System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting the number of mail transmission / reception, the number of outgoing / incoming calls, and the number of conference participations in a calendar from a terminal for business use, a means for encrypting the collected data and transmitting the encrypted data to a server, a means for calculating a work load and a stress degree of each employee by decrypting and analyzing the data on the server side, a means for calculating a condition score on the basis of an analysis result, and a means for providing the condition score in a report format to an appropriate manager or mentor.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Managing the mental and physical health of employees is extremely important in terms of improving productivity across the company and preventing employee turnover. However, conventional methods lack the means to objectively evaluate employees' workloads and stress levels, making it difficult to intervene at the appropriate time. In addition, excessive tracking of personal information can easily violate privacy, and obtaining employee consent can be difficult. Therefore, there is a need for a system that utilizes daily work data to non-invasively and accurately assess employee condition. [Means for solving the problem]

[0005] This invention provides a system that analyzes daily work data collected from business terminals, such as the number of emails sent and received, the number of calls made and received, and the number of meetings attended on a calendar, to assess employees' workload and stress levels. Specifically, the system includes a means for collecting data from business terminals, a means for encrypting the data and sending it to a server, a means for decrypting and analyzing the data on the server, and a means for calculating a condition score based on the analysis results. With the employee's consent, the system also analyzes data on sleep time and exercise volume from wearable devices to improve the accuracy of the assessment. It also includes a means for providing reports based on the condition score to managers and mentors to encourage appropriate support. Furthermore, the system provides employees with feedback via a portal site or application to support self-management. This enables non-invasive and effective management of employees' mental and physical health, contributing to improved productivity and reduced employee turnover across the company.

[0006] "Business devices" is a general term for electronic devices such as PCs, smartphones, and tablets used by employees for work.

[0007] "Number of emails sent and received" refers to the number of emails sent and received via business terminals.

[0008] "Number of outgoing and incoming calls" refers to the number of outgoing and incoming calls made on business terminals.

[0009] "Number of meetings attended in a calendar" refers to the number of meetings attended that are registered in a calendar application.

[0010] "Encryption" refers to the process of using specific algorithms to conceal data and convert it into a form that cannot be deciphered by third parties.

[0011] "Server" refers to a computer system that has functions such as receiving, storing, analyzing, and distributing data over a network.

[0012] "Decryption" refers to the process of returning encrypted data to its original form so that it can be read.

[0013] "Analysis" refers to the act of evaluating and calculating collected data using statistical and algorithmic methods.

[0014] "Workload" is a measure of the amount and frequency of an employee's work activities over a specific period of time.

[0015] "Stress level" is an indicator that shows the degree of psychological stress that employees feel in their work.

[0016] A "condition score" is a numerical value or evaluation that comprehensively evaluates an employee's workload and stress level based on the analysis results.

[0017] A "report" is a document that summarizes the analysis results and condition scores.

[0018] "Managerial position" refers to a person in charge of supervising and managing the work activities of employees.

[0019] A "mentor" is someone who has the role of guiding and supporting employees.

[0020] "Wearable devices" refers to devices worn by employees, such as smartwatches and fitness trackers.

[0021] "Sleep time" refers to the amount of time a user sleeps measured by a wearable device.

[0022] "Amount of exercise" refers to the amount of physical activity of the user measured by a wearable device, such as the number of steps taken or calories burned.

[0023] A "portal site" is a website through which employees can access information and services provided by the system.

[0024] "Feedback" refers to advice and guidance provided to employees based on condition scores, analysis results, etc. [Brief explanation of the drawings]

[0025] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0026] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0027] First, the terms used in the following description will be explained.

[0028] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0029] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0030] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0031] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0032] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0036] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0037] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0038] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0039] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0040] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0043] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0044] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0045] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0046] This invention is a system that assesses the condition of employees by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, etc. This system allows managers and mentors to effectively manage the health of their employees.

[0047] Program processing

[0048] Data collection

[0049] The device collects data from work email clients, phone applications, and calendar applications. It obtains the number of work emails sent and received, the number of calls made and received, and the number of meetings registered in the calendar via API. Additionally, if the employee consents, the device also obtains data on sleep time and exercise volume from wearable devices (e.g., smartwatches).

[0050] Data Encryption and Transmission

[0051] The device conceals the collected data using an encryption library and transmits it securely to the server via the HTTPS protocol.

[0052] Data Reception and Decryption

[0053] The server receives the data sent from the terminal. Since the received data is encrypted, it is decrypted using a decryption library on the server side to restore it to its original format.

[0054] Data analysis

[0055] The server evaluates the employee's workload, activity level, and stress level based on the decoded data. The analysis uses an AI algorithm to comprehensively assess the number of emails sent and received, the number of calls made and received, the number of meetings attended, and wearable data. Appropriate weighting is applied to each data indicator to calculate the overall workload and stress level.

[0056] Calculating the Condition Score

[0057] The server calculates each employee's condition score based on the analysis results. The condition score is a comprehensive assessment of each employee's workload and stress level, and is classified into categories such as "high workload," "medium workload," and "low workload" based on certain thresholds.

[0058] Report generation and delivery

[0059] The server compiles each employee's condition score into a report, which includes detailed analysis results and specific indicators. The generated report is saved in a database and provided to managers and mentors. Managers and mentors are also notified of the report's creation via a notification function.

[0060] Providing feedback

[0061] The server provides employees with feedback based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[0062] Specific examples

[0063] In the case of Mr. A

[0064] The device collects data on the number of emails sent and received (50), the number of calls made and received (10), and the number of meetings attended (5) during Mr. A's daily work. With Mr. A's consent, the device also collects the amount of sleep (6 hours) and exercise (5,000 steps) per day from the wearable device (smartwatch).

[0065] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses an AI algorithm to analyze Mr. A's condition. For example, it can be determined that he sends and receives many emails and attends many meetings, but that he continues to suffer from a lack of sleep.

[0066] The server calculates Person A's condition score based on the analysis results and classifies him / her as "high stress." The server then compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors then review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself / herself via the portal site, which helps support self-management.

[0067] The processing flow will be explained below.

[0068] Program processing steps

[0069] Step 1: Collect business data

[0070] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[0071] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[0072] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[0073] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[0074] Step 2: Collecting wearable device data

[0075] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[0076] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[0077] Step 3: Encrypt the data

[0078] The terminal encrypts the collected business data and wearable data using an encryption library.

[0079] Encryption library: Encrypts data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, the amount of sleep, and the amount of exercise, and stores the encrypted data in a local database.

[0080] Step 4: Sending data

[0081] The terminal sends the encrypted data to the server using the HTTPS protocol.

[0082] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[0083] Step 5: Receive and decrypt the data

[0084] The server receives the data sent from the terminal.

[0085] HTTP request: Temporarily store received data.

[0086] The server decrypts the received data.

[0087] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[0088] Step 6: Data analysis

[0089] The server analyzes the decrypted data.

[0090] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, and amount of exercise to evaluate employees' workload, activity level, and stress level.

[0091] Step 7: Calculating the Condition Score

[0092] The server calculates each employee's condition score based on the analysis results.

[0093] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[0094] Step 8: Generate and deliver reports

[0095] The server compiles each employee's condition score and analysis results into a report.

[0096] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[0097] The server provides the generated reports to managers and mentors.

[0098] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[0099] Step 9: Provide feedback

[0100] The server provides feedback to each employee.

[0101] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] In today's corporate environment, appropriately managing employees' workloads and stress levels and protecting their health are important issues. However, current methods make it difficult to collect and analyze individual work data, making it difficult to accurately assess their condition. Furthermore, there is no established method for integrating and analyzing data from wearable devices with work data. As a result, efficient health management and feedback for employees are currently not being provided.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes means for collecting the number of emails sent and received, the number of communications, and the number of meetings attended in the schedule management system from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side to calculate the workload and stress level of each employee, means for calculating a condition score based on the analysis results, means for compiling the condition score in report format and providing it to an appropriate manager or educational instructor, and means for using a generative artificial intelligence model to analyze the data. This enables integrated analysis of employee work data and individual health data, enabling accurate condition evaluation and effective feedback.

[0107] A "business terminal" is a computer or electronic device used to carry out business within a company or organization.

[0108] "Emails Sent and Received" means the total number of emails received and sent within a specified period of time.

[0109] "Number of communications" means the number of calls made using communication means such as telephone or voice chat.

[0110] A "schedule management system" is software or an electronic system for managing meeting schedules and task schedules.

[0111] "Number of meetings attended" means the total number of meetings attended within a specific period.

[0112] "Encryption" is a technique for converting data into a format that cannot be easily deciphered by third parties.

[0113] A "server" is a computer system that provides data and services to other computers and devices over a network.

[0114] "Decryption" is the technique of returning encrypted data to its original form.

[0115] "Analysis" is the process of analyzing data in detail and extracting specific information.

[0116] "Workload" refers to the total amount of work, difficulty, and time spent by an employee.

[0117] "Stress level" refers to the degree of mental and physical strain felt by employees.

[0118] A "condition score" is a score or index that comprehensively evaluates an employee's workload and stress level.

[0119] A "report" is a document or data that summarizes analysis results and evaluations using text and graphs.

[0120] A "manager" is a person in a company or organization who is responsible for managing the work and health of employees.

[0121] An "educational instructor" is a person who is responsible for improving the skills and providing guidance to employees.

[0122] "Generative artificial intelligence model" is a general term for algorithms or models designed to perform specific tasks using machine learning and deep learning techniques.

[0123] A "wearable device" is an electronic device worn on the body. Examples include smartwatches and fitness bands.

[0124] "Rest time" refers to the time spent sleeping or resting during the day.

[0125] "Physical activity" refers to the total amount of physical activity, such as exercise and movement, that occurs in a day.

[0126] A "portal site" is a website that provides information and services to specific users.

[0127] An "application" is a software program designed to accomplish a particular purpose.

[0128] This invention is a system that collects and analyzes data from employees' daily work to evaluate their workload and stress levels, and supports their health management. This system is primarily composed of business terminals, a server, and wearable devices used by users.

[0129] First, the device collects the following data from the business email client (e.g., Microsoft® Outlook), phone application (e.g., Skype for Business), and calendar application (e.g., Google® Calendar):

[0130] Number of emails sent and received

[0131] Number of communications

[0132] Number of meetings attended in the schedule management system

[0133] Additionally, if the user consents, the device will collect rest time and physical activity data from wearable devices (e.g., Fitbit, Apple Watch).

[0134] The collected data is encrypted by the device using an encryption library (e.g., OpenSSL) and sent to the server via the HTTPS protocol. The server then decrypts the received encrypted data to its original form using a decryption library.

[0135] The server then uses the decoded data to analyze each employee's workload and stress level. The analysis uses a generative artificial intelligence model (e.g., TENSORFLOW®) and comprehensively evaluates the following factors:

[0136] Number of emails sent and received

[0137] Number of communications

[0138] Number of meetings attended

[0139] Wearable data (rest time, physical activity)

[0140] Each data indicator is weighted appropriately to produce a condition score, which is then categorized into "high stress," "medium stress," and "low stress."

[0141] The server compiles the condition scores for each employee based on the analysis results in the form of a report. The report contains details of the analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational instructors. Administrators and educational instructors are notified of the generation of the report via a notification function.

[0142] The server also provides feedback to employees based on their condition scores. This feedback is sent to employees via a portal site or dedicated application, and includes information that helps support self-management and improvement.

[0143] Specific examples

[0144] For example, in the case of Person A, the device will collect data on the number of emails sent and received (50), the number of communications (10), and the number of meetings attended (5) in Person A's daily work. In addition, with Person A's consent, the device will also obtain the amount of rest time (6 hours) and the amount of physical activity (5,000 steps) from the wearable device.

[0145] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses a generative AI model to analyze Person A's condition. For example, it can be determined that although he sends and receives many emails and attends many meetings, he continues to lack rest.

[0146] Based on the analysis results, the server classifies Person A's condition score as "high stress." The analysis results are compiled in a report and provided to administrators and educational instructors. The administrators and educational instructors review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself through the portal site, which helps support his self-management.

[0147] Example prompts for generative AI models

[0148] prompt:

[0149] Calculate your condition score based on the employee data below.

[0150] data:

[0151] Number of emails sent and received: 50

[0152] Number of communications: 10

[0153] Number of meetings attended: 5

[0154] Rest time: 6 hours

[0155] Physical activity: 5,000 steps

[0156] An example of the output produced:

[0157] Condition Score: High Load

[0158] Details: The workload was assessed as high due to the high volume of emails sent and received and the high number of meetings attended, as well as the continued lack of rest.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1: Collect data

[0161] The device collects data from the user's daily work. Specifically, data on the number of emails sent and received from the business email client, the number of communications from the phone application, and the number of meetings attended from the calendar application are input. In addition, if the user consents, data on rest time and physical activity levels are also collected from the wearable device. This data is obtained using an API and stored in the device's local storage.

[0162] Input: Number of emails sent and received, number of communications, number of meetings attended, rest time, amount of physical activity

[0163] Output: Collected data (stored in local storage)

[0164] Specific operation: The device makes the following API request:

[0165] GET / api / mail / received?user_id=A

[0166] GET / api / calendar / meetings?user_id=A

[0167] GET / api / phone / calls?user_id=A

[0168] GET / api / wearable / data?user_id=A

[0169] Step 2: Encrypt the data and send it to the server

[0170] The device encrypts the collected data using an encryption library (e.g., OpenSSL), and the encrypted data is sent to the server via the HTTPS protocol to ensure security.

[0171] Input: Collected data

[0172] Output: Encrypted data (sent to server)

[0173] Specific operation: Encrypts the data in JSON format and sends a POST request to the server.

[0174] POST / api / data

[0175] Content-Type: application / json

[0176] {

[0177] "user_id": "A",

[0178] "data": "encryptedData"

[0179] }

[0180] Step 3: Receive and decrypt the data

[0181] The server receives the encrypted data sent from the device, and uses a decryption library to restore the data to its original format.

[0182] Input: Encrypted data

[0183] Output: Decrypted data

[0184] What happens: The server uses an encryption library to decrypt the data.

[0185] encryptedData = request.body.data;

[0186] rawData = OpenSSL::Decrypt(encryptedData);

[0187] Step 4: Analyze the data

[0188] The server uses the decoded data it receives to analyze each employee's workload and stress level. A generative AI model (e.g., TensorFlow) is used for the analysis, and a comprehensive evaluation is made of the number of emails sent and received, the number of communications, the number of meetings attended, and wearable data. An appropriate weighting is then assigned to each data indicator to calculate an overall condition score.

[0189] Input: Decrypted data

[0190] Output: Analysis results (work load and stress level, condition score)

[0191] What it does: It uses an AI model to analyze data and predict scores.

[0192] model = tf.keras.models.load_model('condition_model.h5')

[0193] data = {"emails": rawData["emails"], "calls": rawData["calls"], "meetings": rawData["meetings"], "sleep": rawData["sleep"], "steps": rawData["steps"]}

[0194] condition_score = model.predict(data)

[0195] Step 5: Calculating the Condition Score

[0196] Based on the results of the AI ​​algorithm analysis, the server calculates a condition score for each employee, which is categorized into "high load," "medium load," and "low load."

[0197] Input: Analysis results

[0198] Output: Condition Score

[0199] Specific Behavior: Evaluate condition scores and categorize them.

[0200] thresholds = {"low": 0.3, "medium": 0.7, "high": 1.0}

[0201] condition_value = condition_score[0]

[0202] if condition_value < thresholds["low"]:

[0203] condition_category = "Low load"

[0204] elif condition_value < thresholds["medium"]:

[0205] condition_category = "Medium load"

[0206] else:

[0207] condition_category = "High load"

[0208] Step 6: Generate and deliver reports

[0209] The server generates a report based on the calculated condition score. The report contains detailed analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational leaders. Administrators and educational leaders are notified of the generation of the report via a notification function.

[0210] Input: Condition score, analysis results

[0211] Output: Report (Saved to database, Notification)

[0212] Specific actions: Generate a report, save it in a database, and notify the administrator.

[0213] report = {

[0214] "user_id": "A",

[0215] "condition_score": condition_category,

[0216] "details": rawData,

[0217] "analysis_time": datetime.now()

[0218] }

[0219] db.save(report)

[0220] notification.send("Report generated", user_id="A")

[0221] Step 7: Provide feedback

[0222] The server provides feedback to employees based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[0223] Input: Condition Score

[0224] Output: Feedback (notification)

[0225] Specific behavior: Generate feedback and communicate it through portals and applications.

[0226] feedback = f"{condition_category}:Due to the increased workload recently, we recommend that you take a proper rest."

[0227] notification.send(feedback, user_id="A")

[0228] (Application example 1)

[0229] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0230] In recent years, there has been growing emphasis on managing the health and workload of factory workers, but conventional systems only collect and analyze data from office work, making it difficult to accurately grasp the condition of factory workers. For this reason, there is a need for a new system that can detect worker fatigue and stress early and provide appropriate feedback.

