaly is detected, the server will notify the administrator based on the determined action. Notifications will be sent via email or the company's internal messaging system to ensure timely information dissemination.

[0053] Step 6:

[0054] The server also notifies the employee in question of the anomaly detection result. This could include a health management message, such as "Please consider taking appropriate leave."

[0055] Step 7:

[0056] The server generates and notifies employees suspected of working long hours or excessive workloads, offering suggestions for health management and work-life balance improvement. These suggestions are personalized based on past data and individual work situations.

[0057] Step 8:

[0058] The terminal displays notifications and alerts sent from the server and provides an interface for users to take necessary actions. Users can modify attendance data, submit leave requests, and perform other actions depending on the content of the notifications.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] As workers' working hours and environments become more diverse, it is necessary to prevent adverse health effects caused by overwork and inappropriate work patterns. However, conventional attendance management systems have difficulty grasping work conditions in real time and immediately detecting and notifying abnormalities, which can lead to decreased labor productivity and employee health problems. To solve this problem, a system is needed that integrates and analyzes workers' attendance information and computer usage history to quickly detect and respond to abnormal events.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for acquiring employee attendance information in real time, means for integrating and pre-processing the acquired attendance information and computer usage history, and means for analyzing abnormal events that deviate from normal work patterns using artificial intelligence technology. This makes it possible to quickly and automatically detect abnormal work patterns of employees and immediately notify relevant managers and employees.

[0064] "Worker attendance information" refers to records of work-related information such as working hours, arrival and departure times, and leave status.

[0065] "Computer usage history" refers to records of operations performed on computers used by employees for work, login times, application usage times, and other similar information.

[0066] "Artificial intelligence technology" refers to techniques that use machine learning and statistical analysis to learn and analyze patterns from data.

[0067] An "abnormal event" is data or an incident that indicates a deviation from the normal work pattern, such as working long hours or repeated tardiness.

[0068] A "management supervisor" is a person in charge of supervising the working environment and work conditions of employees and taking appropriate action.

[0069] "Message communication technology" refers to the technology used to send and receive information using email and messaging services.

[0070] "Health management" refers to measures and guidance aimed at maintaining and improving the physical and mental health of workers.

[0071] "Work-life balance" refers to a balance in life where a worker's working hours and personal life time are in harmony, and both are considered important.

[0072] This invention relates to a system that collects and analyzes workers' attendance information and computer usage history, and detects and notifies them of abnormal work patterns. This system primarily operates through a server.

[0073] The server accesses the employee attendance database via the network and retrieves attendance information such as working hours, clock-in and clock-out times, and leave status in real time. Database management software is used to efficiently retrieve and store the data on the server. Additionally, computer usage history for work-related activities is locally retrieved from terminals and sent to the server. This allows for the integration of data on the server, enabling consistent information management.

[0074] On the server, collected attendance information and computer usage history are integrated and preprocessed. This involves data cleaning and normalization, converting the data into a format suitable for analysis. Then, artificial intelligence technology is used to analyze abnormal events that deviate from normal work patterns. Specifically, machine learning algorithms are used to detect abnormally long working hours, repeated tardiness, and other such issues. The AI ​​model has learned from past data and possesses pattern recognition capabilities to accurately identify anomalies.

[0075] If an anomaly is detected, the server will immediately notify the administrator and the affected workers. The notification will be sent via email or messaging systems using electronic communication technology. Reminders will also be sent to relevant parties using messaging technology.

[0076] Regarding health management and work-life balance suggestions, the server automatically generates personalized improvement plans for each employee based on an analysis of past attendance data and work history. These suggestions are generated weekly or monthly and shared with relevant parties, playing a role in supporting the creation of a sustainable work environment.

[0077] As a concrete example, the system might detect a situation where "Employee A has worked a total of 40 hours in the past three days," identify this pattern as abnormal, and send an email to the manager stating "Employee A may be working excessive hours." Such functionality enables rapid and automatic detection of anomalies, thereby improving worker health and productivity.

[0078] As an example of a prompt, it is assumed that the following sentence would be input to the generating AI model: "Please tell me how to build a system that detects and notifies of abnormal work patterns from employee attendance data and computer usage records."

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server accesses the employee attendance database to obtain real-time information on employees' working hours, clock-in and clock-out times, and leave status. It receives attendance information from the database as input, organizes and stores the data within the server, and provides a formatted set of attendance information as output. Specifically, the server issues database queries, extracts the necessary data for each employee, and formats it.

[0082] Step 2:

[0083] The terminal locally retrieves the usage history of the computer used by the worker for work and sends that data to the server. As input, it retrieves usage history information from the terminal's local file system and log system. As output, the collected usage history is sent to the server and stored. Specifically, the terminal checks the usage history at regular intervals and uploads the latest log information to the server.

[0084] Step 3:

[0085] The server integrates and preprocesses the acquired attendance information and computer usage history. It receives the data obtained in steps 1 and 2 as input. As output, it generates an integrated and preprocessed dataset within the server. Specifically, it removes redundant data, converts data formats, and corrects outliers to create a consistent dataset.

[0086] Step 4:

[0087] The server uses artificial intelligence technology to analyze integrated data and detect anomalous events. It utilizes a pre-processed dataset as input and generates anomalous event detection results as output. Specifically, the server inputs data into an AI model, which then uses its learning to determine abnormal work patterns. Based on these results, it identifies which workers are exhibiting abnormal behavior.

[0088] Step 5:

[0089] The server immediately notifies the manager and the relevant worker if an anomaly is detected. The anomaly detection result from step 4 is used as input. A warning message is generated as output and sent to the relevant parties. Specifically, the server uses an email API or messaging service to construct and send a message for notification.

[0090] Step 6:

[0091] The server generates health management and work-life balance suggestions based on an analysis of past attendance data and usage history. Past attendance data and work patterns are used as input. The output is personalized improvement suggestions optimized for each employee. Specifically, the server utilizes a generation AI model to automatically generate advice and suggestions based on past trend analysis and provides them to relevant parties.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] In today's work environment, health deterioration and decreased work efficiency due to overwork are serious concerns. In particular, there is a need to accurately identify abnormalities in the work and activity patterns of employees and provide feedback to help them work efficiently while maintaining their health. However, conventional systems lacked real-time anomaly detection, health monitoring, and effective rest promotion. Therefore, preventing a decline in work performance due to overwork and poor health, and maintaining a sustainable balance in work life, is a key challenge.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for acquiring worker activity data in real time, means for analyzing the activity data to detect abnormalities, and means for providing health-promoting feedback to the worker through a visual display. This makes it possible to continuously monitor the health status of workers and provide appropriate alerts and rest instructions in real time when abnormalities are detected, thereby creating an efficient and healthy work environment.

[0097] "Worker activity data" refers to information generated by workers during their work, such as working hours, break times, and work content.

[0098] "Real-time" refers to processing and information provision occurring immediately, meaning that data collection and analysis are carried out without delay.

[0099] "Detecting anomalies" means identifying behaviors or malfunctions that deviate from normal activity patterns and recognizing them as problems.

[0100] "Immediate notification to administrators and relevant participants" means that information about the discovered problem is communicated to the relevant parties without delay.

[0101] "Machine usage records" refer to the operation history of devices and tools used by workers during their work.

[0102] "Health management" refers to the act of collecting and analyzing information and proposing improvements with the aim of maintaining and improving the health of workers.

[0103] "Harmony between work and life" means that workers achieve a healthy and sustainable lifestyle by appropriately balancing their work time and rest time.

[0104] A "visual display" refers to visual devices or functions that display information in a way that can be seen by the human eye.

[0105] "Monitoring physical condition using sensors" means using technical equipment to measure physiological indicators and observe the health status of workers.

[0106] A description of embodiments for carrying out the present invention will be provided.

[0107] The server utilizes software to collect and retrieve worker activity data in real time. This system aggregates information about workers' working hours, break times, and work content into a database. The data is organized using the Pandas library, and AI technologies such as TENSORFLOW® are used to perform analysis and detect anomaly patterns.

[0108] The device monitors collected activity data along with physical condition via sensors and uses a visual display function to provide feedback to the user. This feedback immediately notifies supervisors and workers when an anomaly is detected and visually communicates suggestions for balancing efficient work and rest.

[0109] The system supports users in maintaining a healthy and efficient work environment by providing real-time alerts and feedback. For example, if a new employee is working long hours, the system analyzes their activity data and detects unusual signs of overwork. It then informs the employee of their current situation via a visual display and suggests taking a break, thereby preventing overwork.

[0110] Using a generative AI model, we can present example prompts such as: "Please suggest the optimal allocation of working hours to allow employees to work efficiently while maintaining their health. Please propose approaches to mitigate the risks associated with working more than 50 hours per week."

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server acquires worker activity data in real time from sensors and other input devices. This data includes work time, break times, and equipment usage history. The acquired data is organized into a dataframe format using Pandas.

[0114] Step 2:

[0115] The server uses the acquired activity data to perform analysis for anomaly detection. Using AI models such as TensorFlow, it analyzes signs of deviations from normal work patterns and detects anomalies. This analysis utilizes machine learning models based on historical data.

[0116] Step 3:

[0117] If an anomaly is detected, the server immediately sends a notification to the administrator and the relevant worker's terminal. The notification includes the worker's current status and recommended next actions. The data is transmitted via electronic communication.

[0118] Step 4:

[0119] The device displays received notifications on its visual display. This display includes suggestions for healthy work practices for workers, specifically messages encouraging them to take breaks.

[0120] Step 5:

[0121] Users can receive the feedback provided and adjust their work patterns accordingly. If additional support is needed, users can provide feedback to the system to receive further solutions and advice.

[0122] Step 6:

[0123] Using a generative AI model, prompts are generated to provide users with further suggestions for improvement and advice. The AI ​​analyzes workers' past data and provides insights based on prompts such as, "Show us the optimal way to allocate working hours so that employees can work efficiently while maintaining their health."

[0124] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0125] This invention provides a system that collects and analyzes employee attendance data and computer usage records in real time, notifies administrators and employees when anomalies are detected, and offers suggestions to improve health management and work-life balance. Furthermore, by incorporating an emotion engine that detects user emotions, it is possible to combine work data and emotion data to provide more precise suggestions for improving work styles.

[0126] This system operates primarily via a server. The server retrieves data from employee attendance databases and computer usage records. In addition, the server collects emotional data from various employee sensors and input devices. This emotional data includes facial recognition, voice analysis, and stress level measurements using biosensors.

[0127] The server first processes the data entry, then integrates attendance data, computer usage records, and emotional data, formatting them into an analyzable form. Next, it uses analytical tools to detect deviations or abnormalities from normal work patterns. During this process, emotional data is also included in the analysis to assess whether stress levels are high.

[0128] When an anomaly is detected, notifications are sent to specific administrators and the relevant employees. The server sends these notifications via email or messaging systems. The notifications may also include information about any psychological issues the worker may be experiencing.

[0129] Furthermore, the server generates health management advice and work-life balance improvement suggestions for employees suspected of working long hours or experiencing high stress levels, combining past work and emotional data. These suggestions are personalized to each employee's situation, and specifically provide concrete actions to adjust their workload, particularly for employees experiencing high stress levels.

[0130] For example, if a user's weekly working hours exceed 50 hours and their daily emotional data indicates a high stress level, the server will send a notification to the administrator stating, "This user shows signs of potential fatigue; it is recommended that they reduce their workload." At the same time, the user will receive a suggestion to "take regular breaks and consider stress reduction measures."

[0131] Thus, the present invention enables real-time attendance and health management by utilizing multifaceted employee data, and supports the creation of an appropriate work environment tailored to the employee's health and psychological state. Meanwhile, the terminal receives notifications from the server and provides an interface for the user to take action.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server periodically retrieves data from employee attendance databases and computer usage log databases. This includes employee start and end times, application logs used, and other relevant information.

[0135] Step 2:

[0136] The server collects emotional data from sensors associated with each employee. This emotional data is collected through facial recognition cameras, voice analysis devices, and biosensors (such as heart rate and skin temperature sensors).

[0137] Step 3:

[0138] The server integrates and preprocesses the collected attendance data, computer usage records, and sentiment data, and performs data cleansing. This includes processes such as deduplication, formatting standardization, and imputation of missing values.

[0139] Step 4:

[0140] The server uses a data analysis engine to detect anomalies that deviate from normal work patterns. At the same time, it analyzes emotional data to determine if stress levels are high and if attention is needed.

[0141] Step 5:

[0142] Based on the analysis results, the server will send an email or messaging notification to the relevant administrator if it detects an anomaly or high-stress condition. The notification will include a detailed explanation of the anomaly and possible countermeasures.

[0143] Step 6:

[0144] Based on the results of an analysis using emotional data, the server sends notifications to the relevant employees. These notifications may include suggestions for stress reduction or recommendations for taking breaks.

[0145] Step 7:

[0146] The server generates and provides personalized health management advice to individual employees based on accumulated historical work and emotional data. This advice is personalized and includes specific action plans.

[0147] Step 8:

[0148] The terminal displays various notifications and suggestions from the server to the user and provides an interface for the user to manage their work patterns and health status based on that information.

[0149] (Example 2)

[0150] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0151] Maintaining employee health and work-life balance is a critical challenge in many workplaces. However, traditional systems often lack sufficient time management and emotional data, making it difficult to timely detect signs of employee stress and fatigue and take appropriate measures. Furthermore, even when abnormalities are detected, notifications and specific improvement suggestions tend to be delayed, resulting in a lack of real-time capabilities in employee health management.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for acquiring employee time management information in real time, means for integrating and analyzing the time management information to detect anomalies, and means for acquiring emotional information using facial recognition, voice analysis, and biosensors. This makes it possible to grasp information on employee stress and work balance in real time and to quickly provide appropriate health management and work improvement suggestions.

[0154] "Time management information" refers to data related to working hours, such as employee work hours, break times, and attendance records.

[0155] "Abnormal" refers to a state that deviates from normal work patterns or emotional states, and particularly includes situations where high stress or long working hours are suspected.

[0156] A "manager" refers to a person responsible for supervising employees' work conditions and making improvement suggestions as needed.

[0157] "Emotional information" refers to data that represents the psychological state of employees, and is acquired through methods such as facial recognition, voice analysis, and biosensors.

[0158] "Suggestions" refer to specific action plans and advice generated by the server with the aim of improving workers' health and work-life balance.

[0159] "Notification" refers to the act of a server using electronic communication means to inform an administrator or employee when an anomaly is detected or a suggestion is generated.

[0160] "Analysis means" refers to methods or techniques for processing acquired data and performing comparisons with normal patterns or detecting anomalies.

[0161] This invention relates to a system that acquires employee time management information and emotional state in real time, analyzes them, and detects work abnormalities. The main components of the system include a server that collects and processes data, and a terminal that displays the results. Specifically, the server is integrated with the attendance system to acquire time management information. It also acquires emotional information through a facial recognition camera, a voice analysis system, and biosensors, and evaluates stress levels.

[0162] The server integrates this data and uses analytical algorithms to perform calculations to detect deviations from normal work patterns. The integrated data helps in the early detection of anomalies, enabling highly accurate analysis. Emotional information is also treated as quantified data and analyzed along with time management information.

[0163] When an anomaly is detected, the server uses email and messaging functions to send notifications to administrators and the relevant employees. These notifications include detailed analysis results based on the type of anomaly and emotional information. Furthermore, the server generates personalized health management suggestions based on historical data. These suggestions form concrete action plans for stress reduction.

[0164] The terminal displays notifications and suggestions from the server to employees and provides an interface for users to improve their work environment based on this information. Users are encouraged to review the advice through the terminal and act according to the instructions.

[0165] For example, if the server analyzes an employee's weekly working hours to determine that their stress level is high based on emotional data, a notification will be sent to the administrator stating, "User A's stress level is higher than normal; it is recommended to reduce their workload." Simultaneously, the user will receive a specific suggestion, such as, "It is recommended that you take a break of 30 minutes or more each day to reduce stress."

[0166] An example of a prompt would be, "Explain how to use employee time management and emotional data to detect anomalies in work patterns and generate health management suggestions." This prompt supports the generation of appropriate suggestions by the generative AI model.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server acquires employee time management information in real time. This input information includes clock-in and clock-out times, break times, and working hours. The server collects this data and stores it in a database. This storage process forms the basis for subsequent data analysis.

[0170] Step 2:

[0171] The server acquires data in real time from facial recognition cameras, voice analysis systems, and biosensors to collect emotional information. This emotional information includes facial expressions, voice tone, and heart rate. The server converts this data into an analyzable format and stores it in a database. This conversion process yields quantified emotional information.

[0172] Step 3:

[0173] The server integrates collected time management and emotional data and prepares a dataset for comparison with normal work patterns. This integration process creates a synthetic dataset for each employee, laying the foundation for detecting anomalies.

[0174] Step 4:

[0175] The server uses an analysis algorithm to detect anomalies in the integrated data. The input is the integrated dataset. The server compares this data with historical data to assess whether working hours are excessively long or whether stress levels are elevated. This analysis extracts cases suspected of high stress or excessive working hours.

[0176] Step 5:

[0177] If an anomaly is detected, the server will send a notification to the administrator and the relevant employee. This notification will be sent via email or messaging. The input information will include the analysis results indicating the anomaly and information about the employee. The notification will include specific issues and suggested countermeasures.

[0178] Step 6:

[0179] The server generates suggestions for improving health management and work-life balance based on past time management and emotional data. This suggestion generation uses the individual's historical data and analysis results as input. The server creates specific action plans and notifies employees and managers. This output constitutes the improvement measures provided.

[0180] Step 7:

[0181] The terminal displays notifications and suggestions received from the server to the user. During this display process, the user can adjust their actions based on the presented information. Specifically, the user uses the terminal to follow the suggestions and take concrete actions such as adjusting working hours or ensuring sufficient break time.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In today's work environment, it is essential to appropriately monitor employees' work conditions and emotional states and provide timely interventions and corrective measures. However, many existing systems make decisions based solely on work data and do not adequately consider human factors such as emotional states. As a result, there is a challenge in detecting abnormalities in employees' health and stress levels early and taking prompt action.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for acquiring employee work information in real time, means for analyzing the work information to detect anomalies, means for immediately notifying the manager and the relevant employee when an anomaly is detected, and means for analyzing emotional states and providing stress reduction measures when an anomaly is detected. This enables comprehensive monitoring and the provision of improvement measures that take into account the emotional states of employees.

[0187] An "employee" is an individual who is employed by a company or organization and provides labor.

[0188] "Labor information" refers to data concerning an employee's working hours and work content, including start and end times of work and job duties.

[0189] "Computer usage history" refers to information that shows the operation records and application usage status of computers used by employees for their work.

[0190] "Emotional state" refers to data indicating the psychological and emotional health of employees, including information obtained through facial recognition and voice analysis.

[0191] "Stress reduction measures" refer to specific suggestions and methods provided to reduce employee stress and maintain a healthy work environment.

[0192] A "server" is a computer system that aggregates and analyzes data and generates notifications and suggestions.

[0193] A "manager" is an individual or position within a company or organization that is responsible for supervising the working conditions of employees and managing all aspects of operations.

[0194] The server, connected to the company's internal systems, collects employee work information and computer usage history in real time and stores it in a database. Based on this information, the server detects deviations from normal work patterns and analyzes anomalies using specific algorithms. Furthermore, it incorporates emotion detection technologies such as facial recognition, voice analysis, and biosensors to analyze emotional states and evaluate workers' stress levels.

[0195] If an anomaly is detected, the server will immediately notify administrators and the affected employees. This notification will use digital messaging or a communication function to immediately provide stakeholders with improvement suggestions, including stress reduction measures. For example, if the server detects data indicating high stress, administrators will receive a notification stating that "a reassessment of the workload for the affected employee is necessary," and employees will be provided with specific advice such as "we recommend taking deep breaths or short breaks."

[0196] This system facilitates comprehensive monitoring and the suggestion of improvement measures that take emotional states into account, contributing to employee health maintenance and productivity improvement. Data obtained through emotion detection is used to generate more precise suggestions for improving work-life balance. Furthermore, a generative AI model can be used to automatically generate appropriate suggestions based on the situation.

[0197] As a concrete example, here is an example of a prompt message to be input to a generating AI model: "Create suggestions to reduce security risks based on employee emotional data and attendance data." Based on this prompt, the AI ​​analyzes the workers' health status and emotional data and presents appropriate improvement measures based on the results.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The server retrieves work information and computer usage history from employees in real time. This input data includes employee start and end times, and logs of applications used. The server stores this data in a database and prepares it for subsequent analysis steps.

[0201] Step 2:

[0202] The server analyzes the acquired work information and computer usage history to detect deviations from normal work patterns. At this stage, specific algorithms are used to process the data and identify anomalies. The output is a list of detected anomalies, indicating which data is abnormal.

[0203] Step 3:

[0204] The server analyzes the emotional state of employees using emotion detection technology. Input data includes stress levels from biosensors, facial recognition, and voice analysis data. The server integrates this data to evaluate the employee's stress level. The output is an emotional state report.

[0205] Step 4:

[0206] The server sends notifications to administrators and relevant employees when it detects an anomaly. Inputs include a list of anomalies and a mood status report. Based on this information, the server sends necessary notifications using digital messaging or a contact function. Outputs are notification messages to administrators and employees.

[0207] Step 5:

[0208] The server uses a generative AI model to automatically generate improvement suggestions that take into account work information and emotional states. The input consists of historical work data and emotional data. The server inputs prompts into the generative AI model, which then generates appropriate suggestions. This output is the improvement suggestion provided to the employee.

[0209] Step 6:

[0210] The terminal displays notifications and improvement suggestions received from the server to employees, prompting them to take action. Input consists of notification messages and improvement suggestions from the server. The terminal presents information in a user-friendly interface, making it easy for employees to understand and act upon. Output consists of specific action suggestions for employees.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0227] This invention provides a labor management system that collects employee attendance data and computer usage records in real time and immediately notifies relevant managers and employees when abnormal work patterns are detected. This system primarily operates via a server.

[0228] The server first automatically retrieves information such as working hours and leave status from the employee attendance database, and simultaneously collects computer usage records from the terminals used by employees for work. All data is integrated within the server and organized in a format that allows for analysis.

[0229] The server uses AI to analyze the acquired data. Specifically, it detects abnormal events that deviate from normal work patterns (for example, long working hours or repeated tardiness), and also analyzes PC usage logs to check for errors such as missing entries.

[0230] If an anomaly is detected, the server immediately notifies the relevant administrator. The notification is sent via email or internal messaging tools, allowing for swift action. Additionally, the affected employee receives a reminder or notification tailored to the nature of the anomaly, encouraging proactive response.

[0231] For example, if an employee works more than 50 hours continuously in a week, the server will detect this as an anomaly and send an alert to the administrator stating "Possible employee overwork." The employee will also receive a notification recommending that they take appropriate breaks.

[0232] Furthermore, the server is equipped with a function that provides suggestions for improving health management and work-life balance. Based on analysis of past attendance data and thought patterns, it provides improvement suggestions tailored to each employee's situation, supporting the maintenance of a sustainable work-life balance.

[0233] Thus, this invention enables real-time attendance management, allows for a rapid response in the event of an anomaly, and aims to improve employee health and motivation.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The server automatically retrieves the latest data from employee attendance databases and computer usage databases periodically (for example, every 5 minutes). This enables real-time data collection, ensuring that the most up-to-date information is always available.

[0237] Step 2:

[0238] The server performs data preprocessing on the acquired data as input. This includes formatting the data, imputing missing values, and filtering outliers. If necessary, it standardizes the data format and prepares it for analysis.

[0239] Step 3:

[0240] The server uses an AI analysis module to analyze the formatted data. Here, it checks whether there are deviations from normal attendance patterns and whether working hours exceed the regulations. It also checks for inconsistencies between computer usage records and attendance data.

[0241] Step 4:

[0242] The server identifies anomalies based on the analysis results. Anomalies include, for example, consecutive long working hours, failure to enter attendance records, and consecutive lateness. In this case, the server determines the next course of action based on the severity of the anomaly.

[0243] Step 5:

[0244] If an anomaly is detected, the server will notify the administrator based on the determined action. Notifications will be sent via email or the company's internal messaging system to ensure timely information dissemination.

[0245] Step 6:

[0246] The server also notifies the employee in question of the anomaly detection result. This could include a health management message, such as "Please consider taking appropriate leave."

[0247] Step 7:

[0248] The server generates and notifies employees suspected of working long hours or excessive workloads, offering suggestions for health management and work-life balance improvement. These suggestions are personalized based on past data and individual work situations.

[0249] Step 8:

[0250] The terminal displays notifications and alerts sent from the server and provides an interface for users to take necessary actions. Users can modify attendance data, submit leave requests, and perform other actions depending on the content of the notifications.

[0251] (Example 1)

[0252] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0253] As workers' working hours and environments become more diverse, it is necessary to prevent adverse health effects caused by overwork and inappropriate work patterns. However, conventional attendance management systems have difficulty grasping work conditions in real time and immediately detecting and notifying abnormalities, which can lead to decreased labor productivity and employee health problems. To solve this problem, a system is needed that integrates and analyzes workers' attendance information and computer usage history to quickly detect and respond to abnormal events.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for acquiring employee attendance information in real time, means for integrating and pre-processing the acquired attendance information and computer usage history, and means for analyzing abnormal events that deviate from normal work patterns using artificial intelligence technology. This makes it possible to quickly and automatically detect abnormal work patterns of employees and immediately notify relevant managers and employees.