[0231] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0232] In this invention, the server includes: means for collecting the number of emails sent and received, the number of outgoing and incoming calls, and the number of calendar meetings attended from business terminals; means for encrypting the collected data and sending it to the server; means for decrypting and analyzing the data on the server side to calculate each employee's workload and stress level; means for calculating a condition score based on the analysis results; means for compiling the condition score in report format and providing it to an appropriate manager or mentor; means for collecting the body temperature, heart rate, and work log of factory workers using smart glasses, encrypting the data in the same way, and sending it to the server; and means for evaluating the fatigue and stress levels of factory workers based on the collected data and providing breaks and feedback at appropriate times. This allows for real-time monitoring of the health status of factory workers, improving work efficiency, and ensuring safety.

[0233] A "business terminal" is an information processing device such as a computer used by a company or organization.

[0234] "Number of emails sent and received" is the total number of emails sent and received during a certain period of time.

[0235] "Number of calls made and received" refers to the total number of calls made and received via telephone or communication apps over a certain period of time.

[0236] "Number of meetings attended in calendar" refers to the number of times a person has attended a conference or meeting registered in an electronic calendar.

[0237] A "collection means" is a method or device used to obtain and store particular data.

[0238] An "encryption means" is a method or device that converts data from a readable form to an obfuscated form in order to protect it.

[0239] A "server" is a computer system that stores data and provides services to other computers and devices over a network.

[0240] A "decryption means" is a method or device that returns encrypted data to its original, readable form.

[0241] An "analyzing means" is a method or device for processing collected data and extracting meaningful information.

[0242] "Workload" refers to the amount of tasks or work that an employee handles as part of their job during a specific period of time.

[0243] "Stress level" refers to the degree of mental and physical stress felt by employees over a specific period of time.

[0244] A "condition score" is a numerical indicator that represents an employee's health status and workload.

[0245] A "report format" is a document format that summarizes collected and analyzed information in an easy-to-understand format.

[0246] A "management position" is a person in a position responsible for management or leadership within an organization.

[0247] A "mentor" is someone whose role is to provide guidance and advice on specific knowledge and skills.

[0248] "Smart glasses" are a wearable device in the form of glasses that displays visual information on a screen and can be connected to a computer or network.

[0249] "Body temperature" is an indicator of the worker's body temperature.

[0250] "Heart rate" is the number of times the heart beats within a certain period of time.

[0251] A "work log" is a detailed record of the work performed by a worker.

[0252] "Fatigue level" refers to the degree of physical and mental fatigue felt during work.

[0253] "Real-time" means that information is updated and processed almost immediately.

[0254] The present invention is a system for monitoring the health and workload of factory workers in real time and providing appropriate feedback. The system includes a business terminal, smart glasses, a wearable device, and a server.

[0255] Data collection

[0256] The business devices collect business data such as the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. In addition, smart glasses are used to collect the factory workers' body temperature, heart rate, and work logs. This data is encrypted immediately upon collection. The encryption uses the OpenSSL library to protect the data.

[0257] Data Encryption and Transmission

[0258] The data is encrypted and then securely transmitted to the server using the HTTPS protocol, using the standard SSL / TLS protocol to ensure secure communication.

[0259] Data Reception and Decryption

[0260] The server then decrypts the received data using the PyCrypto library, which returns the data to its original, readable form for analysis.

[0261] Data analysis

[0262] The server calculates the workload and stress level of workers based on the decoded data. The analysis uses TensorFlow and PyTorch and utilizes a generative AI model. Specifically, the server comprehensively analyzes the number of emails sent and received, the number of meetings attended, body temperature, heart rate, and work logs, and assigns appropriate weights to the data indicators.

[0263] Calculating condition scores and providing feedback

[0264] Based on the analysis results, a condition score is calculated for each employee. The condition score is a comprehensive assessment of the employee's workload and stress level. This score is provided to the worker in real time via the smart glasses' built-in display. The analysis results are then compiled into a report and provided to managers and mentors.

[0265] Specific examples

[0266] For example, suppose a factory worker has a body temperature of 37.2°C, a heart rate of 85 bpm, and has not taken a break in the past hour. Based on this data, the system determines that the worker is highly fatigued and displays an alert on the smart glasses display urging the worker to take a break. The system also notifies managers that the worker's condition score is "high strain."

[0267] Prompt Sentence Examples

[0268] "Collect daily work data (body temperature, heart rate, break times) from factory workers and create an AI model that evaluates their condition from the analysis results. Design an application that provides feedback and alerts based on the condition score."

[0269] This will not only enable factory workers to properly manage their health, but also enable managers and mentors to understand the health of workers and provide appropriate support. By using this system, it will be possible to improve work efficiency and safety.

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1:

[0272] The business device collects the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee. This data is obtained using the business device's API. The input data is employee activity information, and the output is business data before encryption. Specifically, this includes operations that make API calls from email clients, phone apps, and calendar apps.

[0273] Step 2:

[0274] The terminal encrypts the data collected in step 1 using the OpenSSL library. The input data is the business data described above, and the output data is the encrypted business data. Specifically, this includes the operation of performing encryption processing using AES encryption.

[0275] Step 3:

[0276] The terminal sends encrypted data to the server using the HTTPS protocol. The input data is encrypted business data, and the output is the data sent to the server. Specifically, this includes the operation of creating and sending an HTTPS request.

[0277] Step 4:

[0278] The server decrypts the data sent from the terminal using the PyCrypto library. The input data is encrypted business data, and the output is decrypted business data. Specifically, it includes the operation of performing decryption processing using AES decryption.

[0279] Step 5:

[0280] The server inputs the decoded data into a generative AI model using TensorFlow or PyTorch to analyze workload and stress levels. The input data is the decoded workload data, and the output is the evaluation results of workload and stress levels. Specifically, this includes the operation of performing data analysis processing using the AI ​​model.

[0281] Step 6:

[0282] The server calculates a condition score for each employee based on the analysis results. The input data are the evaluation results of workload and stress level, and the output is a condition score for each employee. Specifically, it includes operations for weighting and score calculation based on the evaluation results.

[0283] Step 7:

[0284] The server compiles the condition scores into a report and provides it to the appropriate manager or mentor. The input data is the condition score, and the output is a report that is delivered to the manager or mentor. Specifically, it uses a report generation algorithm and includes operations such as email and dashboard notifications.

[0285] Step 8:

[0286] The smart glasses collect the body temperature, heart rate, and work logs (such as working hours and break times) of factory workers. This data is acquired using the smart glasses' sensors and API. The input data is sensor information, and the output is work data before encryption. Specifically, this includes operations that utilize the body temperature sensor, heart rate sensor, and work log recording function.

[0287] Step 9:

[0288] The smart glasses encrypt the collected data using the OpenSSL library and send it to the server. The input data is sensor information, and the output is encrypted working data. Specifically, the glasses perform operations including encryption using AES encryption and sending HTTPS requests.

[0289] Step 10:

[0290] The server decrypts the data sent from the smart glasses and analyzes the condition of the factory workers. The input data is encrypted work data, and the output is the worker condition evaluation results. Specifically, the server performs operations such as decryption processing and evaluation processing using a data analysis model.

[0291] Step 11:

[0292] The smart glasses display break and feedback alerts to workers in real time. The input data is the condition assessment results from the server, and the output is the alerts displayed on the smart glasses display. Specifically, it includes the operation of displaying feedback messages on the display.

[0293] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0294] This invention is a system that accurately assesses an employee's condition by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, and combining it with user emotional data, allowing managers and mentors to effectively monitor and support the health of their employees.

[0295] Program processing

[0296] Data collection

[0297] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of meetings attended from the email client, phone application, and calendar application installed on the work device. If the employee consents, the device also collects data on sleep time and exercise volume from wearable devices (e.g., smartwatches). Furthermore, the device uses an emotion engine to analyze the user's emotional state from their voice data and facial expression data.

[0298] Data Encryption and Transmission

[0299] The device encrypts the collected business data, wearable data, and emotion data and transmits them securely to the server using an encryption library and the HTTPS protocol.

[0300] Data Reception and Decryption

[0301] The server receives the data sent from the device, decrypts the encrypted data, and stores it in a database, ready for analysis.

[0302] Data analysis

[0303] The server analyzes the decrypted data, integrating data such as the number of emails sent and received, the number of meetings attended, sleep time, exercise level, and emotional data. An AI algorithm is used for the analysis, weighting each data indicator appropriately to assess the employee's workload and stress level.

[0304] Calculating the Condition Score

[0305] The server calculates a condition score for each employee based on the analysis results. By combining this with emotional data, stress levels can be corrected to provide a more accurate condition score. Scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[0306] Report generation and delivery

[0307] The server compiles each employee's condition score and analysis results into a report. The generated report is saved in a database and notified to managers and mentors. A notification function also encourages employees to check the report.

[0308] Providing feedback

[0309] The server provides feedback to each employee, who is then notified of the feedback via a portal site or dedicated application, providing support for self-management and improvement.

[0310] Specific examples

[0311] In the case of person B

[0312] The device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during B's daily work. With B's consent, the device also collects the amount of sleep (7 hours) and exercise (6,000 steps) per day from the wearable device (smartwatch).

[0313] In addition, the device uses an emotion engine to analyze B's voice and facial expression data to determine his / her stress level. For example, it may detect that B is under high stress based on his / her voice tone and facial expression.

[0314] The device encrypts all collected data and sends it to the server. The server decrypts the data and analyzes Mr. B's condition using an AI algorithm. Based on the analysis results, Mr. B's condition score is classified as "medium load."

[0315] The server compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors review the report and provide appropriate support and feedback to Person B. Feedback is also provided to Person B himself via the portal site, which helps support his self-management.

[0316] The processing flow will be explained below.

[0317] MODE FOR CARRYING OUT THE INVENTION

[0318] This invention is a system that collects and analyzes work data, wearable data, and emotional data to assess an employee's condition, allowing managers and mentors to gain a detailed understanding of their employees' health status and provide appropriate support.

[0319] Program processing steps

[0320] Step 1: Collect business data

[0321] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[0322] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[0323] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[0324] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[0325] Step 2: Collecting wearable device data

[0326] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[0327] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[0328] Step 3: Collecting emotion data

[0329] The device uses an emotion engine to analyze the user's voice data and facial expression data to determine the user's stress level and emotional state.

[0330] Emotion Engine: Using voice recordings and camera data, it analyzes changes in voice tone and facial expressions to generate emotion data, which is then stored in a local database.

[0331] Step 4: Encrypt the data

[0332] The device encrypts the collected business data, wearable data, and emotion data using an encryption library.

[0333] Encryption library: Encrypts data such as the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, exercise amount, and emotional data, and stores the encrypted data in a local database.

[0334] Step 5: Sending data

[0335] The terminal sends the encrypted data to the server using the HTTPS protocol.

[0336] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[0337] Step 6: Receive and decrypt data

[0338] The server receives the data sent from the terminal.

[0339] HTTP request: Temporarily store received data.

[0340] The server decrypts the received data.

[0341] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[0342] Step 7: Data analysis

[0343] The server analyzes the decrypted data.

[0344] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, amount of exercise, and emotional data to evaluate employees' workload, activity level, and stress level.

[0345] Analysis results: Based on the analysis results, the workload and stress level of each employee are evaluated and expressed as a numerical value.

[0346] Step 8: Calculating the Condition Score

[0347] The server calculates each employee's condition score based on the analysis results.

[0348] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[0349] Step 9: Generate and deliver reports

[0350] The server compiles each employee's condition score and analysis results into a report.

[0351] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[0352] The server provides the generated reports to managers and mentors.

[0353] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[0354] Step 10: Provide feedback

[0355] The server provides feedback to each employee.

[0356] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[0357] Example 2

[0358] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0359] In today's corporate environment, it is important to accurately understand employees' workloads and stress levels and provide appropriate support. However, conventional systems only collect operational data such as the number of emails sent and received, phone calls made and received, and number of meetings attended, which is not enough to accurately assess an employee's condition. Furthermore, relying solely on numerical data makes it difficult to consider an employee's mental state or physical health. To solve this problem, a more diversified and comprehensive method of data collection and analysis is needed.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0361] In this invention, the server includes means for collecting the number of emails sent and received, the number of phone calls made and received, and the number of calendar meetings attended from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side, means for analyzing the emotional state of employees from their voice data and facial expression data, means for calculating the workload and stress level of each employee, means for calculating a condition score based on the analysis results, and means for compiling the condition score in report format and providing it to an appropriate manager or instructor. This allows for an integrated analysis of employee work data as well as emotional and physical data, enabling more accurate condition evaluations.

[0362] "Business terminals" are computers and smart devices used by employees within a company to carry out their work.

[0363] "Emails Sent and Received" means the total number of emails sent and received by an employee within a specified period of time.

[0364] "Number of calls made and received" is the total number of calls made and received by an employee during a specified period.

[0365] "Calendar Meeting Attendance" is the total number of meetings that an employee has registered to attend in scheduling software.

[0366] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is a means of ensuring security.

[0367] A "server" is a computer system that provides data or services to multiple clients over a network.

[0368] "Decryption" is the process of returning encrypted data to its original, readable form.

[0369] "Analysis" is the process of using collected data to extract and evaluate information for a specific purpose.

[0370] "Emotional state" is the result of judging an individual's mental state obtained through voice and facial expression data.

[0371] "Workload" is a measure of the amount of work and difficulty an employee feels when performing their job.

[0372] "Stress level" is a measure of the degree of psychological and physiological stress felt by an individual.

[0373] A "Condition Score" is a comprehensive score calculated to assess an employee's overall work situation and health.

[0374] A "report format" is a document format that visually organizes analysis results and presents them in an easy-to-understand manner.

[0375] A "manager" is someone who supervises and supports the work of employees within an organization.

[0376] A "leader" is someone whose role is to educate and support employees within an organization.

[0377] "Wearable devices" are small electronic devices and related technologies that can be worn by a user.

[0378] "Sleep time" is the total time an employee was asleep.

[0379] "Amount of exercise" is the cumulative amount of physical activity an employee engages in within a specific period of time.

[0380] This invention is a system that accurately assesses the condition of employees by collecting and analyzing data from various angles related to their daily work. The system analyzes data collected from business terminals on a server and provides useful information to managers and instructors, aiming to effectively monitor and support employees' health and stress levels.

[0381] Data collection

[0382] The device collects data from the email client, phone application, and calendar application installed on the work device. Specifically, it uses an API to obtain the number of emails sent and received, the number of phone calls made and received, and the number of meetings attended. If the employee consents, the device also collects data on sleep time and exercise volume from a wearable device (e.g., a smartwatch). Furthermore, an emotion engine is used to analyze the user's voice data and facial expression data to evaluate their emotional state. This makes it possible to collect data that can be used to comprehensively evaluate not only employees' work performance, but also their mental and health states.

[0383] Data Encryption and Transmission

[0384] The device encrypts the collected and analyzed data and transmits it to the server with a high level of security. The encryption is performed using the AES encryption library and the HTTPS protocol for data transmission, ensuring confidentiality and integrity of the data.

[0385] Data Reception and Decryption

[0386] The server receives the encrypted data sent from the device and decrypts it in a secure environment, where it is stored in a database until it is ready to be analyzed.

[0387] Data analysis

[0388] The server performs an integrated analysis of data collected from various data sources. First, it integrates business data (emails, phone calls, meeting participation), wearable data, and emotional data, and then analyzes them using an AI algorithm. The specific algorithm assigns appropriate weights to each data indicator to evaluate employees' workload and stress levels.

[0389] Calculating the Condition Score

[0390] Based on the analysis results, the server calculates a condition score for each employee. This score can be combined with emotional data to correct for stress levels, enabling more accurate assessments. Condition scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[0391] Report generation and delivery

[0392] The server compiles the analysis results and condition scores into a report. The generated report is saved in a database and notified to the appropriate administrator or instructor. Notifications are sent via email or the alert function on the portal site.

[0393] Providing feedback

[0394] Finally, the server provides feedback to each employee, which is then communicated to the employee via a portal site or dedicated application, and used as a guide for self-management and improvement.

[0395] Specific examples

[0396] For example, in the case of Person B, the device collects data on the number of emails sent and received (30), the number of phone calls made and received (15), and the number of meetings attended (3) in Person B's daily work. Furthermore, with Person B's consent, data on the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps) is also collected from the wearable device. Person B's voice data and facial expression data are analyzed using an emotion engine to determine their stress level. For example, it can detect that Person B is feeling increasingly stressed from their voice tone and facial expression.

[0397] The device encrypts all of this data and sends it to the server. The server decrypts the data and uses an AI algorithm to analyze Person B's condition. Based on the results of this analysis, Person B's condition score is classified as "medium load." The server compiles the analysis results into a report and provides it to the manager or coach. The manager or coach reviews the report and provides appropriate support and feedback to Person B. Person B also receives feedback via a portal site, which can be used to help with self-management.