[0256] "Worker attendance information" refers to records of work-related information such as working hours, arrival and departure times, and leave status.

[0257] "Computer usage history" refers to records of operations performed on computers used by employees for work, login times, application usage times, and other similar information.

[0258] "Artificial intelligence technology" refers to techniques that use machine learning and statistical analysis to learn and analyze patterns from data.

[0259] An "abnormal event" is data or an incident that indicates a deviation from the normal work pattern, such as working long hours or repeated tardiness.

[0260] A "management supervisor" is a person in charge of supervising the working environment and work conditions of employees and taking appropriate action.

[0261] "Message communication technology" refers to the technology used to send and receive information using email and messaging services.

[0262] "Health management" refers to measures and guidance aimed at maintaining and improving the physical and mental health of workers.

[0263] "Work-life balance" refers to a balance in life where a worker's working hours and personal life time are in harmony, and both are considered important.

[0264] This invention relates to a system that collects and analyzes workers' attendance information and computer usage history, and detects and notifies them of abnormal work patterns. This system primarily operates through a server.

[0265] The server accesses the employee attendance database via the network and retrieves attendance information such as working hours, clock-in and clock-out times, and leave status in real time. Database management software is used to efficiently retrieve and store the data on the server. Additionally, computer usage history for work-related activities is locally retrieved from terminals and sent to the server. This allows for the integration of data on the server, enabling consistent information management.

[0266] On the server, collected attendance information and computer usage history are integrated and preprocessed. This involves data cleaning and normalization, converting the data into a format suitable for analysis. Then, artificial intelligence technology is used to analyze abnormal events that deviate from normal work patterns. Specifically, machine learning algorithms are used to detect abnormally long working hours, repeated tardiness, and other such issues. The AI ​​model has learned from past data and possesses pattern recognition capabilities to accurately identify anomalies.

[0267] If an anomaly is detected, the server will immediately notify the administrator and the affected workers. The notification will be sent via email or messaging systems using electronic communication technology. Reminders will also be sent to relevant parties using messaging technology.

[0268] Regarding health management and work-life balance suggestions, the server automatically generates personalized improvement plans for each employee based on an analysis of past attendance data and work history. These suggestions are generated weekly or monthly and shared with relevant parties, playing a role in supporting the creation of a sustainable work environment.

[0269] As a concrete example, the system might detect a situation where "Employee A has worked a total of 40 hours in the past three days," identify this pattern as abnormal, and send an email to the manager stating "Employee A may be working excessive hours." Such functionality enables rapid and automatic detection of anomalies, thereby improving worker health and productivity.

[0270] As an example of a prompt, it is assumed that the following sentence would be input to the generating AI model: "Please tell me how to build a system that detects and notifies of abnormal work patterns from employee attendance data and computer usage records."

[0271] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0272] Step 1:

[0273] The server accesses the employee attendance database to obtain real-time information on employees' working hours, clock-in and clock-out times, and leave status. It receives attendance information from the database as input, organizes and stores the data within the server, and provides a formatted set of attendance information as output. Specifically, the server issues database queries, extracts the necessary data for each employee, and formats it.

[0274] Step 2:

[0275] The terminal locally retrieves the usage history of the computer used by the worker for work and sends that data to the server. As input, it retrieves usage history information from the terminal's local file system and log system. As output, the collected usage history is sent to the server and stored. Specifically, the terminal checks the usage history at regular intervals and uploads the latest log information to the server.

[0276] Step 3:

[0277] The server integrates and preprocesses the acquired attendance information and computer usage history. It receives the data obtained in steps 1 and 2 as input. As output, it generates an integrated and preprocessed dataset within the server. Specifically, it removes redundant data, converts data formats, and corrects outliers to create a consistent dataset.

[0278] Step 4:

[0279] The server analyzes the integrated data using artificial intelligence technology to detect abnormal events. As input, it utilizes the preprocessed dataset. As output, it generates the detection results of abnormal events. Specifically, the server inputs the data into the AI model, and the model determines based on learning abnormal labor patterns. Based on this result, it identifies which workers have abnormalities.

[0280] Step 5:

[0281] When an abnormality is detected, the server immediately notifies the management responsible person and the corresponding worker. As input, the abnormal event detection result of Step 4 is used. As output, a warning message is generated and sent to the relevant persons. As a specific operation, the server uses the mail API or messaging service to construct and send a message for notification.

[0282] Step 6:

[0283] The server generates proposals for health management and work-life balance based on the analysis of past attendance information and usage history. As input, past attendance information and labor patterns are used. As output, improvement proposals optimized for each worker are created. As a specific operation, the server utilizes the generation AI model to automatically generate advice and proposals based on past trend analysis and provide them to the relevant persons.

[0284] (Application Example 1)

[0285] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0286] In modern working environments, the deterioration of health due to overwork and the decline in work efficiency are regarded as problems. In particular, it is required to accurately grasp the abnormal labor and activity patterns of employees and activists, and provide feedback to work efficiently while maintaining health. However, conventional systems have lacked real-time anomaly detection, health status monitoring, and effective rest promotion. Therefore, it is an issue to prevent the decline in work performance due to overwork and illness, and to maintain the harmony of a sustainable working life.

[0287] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0288] In this invention, the server includes means for acquiring the activity data of workers in real time, means for analyzing the activity data to detect anomalies, and means for providing health promotion feedback to the activists through a visual display. As a result, while continuously monitoring the health status of workers, when an anomaly is detected, appropriate alerts and rest instructions can be provided in real time, making it possible to construct an efficient and healthy working environment.

[0289] "The activity data of workers" refers to information such as working hours, rest hours, and work content generated by workers during work.

[0290] "Real time" means that processing and information provision are carried out immediately, and data collection and analysis are implemented without delay.

[0291] "Detecting an anomaly" means identifying actions and malfunctions that deviate from the normal activity pattern and recognizing them as problems.

[0292] "Immediately notifying the administrator and the corresponding activists" means transmitting information about the discovered problem to the relevant parties without delay.

[0293] "Machine usage record" refers to the operation history of devices and tools used by workers during work.

[0294] "Health management" refers to the act of collecting and analyzing information and proposing improvements with the aim of maintaining and improving the health of workers.

[0295] "Harmony between work and life" means that workers achieve a healthy and sustainable lifestyle by appropriately balancing their work time and rest time.

[0296] A "visual display" refers to visual devices or functions that display information in a way that can be seen by the human eye.

[0297] "Monitoring physical condition using sensors" means using technical equipment to measure physiological indicators and observe the health status of workers.

[0298] A description of embodiments for carrying out the present invention will be provided.

[0299] The server utilizes software to collect and retrieve worker activity data in real time. This system aggregates information about workers' working hours, break times, and work content into a database. The data is organized using the Pandas library, and analysis is performed using AI technologies such as TensorFlow to detect anomaly patterns.

[0300] The device monitors collected activity data along with physical condition via sensors and uses a visual display function to provide feedback to the user. This feedback immediately notifies supervisors and workers when an anomaly is detected and visually communicates suggestions for balancing efficient work and rest.

[0301] The system supports maintaining a healthy and efficient working environment by providing real-time alerts and feedback to users. As a specific example, when a new employee is working for a long time, the system analyzes the activity data, detects signs of overwork different from normal, and then notifies the current situation through a visual display and proposes taking a break to prevent the worker from overworking.

[0302] Using a generative AI model, examples of the following prompt sentences can be presented. "Please show the optimal allocation method of working hours for employees to work efficiently while maintaining their health. Please propose an approach to reduce the risks when working more than 50 hours a week."

[0303] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0304] Step 1:

[0305] The server acquires the activity data of workers in real time from sensors and other input devices. This data includes working hours, break times, and the operation history of the equipment used. The acquired data is organized in the form of a data frame using Pandas.

[0306] Step 2:

[0307] The server performs an analysis to detect anomalies using the acquired activity data. An AI model such as TensorFlow is used to analyze signs deviating from the normal labor pattern and detect anomalies. A machine learning model based on past data is used for this analysis.

[0308] Step 3:

[0309] If an anomaly is detected, the server immediately sends notifications to the administrator and the terminal of the corresponding worker. The notification includes the current status of the worker and the recommended next action. The data is sent through the electronic communication function.

[0310] Step 4:

[0311] The device displays received notifications on its visual display. This display includes suggestions for healthy work practices for workers, specifically messages encouraging them to take breaks.

[0312] Step 5:

[0313] Users can receive the feedback provided and adjust their work patterns accordingly. If additional support is needed, users can provide feedback to the system to receive further solutions and advice.

[0314] Step 6:

[0315] Using a generative AI model, prompts are generated to provide users with further suggestions for improvement and advice. The AI ​​analyzes workers' past data and provides insights based on prompts such as, "Show us the optimal way to allocate working hours so that employees can work efficiently while maintaining their health."

[0316] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0317] This invention provides a system that collects and analyzes employee attendance data and computer usage records in real time, notifies administrators and employees when anomalies are detected, and offers suggestions to improve health management and work-life balance. Furthermore, by incorporating an emotion engine that detects user emotions, it is possible to combine work data and emotion data to provide more precise suggestions for improving work styles.

[0318] This system operates primarily via a server. The server retrieves data from employee attendance databases and computer usage records. In addition, the server collects emotional data from various employee sensors and input devices. This emotional data includes facial recognition, voice analysis, and stress level measurements using biosensors.

[0319] The server first processes the data entry, then integrates attendance data, computer usage records, and emotional data, formatting them into an analyzable form. Next, it uses analytical tools to detect deviations or abnormalities from normal work patterns. During this process, emotional data is also included in the analysis to assess whether stress levels are high.

[0320] When an anomaly is detected, notifications are sent to specific administrators and the relevant employees. The server sends these notifications via email or messaging systems. The notifications may also include information about any psychological issues the worker may be experiencing.

[0321] Furthermore, the server generates health management advice and work-life balance improvement suggestions for employees suspected of working long hours or experiencing high stress levels, combining past work and emotional data. These suggestions are personalized to each employee's situation, and specifically provide concrete actions to adjust their workload, particularly for employees experiencing high stress levels.

[0322] For example, if a user's weekly working hours exceed 50 hours and their daily emotional data indicates a high stress level, the server will send a notification to the administrator stating, "This user shows signs of potential fatigue; it is recommended that they reduce their workload." At the same time, the user will receive a suggestion to "take regular breaks and consider stress reduction measures."

[0323] Thus, the present invention enables real-time attendance and health management by utilizing multifaceted employee data, and supports the creation of an appropriate work environment tailored to the employee's health and psychological state. Meanwhile, the terminal receives notifications from the server and provides an interface for the user to take action.

[0324] The following describes the processing flow.

[0325] Step 1:

[0326] The server periodically retrieves data from employee attendance databases and computer usage log databases. This includes employee start and end times, application logs used, and other relevant information.

[0327] Step 2:

[0328] The server collects emotional data from sensors associated with each employee. This emotional data is collected through facial recognition cameras, voice analysis devices, and biosensors (such as heart rate and skin temperature sensors).

[0329] Step 3:

[0330] The server integrates and preprocesses the collected attendance data, computer usage records, and sentiment data, and performs data cleansing. This includes processes such as deduplication, formatting standardization, and imputation of missing values.

[0331] Step 4:

[0332] The server uses a data analysis engine to detect anomalies that deviate from normal work patterns. At the same time, it analyzes emotional data to determine if stress levels are high and if attention is needed.

[0333] Step 5:

[0334] Based on the analysis results, the server will send an email or messaging notification to the relevant administrator if it detects an anomaly or high-stress condition. The notification will include a detailed explanation of the anomaly and possible countermeasures.

[0335] Step 6:

[0336] Based on the results of an analysis using emotional data, the server sends notifications to the relevant employees. These notifications may include suggestions for stress reduction or recommendations for taking breaks.

[0337] Step 7:

[0338] The server generates and provides personalized health management advice to individual employees based on accumulated historical work and emotional data. This advice is personalized and includes specific action plans.

[0339] Step 8:

[0340] The terminal displays various notifications and suggestions from the server to the user and provides an interface for the user to manage their work patterns and health status based on that information.

[0341] (Example 2)

[0342] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] Maintaining employee health and work-life balance is a critical challenge in many workplaces. However, traditional systems often lack sufficient time management and emotional data, making it difficult to timely detect signs of employee stress and fatigue and take appropriate measures. Furthermore, even when abnormalities are detected, notifications and specific improvement suggestions tend to be delayed, resulting in a lack of real-time capabilities in employee health management.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for acquiring employee time management information in real time, means for integrating and analyzing the time management information to detect anomalies, and means for acquiring emotional information using facial recognition, voice analysis, and biosensors. This makes it possible to grasp information on employee stress and work balance in real time and to quickly provide appropriate health management and work improvement suggestions.

[0346] "Time management information" refers to data related to working hours, such as employee work hours, break times, and attendance records.

[0347] "Abnormal" refers to a state that deviates from normal work patterns or emotional states, and particularly includes situations where high stress or long working hours are suspected.

[0348] A "manager" refers to a person responsible for supervising employees' work conditions and making improvement suggestions as needed.

[0349] "Emotional information" refers to data that represents the psychological state of employees, and is acquired through methods such as facial recognition, voice analysis, and biosensors.

[0350] "Suggestions" refer to specific action plans and advice generated by the server with the aim of improving workers' health and work-life balance.

[0351] "Notification" refers to the act of a server using electronic communication means to inform an administrator or employee when an anomaly is detected or a suggestion is generated.

[0352] "Analysis means" refers to methods or techniques for processing acquired data and performing comparisons with normal patterns or detecting anomalies.

[0353] This invention relates to a system that acquires employee time management information and emotional state in real time, analyzes them, and detects work abnormalities. The main components of the system include a server that collects and processes data, and a terminal that displays the results. Specifically, the server is integrated with the attendance system to acquire time management information. It also acquires emotional information through a facial recognition camera, a voice analysis system, and biosensors, and evaluates stress levels.

[0354] The server integrates this data and uses analytical algorithms to perform calculations to detect deviations from normal work patterns. The integrated data helps in the early detection of anomalies, enabling highly accurate analysis. Emotional information is also treated as quantified data and analyzed along with time management information.

[0355] When an anomaly is detected, the server uses email and messaging functions to send notifications to administrators and the relevant employees. These notifications include detailed analysis results based on the type of anomaly and emotional information. Furthermore, the server generates personalized health management suggestions based on historical data. These suggestions form concrete action plans for stress reduction.

[0356] The terminal displays notifications and suggestions from the server to employees and provides an interface for users to improve their work environment based on this information. Users are encouraged to review the advice through the terminal and act according to the instructions.

[0357] For example, if the server analyzes an employee's weekly working hours to determine that their stress level is high based on emotional data, a notification will be sent to the administrator stating, "User A's stress level is higher than normal; it is recommended to reduce their workload." Simultaneously, the user will receive a specific suggestion, such as, "It is recommended that you take a break of 30 minutes or more each day to reduce stress."

[0358] An example of a prompt would be, "Explain how to use employee time management and emotional data to detect anomalies in work patterns and generate health management suggestions." This prompt supports the generation of appropriate suggestions by the generative AI model.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The server acquires employee time management information in real time. This input information includes clock-in and clock-out times, break times, and working hours. The server collects this data and stores it in a database. This storage process forms the basis for subsequent data analysis.

[0362] Step 2:

[0363] The server acquires data in real time from facial recognition cameras, voice analysis systems, and biosensors to collect emotional information. This emotional information includes facial expressions, voice tone, and heart rate. The server converts this data into an analyzable format and stores it in a database. This conversion process yields quantified emotional information.

[0364] Step 3:

[0365] The server integrates collected time management and emotional data and prepares a dataset for comparison with normal work patterns. This integration process creates a synthetic dataset for each employee, laying the foundation for detecting anomalies.

[0366] Step 4:

[0367] The server uses an analysis algorithm to detect anomalies in the integrated data. The input is the integrated dataset. The server compares this data with historical data to assess whether working hours are excessively long or whether stress levels are elevated. This analysis extracts cases suspected of high stress or excessive working hours.

[0368] Step 5:

[0369] If an anomaly is detected, the server will send a notification to the administrator and the relevant employee. This notification will be sent via email or messaging. The input information will include the analysis results indicating the anomaly and information about the employee. The notification will include specific issues and suggested countermeasures.

[0370] Step 6:

[0371] The server generates suggestions for improving health management and work-life balance based on past time management and emotional data. This suggestion generation uses the individual's historical data and analysis results as input. The server creates specific action plans and notifies employees and managers. This output constitutes the improvement measures provided.

[0372] Step 7:

[0373] The terminal displays notifications and suggestions received from the server to the user. During this display process, the user can adjust their actions based on the presented information. Specifically, the user uses the terminal to follow the suggestions and take concrete actions such as adjusting working hours or ensuring sufficient break time.

[0374] (Application Example 2)

[0375] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0376] In today's work environment, it is essential to appropriately monitor employees' work conditions and emotional states and provide timely interventions and corrective measures. However, many existing systems make decisions based solely on work data and do not adequately consider human factors such as emotional states. As a result, there is a challenge in detecting abnormalities in employees' health and stress levels early and taking prompt action.

[0377] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0378] In this invention, the server includes means for acquiring employee work information in real time, means for analyzing the work information to detect anomalies, means for immediately notifying the manager and the relevant employee when an anomaly is detected, and means for analyzing emotional states and providing stress reduction measures when an anomaly is detected. This enables comprehensive monitoring and the provision of improvement measures that take into account the emotional states of employees.

[0379] An "employee" is an individual who is employed by a company or organization and provides labor.

[0380] "Labor information" refers to data concerning an employee's working hours and work content, including start and end times of work and job duties.

[0381] "Computer usage history" refers to information that shows the operation records and application usage status of computers used by employees for their work.

[0382] "Emotional state" refers to data indicating the psychological and emotional health of employees, including information obtained through facial recognition and voice analysis.

[0383] "Stress reduction measures" refer to specific suggestions and methods provided to reduce employee stress and maintain a healthy work environment.

[0384] A "server" is a computer system that aggregates and analyzes data and generates notifications and suggestions.

[0385] A "manager" is an individual or position within a company or organization that is responsible for supervising the working conditions of employees and managing all aspects of operations.

[0386] The server, connected to the company's internal systems, collects employee work information and computer usage history in real time and stores it in a database. Based on this information, the server detects deviations from normal work patterns and analyzes anomalies using specific algorithms. Furthermore, it incorporates emotion detection technologies such as facial recognition, voice analysis, and biosensors to analyze emotional states and evaluate workers' stress levels.

[0387] If an anomaly is detected, the server will immediately notify administrators and the affected employees. This notification will use digital messaging or a communication function to immediately provide stakeholders with improvement suggestions, including stress reduction measures. For example, if the server detects data indicating high stress, administrators will receive a notification stating that "a reassessment of the workload for the affected employee is necessary," and employees will be provided with specific advice such as "we recommend taking deep breaths or short breaks."

[0388] This system facilitates comprehensive monitoring and the suggestion of improvement measures that take emotional states into account, contributing to employee health maintenance and productivity improvement. Data obtained through emotion detection is used to generate more precise suggestions for improving work-life balance. Furthermore, a generative AI model can be used to automatically generate appropriate suggestions based on the situation.

[0389] As a concrete example, here is an example of a prompt message to be input to a generating AI model: "Create suggestions to reduce security risks based on employee emotional data and attendance data." Based on this prompt, the AI ​​analyzes the workers' health status and emotional data and presents appropriate improvement measures based on the results.

[0390] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0391] Step 1:

[0392] The server retrieves work information and computer usage history from employees in real time. This input data includes employee start and end times, and logs of applications used. The server stores this data in a database and prepares it for subsequent analysis steps.

[0393] Step 2:

[0394] The server analyzes the acquired work information and computer usage history to detect deviations from normal work patterns. At this stage, specific algorithms are used to process the data and identify anomalies. The output is a list of detected anomalies, indicating which data is abnormal.

[0395] Step 3:

[0396] The server analyzes the emotional state of employees using emotion detection technology. Input data includes stress levels from biosensors, facial recognition, and voice analysis data. The server integrates this data to evaluate the employee's stress level. The output is an emotional state report.

[0397] Step 4:

[0398] The server sends notifications to administrators and relevant employees when it detects an anomaly. Inputs include a list of anomalies and a mood status report. Based on this information, the server sends necessary notifications using digital messaging or a contact function. Outputs are notification messages to administrators and employees.

[0399] Step 5:

[0400] The server uses a generative AI model to automatically generate improvement suggestions that take into account work information and emotional states. The input consists of historical work data and emotional data. The server inputs prompts into the generative AI model, which then generates appropriate suggestions. This output is the improvement suggestion provided to the employee.

[0401] Step 6:

[0402] The terminal displays notifications and improvement suggestions received from the server to employees, prompting them to take action. Input consists of notification messages and improvement suggestions from the server. The terminal presents information in a user-friendly interface, making it easy for employees to understand and act upon. Output consists of specific action suggestions for employees.

[0403] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0404] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0405] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0406] [Third Embodiment]

[0407] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0408] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0409] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0410] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0411] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0413] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0414] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0415] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0416] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0417] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0418] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0419] This invention provides a labor management system that collects employee attendance data and computer usage records in real time and immediately notifies relevant managers and employees when abnormal work patterns are detected. This system primarily operates via a server.

[0420] The server first automatically retrieves information such as working hours and leave status from the employee attendance database, and simultaneously collects computer usage records from the terminals used by employees for work. All data is integrated within the server and organized in a format that allows for analysis.

[0421] The server uses AI to analyze the acquired data. Specifically, it detects abnormal events that deviate from normal work patterns (for example, long working hours or repeated tardiness), and also analyzes PC usage logs to check for errors such as missing entries.

[0422] If an anomaly is detected, the server immediately notifies the relevant administrator. The notification is sent via email or internal messaging tools, allowing for swift action. Additionally, the affected employee receives a reminder or notification tailored to the nature of the anomaly, encouraging proactive response.

[0423] For example, if an employee works more than 50 hours continuously in a week, the server will detect this as an anomaly and send an alert to the administrator stating "Possible employee overwork." The employee will also receive a notification recommending that they take appropriate breaks.

[0424] Furthermore, the server is equipped with a function that provides suggestions for improving health management and work-life balance. Based on analysis of past attendance data and thought patterns, it provides improvement suggestions tailored to each employee's situation, supporting the maintenance of a sustainable work-life balance.

[0425] Thus, this invention enables real-time attendance management, allows for a rapid response in the event of an anomaly, and aims to improve employee health and motivation.

[0426] The following describes the processing flow.

[0427] Step 1:

[0428] The server automatically retrieves the latest data from employee attendance databases and computer usage databases periodically (for example, every 5 minutes). This enables real-time data collection, ensuring that the most up-to-date information is always available.

[0429] Step 2:

[0430] The server performs data preprocessing on the acquired data as input. This includes formatting the data, imputing missing values, and filtering outliers. If necessary, it standardizes the data format and prepares it for analysis.

[0431] Step 3:

[0432] The server uses an AI analysis module to analyze the formatted data. Here, it checks whether there are deviations from normal attendance patterns and whether working hours exceed the regulations. It also checks for inconsistencies between computer usage records and attendance data.

[0433] Step 4:

[0434] The server identifies anomalies based on the analysis results. Anomalies include, for example, consecutive long working hours, failure to enter attendance records, and consecutive lateness. In this case, the server determines the next course of action based on the severity of the anomaly.

[0435] Step 5:

[0436] If an anomaly is detected, the server will notify the administrator based on the determined action. Notifications will be sent via email or the company's internal messaging system to ensure timely information dissemination.

[0437] Step 6:

[0438] The server also notifies the employee in question of the anomaly detection result. This could include a health management message, such as "Please consider taking appropriate leave."

[0439] Step 7:

[0440] The server generates and notifies employees suspected of working long hours or excessive workloads, offering suggestions for health management and work-life balance improvement. These suggestions are personalized based on past data and individual work situations.

[0441] Step 8:

[0442] The terminal displays notifications and alerts sent from the server and provides an interface for users to take necessary actions. Users can modify attendance data, submit leave requests, and perform other actions depending on the content of the notifications.

[0443] (Example 1)

[0444] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0445] As workers' working hours and environments become more diverse, it is necessary to prevent adverse health effects caused by overwork and inappropriate work patterns. However, conventional attendance management systems have difficulty grasping work conditions in real time and immediately detecting and notifying abnormalities, which can lead to decreased labor productivity and employee health problems. To solve this problem, a system is needed that integrates and analyzes workers' attendance information and computer usage history to quickly detect and respond to abnormal events.

[0446] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0447] In this invention, the server includes means for acquiring employee attendance information in real time, means for integrating and pre-processing the acquired attendance information and computer usage history, and means for analyzing abnormal events that deviate from normal work patterns using artificial intelligence technology. This makes it possible to quickly and automatically detect abnormal work patterns of employees and immediately notify relevant managers and employees.