[0398] Prompt Sentence Examples

[0399] "Please explain in detail the specific steps you take to collect data on Mr. B's daily work and analyze his condition."

[0400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0401] Program processing steps

[0402] Step 1: Start collecting data

[0403] The device accesses the email client, phone application, and calendar application on the business device according to a specific time schedule.

[0404] Input: Each application on the user's work computer.

[0405] Output: Raw data obtained from each application.

[0406] Specific operation:

[0407] The device calls the email client's API and collects the number of emails sent and received.

[0408] The device calls the API of the phone application and collects the number of calls made and received.

[0409] The device calls the calendar application API to collect the number of meetings attended.

[0410] Step 2: Wearable data collection

[0411] The device works in conjunction with a wearable device (e.g., a smartwatch) to obtain the user's sleep time and exercise volume.

[0412] Input: Sensor data from wearable devices.

[0413] Output: Data on sleep duration and exercise.

[0414] Specific operation:

[0415] The device retrieves the data via the wearable device's API and stores it locally.

[0416] Sleep duration is obtained from the wearable device's activity tracker, and exercise volume is obtained from the pedometer sensor.

[0417] Step 3: Sentiment Data Analysis

[0418] The device uses an emotion engine to analyze the user's voice data and facial expression data to evaluate their emotional state.

[0419] Input: User's voice and facial expression data.

[0420] Output: Parsed emotion data.

[0421] Specific operation:

[0422] The device uses a voice recognition engine to analyze voice tone and pitch.

[0423] Using a facial expression recognition engine, facial images acquired from a camera are analyzed to determine the emotional state.

[0424] Step 4: Data Encryption

[0425] The device encrypts all collected data and prepares it for transmission to the server.

[0426] Input: Each dataset collected and analyzed.

[0427] Output: Encrypted data bundle.

[0428] Specific operation:

[0429] The terminal uses the AES encryption library to encrypt the data set.

[0430] Create a batch to send encrypted data to the server via HTTPS protocol.

[0431] Step 5: Send data

[0432] The terminal transmits the encrypted data to the server.

[0433] Input: Encrypted data bundle.

[0434] Output: The data sent to the server.

[0435] Specific operation:

[0436] The device uses the HTTPS protocol to send encrypted data to the server.

[0437] A manual or automated submission process sends the data to an endpoint where the server can receive it.

[0438] Step 6: Data Reception and Decryption

[0439] The server receives and decrypts the data sent from the terminal.

[0440] Input: The received encrypted data.

[0441] Output: Decoded raw data.

[0442] Specific operation:

[0443] The server uses a secure endpoint to receive encrypted data.

[0444] The received data is decrypted to restore it to its original data format.

[0445] Step 7: Data integration and analysis

[0446] The server integrates and analyzes business data, wearable data, and emotional data.

[0447] Input: The decoded dataset.

[0448] Output: Analysis results.

[0449] Specific operation:

[0450] The server uses a data management system to integrate each dataset.

[0451] AI algorithms are applied to analyze data and evaluate workload and stress levels.

[0452] Step 8: Calculating the Condition Score

[0453] Based on the analysis results, the server calculates each employee's condition score.

[0454] Input: Analysis results.

[0455] Output: Condition score.

[0456] Specific operation:

[0457] The condition score is calculated based on an AI algorithm.

[0458] The calculation results are classified into specific score categories (high load, medium load, low load).

[0459] Step 9: Reporting and Notifications

[0460] The server compiles each employee's condition score and analysis data into a report format and provides it to managers and instructors.

[0461] Input: Condition score and analysis data.

[0462] Output: The generated report.

[0463] Specific operation:

[0464] The server organizes and structures the analysis results using report generation templates.

[0465] The completed reports are stored in a database and notifications are sent to managers and leaders through a notification system.

[0466] Step 10: Provide feedback

[0467] The server provides individual feedback to each employee.

[0468] Input: Condition score and analysis results.

[0469] Output: The feedback provided.

[0470] Specific operation:

[0471] The server automatically generates feedback content and notifies employees via a portal site or dedicated application.

[0472] Employees can refer to the feedback provided to help them self-manage and improve.

[0473] (Application example 2)

[0474] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0475] In many modern business situations, it is important to properly manage employee workload and stress. However, conventional systems assess employee health based solely on work data, making it difficult to accurately assess workload. Furthermore, systems lacked the mechanisms for combining emotional data and data from wearable devices, resulting in delayed or inaccurate feedback. This can lead to a deterioration in employee health and a drop in productivity.

[0476] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the number of emails sent and received, the number of calls made and received, and the number of meetings attended on the calendar from the business terminals, means for encrypting the collected data and sending it to the server, and means for decrypting and analyzing the data on the server side and calculating the workload and stress level of each employee. This enables detailed data collection and analysis.

[0477] Furthermore, the server includes means for collecting data on sleep duration and exercise volume from the smartphone and wearable device, analyzing voice and facial expressions using an emotion recognition engine, means for classifying condition scores into categories such as high, medium, and low stress based on the analysis results, and means for notifying managers and leaders of the analysis results through a notification function, thereby enabling real-time evaluation of the overall health status of employees and providing prompt feedback.

[0478] "Business terminals" are electronic devices such as computers and smartphones used in companies and organizations.

[0479] "Emails Sent and Received" means the total number of emails sent and received within a specified period of time.

[0480] "Number of outgoing and incoming calls" refers to the total number of outgoing and incoming voice calls made within a specific period of time.

[0481] "Calendar meeting attendance count" refers to the number of scheduled meetings attended within a specific period.

[0482] A "collection means" is a method or device for obtaining and recording data.

[0483] "Encryption" is the process of transforming data using a specific algorithm in order to secure it.

[0484] A "server" is a computer system that stores, manages, and analyzes data.

[0485] "Decryption" is the process of restoring encrypted data to its original state.

[0486] "Analysis" is the process of examining data in detail to derive useful information.

[0487] "Workload" refers to the amount of work an employee handles in a given period of time.

[0488] "Stress level" is the degree of mental or emotional strain experienced by an employee.

[0489] The "condition score" is a numerical representation of an employee's health status and workload calculated based on the analysis results.

[0490] A "report" is a report that summarizes and organizes the results of analysis.

[0491] A "smartphone" is a mobile phone that can connect to the Internet and use applications in addition to making calls.

[0492] A "wearable device" is an electronic device that can be worn and used.

[0493] "Sleep time" refers to the actual time spent asleep within a specific period of time.

[0494] "Movement" is the amount of physical activity performed within a specific period of time.

[0495] An "emotion recognition engine" is software or a system for analyzing emotional states from voice, facial expressions, etc.

[0496] "Analysis of voice and facial expressions" is the process of extracting specific information from voice and facial expressions and making judgments based on that information.

[0497] "High workload, medium workload, low workload" refers to the level of workload and stress classified based on the condition score.

[0498] The "notification function" is a function for notifying the user of specific information.

[0499] "Managers and leaders" are people in positions that involve managing and guiding employees.

[0500] This invention is a system for accurately assessing the health status and workload of employees in a corporate environment such as a factory. The system collects data using smartphones and wearable devices, analyzes the data on a server, and provides the results to managers and instructors.

[0501] System Configuration

[0502] The system consists of the following hardware and software:

[0503] Smartphones (e.g., iPhone (registered trademark), ANDROID (registered trademark) devices)

[0504] Wearable devices (e.g., Apple Watch, Fitbit)

[0505] Server (e.g., Amazon Web Services (AWS(registered trademark), Google Cloud Platform)

[0506] Data collection

[0507] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee during their daily work. It also collects data on sleep time and exercise volume from smartphones and wearable devices. Furthermore, it uses an emotion recognition engine to analyze voice and facial expression data.

[0508] Data Encryption and Transmission

[0509] The device encrypts the collected data and sends it to a server using the HTTPS protocol, for example using the PyCryptodome library.

[0510] Data Reception and Decryption

[0511] The server receives the encrypted data and decrypts it. The data is then stored in a database, ready for analysis. Examples of databases used include MySQL (registered trademark) and PostgreSQL.

[0512] Data analysis

[0513] The server analyzes the decoded data using AI algorithms (e.g., TensorFlow, PyTorch), which quantify each employee's workload and stress level and calculate a condition score based on that data.

[0514] Calculating the Condition Score

[0515] Based on the analysis results, the server classifies each employee's condition score into "high load," "medium load," "low load," etc. This score is calculated by integrating the collected work data, wearable data, and emotional data.

[0516] Report generation and delivery

[0517] The server compiles each employee's condition score and analysis results into a report and notifies the appropriate manager or leader via email or a dedicated application.

[0518] Providing feedback

[0519] Feedback is provided to each employee via a portal site or application, using a generative AI model to suggest specific actions.

[0520] For example, if an employee's condition score is determined to be "high workload," the feedback will be as follows:

[0521] Example prompt sentence:

[0522] User ID: user123, Condition score: High load, Sleep time: 4 hours, Emails sent / received: 50, Phone calls made / received: 20, Meeting participation: 5, Steps taken: 2000

[0523] Based on this condition, suggest specific actions to reduce operator stress.

[0524] Example output of a generative AI model:

[0525] The condition score for user ID: user123 has been determined to be "High Load." The following actions are recommended:

[0526] 1. Make time to relax: Do deep breathing exercises or meditation several times a day.

[0527] 2. Increase physical activity: Incorporate moderate exercise into your daily routine and aim to take at least 5,000 steps per day.

[0528] 3. Improve your sleep quality: Avoid electronic devices and create a relaxing environment before bedtime.

[0529] 4. Manage emails and phone calls: Prioritize and defer non-essential emails and phone calls.

[0530] By implementing these actions, we hope to see improvements in conditions.

[0531] Specific examples

[0532] In the case of Person B, the device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during daily work. The wearable device also collects the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps), and an emotion recognition engine analyzes Person B's stress level from his tone of voice and facial expressions. Person B's data is encrypted and sent to a server, where it is decrypted and analyzed. Based on the analysis results, Person B's condition score is classified as "medium stress" and appropriate feedback is provided.

[0533] The above is a specific embodiment of the present invention.

[0534] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0535] Step 1:

[0536] The device collects data from work devices, including the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. It also obtains data on sleep time and exercise volume from smartphones and wearable devices. It also uses an emotion recognition engine to analyze voice tone and facial expression data. The input at this step is raw data collected from each device, and the output is unencrypted, integrated data.

[0537] Step 2:

[0538] The terminal encrypts the data collected in step 1. In this process, all collected data is encrypted using the PyCryptodome library. The input is the consolidated raw data and the output is the encrypted data.

[0539] Step 3:

[0540] The terminal sends encrypted data to the server using the HTTPS protocol, where the input is the encrypted data and the output is the state of transmission to the server.

[0541] Step 4:

[0542] The server receives the transmitted data and decrypts the encrypted data using the same encryption algorithm (PyCryptodome). The input to this step is the encrypted data, and the output is the decrypted raw data.

[0543] Step 5:

[0544] The server then analyzes the decoded data using AI algorithms. During this process, TensorFlow, PyTorch, and other tools are used to comprehensively evaluate workload, stress level, exercise volume, sleep time, and emotional data. The input is the decoded raw data, and the output is quantified data on workload and stress levels.

[0545] Step 6:

[0546] The server calculates a condition score for each employee based on the analysis results. This score is classified as "high load," "medium load," or "low load." The input in this step is the analyzed data, and the output is the condition score.

[0547] Step 7:

[0548] The server compiles the condition scores into a report format. It integrates the analysis results of the business data, wearable data, and emotional data, and generates a report to provide to managers and leaders. The input is the condition score, and the output is data in report format.

[0549] Step 8:

[0550] The server notifies managers and leaders of the generated report through a notification function. Notifications are sent via email or a dedicated application. The input in this step is the report format data, and the output is the notified state.

[0551] Step 9:

[0552] The server uses the generative AI model to provide specific feedback to employees. For example, if an employee's condition score is determined to be "high workload," the server sends the following prompt sentence as input to the generative AI model. The output is the feedback action.

[0553] Example prompt sentence:

[0554] User ID: user123, Condition score: High load, Sleep time: 4 hours, Emails sent / received: 50, Phone calls made / received: 20, Meeting participation: 5, Steps taken: 2000

[0555] Based on this condition, suggest specific actions to reduce operator stress.

[0556] Based on this prompt, the generative AI model provides the following feedback:

[0557] The condition score for user ID: user123 has been determined to be "High Load." The following actions are recommended:

[0558] 1. Make time to relax: Do deep breathing exercises or meditation several times a day.

[0559] 2. Increase physical activity: Incorporate moderate exercise into your daily routine and aim to take at least 5,000 steps per day.

[0560] 3. Improve your sleep quality: Avoid electronic devices and create a relaxing environment before bedtime.

[0561] 4. Manage emails and phone calls: Prioritize and defer non-essential emails and phone calls.

[0562] By implementing these actions, we hope to see improvements in conditions.

[0563] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0564] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0565] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0566] [Second embodiment]

[0567] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0568] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0569] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0570] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0571] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0572] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0573] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0574] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0575] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0576] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0577] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0578] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0579] This invention is a system that assesses the condition of employees by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, etc. This system allows managers and mentors to effectively manage the health of their employees.

[0580] Program processing

[0581] Data collection

[0582] The device collects data from work email clients, phone applications, and calendar applications. It obtains the number of work emails sent and received, the number of calls made and received, and the number of meetings registered in the calendar via API. Additionally, if the employee consents, the device also obtains data on sleep time and exercise volume from wearable devices (e.g., smartwatches).

[0583] Data Encryption and Transmission

[0584] The device conceals the collected data using an encryption library and transmits it securely to the server via the HTTPS protocol.

[0585] Data Reception and Decryption

[0586] The server receives the data sent from the terminal. Since the received data is encrypted, it is decrypted using a decryption library on the server side to restore it to its original format.

[0587] Data analysis

[0588] The server evaluates the employee's workload, activity level, and stress level based on the decoded data. The analysis uses an AI algorithm to comprehensively assess the number of emails sent and received, the number of calls made and received, the number of meetings attended, and wearable data. Appropriate weighting is applied to each data indicator to calculate the overall workload and stress level.

[0589] Calculating the Condition Score

[0590] The server calculates each employee's condition score based on the analysis results. The condition score is a comprehensive assessment of each employee's workload and stress level, and is classified into categories such as "high workload," "medium workload," and "low workload" based on certain thresholds.

[0591] Report generation and delivery

[0592] The server compiles each employee's condition score into a report, which includes detailed analysis results and specific indicators. The generated report is saved in a database and provided to managers and mentors. Managers and mentors are also notified of the report's creation via a notification function.

[0593] Providing feedback

[0594] The server provides employees with feedback based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[0595] Specific examples

[0596] In the case of Mr. A

[0597] The device collects data on the number of emails sent and received (50), the number of calls made and received (10), and the number of meetings attended (5) during Mr. A's daily work. With Mr. A's consent, the device also collects the amount of sleep (6 hours) and exercise (5,000 steps) per day from the wearable device (smartwatch).

[0598] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses an AI algorithm to analyze Mr. A's condition. For example, it can be determined that he sends and receives many emails and attends many meetings, but that he continues to suffer from a lack of sleep.

[0599] The server calculates Person A's condition score based on the analysis results and classifies him / her as "high stress." The server then compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors then review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself / herself via the portal site, which helps support self-management.

[0600] The processing flow will be explained below.

[0601] Program processing steps

[0602] Step 1: Collect business data

[0603] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[0604] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[0605] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[0606] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[0607] Step 2: Collecting wearable device data

[0608] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[0609] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[0610] Step 3: Encrypt the data

[0611] The terminal encrypts the collected business data and wearable data using an encryption library.

[0612] Encryption library: Encrypts data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, the amount of sleep, and the amount of exercise, and stores the encrypted data in a local database.

[0613] Step 4: Sending data

[0614] The terminal sends the encrypted data to the server using the HTTPS protocol.

[0615] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[0616] Step 5: Receive and decrypt the data

[0617] The server receives the data sent from the terminal.

[0618] HTTP request: Temporarily store received data.

[0619] The server decrypts the received data.

[0620] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[0621] Step 6: Data analysis

[0622] The server analyzes the decrypted data.

[0623] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, and amount of exercise to evaluate employees' workload, activity level, and stress level.

[0624] Step 7: Calculating the Condition Score

[0625] The server calculates each employee's condition score based on the analysis results.

[0626] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[0627] Step 8: Generate and deliver reports

[0628] The server compiles each employee's condition score and analysis results into a report.

[0629] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[0630] The server provides the generated reports to managers and mentors.

[0631] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[0632] Step 9: Provide feedback

[0633] The server provides feedback to each employee.

[0634] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[0635] Example 1

[0636] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0637] In today's corporate environment, appropriately managing employees' workloads and stress levels and protecting their health are important issues. However, current methods make it difficult to collect and analyze individual work data, making it difficult to accurately assess their condition. Furthermore, there is no established method for integrating and analyzing data from wearable devices with work data. As a result, efficient health management and feedback for employees are currently not being provided.

[0638] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0639] In this invention, the server includes means for collecting the number of emails sent and received, the number of communications, and the number of meetings attended in the schedule management system from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side to calculate the workload and stress level of each employee, means for calculating a condition score based on the analysis results, means for compiling the condition score in report format and providing it to an appropriate manager or educational instructor, and means for using a generative artificial intelligence model to analyze the data. This enables integrated analysis of employee work data and individual health data, enabling accurate condition evaluation and effective feedback.

[0640] A "business terminal" is a computer or electronic device used to carry out business within a company or organization.

[0641] "Emails Sent and Received" means the total number of emails received and sent within a specified period of time.

[0642] "Number of communications" means the number of calls made using communication means such as telephone or voice chat.

[0643] A "schedule management system" is software or an electronic system for managing meeting schedules and task schedules.

[0644] "Number of meetings attended" means the total number of meetings attended within a specific period.

[0645] "Encryption" is a technique for converting data into a format that cannot be easily deciphered by third parties.

[0646] A "server" is a computer system that provides data and services to other computers and devices over a network.

[0647] "Decryption" is the technique of returning encrypted data to its original form.

[0648] "Analysis" is the process of analyzing data in detail and extracting specific information.

[0649] "Workload" refers to the total amount of work, difficulty, and time spent by an employee.

[0650] "Stress level" refers to the degree of mental and physical strain felt by employees.

[0651] A "condition score" is a score or index that comprehensively evaluates an employee's workload and stress level.

[0652] A "report" is a document or data that summarizes analysis results and evaluations using text and graphs.

[0653] A "manager" is a person in a company or organization who is responsible for managing the work and health of employees.

[0654] An "educational instructor" is a person who is responsible for improving the skills and providing guidance to employees.

[0655] "Generative artificial intelligence model" is a general term for algorithms or models designed to perform specific tasks using machine learning and deep learning techniques.

[0656] A "wearable device" is an electronic device worn on the body. Examples include smartwatches and fitness bands.

[0657] "Rest time" refers to the time spent sleeping or resting during the day.

[0658] "Physical activity" refers to the total amount of physical activity, such as exercise and movement, that occurs in a day.

[0659] A "portal site" is a website that provides information and services to specific users.

[0660] An "application" is a software program designed to accomplish a particular purpose.

[0661] This invention is a system that collects and analyzes data from employees' daily work to evaluate their workload and stress levels, and supports their health management. This system is primarily composed of business terminals, a server, and wearable devices used by users.

[0662] First, the device collects the following data from your business email client (e.g., Microsoft Outlook), phone application (e.g., Skype for Business), and calendar application (e.g., Google Calendar):

[0663] Number of emails sent and received

[0664] Number of communications

[0665] Number of meetings attended in the schedule management system

[0666] Additionally, if the user consents, the device will collect rest time and physical activity data from wearable devices (e.g., Fitbit, Apple Watch).

[0667] The collected data is encrypted by the device using an encryption library (e.g., OpenSSL) and sent to the server via the HTTPS protocol. The server then decrypts the received encrypted data to its original form using a decryption library.

[0668] The server then uses the decoded data to analyze each employee's workload and stress level using a generative artificial intelligence model (e.g., TensorFlow) and comprehensively evaluates the following factors:

[0669] Number of emails sent and received

[0670] Number of communications

[0671] Number of meetings attended

[0672] Wearable data (rest time, physical activity)

[0673] Each data indicator is weighted appropriately to produce a condition score, which is then categorized into "high stress," "medium stress," and "low stress."

[0674] The server compiles the condition scores for each employee based on the analysis results in the form of a report. The report contains details of the analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational instructors. Administrators and educational instructors are notified of the generation of the report via a notification function.

[0675] The server also provides feedback to employees based on their condition scores. This feedback is sent to employees via a portal site or dedicated application, and includes information that helps support self-management and improvement.

[0676] Specific examples

[0677] For example, in the case of Person A, the device will collect data on the number of emails sent and received (50), the number of communications (10), and the number of meetings attended (5) in Person A's daily work. In addition, with Person A's consent, the device will also obtain the amount of rest time (6 hours) and the amount of physical activity (5,000 steps) from the wearable device.

[0678] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses a generative AI model to analyze Person A's condition. For example, it can be determined that although he sends and receives many emails and attends many meetings, he continues to lack rest.

[0679] Based on the analysis results, the server classifies Person A's condition score as "high stress." The analysis results are compiled in a report and provided to administrators and educational instructors. The administrators and educational instructors review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself through the portal site, which helps support his self-management.

[0680] Example prompts for generative AI models

[0681] prompt:

[0682] Calculate your condition score based on the employee data below.

[0683] data:

[0684] Number of emails sent and received: 50

[0685] Number of communications: 10

[0686] Number of meetings attended: 5

[0687] Rest time: 6 hours

[0688] Physical activity: 5,000 steps

[0689] An example of the output produced:

[0690] Condition Score: High Load

[0691] Details: The workload was assessed as high due to the high volume of emails sent and received and the high number of meetings attended, as well as the continued lack of rest.

[0692] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0693] Step 1: Collect data

[0694] The device collects data from the user's daily work. Specifically, data on the number of emails sent and received from the business email client, the number of communications from the phone application, and the number of meetings attended from the calendar application are input. In addition, if the user consents, data on rest time and physical activity levels are also collected from the wearable device. This data is obtained using an API and stored in the device's local storage.

[0695] Input: Number of emails sent and received, number of communications, number of meetings attended, rest time, amount of physical activity

[0696] Output: Collected data (stored in local storage)

[0697] Specific operation: The device makes the following API request:

[0698] GET / api / mail / received?user_id=A

[0699] GET / api / calendar / meetings?user_id=A

[0700] GET / api / phone / calls?user_id=A

[0701] GET / api / wearable / data?user_id=A

[0702] Step 2: Encrypt the data and send it to the server

[0703] The device encrypts the collected data using an encryption library (e.g., OpenSSL), and the encrypted data is sent to the server via the HTTPS protocol to ensure security.

[0704] Input: Collected data

[0705] Output: Encrypted data (sent to server)

[0706] Specific operation: Encrypts the data in JSON format and sends a POST request to the server.

[0707] POST / api / data

[0708] Content-Type: application / json

[0709] {

[0710] "user_id": "A",

[0711] "data": "encryptedData"

[0712] }

[0713] Step 3: Receive and decrypt the data

[0714] The server receives the encrypted data sent from the device, and uses a decryption library to restore the data to its original format.

[0715] Input: Encrypted data

[0716] Output: Decrypted data

[0717] What happens: The server uses an encryption library to decrypt the data.

[0718] encryptedData = request.body.data;

[0719] rawData = OpenSSL::Decrypt(encryptedData);

[0720] Step 4: Analyze the data

[0721] The server uses the decoded data it receives to analyze each employee's workload and stress level. A generative AI model (e.g., TensorFlow) is used for the analysis, and a comprehensive evaluation is made of the number of emails sent and received, the number of communications, the number of meetings attended, and wearable data. An appropriate weighting is then assigned to each data indicator to calculate an overall condition score.

[0722] Input: Decrypted data

[0723] Output: Analysis results (work load and stress level, condition score)

[0724] What it does: It uses an AI model to analyze data and predict scores.

[0725] model = tf.keras.models.load_model('condition_model.h5')

[0726] data = {"emails": rawData["emails"], "calls": rawData["calls"], "meetings": rawData["meetings"], "sleep": rawData["sleep"], "steps": rawData["steps"]}

[0727] condition_score = model.predict(data)

[0728] Step 5: Calculating the Condition Score

[0729] Based on the results of the AI ​​algorithm analysis, the server calculates a condition score for each employee, which is categorized into "high load," "medium load," and "low load."

[0730] Input: Analysis results

[0731] Output: Condition Score

[0732] Specific Behavior: Evaluate condition scores and categorize them.

[0733] thresholds = {"low": 0.3, "medium": 0.7, "high": 1.0}

[0734] condition_value = condition_score[0]

[0735] if condition_value < thresholds["low"]:

[0736] condition_category = "Low load"

[0737] elif condition_value < thresholds["medium"]:

[0738] condition_category = "Medium load"

[0739] else:

[0740] condition_category = "High load"

[0741] Step 6: Generate and deliver reports

[0742] The server generates a report based on the calculated condition score. The report contains detailed analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational leaders. Administrators and educational leaders are notified of the generation of the report via a notification function.

[0743] Input: Condition score, analysis results

[0744] Output: Report (Saved to database, Notification)

[0745] Specific actions: Generate a report, save it in a database, and notify the administrator.

[0746] report = {

[0747] "user_id": "A",

[0748] "condition_score": condition_category,

[0749] "details": rawData,

[0750] "analysis_time": datetime.now()

[0751] }

[0752] db.save(report)

[0753] notification.send("Report generated", user_id="A")

[0754] Step 7: Provide feedback

[0755] The server provides feedback to employees based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[0756] Input: Condition Score

[0757] Output: Feedback (notification)

[0758] Specific behavior: Generate feedback and communicate it through portals and applications.

[0759] feedback = f"{condition_category}:Due to the increased workload recently, we recommend that you take a proper rest."

[0760] notification.send(feedback, user_id="A")

[0761] (Application example 1)

[0762] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0763] In recent years, there has been growing emphasis on managing the health and workload of factory workers, but conventional systems only collect and analyze data from office work, making it difficult to accurately grasp the condition of factory workers. For this reason, there is a need for a new system that can detect worker fatigue and stress early and provide appropriate feedback.

[0764] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0765] In this invention, the server includes: means for collecting the number of emails sent and received, the number of outgoing and incoming calls, and the number of calendar meetings attended from business terminals; means for encrypting the collected data and sending it to the server; means for decrypting and analyzing the data on the server side to calculate each employee's workload and stress level; means for calculating a condition score based on the analysis results; means for compiling the condition score in report format and providing it to an appropriate manager or mentor; means for collecting the body temperature, heart rate, and work log of factory workers using smart glasses, encrypting the data in the same way, and sending it to the server; and means for evaluating the fatigue and stress levels of factory workers based on the collected data and providing breaks and feedback at appropriate times. This allows for real-time monitoring of the health status of factory workers, improving work efficiency, and ensuring safety.

[0766] A "business terminal" is an information processing device such as a computer used by a company or organization.

[0767] "Number of emails sent and received" is the total number of emails sent and received during a certain period of time.

[0768] "Number of calls made and received" refers to the total number of calls made and received via telephone or communication apps over a certain period of time.

[0769] "Number of meetings attended in calendar" refers to the number of times a person has attended a conference or meeting registered in an electronic calendar.

[0770] A "collection means" is a method or device used to obtain and store particular data.

[0771] An "encryption means" is a method or device that converts data from a readable form to an obfuscated form in order to protect it.

[0772] A "server" is a computer system that stores data and provides services to other computers and devices over a network.

[0773] A "decryption means" is a method or device that returns encrypted data to its original, readable form.

[0774] An "analyzing means" is a method or device for processing collected data and extracting meaningful information.

[0775] "Workload" refers to the amount of tasks or work that an employee handles as part of their job during a specific period of time.

[0776] "Stress level" refers to the degree of mental and physical stress felt by employees over a specific period of time.

[0777] A "condition score" is a numerical indicator that represents an employee's health status and workload.

[0778] A "report format" is a document format that summarizes collected and analyzed information in an easy-to-understand format.

[0779] A "management position" is a person in a position responsible for management or leadership within an organization.

[0780] A "mentor" is someone whose role is to provide guidance and advice on specific knowledge and skills.

[0781] "Smart glasses" are a wearable device in the form of glasses that displays visual information on a screen and can be connected to a computer or network.

[0782] "Body temperature" is an indicator of the worker's body temperature.

[0783] "Heart rate" is the number of times the heart beats within a certain period of time.

[0784] A "work log" is a detailed record of the work performed by a worker.

[0785] "Fatigue level" refers to the degree of physical and mental fatigue felt during work.

[0786] "Real-time" means that information is updated and processed almost immediately.

[0787] The present invention is a system for monitoring the health and workload of factory workers in real time and providing appropriate feedback. The system includes a business terminal, smart glasses, a wearable device, and a server.

[0788] Data collection

[0789] The business devices collect business data such as the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. In addition, smart glasses are used to collect the factory workers' body temperature, heart rate, and work logs. This data is encrypted immediately upon collection. The encryption uses the OpenSSL library to protect the data.

[0790] Data Encryption and Transmission

[0791] The data is encrypted and then securely transmitted to the server using the HTTPS protocol, using the standard SSL / TLS protocol to ensure secure communication.

[0792] Data Reception and Decryption

[0793] The server then decrypts the received data using the PyCrypto library, which returns the data to its original, readable form for analysis.

[0794] Data analysis

[0795] The server calculates the workload and stress level of workers based on the decoded data. The analysis uses TensorFlow and PyTorch and utilizes a generative AI model. Specifically, the server comprehensively analyzes the number of emails sent and received, the number of meetings attended, body temperature, heart rate, and work logs, and assigns appropriate weights to the data indicators.

[0796] Calculating condition scores and providing feedback

[0797] Based on the analysis results, a condition score is calculated for each employee. The condition score is a comprehensive assessment of the employee's workload and stress level. This score is provided to the worker in real time via the smart glasses' built-in display. The analysis results are then compiled into a report and provided to managers and mentors.

[0798] Specific examples

[0799] For example, suppose a factory worker has a body temperature of 37.2°C, a heart rate of 85 bpm, and has not taken a break in the past hour. Based on this data, the system determines that the worker is highly fatigued and displays an alert on the smart glasses display urging the worker to take a break. The system also notifies managers that the worker's condition score is "high strain."

[0800] Prompt Sentence Examples

[0801] "Collect daily work data (body temperature, heart rate, break times) from factory workers and create an AI model that evaluates their condition from the analysis results. Design an application that provides feedback and alerts based on the condition score."

[0802] This will not only enable factory workers to properly manage their health, but also enable managers and mentors to understand the health of workers and provide appropriate support. By using this system, it will be possible to improve work efficiency and safety.

[0803] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0804] Step 1:

[0805] The business device collects the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee. This data is obtained using the business device's API. The input data is employee activity information, and the output is business data before encryption. Specifically, this includes operations that make API calls from email clients, phone apps, and calendar apps.

[0806] Step 2:

[0807] The terminal encrypts the data collected in step 1 using the OpenSSL library. The input data is the business data described above, and the output data is the encrypted business data. Specifically, this includes the operation of performing encryption processing using AES encryption.

[0808] Step 3:

[0809] The terminal sends encrypted data to the server using the HTTPS protocol. The input data is encrypted business data, and the output is the data sent to the server. Specifically, this includes the operation of creating and sending an HTTPS request.

[0810] Step 4:

[0811] The server decrypts the data sent from the terminal using the PyCrypto library. The input data is encrypted business data, and the output is decrypted business data. Specifically, it includes the operation of performing decryption processing using AES decryption.

[0812] Step 5:

[0813] The server inputs the decoded data into a generative AI model using TensorFlow or PyTorch to analyze workload and stress levels. The input data is the decoded workload data, and the output is the evaluation results of workload and stress levels. Specifically, this includes the operation of performing data analysis processing using the AI ​​model.

[0814] Step 6:

[0815] The server calculates a condition score for each employee based on the analysis results. The input data are the evaluation results of workload and stress level, and the output is a condition score for each employee. Specifically, it includes operations for weighting and score calculation based on the evaluation results.

[0816] Step 7:

[0817] The server compiles the condition scores into a report and provides it to the appropriate manager or mentor. The input data is the condition score, and the output is a report that is delivered to the manager or mentor. Specifically, it uses a report generation algorithm and includes operations such as email and dashboard notifications.

[0818] Step 8:

[0819] The smart glasses collect the body temperature, heart rate, and work logs (such as working hours and break times) of factory workers. This data is acquired using the smart glasses' sensors and API. The input data is sensor information, and the output is work data before encryption. Specifically, this includes operations that utilize the body temperature sensor, heart rate sensor, and work log recording function.

[0820] Step 9:

[0821] The smart glasses encrypt the collected data using the OpenSSL library and send it to the server. The input data is sensor information, and the output is encrypted working data. Specifically, the glasses perform operations including encryption using AES encryption and sending HTTPS requests.

[0822] Step 10:

[0823] The server decrypts the data sent from the smart glasses and analyzes the condition of the factory workers. The input data is encrypted work data, and the output is the worker condition evaluation results. Specifically, the server performs operations such as decryption processing and evaluation processing using a data analysis model.

[0824] Step 11:

[0825] The smart glasses display break and feedback alerts to workers in real time. The input data is the condition assessment results from the server, and the output is the alerts displayed on the smart glasses display. Specifically, it includes the operation of displaying feedback messages on the display.

[0826] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0827] This invention is a system that accurately assesses an employee's condition by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, and combining it with user emotional data, allowing managers and mentors to effectively monitor and support the health of their employees.