[0448] "Worker attendance information" refers to records of work-related information such as working hours, arrival and departure times, and leave status.

[0449] "Computer usage history" refers to records of operations performed on computers used by employees for work, login times, application usage times, and other similar information.

[0450] "Artificial intelligence technology" refers to techniques that use machine learning and statistical analysis to learn and analyze patterns from data.

[0451] An "abnormal event" is data or an incident that indicates a deviation from the normal work pattern, such as working long hours or repeated tardiness.

[0452] A "management supervisor" is a person in charge of supervising the working environment and work conditions of employees and taking appropriate action.

[0453] "Message communication technology" refers to the technology used to send and receive information using email and messaging services.

[0454] "Health management" refers to measures and guidance aimed at maintaining and improving the physical and mental health of workers.

[0455] "Work-life balance" refers to a balance in life where a worker's working hours and personal life time are in harmony, and both are considered important.

[0456] This invention relates to a system that collects and analyzes workers' attendance information and computer usage history, and detects and notifies them of abnormal work patterns. This system primarily operates through a server.

[0457] The server accesses the employee attendance database via the network and retrieves attendance information such as working hours, clock-in and clock-out times, and leave status in real time. Database management software is used to efficiently retrieve and store the data on the server. Additionally, computer usage history for work-related activities is locally retrieved from terminals and sent to the server. This allows for the integration of data on the server, enabling consistent information management.

[0458] On the server, collected attendance information and computer usage history are integrated and preprocessed. This involves data cleaning and normalization, converting the data into a format suitable for analysis. Then, artificial intelligence technology is used to analyze abnormal events that deviate from normal work patterns. Specifically, machine learning algorithms are used to detect abnormally long working hours, repeated tardiness, and other such issues. The AI ​​model has learned from past data and possesses pattern recognition capabilities to accurately identify anomalies.

[0459] If an anomaly is detected, the server will immediately notify the administrator and the affected workers. The notification will be sent via email or messaging systems using electronic communication technology. Reminders will also be sent to relevant parties using messaging technology.

[0460] Regarding health management and work-life balance suggestions, the server automatically generates personalized improvement plans for each employee based on an analysis of past attendance data and work history. These suggestions are generated weekly or monthly and shared with relevant parties, playing a role in supporting the creation of a sustainable work environment.

[0461] As a concrete example, the system might detect a situation where "Employee A has worked a total of 40 hours in the past three days," identify this pattern as abnormal, and send an email to the manager stating "Employee A may be working excessive hours." Such functionality enables rapid and automatic detection of anomalies, thereby improving worker health and productivity.

[0462] As an example of a prompt, it is assumed that the following sentence would be input to the generating AI model: "Please tell me how to build a system that detects and notifies of abnormal work patterns from employee attendance data and computer usage records."

[0463] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0464] Step 1:

[0465] The server accesses the employee attendance database to obtain real-time information on employees' working hours, clock-in and clock-out times, and leave status. It receives attendance information from the database as input, organizes and stores the data within the server, and provides a formatted set of attendance information as output. Specifically, the server issues database queries, extracts the necessary data for each employee, and formats it.

[0466] Step 2:

[0467] The terminal locally retrieves the usage history of the computer used by the worker for work and sends that data to the server. As input, it retrieves usage history information from the terminal's local file system and log system. As output, the collected usage history is sent to the server and stored. Specifically, the terminal checks the usage history at regular intervals and uploads the latest log information to the server.

[0468] Step 3:

[0469] The server integrates and preprocesses the acquired attendance information and computer usage history. It receives the data obtained in steps 1 and 2 as input. As output, it generates an integrated and preprocessed dataset within the server. Specifically, it removes redundant data, converts data formats, and corrects outliers to create a consistent dataset.

[0470] Step 4:

[0471] The server uses artificial intelligence technology to analyze integrated data and detect anomalous events. It utilizes a pre-processed dataset as input and generates anomalous event detection results as output. Specifically, the server inputs data into an AI model, which then uses its learning to determine abnormal work patterns. Based on these results, it identifies which workers are exhibiting abnormal behavior.

[0472] Step 5:

[0473] The server immediately notifies the manager and the relevant worker if an anomaly is detected. The anomaly detection result from step 4 is used as input. A warning message is generated as output and sent to the relevant parties. Specifically, the server uses an email API or messaging service to construct and send a message for notification.

[0474] Step 6:

[0475] The server generates health management and work-life balance suggestions based on an analysis of past attendance data and usage history. Past attendance data and work patterns are used as input. The output is personalized improvement suggestions optimized for each employee. Specifically, the server utilizes a generation AI model to automatically generate advice and suggestions based on past trend analysis and provides them to relevant parties.

[0476] (Application Example 1)

[0477] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0478] In today's work environment, health deterioration and decreased work efficiency due to overwork are serious concerns. In particular, there is a need to accurately identify abnormalities in the work and activity patterns of employees and provide feedback to help them work efficiently while maintaining their health. However, conventional systems lacked real-time anomaly detection, health monitoring, and effective rest promotion. Therefore, preventing a decline in work performance due to overwork and poor health, and maintaining a sustainable balance in work life, is a key challenge.

[0479] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0480] In this invention, the server includes means for acquiring worker activity data in real time, means for analyzing the activity data to detect abnormalities, and means for providing health-promoting feedback to the worker through a visual display. This makes it possible to continuously monitor the health status of workers and provide appropriate alerts and rest instructions in real time when abnormalities are detected, thereby creating an efficient and healthy work environment.

[0481] "Worker activity data" refers to information generated by workers during their work, such as working hours, break times, and work content.

[0482] "Real-time" refers to processing and information provision occurring immediately, meaning that data collection and analysis are carried out without delay.

[0483] "Detecting anomalies" means identifying behaviors or malfunctions that deviate from normal activity patterns and recognizing them as problems.

[0484] "Immediate notification to administrators and relevant participants" means that information about the discovered problem is communicated to the relevant parties without delay.

[0485] "Machine usage records" refer to the operation history of devices and tools used by workers during their work.

[0486] "Health management" refers to the act of collecting and analyzing information and proposing improvements with the aim of maintaining and improving the health of workers.

[0487] "Harmony between work and life" means that workers achieve a healthy and sustainable lifestyle by appropriately balancing their work time and rest time.

[0488] A "visual display" refers to visual devices or functions that display information in a way that can be seen by the human eye.

[0489] "Monitoring physical condition using sensors" means using technical equipment to measure physiological indicators and observe the health status of workers.

[0490] A description of embodiments for carrying out the present invention will be provided.

[0491] The server utilizes software to collect and retrieve worker activity data in real time. This system aggregates information about workers' working hours, break times, and work content into a database. The data is organized using the Pandas library, and analysis is performed using AI technologies such as TensorFlow to detect anomaly patterns.

[0492] The device monitors collected activity data along with physical condition via sensors and uses a visual display function to provide feedback to the user. This feedback immediately notifies supervisors and workers when an anomaly is detected and visually communicates suggestions for balancing efficient work and rest.

[0493] The system supports users in maintaining a healthy and efficient work environment by providing real-time alerts and feedback. For example, if a new employee is working long hours, the system analyzes their activity data and detects unusual signs of overwork. It then informs the employee of their current situation via a visual display and suggests taking a break, thereby preventing overwork.

[0494] Using a generative AI model, we can present example prompts such as: "Please suggest the optimal allocation of working hours to allow employees to work efficiently while maintaining their health. Please propose approaches to mitigate the risks associated with working more than 50 hours per week."

[0495] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0496] Step 1:

[0497] The server acquires worker activity data in real time from sensors and other input devices. This data includes work time, break times, and equipment usage history. The acquired data is organized into a dataframe format using Pandas.

[0498] Step 2:

[0499] The server uses the acquired activity data to perform analysis for anomaly detection. Using AI models such as TensorFlow, it analyzes signs of deviations from normal work patterns and detects anomalies. This analysis utilizes machine learning models based on historical data.

[0500] Step 3:

[0501] If an anomaly is detected, the server immediately sends a notification to the administrator and the relevant worker's terminal. The notification includes the worker's current status and recommended next actions. The data is transmitted via electronic communication.

[0502] Step 4:

[0503] The device displays received notifications on its visual display. This display includes suggestions for healthy work practices for workers, specifically messages encouraging them to take breaks.

[0504] Step 5:

[0505] Users can receive the feedback provided and adjust their work patterns accordingly. If additional support is needed, users can provide feedback to the system to receive further solutions and advice.

[0506] Step 6:

[0507] Using a generative AI model, prompts are generated to provide users with further suggestions for improvement and advice. The AI ​​analyzes workers' past data and provides insights based on prompts such as, "Show us the optimal way to allocate working hours so that employees can work efficiently while maintaining their health."

[0508] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0509] This invention provides a system that collects and analyzes employee attendance data and computer usage records in real time, notifies administrators and employees when anomalies are detected, and offers suggestions to improve health management and work-life balance. Furthermore, by incorporating an emotion engine that detects user emotions, it is possible to combine work data and emotion data to provide more precise suggestions for improving work styles.

[0510] This system operates primarily via a server. The server retrieves data from employee attendance databases and computer usage records. In addition, the server collects emotional data from various employee sensors and input devices. This emotional data includes facial recognition, voice analysis, and stress level measurements using biosensors.

[0511] The server first processes the data entry, then integrates attendance data, computer usage records, and emotional data, formatting them into an analyzable form. Next, it uses analytical tools to detect deviations or abnormalities from normal work patterns. During this process, emotional data is also included in the analysis to assess whether stress levels are high.

[0512] When an anomaly is detected, notifications are sent to specific administrators and the relevant employees. The server sends these notifications via email or messaging systems. The notifications may also include information about any psychological issues the worker may be experiencing.

[0513] Furthermore, the server generates health management advice and work-life balance improvement suggestions for employees suspected of working long hours or experiencing high stress levels, combining past work and emotional data. These suggestions are personalized to each employee's situation, and specifically provide concrete actions to adjust their workload, particularly for employees experiencing high stress levels.

[0514] For example, if a user's weekly working hours exceed 50 hours and their daily emotional data indicates a high stress level, the server will send a notification to the administrator stating, "This user shows signs of potential fatigue; it is recommended that they reduce their workload." At the same time, the user will receive a suggestion to "take regular breaks and consider stress reduction measures."

[0515] Thus, the present invention enables real-time attendance and health management by utilizing multifaceted employee data, and supports the creation of an appropriate work environment tailored to the employee's health and psychological state. Meanwhile, the terminal receives notifications from the server and provides an interface for the user to take action.

[0516] The following describes the processing flow.

[0517] Step 1:

[0518] The server periodically retrieves data from employee attendance databases and computer usage log databases. This includes employee start and end times, application logs used, and other relevant information.

[0519] Step 2:

[0520] The server collects emotional data from sensors associated with each employee. This emotional data is collected through facial recognition cameras, voice analysis devices, and biosensors (such as heart rate and skin temperature sensors).

[0521] Step 3:

[0522] The server integrates and preprocesses the collected attendance data, computer usage records, and sentiment data, and performs data cleansing. This includes processes such as deduplication, formatting standardization, and imputation of missing values.

[0523] Step 4:

[0524] The server uses a data analysis engine to detect anomalies that deviate from normal work patterns. At the same time, it analyzes emotional data to determine if stress levels are high and if attention is needed.

[0525] Step 5:

[0526] Based on the analysis results, the server will send an email or messaging notification to the relevant administrator if it detects an anomaly or high-stress condition. The notification will include a detailed explanation of the anomaly and possible countermeasures.

[0527] Step 6:

[0528] Based on the results of an analysis using emotional data, the server sends notifications to the relevant employees. These notifications may include suggestions for stress reduction or recommendations for taking breaks.

[0529] Step 7:

[0530] The server generates and provides personalized health management advice to individual employees based on accumulated historical work and emotional data. This advice is personalized and includes specific action plans.

[0531] Step 8:

[0532] The terminal displays various notifications and suggestions from the server to the user and provides an interface for the user to manage their work patterns and health status based on that information.

[0533] (Example 2)

[0534] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0535] Maintaining employee health and work-life balance is a critical challenge in many workplaces. However, traditional systems often lack sufficient time management and emotional data, making it difficult to timely detect signs of employee stress and fatigue and take appropriate measures. Furthermore, even when abnormalities are detected, notifications and specific improvement suggestions tend to be delayed, resulting in a lack of real-time capabilities in employee health management.

[0536] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0537] In this invention, the server includes means for acquiring employee time management information in real time, means for integrating and analyzing the time management information to detect anomalies, and means for acquiring emotional information using facial recognition, voice analysis, and biosensors. This makes it possible to grasp information on employee stress and work balance in real time and to quickly provide appropriate health management and work improvement suggestions.