[0828] Program processing

[0829] Data collection

[0830] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of meetings attended from the email client, phone application, and calendar application installed on the work device. If the employee consents, the device also collects data on sleep time and exercise volume from wearable devices (e.g., smartwatches). Furthermore, the device uses an emotion engine to analyze the user's emotional state from their voice data and facial expression data.

[0831] Data Encryption and Transmission

[0832] The device encrypts the collected business data, wearable data, and emotion data and transmits them securely to the server using an encryption library and the HTTPS protocol.

[0833] Data Reception and Decryption

[0834] The server receives the data sent from the device, decrypts the encrypted data, and stores it in a database, ready for analysis.

[0835] Data analysis

[0836] The server analyzes the decrypted data, integrating data such as the number of emails sent and received, the number of meetings attended, sleep time, exercise level, and emotional data. An AI algorithm is used for the analysis, weighting each data indicator appropriately to assess the employee's workload and stress level.

[0837] Calculating the Condition Score

[0838] The server calculates a condition score for each employee based on the analysis results. By combining this with emotional data, stress levels can be corrected to provide a more accurate condition score. Scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[0839] Report generation and delivery

[0840] The server compiles each employee's condition score and analysis results into a report. The generated report is saved in a database and notified to managers and mentors. A notification function also encourages employees to check the report.

[0841] Providing feedback

[0842] The server provides feedback to each employee, who is then notified of the feedback via a portal site or dedicated application, providing support for self-management and improvement.

[0843] Specific examples

[0844] In the case of person B

[0845] The device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during B's daily work. With B's consent, the device also collects the amount of sleep (7 hours) and exercise (6,000 steps) per day from the wearable device (smartwatch).

[0846] In addition, the device uses an emotion engine to analyze B's voice and facial expression data to determine his / her stress level. For example, it may detect that B is under high stress based on his / her voice tone and facial expression.

[0847] The device encrypts all collected data and sends it to the server. The server decrypts the data and analyzes Mr. B's condition using an AI algorithm. Based on the analysis results, Mr. B's condition score is classified as "medium load."

[0848] The server compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors review the report and provide appropriate support and feedback to Person B. Feedback is also provided to Person B himself via the portal site, which helps support his self-management.

[0849] The processing flow will be explained below.

[0850] MODE FOR CARRYING OUT THE INVENTION

[0851] This invention is a system that collects and analyzes work data, wearable data, and emotional data to assess an employee's condition, allowing managers and mentors to gain a detailed understanding of their employees' health status and provide appropriate support.

[0852] Program processing steps

[0853] Step 1: Collect business data

[0854] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[0855] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[0856] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[0857] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[0858] Step 2: Collecting wearable device data

[0859] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[0860] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[0861] Step 3: Collecting emotion data

[0862] The device uses an emotion engine to analyze the user's voice data and facial expression data to determine the user's stress level and emotional state.

[0863] Emotion Engine: Using voice recordings and camera data, it analyzes changes in voice tone and facial expressions to generate emotion data, which is then stored in a local database.

[0864] Step 4: Encrypt the data

[0865] The device encrypts the collected business data, wearable data, and emotion data using an encryption library.

[0866] Encryption library: Encrypts data such as the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, exercise amount, and emotional data, and stores the encrypted data in a local database.

[0867] Step 5: Sending data

[0868] The terminal sends the encrypted data to the server using the HTTPS protocol.

[0869] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[0870] Step 6: Receive and decrypt data

[0871] The server receives the data sent from the terminal.

[0872] HTTP request: Temporarily store received data.

[0873] The server decrypts the received data.

[0874] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[0875] Step 7: Data analysis

[0876] The server analyzes the decrypted data.

[0877] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, amount of exercise, and emotional data to evaluate employees' workload, activity level, and stress level.

[0878] Analysis results: Based on the analysis results, the workload and stress level of each employee are evaluated and expressed as a numerical value.

[0879] Step 8: Calculating the Condition Score

[0880] The server calculates each employee's condition score based on the analysis results.

[0881] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[0882] Step 9: Generate and deliver reports

[0883] The server compiles each employee's condition score and analysis results into a report.

[0884] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[0885] The server provides the generated reports to managers and mentors.

[0886] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[0887] Step 10: Provide feedback

[0888] The server provides feedback to each employee.

[0889] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[0890] Example 2

[0891] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0892] In today's corporate environment, it is important to accurately understand employees' workloads and stress levels and provide appropriate support. However, conventional systems only collect operational data such as the number of emails sent and received, phone calls made and received, and number of meetings attended, which is not enough to accurately assess an employee's condition. Furthermore, relying solely on numerical data makes it difficult to consider an employee's mental state or physical health. To solve this problem, a more diversified and comprehensive method of data collection and analysis is needed.

[0893] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0894] In this invention, the server includes means for collecting the number of emails sent and received, the number of phone calls made and received, and the number of calendar meetings attended from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side, means for analyzing the emotional state of employees from their voice data and facial expression data, means for calculating the workload and stress level of each employee, means for calculating a condition score based on the analysis results, and means for compiling the condition score in report format and providing it to an appropriate manager or instructor. This allows for an integrated analysis of employee work data as well as emotional and physical data, enabling more accurate condition evaluations.

[0895] "Business terminals" are computers and smart devices used by employees within a company to carry out their work.

[0896] "Emails Sent and Received" means the total number of emails sent and received by an employee within a specified period of time.

[0897] "Number of calls made and received" is the total number of calls made and received by an employee during a specified period.

[0898] "Calendar Meeting Attendance" is the total number of meetings that an employee has registered to attend in scheduling software.

[0899] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is a means of ensuring security.

[0900] A "server" is a computer system that provides data or services to multiple clients over a network.

[0901] "Decryption" is the process of returning encrypted data to its original, readable form.

[0902] "Analysis" is the process of using collected data to extract and evaluate information for a specific purpose.

[0903] "Emotional state" is the result of judging an individual's mental state obtained through voice and facial expression data.

[0904] "Workload" is a measure of the amount of work and difficulty an employee feels when performing their job.

[0905] "Stress level" is a measure of the degree of psychological and physiological stress felt by an individual.

[0906] A "Condition Score" is a comprehensive score calculated to assess an employee's overall work situation and health.

[0907] A "report format" is a document format that visually organizes analysis results and presents them in an easy-to-understand manner.

[0908] A "manager" is someone who supervises and supports the work of employees within an organization.

[0909] A "leader" is someone whose role is to educate and support employees within an organization.

[0910] "Wearable devices" are small electronic devices and related technologies that can be worn by a user.

[0911] "Sleep time" is the total time an employee was asleep.

[0912] "Amount of exercise" is the cumulative amount of physical activity an employee engages in within a specific period of time.

[0913] This invention is a system that accurately assesses the condition of employees by collecting and analyzing data from various angles related to their daily work. The system analyzes data collected from business terminals on a server and provides useful information to managers and instructors, aiming to effectively monitor and support employees' health and stress levels.

[0914] Data collection

[0915] The device collects data from the email client, phone application, and calendar application installed on the work device. Specifically, it uses an API to obtain the number of emails sent and received, the number of phone calls made and received, and the number of meetings attended. If the employee consents, the device also collects data on sleep time and exercise volume from a wearable device (e.g., a smartwatch). Furthermore, an emotion engine is used to analyze the user's voice data and facial expression data to evaluate their emotional state. This makes it possible to collect data that can be used to comprehensively evaluate not only employees' work performance, but also their mental and health states.

[0916] Data Encryption and Transmission

[0917] The device encrypts the collected and analyzed data and transmits it to the server with a high level of security. The encryption is performed using the AES encryption library and the HTTPS protocol for data transmission, ensuring confidentiality and integrity of the data.

[0918] Data Reception and Decryption

[0919] The server receives the encrypted data sent from the device and decrypts it in a secure environment, where it is stored in a database until it is ready to be analyzed.

[0920] Data analysis

[0921] The server performs an integrated analysis of data collected from various data sources. First, it integrates business data (emails, phone calls, meeting participation), wearable data, and emotional data, and then analyzes them using an AI algorithm. The specific algorithm assigns appropriate weights to each data indicator to evaluate employees' workload and stress levels.

[0922] Calculating the Condition Score

[0923] Based on the analysis results, the server calculates a condition score for each employee. This score can be combined with emotional data to correct for stress levels, enabling more accurate assessments. Condition scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[0924] Report generation and delivery

[0925] The server compiles the analysis results and condition scores into a report. The generated report is saved in a database and notified to the appropriate administrator or instructor. Notifications are sent via email or the alert function on the portal site.

[0926] Providing feedback

[0927] Finally, the server provides feedback to each employee, which is then communicated to the employee via a portal site or dedicated application, and used as a guide for self-management and improvement.

[0928] Specific examples

[0929] For example, in the case of Person B, the device collects data on the number of emails sent and received (30), the number of phone calls made and received (15), and the number of meetings attended (3) in Person B's daily work. Furthermore, with Person B's consent, data on the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps) is also collected from the wearable device. Person B's voice data and facial expression data are analyzed using an emotion engine to determine their stress level. For example, it can detect that Person B is feeling increasingly stressed from their voice tone and facial expression.

[0930] The device encrypts all of this data and sends it to the server. The server decrypts the data and uses an AI algorithm to analyze Person B's condition. Based on the results of this analysis, Person B's condition score is classified as "medium load." The server compiles the analysis results into a report and provides it to the manager or coach. The manager or coach reviews the report and provides appropriate support and feedback to Person B. Person B also receives feedback via a portal site, which can be used to help with self-management.

[0931] Prompt Sentence Examples

[0932] "Please explain in detail the specific steps you take to collect data on Mr. B's daily work and analyze his condition."

[0933] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0934] Program processing steps

[0935] Step 1: Start collecting data

[0936] The device accesses the email client, phone application, and calendar application on the business device according to a specific time schedule.

[0937] Input: Each application on the user's work computer.

[0938] Output: Raw data obtained from each application.

[0939] Specific operation:

[0940] The device calls the email client's API and collects the number of emails sent and received.

[0941] The device calls the API of the phone application and collects the number of calls made and received.

[0942] The device calls the calendar application API to collect the number of meetings attended.

[0943] Step 2: Wearable data collection

[0944] The device works in conjunction with a wearable device (e.g., a smartwatch) to obtain the user's sleep time and exercise volume.

[0945] Input: Sensor data from wearable devices.

[0946] Output: Data on sleep duration and exercise.

[0947] Specific operation:

[0948] The device retrieves the data via the wearable device's API and stores it locally.

[0949] Sleep duration is obtained from the wearable device's activity tracker, and exercise volume is obtained from the pedometer sensor.

[0950] Step 3: Sentiment Data Analysis

[0951] The device uses an emotion engine to analyze the user's voice data and facial expression data to evaluate their emotional state.

[0952] Input: User's voice and facial expression data.

[0953] Output: Parsed emotion data.

[0954] Specific operation:

[0955] The device uses a voice recognition engine to analyze voice tone and pitch.

[0956] Using a facial expression recognition engine, facial images acquired from a camera are analyzed to determine the emotional state.

[0957] Step 4: Data Encryption

[0958] The device encrypts all collected data and prepares it for transmission to the server.

[0959] Input: Each dataset collected and analyzed.

[0960] Output: Encrypted data bundle.

[0961] Specific operation:

[0962] The terminal uses the AES encryption library to encrypt the data set.

[0963] Create a batch to send encrypted data to the server via HTTPS protocol.

[0964] Step 5: Send data

[0965] The terminal transmits the encrypted data to the server.

[0966] Input: Encrypted data bundle.

[0967] Output: The data sent to the server.

[0968] Specific operation:

[0969] The device uses the HTTPS protocol to send encrypted data to the server.

[0970] A manual or automated submission process sends the data to an endpoint where the server can receive it.

[0971] Step 6: Data Reception and Decryption

[0972] The server receives and decrypts the data sent from the terminal.

[0973] Input: The received encrypted data.

[0974] Output: Decoded raw data.

[0975] Specific operation:

[0976] The server uses a secure endpoint to receive encrypted data.

[0977] The received data is decrypted to restore it to its original data format.

[0978] Step 7: Data integration and analysis

[0979] The server integrates and analyzes business data, wearable data, and emotional data.

[0980] Input: The decoded dataset.

[0981] Output: Analysis results.

[0982] Specific operation:

[0983] The server uses a data management system to integrate each dataset.

[0984] AI algorithms are applied to analyze data and evaluate workload and stress levels.

[0985] Step 8: Calculating the Condition Score

[0986] Based on the analysis results, the server calculates each employee's condition score.

[0987] Input: Analysis results.

[0988] Output: Condition score.

[0989] Specific operation:

[0990] The condition score is calculated based on an AI algorithm.

[0991] The calculation results are classified into specific score categories (high load, medium load, low load).

[0992] Step 9: Reporting and Notifications

[0993] The server compiles each employee's condition score and analysis data into a report format and provides it to managers and instructors.

[0994] Input: Condition score and analysis data.

[0995] Output: The generated report.

[0996] Specific operation:

[0997] The server organizes and structures the analysis results using report generation templates.

[0998] The completed reports are stored in a database and notifications are sent to managers and leaders through a notification system.

[0999] Step 10: Provide feedback

[1000] The server provides individual feedback to each employee.

[1001] Input: Condition score and analysis results.

[1002] Output: The feedback provided.

[1003] Specific operation:

[1004] The server automatically generates feedback content and notifies employees via a portal site or dedicated application.

[1005] Employees can refer to the feedback provided to help them self-manage and improve.

[1006] (Application example 2)

[1007] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1008] In many modern business situations, it is important to properly manage employee workload and stress. However, conventional systems assess employee health based solely on work data, making it difficult to accurately assess workload. Furthermore, systems lacked the mechanisms for combining emotional data and data from wearable devices, resulting in delayed or inaccurate feedback. This can lead to a deterioration in employee health and a drop in productivity.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the number of emails sent and received, the number of calls made and received, and the number of meetings attended on the calendar from the business terminals, means for encrypting the collected data and sending it to the server, and means for decrypting and analyzing the data on the server side and calculating the workload and stress level of each employee. This enables detailed data collection and analysis.

[1010] Furthermore, the server includes means for collecting data on sleep duration and exercise volume from the smartphone and wearable device, analyzing voice and facial expressions using an emotion recognition engine, means for classifying condition scores into categories such as high, medium, and low stress based on the analysis results, and means for notifying managers and leaders of the analysis results through a notification function, thereby enabling real-time evaluation of the overall health status of employees and providing prompt feedback.

[1011] "Business terminals" are electronic devices such as computers and smartphones used in companies and organizations.

[1012] "Emails Sent and Received" means the total number of emails sent and received within a specified period of time.

[1013] "Number of outgoing and incoming calls" refers to the total number of outgoing and incoming voice calls made within a specific period of time.

[1014] "Calendar meeting attendance count" refers to the number of scheduled meetings attended within a specific period.

[1015] A "collection means" is a method or device for obtaining and recording data.

[1016] "Encryption" is the process of transforming data using a specific algorithm in order to secure it.

[1017] A "server" is a computer system that stores, manages, and analyzes data.

[1018] "Decryption" is the process of restoring encrypted data to its original state.

[1019] "Analysis" is the process of examining data in detail to derive useful information.

[1020] "Workload" refers to the amount of work an employee handles in a given period of time.

[1021] "Stress level" is the degree of mental or emotional strain experienced by an employee.

[1022] The "condition score" is a numerical representation of an employee's health status and workload calculated based on the analysis results.

[1023] A "report" is a report that summarizes and organizes the results of analysis.

[1024] A "smartphone" is a mobile phone that can connect to the Internet and use applications in addition to making calls.

[1025] A "wearable device" is an electronic device that can be worn and used.

[1026] "Sleep time" refers to the actual time spent asleep within a specific period of time.

[1027] "Movement" is the amount of physical activity performed within a specific period of time.

[1028] An "emotion recognition engine" is software or a system for analyzing emotional states from voice, facial expressions, etc.

[1029] "Analysis of voice and facial expressions" is the process of extracting specific information from voice and facial expressions and making judgments based on that information.

[1030] "High workload, medium workload, low workload" refers to the level of workload and stress classified based on the condition score.

[1031] The "notification function" is a function for notifying the user of specific information.

[1032] "Managers and leaders" are people in positions that involve managing and guiding employees.

[1033] This invention is a system for accurately assessing the health status and workload of employees in a corporate environment such as a factory. The system collects data using smartphones and wearable devices, analyzes the data on a server, and provides the results to managers and instructors.

[1034] System Configuration

[1035] The system consists of the following hardware and software:

[1036] Smartphones (e.g. iPhone, Android devices)

[1037] Wearable devices (e.g., Apple Watch, Fitbit)

[1038] Server (e.g. Amazon Web Services (AWS), Google Cloud Platform)

[1039] Data collection

[1040] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee during their daily work. It also collects data on sleep time and exercise volume from smartphones and wearable devices. Furthermore, it uses an emotion recognition engine to analyze voice and facial expression data.

[1041] Data Encryption and Transmission

[1042] The device encrypts the collected data and sends it to a server using the HTTPS protocol, for example using the PyCryptodome library.

[1043] Data Reception and Decryption

[1044] The server receives the encrypted data, decrypts it, and stores it in a database, ready for analysis. Databases used include MySQL and PostgreSQL.

[1045] Data analysis

[1046] The server analyzes the decoded data using AI algorithms (e.g., TensorFlow, PyTorch), which quantify each employee's workload and stress level and calculate a condition score based on that data.

[1047] Calculating the Condition Score

[1048] Based on the analysis results, the server classifies each employee's condition score into "high load," "medium load," "low load," etc. This score is calculated by integrating the collected work data, wearable data, and emotional data.

[1049] Report generation and delivery

[1050] The server compiles each employee's condition score and analysis results into a report and notifies the appropriate manager or leader via email or a dedicated application.

[1051] Providing feedback

[1052] Feedback is provided to each employee via a portal site or application, using a generative AI model to suggest specific actions.

[1053] For example, if an employee's condition score is determined to be "high workload," the feedback will be as follows:

[1054] Example prompt sentence:

[1055] User ID: user123, Condition score: High load, Sleep time: 4 hours, Emails sent / received: 50, Phone calls made / received: 20, Meeting participation: 5, Steps taken: 2000

[1056] Based on this condition, suggest specific actions to reduce operator stress.

[1057] Example output of a generative AI model:

[1058] The condition score for user ID: user123 has been determined to be "High Load." The following actions are recommended:

[1059] 1. Make time to relax: Do deep breathing exercises or meditation several times a day.

[1060] 2. Increase physical activity: Incorporate moderate exercise into your daily routine and aim to take at least 5,000 steps per day.

[1061] 3. Improve your sleep quality: Avoid electronic devices and create a relaxing environment before bedtime.

[1062] 4. Manage emails and phone calls: Prioritize and defer non-essential emails and phone calls.

[1063] By implementing these actions, we hope to see improvements in conditions.

[1064] Specific examples

[1065] In the case of Person B, the device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during daily work. The wearable device also collects the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps), and an emotion recognition engine analyzes Person B's stress level from his tone of voice and facial expressions. Person B's data is encrypted and sent to a server, where it is decrypted and analyzed. Based on the analysis results, Person B's condition score is classified as "medium stress" and appropriate feedback is provided.

[1066] The above is a specific embodiment of the present invention.

[1067] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1068] Step 1:

[1069] The device collects data from work devices, including the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. It also obtains data on sleep time and exercise volume from smartphones and wearable devices. It also uses an emotion recognition engine to analyze voice tone and facial expression data. The input at this step is raw data collected from each device, and the output is unencrypted, integrated data.

[1070] Step 2:

[1071] The terminal encrypts the data collected in step 1. In this process, all collected data is encrypted using the PyCryptodome library. The input is the consolidated raw data and the output is the encrypted data.

[1072] Step 3:

[1073] The terminal sends encrypted data to the server using the HTTPS protocol, where the input is the encrypted data and the output is the state of transmission to the server.

[1074] Step 4:

[1075] The server receives the transmitted data and decrypts the encrypted data using the same encryption algorithm (PyCryptodome). The input to this step is the encrypted data, and the output is the decrypted raw data.

[1076] Step 5:

[1077] The server then analyzes the decoded data using AI algorithms. During this process, TensorFlow, PyTorch, and other tools are used to comprehensively evaluate workload, stress level, exercise volume, sleep time, and emotional data. The input is the decoded raw data, and the output is quantified data on workload and stress levels.

[1078] Step 6:

[1079] The server calculates a condition score for each employee based on the analysis results. This score is classified as "high load," "medium load," or "low load." The input in this step is the analyzed data, and the output is the condition score.

[1080] Step 7:

[1081] The server compiles the condition scores into a report format. It integrates the analysis results of the business data, wearable data, and emotional data, and generates a report to provide to managers and leaders. The input is the condition score, and the output is data in report format.

[1082] Step 8:

[1083] The server notifies managers and leaders of the generated report through a notification function. Notifications are sent via email or a dedicated application. The input in this step is the report format data, and the output is the notified state.

[1084] Step 9:

[1085] The server uses the generative AI model to provide specific feedback to employees. For example, if an employee's condition score is determined to be "high workload," the server sends the following prompt sentence as input to the generative AI model. The output is the feedback action.

[1086] Example prompt sentence:

[1087] User ID: user123, Condition score: High load, Sleep time: 4 hours, Emails sent / received: 50, Phone calls made / received: 20, Meeting participation: 5, Steps taken: 2000

[1088] Based on this condition, suggest specific actions to reduce operator stress.

[1089] Based on this prompt, the generative AI model provides the following feedback:

[1090] The condition score for user ID: user123 has been determined to be "High Load." The following actions are recommended:

[1091] 1. Make time to relax: Do deep breathing exercises or meditation several times a day.

[1092] 2. Increase physical activity: Incorporate moderate exercise into your daily routine and aim to take at least 5,000 steps per day.

[1093] 3. Improve your sleep quality: Avoid electronic devices and create a relaxing environment before bedtime.

[1094] 4. Manage emails and phone calls: Prioritize and defer non-essential emails and phone calls.

[1095] By implementing these actions, we hope to see improvements in conditions.

[1096] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1097] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1098] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1099] [Third embodiment]

[1100] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1101] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1102] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1103] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1104] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1105] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1106] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1107] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1108] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1109] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1110] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1111] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1112] This invention is a system that assesses the condition of employees by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, etc. This system allows managers and mentors to effectively manage the health of their employees.

[1113] Program processing

[1114] Data collection

[1115] The device collects data from work email clients, phone applications, and calendar applications. It obtains the number of work emails sent and received, the number of calls made and received, and the number of meetings registered in the calendar via API. Additionally, if the employee consents, the device also obtains data on sleep time and exercise volume from wearable devices (e.g., smartwatches).

[1116] Data Encryption and Transmission

[1117] The device conceals the collected data using an encryption library and transmits it securely to the server via the HTTPS protocol.

[1118] Data Reception and Decryption

[1119] The server receives the data sent from the terminal. Since the received data is encrypted, it is decrypted using a decryption library on the server side to restore it to its original format.

[1120] Data analysis

[1121] The server evaluates the employee's workload, activity level, and stress level based on the decoded data. The analysis uses an AI algorithm to comprehensively assess the number of emails sent and received, the number of calls made and received, the number of meetings attended, and wearable data. Appropriate weighting is applied to each data indicator to calculate the overall workload and stress level.

[1122] Calculating the Condition Score

[1123] The server calculates each employee's condition score based on the analysis results. The condition score is a comprehensive assessment of each employee's workload and stress level, and is classified into categories such as "high workload," "medium workload," and "low workload" based on certain thresholds.

[1124] Report generation and delivery

[1125] The server compiles each employee's condition score into a report, which includes detailed analysis results and specific indicators. The generated report is saved in a database and provided to managers and mentors. Managers and mentors are also notified of the report's creation via a notification function.

[1126] Providing feedback

[1127] The server provides employees with feedback based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[1128] Specific examples

[1129] In the case of Mr. A

[1130] The device collects data on the number of emails sent and received (50), the number of calls made and received (10), and the number of meetings attended (5) during Mr. A's daily work. With Mr. A's consent, the device also collects the amount of sleep (6 hours) and exercise (5,000 steps) per day from the wearable device (smartwatch).

[1131] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses an AI algorithm to analyze Mr. A's condition. For example, it can be determined that he sends and receives many emails and attends many meetings, but that he continues to suffer from a lack of sleep.

[1132] The server calculates Person A's condition score based on the analysis results and classifies him / her as "high stress." The server then compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors then review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself / herself via the portal site, which helps support self-management.

[1133] The processing flow will be explained below.

[1134] Program processing steps

[1135] Step 1: Collect business data

[1136] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[1137] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[1138] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[1139] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[1140] Step 2: Collecting wearable device data

[1141] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[1142] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[1143] Step 3: Encrypt the data

[1144] The terminal encrypts the collected business data and wearable data using an encryption library.

[1145] Encryption library: Encrypts data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, the amount of sleep, and the amount of exercise, and stores the encrypted data in a local database.

[1146] Step 4: Sending data

[1147] The terminal sends the encrypted data to the server using the HTTPS protocol.

[1148] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[1149] Step 5: Receive and decrypt the data

[1150] The server receives the data sent from the terminal.

[1151] HTTP request: Temporarily store received data.

[1152] The server decrypts the received data.

[1153] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[1154] Step 6: Data analysis

[1155] The server analyzes the decrypted data.

[1156] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, and amount of exercise to evaluate employees' workload, activity level, and stress level.

[1157] Step 7: Calculating the Condition Score

[1158] The server calculates each employee's condition score based on the analysis results.

[1159] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[1160] Step 8: Generate and deliver reports

[1161] The server compiles each employee's condition score and analysis results into a report.

[1162] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[1163] The server provides the generated reports to managers and mentors.

[1164] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[1165] Step 9: Provide feedback

[1166] The server provides feedback to each employee.

[1167] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[1168] Example 1

[1169] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1170] In today's corporate environment, appropriately managing employees' workloads and stress levels and protecting their health are important issues. However, current methods make it difficult to collect and analyze individual work data, making it difficult to accurately assess their condition. Furthermore, there is no established method for integrating and analyzing data from wearable devices with work data. As a result, efficient health management and feedback for employees are currently not being provided.

[1171] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1172] In this invention, the server includes means for collecting the number of emails sent and received, the number of communications, and the number of meetings attended in the schedule management system from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side to calculate the workload and stress level of each employee, means for calculating a condition score based on the analysis results, means for compiling the condition score in report format and providing it to an appropriate manager or educational instructor, and means for using a generative artificial intelligence model to analyze the data. This enables integrated analysis of employee work data and individual health data, enabling accurate condition evaluation and effective feedback.

[1173] A "business terminal" is a computer or electronic device used to carry out business within a company or organization.

[1174] "Emails Sent and Received" means the total number of emails received and sent within a specified period of time.

[1175] "Number of communications" means the number of calls made using communication means such as telephone or voice chat.

[1176] A "schedule management system" is software or an electronic system for managing meeting schedules and task schedules.

[1177] "Number of meetings attended" means the total number of meetings attended within a specific period.

[1178] "Encryption" is a technique for converting data into a format that cannot be easily deciphered by third parties.

[1179] A "server" is a computer system that provides data and services to other computers and devices over a network.

[1180] "Decryption" is the technique of returning encrypted data to its original form.

[1181] "Analysis" is the process of analyzing data in detail and extracting specific information.

[1182] "Workload" refers to the total amount of work, difficulty, and time spent by an employee.

[1183] "Stress level" refers to the degree of mental and physical strain felt by employees.

[1184] A "condition score" is a score or index that comprehensively evaluates an employee's workload and stress level.

[1185] A "report" is a document or data that summarizes analysis results and evaluations using text and graphs.

[1186] A "manager" is a person in a company or organization who is responsible for managing the work and health of employees.

[1187] An "educational instructor" is a person who is responsible for improving the skills and providing guidance to employees.

[1188] "Generative artificial intelligence model" is a general term for algorithms or models designed to perform specific tasks using machine learning and deep learning techniques.

[1189] A "wearable device" is an electronic device worn on the body. Examples include smartwatches and fitness bands.

[1190] "Rest time" refers to the time spent sleeping or resting during the day.

[1191] "Physical activity" refers to the total amount of physical activity, such as exercise and movement, that occurs in a day.

[1192] A "portal site" is a website that provides information and services to specific users.

[1193] An "application" is a software program designed to accomplish a particular purpose.

[1194] This invention is a system that collects and analyzes data from employees' daily work to evaluate their workload and stress levels, and supports their health management. This system is primarily composed of business terminals, a server, and wearable devices used by users.

[1195] First, the device collects the following data from your business email client (e.g., Microsoft Outlook), phone application (e.g., Skype for Business), and calendar application (e.g., Google Calendar):

[1196] Number of emails sent and received

[1197] Number of communications

[1198] Number of meetings attended in the schedule management system

[1199] Additionally, if the user consents, the device will collect rest time and physical activity data from wearable devices (e.g., Fitbit, Apple Watch).

[1200] The collected data is encrypted by the device using an encryption library (e.g., OpenSSL) and sent to the server via the HTTPS protocol. The server then decrypts the received encrypted data to its original form using a decryption library.

[1201] The server then uses the decoded data to analyze each employee's workload and stress level using a generative artificial intelligence model (e.g., TensorFlow) and comprehensively evaluates the following factors:

[1202] Number of emails sent and received

[1203] Number of communications

[1204] Number of meetings attended

[1205] Wearable data (rest time, physical activity)

[1206] Each data indicator is weighted appropriately to produce a condition score, which is then categorized into "high stress," "medium stress," and "low stress."

[1207] The server compiles the condition scores for each employee based on the analysis results in the form of a report. The report contains details of the analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational instructors. Administrators and educational instructors are notified of the generation of the report via a notification function.

[1208] The server also provides feedback to employees based on their condition scores. This feedback is sent to employees via a portal site or dedicated application, and includes information that helps support self-management and improvement.

[1209] Specific examples

[1210] For example, in the case of Person A, the device will collect data on the number of emails sent and received (50), the number of communications (10), and the number of meetings attended (5) in Person A's daily work. In addition, with Person A's consent, the device will also obtain the amount of rest time (6 hours) and the amount of physical activity (5,000 steps) from the wearable device.

[1211] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses a generative AI model to analyze Person A's condition. For example, it can be determined that although he sends and receives many emails and attends many meetings, he continues to lack rest.

[1212] Based on the analysis results, the server classifies Person A's condition score as "high stress." The analysis results are compiled in a report and provided to administrators and educational instructors. The administrators and educational instructors review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself through the portal site, which helps support his self-management.

[1213] Example prompts for generative AI models

[1214] prompt:

[1215] Calculate your condition score based on the employee data below.

[1216] data:

[1217] Number of emails sent and received: 50

[1218] Number of communications: 10

[1219] Number of meetings attended: 5

[1220] Rest time: 6 hours

[1221] Physical activity: 5,000 steps

[1222] An example of the output produced:

[1223] Condition Score: High Load

[1224] Details: The workload was assessed as high due to the high volume of emails sent and received and the high number of meetings attended, as well as the continued lack of rest.

[1225] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1226] Step 1: Collect data

[1227] The device collects data from the user's daily work. Specifically, data on the number of emails sent and received from the business email client, the number of communications from the phone application, and the number of meetings attended from the calendar application are input. In addition, if the user consents, data on rest time and physical activity levels are also collected from the wearable device. This data is obtained using an API and stored in the device's local storage.

[1228] Input: Number of emails sent and received, number of communications, number of meetings attended, rest time, amount of physical activity

[1229] Output: Collected data (stored in local storage)

[1230] Specific operation: The device makes the following API request:

[1231] GET / api / mail / received?user_id=A

[1232] GET / api / calendar / meetings?user_id=A

[1233] GET / api / phone / calls?user_id=A

[1234] GET / api / wearable / data?user_id=A

[1235] Step 2: Encrypt the data and send it to the server

[1236] The device encrypts the collected data using an encryption library (e.g., OpenSSL), and the encrypted data is sent to the server via the HTTPS protocol to ensure security.

[1237] Input: Collected data

[1238] Output: Encrypted data (sent to server)

[1239] Specific operation: Encrypts the data in JSON format and sends a POST request to the server.

[1240] POST / api / data

[1241] Content-Type: application / json

[1242] {

[1243] "user_id": "A",

[1244] "data": "encryptedData"

[1245] }

[1246] Step 3: Receive and decrypt the data

[1247] The server receives the encrypted data sent from the device, and uses a decryption library to restore the data to its original format.

[1248] Input: Encrypted data

[1249] Output: Decrypted data

[1250] What happens: The server uses an encryption library to decrypt the data.

[1251] encryptedData = request.body.data;

[1252] rawData = OpenSSL::Decrypt(encryptedData);

[1253] Step 4: Analyze the data

[1254] The server uses the decoded data it receives to analyze each employee's workload and stress level. A generative AI model (e.g., TensorFlow) is used for the analysis, and a comprehensive evaluation is made of the number of emails sent and received, the number of communications, the number of meetings attended, and wearable data. An appropriate weighting is then assigned to each data indicator to calculate an overall condition score.

[1255] Input: Decrypted data

[1256] Output: Analysis results (work load and stress level, condition score)

[1257] What it does: It uses an AI model to analyze data and predict scores.

[1258] model = tf.keras.models.load_model('condition_model.h5')

[1259] data = {"emails": rawData["emails"], "calls": rawData["calls"], "meetings": rawData["meetings"], "sleep": rawData["sleep"], "steps": rawData["steps"]}

[1260] condition_score = model.predict(data)

[1261] Step 5: Calculating the Condition Score

[1262] Based on the results of the AI ​​algorithm analysis, the server calculates a condition score for each employee, which is categorized into "high load," "medium load," and "low load."