[0538] "Time management information" refers to data related to working hours, such as employee work hours, break times, and attendance records.

[0539] "Abnormal" refers to a state that deviates from normal work patterns or emotional states, and particularly includes situations where high stress or long working hours are suspected.

[0540] A "manager" refers to a person responsible for supervising employees' work conditions and making improvement suggestions as needed.

[0541] "Emotional information" refers to data that represents the psychological state of employees, and is acquired through methods such as facial recognition, voice analysis, and biosensors.

[0542] "Suggestions" refer to specific action plans and advice generated by the server with the aim of improving workers' health and work-life balance.

[0543] "Notification" refers to the act of a server using electronic communication means to inform an administrator or employee when an anomaly is detected or a suggestion is generated.

[0544] "Analysis means" refers to methods or techniques for processing acquired data and performing comparisons with normal patterns or detecting anomalies.

[0545] This invention relates to a system that acquires employee time management information and emotional state in real time, analyzes them, and detects work abnormalities. The main components of the system include a server that collects and processes data, and a terminal that displays the results. Specifically, the server is integrated with the attendance system to acquire time management information. It also acquires emotional information through a facial recognition camera, a voice analysis system, and biosensors, and evaluates stress levels.

[0546] The server integrates this data and uses analytical algorithms to perform calculations to detect deviations from normal work patterns. The integrated data helps in the early detection of anomalies, enabling highly accurate analysis. Emotional information is also treated as quantified data and analyzed along with time management information.

[0547] When an anomaly is detected, the server uses email and messaging functions to send notifications to administrators and the relevant employees. These notifications include detailed analysis results based on the type of anomaly and emotional information. Furthermore, the server generates personalized health management suggestions based on historical data. These suggestions form concrete action plans for stress reduction.

[0548] The terminal displays notifications and suggestions from the server to employees and provides an interface for users to improve their work environment based on this information. Users are encouraged to review the advice through the terminal and act according to the instructions.

[0549] For example, if the server analyzes an employee's weekly working hours to determine that their stress level is high based on emotional data, a notification will be sent to the administrator stating, "User A's stress level is higher than normal; it is recommended to reduce their workload." Simultaneously, the user will receive a specific suggestion, such as, "It is recommended that you take a break of 30 minutes or more each day to reduce stress."

[0550] An example of a prompt would be, "Explain how to use employee time management and emotional data to detect anomalies in work patterns and generate health management suggestions." This prompt supports the generation of appropriate suggestions by the generative AI model.

[0551] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0552] Step 1:

[0553] The server acquires employee time management information in real time. This input information includes clock-in and clock-out times, break times, and working hours. The server collects this data and stores it in a database. This storage process forms the basis for subsequent data analysis.

[0554] Step 2:

[0555] The server acquires data in real time from facial recognition cameras, voice analysis systems, and biosensors to collect emotional information. This emotional information includes facial expressions, voice tone, and heart rate. The server converts this data into an analyzable format and stores it in a database. This conversion process yields quantified emotional information.

[0556] Step 3:

[0557] The server integrates collected time management and emotional data and prepares a dataset for comparison with normal work patterns. This integration process creates a synthetic dataset for each employee, laying the foundation for detecting anomalies.

[0558] Step 4:

[0559] The server uses an analysis algorithm to detect anomalies in the integrated data. The input is the integrated dataset. The server compares this data with historical data to assess whether working hours are excessively long or whether stress levels are elevated. This analysis extracts cases suspected of high stress or excessive working hours.

[0560] Step 5:

[0561] If an anomaly is detected, the server will send a notification to the administrator and the relevant employee. This notification will be sent via email or messaging. The input information will include the analysis results indicating the anomaly and information about the employee. The notification will include specific issues and suggested countermeasures.

[0562] Step 6:

[0563] The server generates suggestions for improving health management and work-life balance based on past time management and emotional data. This suggestion generation uses the individual's historical data and analysis results as input. The server creates specific action plans and notifies employees and managers. This output constitutes the improvement measures provided.

[0564] Step 7:

[0565] The terminal displays notifications and suggestions received from the server to the user. During this display process, the user can adjust their actions based on the presented information. Specifically, the user uses the terminal to follow the suggestions and take concrete actions such as adjusting working hours or ensuring sufficient break time.

[0566] (Application Example 2)

[0567] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0568] In today's work environment, it is essential to appropriately monitor employees' work conditions and emotional states and provide timely interventions and corrective measures. However, many existing systems make decisions based solely on work data and do not adequately consider human factors such as emotional states. As a result, there is a challenge in detecting abnormalities in employees' health and stress levels early and taking prompt action.

[0569] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0570] In this invention, the server includes means for acquiring employee work information in real time, means for analyzing the work information to detect anomalies, means for immediately notifying the manager and the relevant employee when an anomaly is detected, and means for analyzing emotional states and providing stress reduction measures when an anomaly is detected. This enables comprehensive monitoring and the provision of improvement measures that take into account the emotional states of employees.

[0571] An "employee" is an individual who is employed by a company or organization and provides labor.

[0572] "Labor information" refers to data concerning an employee's working hours and work content, including start and end times of work and job duties.

[0573] "Computer usage history" refers to information that shows the operation records and application usage status of computers used by employees for their work.

[0574] "Emotional state" refers to data indicating the psychological and emotional health of employees, including information obtained through facial recognition and voice analysis.

[0575] "Stress reduction measures" refer to specific suggestions and methods provided to reduce employee stress and maintain a healthy work environment.

[0576] A "server" is a computer system that aggregates and analyzes data and generates notifications and suggestions.

[0577] A "manager" is an individual or position within a company or organization that is responsible for supervising the working conditions of employees and managing all aspects of operations.

[0578] The server, connected to the company's internal systems, collects employee work information and computer usage history in real time and stores it in a database. Based on this information, the server detects deviations from normal work patterns and analyzes anomalies using specific algorithms. Furthermore, it incorporates emotion detection technologies such as facial recognition, voice analysis, and biosensors to analyze emotional states and evaluate workers' stress levels.

[0579] If an anomaly is detected, the server will immediately notify administrators and the affected employees. This notification will use digital messaging or a communication function to immediately provide stakeholders with improvement suggestions, including stress reduction measures. For example, if the server detects data indicating high stress, administrators will receive a notification stating that "a reassessment of the workload for the affected employee is necessary," and employees will be provided with specific advice such as "we recommend taking deep breaths or short breaks."

[0580] This system facilitates comprehensive monitoring and the suggestion of improvement measures that take emotional states into account, contributing to employee health maintenance and productivity improvement. Data obtained through emotion detection is used to generate more precise suggestions for improving work-life balance. Furthermore, a generative AI model can be used to automatically generate appropriate suggestions based on the situation.

[0581] As a concrete example, here is an example of a prompt message to be input to a generating AI model: "Create suggestions to reduce security risks based on employee emotional data and attendance data." Based on this prompt, the AI ​​analyzes the workers' health status and emotional data and presents appropriate improvement measures based on the results.

[0582] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0583] Step 1:

[0584] The server retrieves work information and computer usage history from employees in real time. This input data includes employee start and end times, and logs of applications used. The server stores this data in a database and prepares it for subsequent analysis steps.

[0585] Step 2:

[0586] The server analyzes the acquired work information and computer usage history to detect deviations from normal work patterns. At this stage, specific algorithms are used to process the data and identify anomalies. The output is a list of detected anomalies, indicating which data is abnormal.

[0587] Step 3:

[0588] The server analyzes the emotional state of employees using emotion detection technology. Input data includes stress levels from biosensors, facial recognition, and voice analysis data. The server integrates this data to evaluate the employee's stress level. The output is an emotional state report.

[0589] Step 4:

[0590] The server sends notifications to administrators and relevant employees when it detects an anomaly. Inputs include a list of anomalies and a mood status report. Based on this information, the server sends necessary notifications using digital messaging or a contact function. Outputs are notification messages to administrators and employees.

[0591] Step 5:

[0592] The server uses a generative AI model to automatically generate improvement suggestions that take into account work information and emotional states. The input consists of historical work data and emotional data. The server inputs prompts into the generative AI model, which then generates appropriate suggestions. This output is the improvement suggestion provided to the employee.

[0593] Step 6:

[0594] The terminal displays notifications and improvement suggestions received from the server to employees, prompting them to take action. Input consists of notification messages and improvement suggestions from the server. The terminal presents information in a user-friendly interface, making it easy for employees to understand and act upon. Output consists of specific action suggestions for employees.

[0595] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0596] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0597] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0598] [Fourth Embodiment]

[0599] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0600] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0601] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0602] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0603] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0604] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0605] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0606] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0607] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0608] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0609] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0610] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0611] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0612] This invention provides a labor management system that collects employee attendance data and computer usage records in real time and immediately notifies relevant managers and employees when abnormal work patterns are detected. This system primarily operates via a server.

[0613] The server first automatically retrieves information such as working hours and leave status from the employee attendance database, and simultaneously collects computer usage records from the terminals used by employees for work. All data is integrated within the server and organized in a format that allows for analysis.

[0614] The server uses AI to analyze the acquired data. Specifically, it detects abnormal events that deviate from normal work patterns (for example, long working hours or repeated tardiness), and also analyzes PC usage logs to check for errors such as missing entries.

[0615] If an anomaly is detected, the server immediately notifies the relevant administrator. The notification is sent via email or internal messaging tools, allowing for swift action. Additionally, the affected employee receives a reminder or notification tailored to the nature of the anomaly, encouraging proactive response.

[0616] For example, if an employee works more than 50 hours continuously in a week, the server will detect this as an anomaly and send an alert to the administrator stating "Possible employee overwork." The employee will also receive a notification recommending that they take appropriate breaks.

[0617] Furthermore, the server is equipped with a function that provides suggestions for improving health management and work-life balance. Based on analysis of past attendance data and thought patterns, it provides improvement suggestions tailored to each employee's situation, supporting the maintenance of a sustainable work-life balance.

[0618] Thus, this invention enables real-time attendance management, allows for a rapid response in the event of an anomaly, and aims to improve employee health and motivation.

[0619] The following describes the processing flow.

[0620] Step 1:

[0621] The server automatically retrieves the latest data from employee attendance databases and computer usage databases periodically (for example, every 5 minutes). This enables real-time data collection, ensuring that the most up-to-date information is always available.

[0622] Step 2:

[0623] The server performs data preprocessing on the acquired data as input. This includes formatting the data, imputing missing values, and filtering outliers. If necessary, it standardizes the data format and prepares it for analysis.

[0624] Step 3:

[0625] The server uses an AI analysis module to analyze the formatted data. Here, it checks whether there are deviations from normal attendance patterns and whether working hours exceed the regulations. It also checks for inconsistencies between computer usage records and attendance data.

[0626] Step 4:

[0627] The server identifies anomalies based on the analysis results. Anomalies include, for example, consecutive long working hours, failure to enter attendance records, and consecutive lateness. In this case, the server determines the next course of action based on the severity of the anomaly.

[0628] Step 5:

[0629] If an anomaly is detected, the server will notify the administrator based on the determined action. Notifications will be sent via email or the company's internal messaging system to ensure timely information dissemination.

[0630] Step 6:

[0631] The server also notifies the employee in question of the anomaly detection result. This could include a health management message, such as "Please consider taking appropriate leave."

[0632] Step 7:

[0633] The server generates and notifies employees suspected of working long hours or excessive workloads, offering suggestions for health management and work-life balance improvement. These suggestions are personalized based on past data and individual work situations.

[0634] Step 8:

[0635] The terminal displays notifications and alerts sent from the server and provides an interface for users to take necessary actions. Users can modify attendance data, submit leave requests, and perform other actions depending on the content of the notifications.

[0636] (Example 1)

[0637] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0638] As workers' working hours and environments become more diverse, it is necessary to prevent adverse health effects caused by overwork and inappropriate work patterns. However, conventional attendance management systems have difficulty grasping work conditions in real time and immediately detecting and notifying abnormalities, which can lead to decreased labor productivity and employee health problems. To solve this problem, a system is needed that integrates and analyzes workers' attendance information and computer usage history to quickly detect and respond to abnormal events.

[0639] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0640] In this invention, the server includes means for acquiring employee attendance information in real time, means for integrating and pre-processing the acquired attendance information and computer usage history, and means for analyzing abnormal events that deviate from normal work patterns using artificial intelligence technology. This makes it possible to quickly and automatically detect abnormal work patterns of employees and immediately notify relevant managers and employees.

[0641] "Worker attendance information" refers to records of work-related information such as working hours, arrival and departure times, and leave status.

[0642] "Computer usage history" refers to records of operations performed on computers used by employees for work, login times, application usage times, and other similar information.

[0643] "Artificial intelligence technology" refers to techniques that use machine learning and statistical analysis to learn and analyze patterns from data.