[1263] Input: Analysis results

[1264] Output: Condition Score

[1265] Specific Behavior: Evaluate condition scores and categorize them.

[1266] thresholds = {"low": 0.3, "medium": 0.7, "high": 1.0}

[1267] condition_value = condition_score[0]

[1268] if condition_value < thresholds["low"]:

[1269] condition_category = "Low load"

[1270] elif condition_value < thresholds["medium"]:

[1271] condition_category = "Medium load"

[1272] else:

[1273] condition_category = "High load"

[1274] Step 6: Generate and deliver reports

[1275] The server generates a report based on the calculated condition score. The report contains detailed analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational leaders. Administrators and educational leaders are notified of the generation of the report via a notification function.

[1276] Input: Condition score, analysis results

[1277] Output: Report (Saved to database, Notification)

[1278] Specific actions: Generate a report, save it in a database, and notify the administrator.

[1279] report = {

[1280] "user_id": "A",

[1281] "condition_score": condition_category,

[1282] "details": rawData,

[1283] "analysis_time": datetime.now()

[1284] }

[1285] db.save(report)

[1286] notification.send("Report generated", user_id="A")

[1287] Step 7: Provide feedback

[1288] The server provides feedback to employees based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[1289] Input: Condition Score

[1290] Output: Feedback (notification)

[1291] Specific behavior: Generate feedback and communicate it through portals and applications.

[1292] feedback = f"{condition_category}:Due to the increased workload recently, we recommend that you take a proper rest."

[1293] notification.send(feedback, user_id="A")

[1294] (Application example 1)

[1295] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1296] In recent years, there has been growing emphasis on managing the health and workload of factory workers, but conventional systems only collect and analyze data from office work, making it difficult to accurately grasp the condition of factory workers. For this reason, there is a need for a new system that can detect worker fatigue and stress early and provide appropriate feedback.

[1297] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1298] In this invention, the server includes: means for collecting the number of emails sent and received, the number of outgoing and incoming calls, and the number of calendar meetings attended from business terminals; means for encrypting the collected data and sending it to the server; means for decrypting and analyzing the data on the server side to calculate each employee's workload and stress level; means for calculating a condition score based on the analysis results; means for compiling the condition score in report format and providing it to an appropriate manager or mentor; means for collecting the body temperature, heart rate, and work log of factory workers using smart glasses, encrypting the data in the same way, and sending it to the server; and means for evaluating the fatigue and stress levels of factory workers based on the collected data and providing breaks and feedback at appropriate times. This allows for real-time monitoring of the health status of factory workers, improving work efficiency, and ensuring safety.

[1299] A "business terminal" is an information processing device such as a computer used by a company or organization.

[1300] "Number of emails sent and received" is the total number of emails sent and received during a certain period of time.

[1301] "Number of calls made and received" refers to the total number of calls made and received via telephone or communication apps over a certain period of time.

[1302] "Number of meetings attended in calendar" refers to the number of times a person has attended a conference or meeting registered in an electronic calendar.

[1303] A "collection means" is a method or device used to obtain and store particular data.

[1304] An "encryption means" is a method or device that converts data from a readable form to an obfuscated form in order to protect it.

[1305] A "server" is a computer system that stores data and provides services to other computers and devices over a network.

[1306] A "decryption means" is a method or device that returns encrypted data to its original, readable form.

[1307] An "analyzing means" is a method or device for processing collected data and extracting meaningful information.

[1308] "Workload" refers to the amount of tasks or work that an employee handles as part of their job during a specific period of time.

[1309] "Stress level" refers to the degree of mental and physical stress felt by employees over a specific period of time.

[1310] A "condition score" is a numerical indicator that represents an employee's health status and workload.

[1311] A "report format" is a document format that summarizes collected and analyzed information in an easy-to-understand format.

[1312] A "management position" is a person in a position responsible for management or leadership within an organization.

[1313] A "mentor" is someone whose role is to provide guidance and advice on specific knowledge and skills.

[1314] "Smart glasses" are a wearable device in the form of glasses that displays visual information on a screen and can be connected to a computer or network.

[1315] "Body temperature" is an indicator of the worker's body temperature.

[1316] "Heart rate" is the number of times the heart beats within a certain period of time.

[1317] A "work log" is a detailed record of the work performed by a worker.

[1318] "Fatigue level" refers to the degree of physical and mental fatigue felt during work.

[1319] "Real-time" means that information is updated and processed almost immediately.

[1320] The present invention is a system for monitoring the health and workload of factory workers in real time and providing appropriate feedback. The system includes a business terminal, smart glasses, a wearable device, and a server.

[1321] Data collection

[1322] The business devices collect business data such as the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. In addition, smart glasses are used to collect the factory workers' body temperature, heart rate, and work logs. This data is encrypted immediately upon collection. The encryption uses the OpenSSL library to protect the data.

[1323] Data Encryption and Transmission

[1324] The data is encrypted and then securely transmitted to the server using the HTTPS protocol, using the standard SSL / TLS protocol to ensure secure communication.

[1325] Data Reception and Decryption

[1326] The server then decrypts the received data using the PyCrypto library, which returns the data to its original, readable form for analysis.

[1327] Data analysis

[1328] The server calculates the workload and stress level of workers based on the decoded data. The analysis uses TensorFlow and PyTorch and utilizes a generative AI model. Specifically, the server comprehensively analyzes the number of emails sent and received, the number of meetings attended, body temperature, heart rate, and work logs, and assigns appropriate weights to the data indicators.

[1329] Calculating condition scores and providing feedback

[1330] Based on the analysis results, a condition score is calculated for each employee. The condition score is a comprehensive assessment of the employee's workload and stress level. This score is provided to the worker in real time via the smart glasses' built-in display. The analysis results are then compiled into a report and provided to managers and mentors.

[1331] Specific examples

[1332] For example, suppose a factory worker has a body temperature of 37.2°C, a heart rate of 85 bpm, and has not taken a break in the past hour. Based on this data, the system determines that the worker is highly fatigued and displays an alert on the smart glasses display urging the worker to take a break. The system also notifies managers that the worker's condition score is "high strain."

[1333] Prompt Sentence Examples

[1334] "Collect daily work data (body temperature, heart rate, break times) from factory workers and create an AI model that evaluates their condition from the analysis results. Design an application that provides feedback and alerts based on the condition score."

[1335] This will not only enable factory workers to properly manage their health, but also enable managers and mentors to understand the health of workers and provide appropriate support. By using this system, it will be possible to improve work efficiency and safety.

[1336] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1337] Step 1:

[1338] The business device collects the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee. This data is obtained using the business device's API. The input data is employee activity information, and the output is business data before encryption. Specifically, this includes operations that make API calls from email clients, phone apps, and calendar apps.

[1339] Step 2:

[1340] The terminal encrypts the data collected in step 1 using the OpenSSL library. The input data is the business data described above, and the output data is the encrypted business data. Specifically, this includes the operation of performing encryption processing using AES encryption.

[1341] Step 3:

[1342] The terminal sends encrypted data to the server using the HTTPS protocol. The input data is encrypted business data, and the output is the data sent to the server. Specifically, this includes the operation of creating and sending an HTTPS request.

[1343] Step 4:

[1344] The server decrypts the data sent from the terminal using the PyCrypto library. The input data is encrypted business data, and the output is decrypted business data. Specifically, it includes the operation of performing decryption processing using AES decryption.

[1345] Step 5:

[1346] The server inputs the decoded data into a generative AI model using TensorFlow or PyTorch to analyze workload and stress levels. The input data is the decoded workload data, and the output is the evaluation results of workload and stress levels. Specifically, this includes the operation of performing data analysis processing using the AI ​​model.

[1347] Step 6:

[1348] The server calculates a condition score for each employee based on the analysis results. The input data are the evaluation results of workload and stress level, and the output is a condition score for each employee. Specifically, it includes operations for weighting and score calculation based on the evaluation results.

[1349] Step 7:

[1350] The server compiles the condition scores into a report and provides it to the appropriate manager or mentor. The input data is the condition score, and the output is a report that is delivered to the manager or mentor. Specifically, it uses a report generation algorithm and includes operations such as email and dashboard notifications.

[1351] Step 8:

[1352] The smart glasses collect the body temperature, heart rate, and work logs (such as working hours and break times) of factory workers. This data is acquired using the smart glasses' sensors and API. The input data is sensor information, and the output is work data before encryption. Specifically, this includes operations that utilize the body temperature sensor, heart rate sensor, and work log recording function.

[1353] Step 9:

[1354] The smart glasses encrypt the collected data using the OpenSSL library and send it to the server. The input data is sensor information, and the output is encrypted working data. Specifically, the glasses perform operations including encryption using AES encryption and sending HTTPS requests.

[1355] Step 10:

[1356] The server decrypts the data sent from the smart glasses and analyzes the condition of the factory workers. The input data is encrypted work data, and the output is the worker condition evaluation results. Specifically, the server performs operations such as decryption processing and evaluation processing using a data analysis model.

[1357] Step 11:

[1358] The smart glasses display break and feedback alerts to workers in real time. The input data is the condition assessment results from the server, and the output is the alerts displayed on the smart glasses display. Specifically, it includes the operation of displaying feedback messages on the display.

[1359] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1360] This invention is a system that accurately assesses an employee's condition by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, and combining it with user emotional data, allowing managers and mentors to effectively monitor and support the health of their employees.

[1361] Program processing

[1362] Data collection

[1363] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of meetings attended from the email client, phone application, and calendar application installed on the work device. If the employee consents, the device also collects data on sleep time and exercise volume from wearable devices (e.g., smartwatches). Furthermore, the device uses an emotion engine to analyze the user's emotional state from their voice data and facial expression data.

[1364] Data Encryption and Transmission

[1365] The device encrypts the collected business data, wearable data, and emotion data and transmits them securely to the server using an encryption library and the HTTPS protocol.

[1366] Data Reception and Decryption

[1367] The server receives the data sent from the device, decrypts the encrypted data, and stores it in a database, ready for analysis.

[1368] Data analysis

[1369] The server analyzes the decrypted data, integrating data such as the number of emails sent and received, the number of meetings attended, sleep time, exercise level, and emotional data. An AI algorithm is used for the analysis, weighting each data indicator appropriately to assess the employee's workload and stress level.

[1370] Calculating the Condition Score

[1371] The server calculates a condition score for each employee based on the analysis results. By combining this with emotional data, stress levels can be corrected to provide a more accurate condition score. Scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[1372] Report generation and delivery

[1373] The server compiles each employee's condition score and analysis results into a report. The generated report is saved in a database and notified to managers and mentors. A notification function also encourages employees to check the report.

[1374] Providing feedback

[1375] The server provides feedback to each employee, who is then notified of the feedback via a portal site or dedicated application, providing support for self-management and improvement.

[1376] Specific examples

[1377] In the case of person B

[1378] The device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during B's daily work. With B's consent, the device also collects the amount of sleep (7 hours) and exercise (6,000 steps) per day from the wearable device (smartwatch).

[1379] In addition, the device uses an emotion engine to analyze B's voice and facial expression data to determine his / her stress level. For example, it may detect that B is under high stress based on his / her voice tone and facial expression.

[1380] The device encrypts all collected data and sends it to the server. The server decrypts the data and analyzes Mr. B's condition using an AI algorithm. Based on the analysis results, Mr. B's condition score is classified as "medium load."

[1381] The server compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors review the report and provide appropriate support and feedback to Person B. Feedback is also provided to Person B himself via the portal site, which helps support his self-management.

[1382] The processing flow will be explained below.

[1383] MODE FOR CARRYING OUT THE INVENTION

[1384] This invention is a system that collects and analyzes work data, wearable data, and emotional data to assess an employee's condition, allowing managers and mentors to gain a detailed understanding of their employees' health status and provide appropriate support.

[1385] Program processing steps

[1386] Step 1: Collect business data

[1387] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[1388] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[1389] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[1390] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[1391] Step 2: Collecting wearable device data

[1392] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[1393] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[1394] Step 3: Collecting emotion data

[1395] The device uses an emotion engine to analyze the user's voice data and facial expression data to determine the user's stress level and emotional state.

[1396] Emotion Engine: Using voice recordings and camera data, it analyzes changes in voice tone and facial expressions to generate emotion data, which is then stored in a local database.

[1397] Step 4: Encrypt the data

[1398] The device encrypts the collected business data, wearable data, and emotion data using an encryption library.

[1399] Encryption library: Encrypts data such as the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, exercise amount, and emotional data, and stores the encrypted data in a local database.

[1400] Step 5: Sending data

[1401] The terminal sends the encrypted data to the server using the HTTPS protocol.

[1402] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[1403] Step 6: Receive and decrypt data

[1404] The server receives the data sent from the terminal.

[1405] HTTP request: Temporarily store received data.

[1406] The server decrypts the received data.

[1407] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[1408] Step 7: Data analysis

[1409] The server analyzes the decrypted data.

[1410] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, amount of exercise, and emotional data to evaluate employees' workload, activity level, and stress level.

[1411] Analysis results: Based on the analysis results, the workload and stress level of each employee are evaluated and expressed as a numerical value.

[1412] Step 8: Calculating the Condition Score

[1413] The server calculates each employee's condition score based on the analysis results.

[1414] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[1415] Step 9: Generate and deliver reports

[1416] The server compiles each employee's condition score and analysis results into a report.

[1417] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[1418] The server provides the generated reports to managers and mentors.

[1419] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[1420] Step 10: Provide feedback

[1421] The server provides feedback to each employee.

[1422] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[1423] Example 2

[1424] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1425] In today's corporate environment, it is important to accurately understand employees' workloads and stress levels and provide appropriate support. However, conventional systems only collect operational data such as the number of emails sent and received, phone calls made and received, and number of meetings attended, which is not enough to accurately assess an employee's condition. Furthermore, relying solely on numerical data makes it difficult to consider an employee's mental state or physical health. To solve this problem, a more diversified and comprehensive method of data collection and analysis is needed.

[1426] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1427] In this invention, the server includes means for collecting the number of emails sent and received, the number of phone calls made and received, and the number of calendar meetings attended from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side, means for analyzing the emotional state of employees from their voice data and facial expression data, means for calculating the workload and stress level of each employee, means for calculating a condition score based on the analysis results, and means for compiling the condition score in report format and providing it to an appropriate manager or instructor. This allows for an integrated analysis of employee work data as well as emotional and physical data, enabling more accurate condition evaluations.

[1428] "Business terminals" are computers and smart devices used by employees within a company to carry out their work.

[1429] "Emails Sent and Received" means the total number of emails sent and received by an employee within a specified period of time.

[1430] "Number of calls made and received" is the total number of calls made and received by an employee during a specified period.

[1431] "Calendar Meeting Attendance" is the total number of meetings that an employee has registered to attend in scheduling software.

[1432] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is a means of ensuring security.

[1433] A "server" is a computer system that provides data or services to multiple clients over a network.

[1434] "Decryption" is the process of returning encrypted data to its original, readable form.

[1435] "Analysis" is the process of using collected data to extract and evaluate information for a specific purpose.

[1436] "Emotional state" is the result of judging an individual's mental state obtained through voice and facial expression data.

[1437] "Workload" is a measure of the amount of work and difficulty an employee feels when performing their job.

[1438] "Stress level" is a measure of the degree of psychological and physiological stress felt by an individual.

[1439] A "Condition Score" is a comprehensive score calculated to assess an employee's overall work situation and health.

[1440] A "report format" is a document format that visually organizes analysis results and presents them in an easy-to-understand manner.

[1441] A "manager" is someone who supervises and supports the work of employees within an organization.

[1442] A "leader" is someone whose role is to educate and support employees within an organization.

[1443] "Wearable devices" are small electronic devices and related technologies that can be worn by a user.

[1444] "Sleep time" is the total time an employee was asleep.

[1445] "Amount of exercise" is the cumulative amount of physical activity an employee engages in within a specific period of time.

[1446] This invention is a system that accurately assesses the condition of employees by collecting and analyzing data from various angles related to their daily work. The system analyzes data collected from business terminals on a server and provides useful information to managers and instructors, aiming to effectively monitor and support employees' health and stress levels.

[1447] Data collection

[1448] The device collects data from the email client, phone application, and calendar application installed on the work device. Specifically, it uses an API to obtain the number of emails sent and received, the number of phone calls made and received, and the number of meetings attended. If the employee consents, the device also collects data on sleep time and exercise volume from a wearable device (e.g., a smartwatch). Furthermore, an emotion engine is used to analyze the user's voice data and facial expression data to evaluate their emotional state. This makes it possible to collect data that can be used to comprehensively evaluate not only employees' work performance, but also their mental and health states.