[0644] An "abnormal event" is data or an incident that indicates a deviation from the normal work pattern, such as working long hours or repeated tardiness.

[0645] A "management supervisor" is a person in charge of supervising the working environment and work conditions of employees and taking appropriate action.

[0646] "Message communication technology" refers to the technology used to send and receive information using email and messaging services.

[0647] "Health management" refers to measures and guidance aimed at maintaining and improving the physical and mental health of workers.

[0648] "Work-life balance" refers to a balance in life where a worker's working hours and personal life time are in harmony, and both are considered important.

[0649] This invention relates to a system that collects and analyzes workers' attendance information and computer usage history, and detects and notifies them of abnormal work patterns. This system primarily operates through a server.

[0650] The server accesses the employee attendance database via the network and retrieves attendance information such as working hours, clock-in and clock-out times, and leave status in real time. Database management software is used to efficiently retrieve and store the data on the server. Additionally, computer usage history for work-related activities is locally retrieved from terminals and sent to the server. This allows for the integration of data on the server, enabling consistent information management.

[0651] On the server, collected attendance information and computer usage history are integrated and preprocessed. This involves data cleaning and normalization, converting the data into a format suitable for analysis. Then, artificial intelligence technology is used to analyze abnormal events that deviate from normal work patterns. Specifically, machine learning algorithms are used to detect abnormally long working hours, repeated tardiness, and other such issues. The AI ​​model has learned from past data and possesses pattern recognition capabilities to accurately identify anomalies.

[0652] If an anomaly is detected, the server will immediately notify the administrator and the affected workers. The notification will be sent via email or messaging systems using electronic communication technology. Reminders will also be sent to relevant parties using messaging technology.

[0653] Regarding health management and work-life balance suggestions, the server automatically generates personalized improvement plans for each employee based on an analysis of past attendance data and work history. These suggestions are generated weekly or monthly and shared with relevant parties, playing a role in supporting the creation of a sustainable work environment.

[0654] As a concrete example, the system might detect a situation where "Employee A has worked a total of 40 hours in the past three days," identify this pattern as abnormal, and send an email to the manager stating "Employee A may be working excessive hours." Such functionality enables rapid and automatic detection of anomalies, thereby improving worker health and productivity.

[0655] As an example of a prompt, it is assumed that the following sentence would be input to the generating AI model: "Please tell me how to build a system that detects and notifies of abnormal work patterns from employee attendance data and computer usage records."

[0656] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0657] Step 1:

[0658] The server accesses the employee attendance database to obtain real-time information on employees' working hours, clock-in and clock-out times, and leave status. It receives attendance information from the database as input, organizes and stores the data within the server, and provides a formatted set of attendance information as output. Specifically, the server issues database queries, extracts the necessary data for each employee, and formats it.

[0659] Step 2:

[0660] The terminal locally retrieves the usage history of the computer used by the worker for work and sends that data to the server. As input, it retrieves usage history information from the terminal's local file system and log system. As output, the collected usage history is sent to the server and stored. Specifically, the terminal checks the usage history at regular intervals and uploads the latest log information to the server.

[0661] Step 3:

[0662] The server integrates and preprocesses the acquired attendance information and computer usage history. It receives the data obtained in steps 1 and 2 as input. As output, it generates an integrated and preprocessed dataset within the server. Specifically, it removes redundant data, converts data formats, and corrects outliers to create a consistent dataset.

[0663] Step 4:

[0664] The server uses artificial intelligence technology to analyze integrated data and detect anomalous events. It utilizes a pre-processed dataset as input and generates anomalous event detection results as output. Specifically, the server inputs data into an AI model, which then uses its learning to determine abnormal work patterns. Based on these results, it identifies which workers are exhibiting abnormal behavior.

[0665] Step 5:

[0666] The server immediately notifies the manager and the relevant worker if an anomaly is detected. The anomaly detection result from step 4 is used as input. A warning message is generated as output and sent to the relevant parties. Specifically, the server uses an email API or messaging service to construct and send a message for notification.

[0667] Step 6:

[0668] The server generates health management and work-life balance suggestions based on an analysis of past attendance data and usage history. Past attendance data and work patterns are used as input. The output is personalized improvement suggestions optimized for each employee. Specifically, the server utilizes a generation AI model to automatically generate advice and suggestions based on past trend analysis and provides them to relevant parties.

[0669] (Application Example 1)

[0670] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0671] In today's work environment, health deterioration and decreased work efficiency due to overwork are serious concerns. In particular, there is a need to accurately identify abnormalities in the work and activity patterns of employees and provide feedback to help them work efficiently while maintaining their health. However, conventional systems lacked real-time anomaly detection, health monitoring, and effective rest promotion. Therefore, preventing a decline in work performance due to overwork and poor health, and maintaining a sustainable balance in work life, is a key challenge.

[0672] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0673] In this invention, the server includes means for acquiring worker activity data in real time, means for analyzing the activity data to detect abnormalities, and means for providing health-promoting feedback to the worker through a visual display. This makes it possible to continuously monitor the health status of workers and provide appropriate alerts and rest instructions in real time when abnormalities are detected, thereby creating an efficient and healthy work environment.

[0674] "Worker activity data" refers to information generated by workers during their work, such as working hours, break times, and work content.

[0675] "Real-time" refers to processing and information provision occurring immediately, meaning that data collection and analysis are carried out without delay.

[0676] "Detecting anomalies" means identifying behaviors or malfunctions that deviate from normal activity patterns and recognizing them as problems.

[0677] "Immediate notification to administrators and relevant participants" means that information about the discovered problem is communicated to the relevant parties without delay.

[0678] "Machine usage records" refer to the operation history of devices and tools used by workers during their work.

[0679] "Health management" refers to the act of collecting and analyzing information and proposing improvements with the aim of maintaining and improving the health of workers.

[0680] "Harmony between work and life" means that workers achieve a healthy and sustainable lifestyle by appropriately balancing their work time and rest time.

[0681] A "visual display" refers to visual devices or functions that display information in a way that can be seen by the human eye.

[0682] "Monitoring physical condition using sensors" means using technical equipment to measure physiological indicators and observe the health status of workers.

[0683] A description of embodiments for carrying out the present invention will be provided.

[0684] The server utilizes software to collect and retrieve worker activity data in real time. This system aggregates information about workers' working hours, break times, and work content into a database. The data is organized using the Pandas library, and analysis is performed using AI technologies such as TensorFlow to detect anomaly patterns.

[0685] The device monitors collected activity data along with physical condition via sensors and uses a visual display function to provide feedback to the user. This feedback immediately notifies supervisors and workers when an anomaly is detected and visually communicates suggestions for balancing efficient work and rest.

[0686] The system supports users in maintaining a healthy and efficient work environment by providing real-time alerts and feedback. For example, if a new employee is working long hours, the system analyzes their activity data and detects unusual signs of overwork. It then informs the employee of their current situation via a visual display and suggests taking a break, thereby preventing overwork.

[0687] Using a generative AI model, we can present example prompts such as: "Please suggest the optimal allocation of working hours to allow employees to work efficiently while maintaining their health. Please propose approaches to mitigate the risks associated with working more than 50 hours per week."

[0688] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0689] Step 1:

[0690] The server acquires worker activity data in real time from sensors and other input devices. This data includes work time, break times, and equipment usage history. The acquired data is organized into a dataframe format using Pandas.

[0691] Step 2:

[0692] The server uses the acquired activity data to perform analysis for anomaly detection. Using AI models such as TensorFlow, it analyzes signs of deviations from normal work patterns and detects anomalies. This analysis utilizes machine learning models based on historical data.

[0693] Step 3:

[0694] If an anomaly is detected, the server immediately sends a notification to the administrator and the relevant worker's terminal. The notification includes the worker's current status and recommended next actions. The data is transmitted via electronic communication.

[0695] Step 4:

[0696] The device displays received notifications on its visual display. This display includes suggestions for healthy work practices for workers, specifically messages encouraging them to take breaks.

[0697] Step 5:

[0698] Users can receive the feedback provided and adjust their work patterns accordingly. If additional support is needed, users can provide feedback to the system to receive further solutions and advice.

[0699] Step 6:

[0700] Using a generative AI model, prompts are generated to provide users with further suggestions for improvement and advice. The AI ​​analyzes workers' past data and provides insights based on prompts such as, "Show us the optimal way to allocate working hours so that employees can work efficiently while maintaining their health."

[0701] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0702] This invention provides a system that collects and analyzes employee attendance data and computer usage records in real time, notifies administrators and employees when anomalies are detected, and offers suggestions to improve health management and work-life balance. Furthermore, by incorporating an emotion engine that detects user emotions, it is possible to combine work data and emotion data to provide more precise suggestions for improving work styles.

[0703] This system operates primarily via a server. The server retrieves data from employee attendance databases and computer usage records. In addition, the server collects emotional data from various employee sensors and input devices. This emotional data includes facial recognition, voice analysis, and stress level measurements using biosensors.

[0704] The server first processes the data entry, then integrates attendance data, computer usage records, and emotional data, formatting them into an analyzable form. Next, it uses analytical tools to detect deviations or abnormalities from normal work patterns. During this process, emotional data is also included in the analysis to assess whether stress levels are high.

[0705] When an anomaly is detected, notifications are sent to specific administrators and the relevant employees. The server sends these notifications via email or messaging systems. The notifications may also include information about any psychological issues the worker may be experiencing.

[0706] Furthermore, the server generates health management advice and work-life balance improvement suggestions for employees suspected of working long hours or experiencing high stress levels, combining past work and emotional data. These suggestions are personalized to each employee's situation, and specifically provide concrete actions to adjust their workload, particularly for employees experiencing high stress levels.

[0707] For example, if a user's weekly working hours exceed 50 hours and their daily emotional data indicates a high stress level, the server will send a notification to the administrator stating, "This user shows signs of potential fatigue; it is recommended that they reduce their workload." At the same time, the user will receive a suggestion to "take regular breaks and consider stress reduction measures."

[0708] Thus, the present invention enables real-time attendance and health management by utilizing multifaceted employee data, and supports the creation of an appropriate work environment tailored to the employee's health and psychological state. Meanwhile, the terminal receives notifications from the server and provides an interface for the user to take action.

[0709] The following describes the processing flow.

[0710] Step 1:

[0711] The server periodically retrieves data from employee attendance databases and computer usage log databases. This includes employee start and end times, application logs used, and other relevant information.

[0712] Step 2:

[0713] The server collects emotional data from sensors associated with each employee. This emotional data is collected through facial recognition cameras, voice analysis devices, and biosensors (such as heart rate and skin temperature sensors).

[0714] Step 3:

[0715] The server integrates and preprocesses the collected attendance data, computer usage records, and sentiment data, and performs data cleansing. This includes processes such as deduplication, formatting standardization, and imputation of missing values.

[0716] Step 4:

[0717] The server uses a data analysis engine to detect anomalies that deviate from normal work patterns. At the same time, it analyzes emotional data to determine if stress levels are high and if attention is needed.

[0718] Step 5:

[0719] Based on the analysis results, the server will send an email or messaging notification to the relevant administrator if it detects an anomaly or high-stress condition. The notification will include a detailed explanation of the anomaly and possible countermeasures.

[0720] Step 6:

[0721] Based on the results of an analysis using emotional data, the server sends notifications to the relevant employees. These notifications may include suggestions for stress reduction or recommendations for taking breaks.

[0722] Step 7:

[0723] The server generates and provides personalized health management advice to individual employees based on accumulated historical work and emotional data. This advice is personalized and includes specific action plans.

[0724] Step 8:

[0725] The terminal displays various notifications and suggestions from the server to the user and provides an interface for the user to manage their work patterns and health status based on that information.

[0726] (Example 2)

[0727] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0728] Maintaining employee health and work-life balance is a critical challenge in many workplaces. However, traditional systems often lack sufficient time management and emotional data, making it difficult to timely detect signs of employee stress and fatigue and take appropriate measures. Furthermore, even when abnormalities are detected, notifications and specific improvement suggestions tend to be delayed, resulting in a lack of real-time capabilities in employee health management.

[0729] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0730] In this invention, the server includes means for acquiring employee time management information in real time, means for integrating and analyzing the time management information to detect anomalies, and means for acquiring emotional information using facial recognition, voice analysis, and biosensors. This makes it possible to grasp information on employee stress and work balance in real time and to quickly provide appropriate health management and work improvement suggestions.

[0731] "Time management information" refers to data related to working hours, such as employee work hours, break times, and attendance records.

[0732] "Abnormal" refers to a state that deviates from normal work patterns or emotional states, and particularly includes situations where high stress or long working hours are suspected.

[0733] A "manager" refers to a person responsible for supervising employees' work conditions and making improvement suggestions as needed.

[0734] "Emotional information" refers to data that represents the psychological state of employees, and is acquired through methods such as facial recognition, voice analysis, and biosensors.

[0735] "Suggestions" refer to specific action plans and advice generated by the server with the aim of improving workers' health and work-life balance.

[0736] "Notification" refers to the act of a server using electronic communication means to inform an administrator or employee when an anomaly is detected or a suggestion is generated.

[0737] "Analysis means" refers to methods or techniques for processing acquired data and performing comparisons with normal patterns or detecting anomalies.

[0738] This invention relates to a system that acquires employee time management information and emotional state in real time, analyzes them, and detects work abnormalities. The main components of the system include a server that collects and processes data, and a terminal that displays the results. Specifically, the server is integrated with the attendance system to acquire time management information. It also acquires emotional information through a facial recognition camera, a voice analysis system, and biosensors, and evaluates stress levels.

[0739] The server integrates this data and uses analytical algorithms to perform calculations to detect deviations from normal work patterns. The integrated data helps in the early detection of anomalies, enabling highly accurate analysis. Emotional information is also treated as quantified data and analyzed along with time management information.

[0740] When an anomaly is detected, the server uses email and messaging functions to send notifications to administrators and the relevant employees. These notifications include detailed analysis results based on the type of anomaly and emotional information. Furthermore, the server generates personalized health management suggestions based on historical data. These suggestions form concrete action plans for stress reduction.

[0741] The terminal displays notifications and suggestions from the server to employees and provides an interface for users to improve their work environment based on this information. Users are encouraged to review the advice through the terminal and act according to the instructions.

[0742] For example, if the server analyzes an employee's weekly working hours to determine that their stress level is high based on emotional data, a notification will be sent to the administrator stating, "User A's stress level is higher than normal; it is recommended to reduce their workload." Simultaneously, the user will receive a specific suggestion, such as, "It is recommended that you take a break of 30 minutes or more each day to reduce stress."

[0743] An example of a prompt would be, "Explain how to use employee time management and emotional data to detect anomalies in work patterns and generate health management suggestions." This prompt supports the generation of appropriate suggestions by the generative AI model.

[0744] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0745] Step 1:

[0746] The server acquires employee time management information in real time. This input information includes clock-in and clock-out times, break times, and working hours. The server collects this data and stores it in a database. This storage process forms the basis for subsequent data analysis.

[0747] Step 2:

[0748] The server acquires data in real time from facial recognition cameras, voice analysis systems, and biosensors to collect emotional information. This emotional information includes facial expressions, voice tone, and heart rate. The server converts this data into an analyzable format and stores it in a database. This conversion process yields quantified emotional information.

[0749] Step 3:

[0750] The server integrates collected time management and emotional data and prepares a dataset for comparison with normal work patterns. This integration process creates a synthetic dataset for each employee, laying the foundation for detecting anomalies.

[0751] Step 4:

[0752] The server uses an analysis algorithm to detect anomalies in the integrated data. The input is the integrated dataset. The server compares this data with historical data to assess whether working hours are excessively long or whether stress levels are elevated. This analysis extracts cases suspected of high stress or excessive working hours.

[0753] Step 5:

[0754] If an anomaly is detected, the server will send a notification to the administrator and the relevant employee. This notification will be sent via email or messaging. The input information will include the analysis results indicating the anomaly and information about the employee. The notification will include specific issues and suggested countermeasures.

[0755] Step 6:

[0756] The server generates suggestions for improving health management and work-life balance based on past time management and emotional data. This suggestion generation uses the individual's historical data and analysis results as input. The server creates specific action plans and notifies employees and managers. This output constitutes the improvement measures provided.

[0757] Step 7:

[0758] The terminal displays notifications and suggestions received from the server to the user. During this display process, the user can adjust their actions based on the presented information. Specifically, the user uses the terminal to follow the suggestions and take concrete actions such as adjusting working hours or ensuring sufficient break time.

[0759] (Application Example 2)

[0760] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0761] In today's work environment, it is essential to appropriately monitor employees' work conditions and emotional states and provide timely interventions and corrective measures. However, many existing systems make decisions based solely on work data and do not adequately consider human factors such as emotional states. As a result, there is a challenge in detecting abnormalities in employees' health and stress levels early and taking prompt action.

[0762] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0763] In this invention, the server includes means for acquiring employee work information in real time, means for analyzing the work information to detect anomalies, means for immediately notifying the manager and the relevant employee when an anomaly is detected, and means for analyzing emotional states and providing stress reduction measures when an anomaly is detected. This enables comprehensive monitoring and the provision of improvement measures that take into account the emotional states of employees.

[0764] An "employee" is an individual who is employed by a company or organization and provides labor.

[0765] "Labor information" refers to data concerning an employee's working hours and work content, including start and end times of work and job duties.

[0766] "Computer usage history" refers to information that shows the operation records and application usage status of computers used by employees for their work.

[0767] "Emotional state" refers to data indicating the psychological and emotional health of employees, including information obtained through facial recognition and voice analysis.

[0768] "Stress reduction measures" refer to specific suggestions and methods provided to reduce employee stress and maintain a healthy work environment.

[0769] A "server" is a computer system that aggregates and analyzes data and generates notifications and suggestions.

[0770] A "manager" is an individual or position within a company or organization that is responsible for supervising the working conditions of employees and managing all aspects of operations.

[0771] The server, connected to the company's internal systems, collects employee work information and computer usage history in real time and stores it in a database. Based on this information, the server detects deviations from normal work patterns and analyzes anomalies using specific algorithms. Furthermore, it incorporates emotion detection technologies such as facial recognition, voice analysis, and biosensors to analyze emotional states and evaluate workers' stress levels.

[0772] If an anomaly is detected, the server will immediately notify administrators and the affected employees. This notification will use digital messaging or a communication function to immediately provide stakeholders with improvement suggestions, including stress reduction measures. For example, if the server detects data indicating high stress, administrators will receive a notification stating that "a reassessment of the workload for the affected employee is necessary," and employees will be provided with specific advice such as "we recommend taking deep breaths or short breaks."

[0773] This system facilitates comprehensive monitoring and the suggestion of improvement measures that take emotional states into account, contributing to employee health maintenance and productivity improvement. Data obtained through emotion detection is used to generate more precise suggestions for improving work-life balance. Furthermore, a generative AI model can be used to automatically generate appropriate suggestions based on the situation.

[0774] As a concrete example, here is an example of a prompt message to be input to a generating AI model: "Create suggestions to reduce security risks based on employee emotional data and attendance data." Based on this prompt, the AI ​​analyzes the workers' health status and emotional data and presents appropriate improvement measures based on the results.

[0775] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0776] Step 1:

[0777] The server retrieves work information and computer usage history from employees in real time. This input data includes employee start and end times, and logs of applications used. The server stores this data in a database and prepares it for subsequent analysis steps.

[0778] Step 2:

[0779] The server analyzes the acquired work information and computer usage history to detect deviations from normal work patterns. At this stage, specific algorithms are used to process the data and identify anomalies. The output is a list of detected anomalies, indicating which data is abnormal.

[0780] Step 3:

[0781] The server analyzes the emotional state of employees using emotion detection technology. Input data includes stress levels from biosensors, facial recognition, and voice analysis data. The server integrates this data to evaluate the employee's stress level. The output is an emotional state report.

[0782] Step 4:

[0783] The server sends notifications to administrators and relevant employees when it detects an anomaly. Inputs include a list of anomalies and a mood status report. Based on this information, the server sends necessary notifications using digital messaging or a contact function. Outputs are notification messages to administrators and employees.

[0784] Step 5:

[0785] The server uses a generative AI model to automatically generate improvement suggestions that take into account work information and emotional states. The input consists of historical work data and emotional data. The server inputs prompts into the generative AI model, which then generates appropriate suggestions. This output is the improvement suggestion provided to the employee.

[0786] Step 6:

[0787] The terminal displays notifications and improvement suggestions received from the server to employees, prompting them to take action. Input consists of notification messages and improvement suggestions from the server. The terminal presents information in a user-friendly interface, making it easy for employees to understand and act upon. Output consists of specific action suggestions for employees.

[0788] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0789] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0790] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0791] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0792] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0793] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0794] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0795] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0796] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0797] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0798] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0799] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0800] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0801] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0802] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0803] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0804] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0805] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0806] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0807] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0808] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0809] The following is further disclosed regarding the embodiments described above.

[0810] (Claim 1)

[0811] A means of acquiring employee work data in real time,

[0812] A means of analyzing labor data to detect anomalies,

[0813] A means of immediately notifying the manager and the relevant worker if an abnormality is detected,

[0814] A means of analyzing computer usage records to check for errors in work input,

[0815] Means for sending notifications and reminders,

[0816] A means of generating suggestions for improving the balance between health management and work life,

[0817] A system that includes this.

[0818] (Claim 2)

[0819] The system according to claim 1, wherein the generated suggestions include health management advice based on past work data.

[0820] (Claim 3)

[0821] The system according to claim 1, wherein notifications are sent via email or messaging.

[0822] "Example 1"

[0823] (Claim 1)

[0824] A means of obtaining employee attendance information in real time,

[0825] A means for integrating and pre-processing acquired attendance information and computer usage history,

[0826] A means of analyzing abnormal events that deviate from normal work patterns using artificial intelligence technology,

[0827] A means of immediately issuing a warning to the supervisor and the relevant worker when an abnormal event is detected,

[0828] A means of sending notifications and reminders using message communication technology,

[0829] A means of generating health management and work-life balance suggestions based on the analysis of past attendance information and work history,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, wherein the generated suggestions include health management recommendations based on past attendance information and work patterns.

[0833] (Claim 3)

[0834] The system according to claim 1, wherein a warning is sent using electronic communication technology.

[0835] "Application Example 1"

[0836] (Claim 1)

[0837] A means of acquiring worker activity data in real time,

[0838] A means of analyzing activity data to detect anomalies,

[0839] A means of immediately notifying administrators and relevant personnel when an anomaly is detected,

[0840] A means of analyzing machine usage records to identify deficiencies in activity input,

[0841] Means for sending notifications and reminders,

[0842] A means of generating suggestions for improving the balance between health management and active lifestyle,

[0843] A means of providing health-promoting feedback to participants through a visual display,

[0844] A means of monitoring physical condition using sensors and comprehensively analyzing it with activity data,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, wherein the generated suggestions include health management advice based on past activity data.

[0848] (Claim 3)

[0849] The system according to claim 1, wherein notifications are transmitted using an electronic communication function or a messaging function.

[0850] "Example 2 of combining an emotion engine"

[0851] (Claim 1)

[0852] A means of obtaining employee time management information in real time,

[0853] A means of integrating and analyzing time management information to detect anomalies,

[0854] A means of immediately notifying administrators and relevant employees when an anomaly is detected,

[0855] A means of identifying deficiencies in work activities by analyzing computer usage records,

[0856] Methods for acquiring emotional information using facial recognition, voice analysis, and biosensors,

[0857] A method for evaluating stress levels using emotional information,

[0858] A means of generating suggestions for improving lifestyle based on acquired information,

[0859] Means for sending suggestions to administrators and employees,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, wherein the generated suggestions include health management advice based on past time management information and emotional information.

[0863] (Claim 3)

[0864] The system according to claim 1, wherein notifications are transmitted using electronic communication functions.

[0865] "Application example 2 when combining with an emotional engine"

[0866] (Claim 1)

[0867] A means of obtaining employee work information in real time,

[0868] A means of analyzing labor information to detect anomalies,

[0869] A means of immediately notifying the manager and the relevant worker if an abnormality is detected,

[0870] A means of analyzing computer usage history to check for errors in work data entry,

[0871] Means for sending notifications and reminders,

[0872] A means of generating suggestions for improving the balance between health management and work life,

[0873] A means of analyzing emotional states and providing stress reduction measures when abnormalities are detected,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, wherein the generated suggestions include health management guidance based on past work information.

[0877] (Claim 3)

[0878] The system according to claim 1, wherein notifications are sent using digital messages or a contact function. [Explanation of Symbols]

[0879] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of acquiring worker activity data in real time, A means of analyzing activity data to detect anomalies, A means of immediately notifying administrators and relevant personnel when an anomaly is detected, A means of analyzing machine usage records to identify deficiencies in activity input, Means for sending notifications and reminders, A means of generating suggestions for improving the balance between health management and active lifestyle, A means of providing health-promoting feedback to participants through a visual display, A means of monitoring physical condition using sensors and comprehensively analyzing it with activity data, A system that includes this.

2. The system according to claim 1, wherein the generated suggestions include health management advice based on past activity data.

3. The system according to claim 1, wherein notifications are transmitted using an electronic communication function or a messaging function.

Images