[1449] Data Encryption and Transmission

[1450] The device encrypts the collected and analyzed data and transmits it to the server with a high level of security. The encryption is performed using the AES encryption library and the HTTPS protocol for data transmission, ensuring confidentiality and integrity of the data.

[1451] Data Reception and Decryption

[1452] The server receives the encrypted data sent from the device and decrypts it in a secure environment, where it is stored in a database until it is ready to be analyzed.

[1453] Data analysis

[1454] The server performs an integrated analysis of data collected from various data sources. First, it integrates business data (emails, phone calls, meeting participation), wearable data, and emotional data, and then analyzes them using an AI algorithm. The specific algorithm assigns appropriate weights to each data indicator to evaluate employees' workload and stress levels.

[1455] Calculating the Condition Score

[1456] Based on the analysis results, the server calculates a condition score for each employee. This score can be combined with emotional data to correct for stress levels, enabling more accurate assessments. Condition scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[1457] Report generation and delivery

[1458] The server compiles the analysis results and condition scores into a report. The generated report is saved in a database and notified to the appropriate administrator or instructor. Notifications are sent via email or the alert function on the portal site.

[1459] Providing feedback

[1460] Finally, the server provides feedback to each employee, which is then communicated to the employee via a portal site or dedicated application, and used as a guide for self-management and improvement.

[1461] Specific examples

[1462] For example, in the case of Person B, the device collects data on the number of emails sent and received (30), the number of phone calls made and received (15), and the number of meetings attended (3) in Person B's daily work. Furthermore, with Person B's consent, data on the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps) is also collected from the wearable device. Person B's voice data and facial expression data are analyzed using an emotion engine to determine their stress level. For example, it can detect that Person B is feeling increasingly stressed from their voice tone and facial expression.

[1463] The device encrypts all of this data and sends it to the server. The server decrypts the data and uses an AI algorithm to analyze Person B's condition. Based on the results of this analysis, Person B's condition score is classified as "medium load." The server compiles the analysis results into a report and provides it to the manager or coach. The manager or coach reviews the report and provides appropriate support and feedback to Person B. Person B also receives feedback via a portal site, which can be used to help with self-management.

[1464] Prompt Sentence Examples

[1465] "Please explain in detail the specific steps you take to collect data on Mr. B's daily work and analyze his condition."

[1466] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1467] Program processing steps

[1468] Step 1: Start collecting data

[1469] The device accesses the email client, phone application, and calendar application on the business device according to a specific time schedule.

[1470] Input: Each application on the user's work computer.

[1471] Output: Raw data obtained from each application.

[1472] Specific operation:

[1473] The device calls the email client's API and collects the number of emails sent and received.

[1474] The device calls the API of the phone application and collects the number of calls made and received.

[1475] The device calls the calendar application API to collect the number of meetings attended.

[1476] Step 2: Wearable data collection

[1477] The device works in conjunction with a wearable device (e.g., a smartwatch) to obtain the user's sleep time and exercise volume.

[1478] Input: Sensor data from wearable devices.

[1479] Output: Data on sleep duration and exercise.

[1480] Specific operation:

[1481] The device retrieves the data via the wearable device's API and stores it locally.

[1482] Sleep duration is obtained from the wearable device's activity tracker, and exercise volume is obtained from the pedometer sensor.

[1483] Step 3: Sentiment Data Analysis

[1484] The device uses an emotion engine to analyze the user's voice data and facial expression data to evaluate their emotional state.

[1485] Input: User's voice and facial expression data.

[1486] Output: Parsed emotion data.

[1487] Specific operation:

[1488] The device uses a voice recognition engine to analyze voice tone and pitch.

[1489] Using a facial expression recognition engine, facial images acquired from a camera are analyzed to determine the emotional state.

[1490] Step 4: Data Encryption

[1491] The device encrypts all collected data and prepares it for transmission to the server.

[1492] Input: Each dataset collected and analyzed.

[1493] Output: Encrypted data bundle.

[1494] Specific operation:

[1495] The terminal uses the AES encryption library to encrypt the data set.

[1496] Create a batch to send encrypted data to the server via HTTPS protocol.

[1497] Step 5: Send data

[1498] The terminal transmits the encrypted data to the server.

[1499] Input: Encrypted data bundle.

[1500] Output: The data sent to the server.

[1501] Specific operation:

[1502] The device uses the HTTPS protocol to send encrypted data to the server.

[1503] A manual or automated submission process sends the data to an endpoint where the server can receive it.

[1504] Step 6: Data Reception and Decryption

[1505] The server receives and decrypts the data sent from the terminal.

[1506] Input: The received encrypted data.

[1507] Output: Decoded raw data.

[1508] Specific operation:

[1509] The server uses a secure endpoint to receive encrypted data.

[1510] The received data is decrypted to restore it to its original data format.

[1511] Step 7: Data integration and analysis

[1512] The server integrates and analyzes business data, wearable data, and emotional data.

[1513] Input: The decoded dataset.

[1514] Output: Analysis results.

[1515] Specific operation:

[1516] The server uses a data management system to integrate each dataset.

[1517] AI algorithms are applied to analyze data and evaluate workload and stress levels.

[1518] Step 8: Calculating the Condition Score

[1519] Based on the analysis results, the server calculates each employee's condition score.

[1520] Input: Analysis results.

[1521] Output: Condition score.

[1522] Specific operation:

[1523] The condition score is calculated based on an AI algorithm.

[1524] The calculation results are classified into specific score categories (high load, medium load, low load).

[1525] Step 9: Reporting and Notifications

[1526] The server compiles each employee's condition score and analysis data into a report format and provides it to managers and instructors.

[1527] Input: Condition score and analysis data.

[1528] Output: The generated report.

[1529] Specific operation:

[1530] The server organizes and structures the analysis results using report generation templates.

[1531] The completed reports are stored in a database and notifications are sent to managers and leaders through a notification system.

[1532] Step 10: Provide feedback

[1533] The server provides individual feedback to each employee.

[1534] Input: Condition score and analysis results.

[1535] Output: The feedback provided.

[1536] Specific operation:

[1537] The server automatically generates feedback content and notifies employees via a portal site or dedicated application.

[1538] Employees can refer to the feedback provided to help them self-manage and improve.

[1539] (Application example 2)

[1540] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1541] In many modern business situations, it is important to properly manage employee workload and stress. However, conventional systems assess employee health based solely on work data, making it difficult to accurately assess workload. Furthermore, systems lacked the mechanisms for combining emotional data and data from wearable devices, resulting in delayed or inaccurate feedback. This can lead to a deterioration in employee health and a drop in productivity.

[1542] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the number of emails sent and received, the number of calls made and received, and the number of meetings attended on the calendar from the business terminals, means for encrypting the collected data and sending it to the server, and means for decrypting and analyzing the data on the server side and calculating the workload and stress level of each employee. This enables detailed data collection and analysis.

[1543] Furthermore, the server includes means for collecting data on sleep duration and exercise volume from the smartphone and wearable device, analyzing voice and facial expressions using an emotion recognition engine, means for classifying condition scores into categories such as high, medium, and low stress based on the analysis results, and means for notifying managers and leaders of the analysis results through a notification function, thereby enabling real-time evaluation of the overall health status of employees and providing prompt feedback.

[1544] "Business terminals" are electronic devices such as computers and smartphones used in companies and organizations.

[1545] "Emails Sent and Received" means the total number of emails sent and received within a specified period of time.

[1546] "Number of outgoing and incoming calls" refers to the total number of outgoing and incoming voice calls made within a specific period of time.

[1547] "Calendar meeting attendance count" refers to the number of scheduled meetings attended within a specific period.

[1548] A "collection means" is a method or device for obtaining and recording data.

[1549] "Encryption" is the process of transforming data using a specific algorithm in order to secure it.

[1550] A "server" is a computer system that stores, manages, and analyzes data.

[1551] "Decryption" is the process of restoring encrypted data to its original state.

[1552] "Analysis" is the process of examining data in detail to derive useful information.

[1553] "Workload" refers to the amount of work an employee handles in a given period of time.

[1554] "Stress level" is the degree of mental or emotional strain experienced by an employee.

[1555] The "condition score" is a numerical representation of an employee's health status and workload calculated based on the analysis results.

[1556] A "report" is a report that summarizes and organizes the results of analysis.

[1557] A "smartphone" is a mobile phone that can connect to the Internet and use applications in addition to making calls.

[1558] A "wearable device" is an electronic device that can be worn and used.

[1559] "Sleep time" refers to the actual time spent asleep within a specific period of time.

[1560] "Movement" is the amount of physical activity performed within a specific period of time.

[1561] An "emotion recognition engine" is software or a system for analyzing emotional states from voice, facial expressions, etc.

[1562] "Analysis of voice and facial expressions" is the process of extracting specific information from voice and facial expressions and making judgments based on that information.

[1563] "High workload, medium workload, low workload" refers to the level of workload and stress classified based on the condition score.

[1564] The "notification function" is a function for notifying the user of specific information.

[1565] "Managers and leaders" are people in positions that involve managing and guiding employees.

[1566] This invention is a system for accurately assessing the health status and workload of employees in a corporate environment such as a factory. The system collects data using smartphones and wearable devices, analyzes the data on a server, and provides the results to managers and instructors.

[1567] System Configuration

[1568] The system consists of the following hardware and software:

[1569] Smartphones (e.g. iPhone, Android devices)

[1570] Wearable devices (e.g., Apple Watch, Fitbit)

[1571] Server (e.g. Amazon Web Services (AWS), Google Cloud Platform)

[1572] Data collection

[1573] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee during their daily work. It also collects data on sleep time and exercise volume from smartphones and wearable devices. Furthermore, it uses an emotion recognition engine to analyze voice and facial expression data.

[1574] Data Encryption and Transmission

[1575] The device encrypts the collected data and sends it to a server using the HTTPS protocol, for example using the PyCryptodome library.

[1576] Data Reception and Decryption

[1577] The server receives the encrypted data, decrypts it, and stores it in a database, ready for analysis. Databases used include MySQL and PostgreSQL.

[1578] Data analysis

[1579] The server analyzes the decoded data using AI algorithms (e.g., TensorFlow, PyTorch), which quantify each employee's workload and stress level and calculate a condition score based on that data.

[1580] Calculating the Condition Score

[1581] Based on the analysis results, the server classifies each employee's condition score into "high load," "medium load," "low load," etc. This score is calculated by integrating the collected work data, wearable data, and emotional data.

[1582] Report generation and delivery

[1583] The server compiles each employee's condition score and analysis results into a report and notifies the appropriate manager or leader via email or a dedicated application.

[1584] Providing feedback

[1585] Feedback is provided to each employee via a portal site or application, using a generative AI model to suggest specific actions.

[1586] For example, if an employee's condition score is determined to be "high workload," the feedback will be as follows:

[1587] Example prompt sentence:

[1588] User ID: user123, Condition score: High load, Sleep time: 4 hours, Emails sent / received: 50, Phone calls made / received: 20, Meeting participation: 5, Steps taken: 2000

[1589] Based on this condition, suggest specific actions to reduce operator stress.

[1590] Example output of a generative AI model:

[1591] The condition score for user ID: user123 has been determined to be "High Load." The following actions are recommended:

[1592] 1. Make time to relax: Do deep breathing exercises or meditation several times a day.

[1593] 2. Increase physical activity: Incorporate moderate exercise into your daily routine and aim to take at least 5,000 steps per day.

[1594] 3. Improve your sleep quality: Avoid electronic devices and create a relaxing environment before bedtime.

[1595] 4. Manage emails and phone calls: Prioritize and defer non-essential emails and phone calls.

[1596] By implementing these actions, we hope to see improvements in conditions.

[1597] Specific examples

[1598] In the case of Person B, the device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during daily work. The wearable device also collects the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps), and an emotion recognition engine analyzes Person B's stress level from his tone of voice and facial expressions. Person B's data is encrypted and sent to a server, where it is decrypted and analyzed. Based on the analysis results, Person B's condition score is classified as "medium stress" and appropriate feedback is provided.

[1599] The above is a specific embodiment of the present invention.

[1600] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1601] Step 1:

[1602] The device collects data from work devices, including the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. It also obtains data on sleep time and exercise volume from smartphones and wearable devices. It also uses an emotion recognition engine to analyze voice tone and facial expression data. The input at this step is raw data collected from each device, and the output is unencrypted, integrated data.

[1603] Step 2:

[1604] The terminal encrypts the data collected in step 1. In this process, all collected data is encrypted using the PyCryptodome library. The input is the consolidated raw data and the output is the encrypted data.

[1605] Step 3:

[1606] The terminal sends encrypted data to the server using the HTTPS protocol, where the input is the encrypted data and the output is the state of transmission to the server.

[1607] Step 4:

[1608] The server receives the transmitted data and decrypts the encrypted data using the same encryption algorithm (PyCryptodome). The input to this step is the encrypted data, and the output is the decrypted raw data.

[1609] Step 5:

[1610] The server then analyzes the decoded data using AI algorithms. During this process, TensorFlow, PyTorch, and other tools are used to comprehensively evaluate workload, stress level, exercise volume, sleep time, and emotional data. The input is the decoded raw data, and the output is quantified data on workload and stress levels.

[1611] Step 6:

[1612] The server calculates a condition score for each employee based on the analysis results. This score is classified as "high load," "medium load," or "low load." The input in this step is the analyzed data, and the output is the condition score.

[1613] Step 7:

[1614] The server compiles the condition scores into a report format. It integrates the analysis results of the business data, wearable data, and emotional data, and generates a report to provide to managers and leaders. The input is the condition score, and the output is data in report format.

[1615] Step 8:

[1616] The server notifies managers and leaders of the generated report through a notification function. Notifications are sent via email or a dedicated application. The input in this step is the report format data, and the output is the notified state.

[1617] Step 9:

[1618] The server uses the generative AI model to provide specific feedback to employees. For example, if an employee's condition score is determined to be "high workload," the server sends the following prompt sentence as input to the generative AI model. The output is the feedback action.

[1619] Example prompt sentence:

[1620] User ID: user123, Condition score: High load, Sleep time: 4 hours, Emails sent / received: 50, Phone calls made / received: 20, Meeting participation: 5, Steps taken: 2000

[1621] Based on this condition, suggest specific actions to reduce operator stress.

[1622] Based on this prompt, the generative AI model provides the following feedback:

[1623] The condition score for user ID: user123 has been determined to be "High Load." The following actions are recommended:

[1624] 1. Make time to relax: Do deep breathing exercises or meditation several times a day.

[1625] 2. Increase physical activity: Incorporate moderate exercise into your daily routine and aim to take at least 5,000 steps per day.

[1626] 3. Improve your sleep quality: Avoid electronic devices and create a relaxing environment before bedtime.

[1627] 4. Manage emails and phone calls: Prioritize and defer non-essential emails and phone calls.

[1628] By implementing these actions, we hope to see improvements in conditions.

[1629] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1630] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1631] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1632] [Fourth embodiment]

[1633] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1634] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1635] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1636] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1637] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1638] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1639] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1640] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1641] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1642] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1643] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1644] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1645] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1646] This invention is a system that assesses the condition of employees by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, etc. This system allows managers and mentors to effectively manage the health of their employees.

[1647] Program processing

[1648] Data collection

[1649] The device collects data from work email clients, phone applications, and calendar applications. It obtains the number of work emails sent and received, the number of calls made and received, and the number of meetings registered in the calendar via API. Additionally, if the employee consents, the device also obtains data on sleep time and exercise volume from wearable devices (e.g., smartwatches).

[1650] Data Encryption and Transmission

[1651] The device conceals the collected data using an encryption library and transmits it securely to the server via the HTTPS protocol.

[1652] Data Reception and Decryption

[1653] The server receives the data sent from the terminal. Since the received data is encrypted, it is decrypted using a decryption library on the server side to restore it to its original format.

[1654] Data analysis

[1655] The server evaluates the employee's workload, activity level, and stress level based on the decoded data. The analysis uses an AI algorithm to comprehensively assess the number of emails sent and received, the number of calls made and received, the number of meetings attended, and wearable data. Appropriate weighting is applied to each data indicator to calculate the overall workload and stress level.

[1656] Calculating the Condition Score

[1657] The server calculates each employee's condition score based on the analysis results. The condition score is a comprehensive assessment of each employee's workload and stress level, and is classified into categories such as "high workload," "medium workload," and "low workload" based on certain thresholds.

[1658] Report generation and delivery

[1659] The server compiles each employee's condition score into a report, which includes detailed analysis results and specific indicators. The generated report is saved in a database and provided to managers and mentors. Managers and mentors are also notified of the report's creation via a notification function.

[1660] Providing feedback

[1661] The server provides employees with feedback based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[1662] Specific examples

[1663] In the case of Mr. A

[1664] The device collects data on the number of emails sent and received (50), the number of calls made and received (10), and the number of meetings attended (5) during Mr. A's daily work. With Mr. A's consent, the device also collects the amount of sleep (6 hours) and exercise (5,000 steps) per day from the wearable device (smartwatch).

[1665] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses an AI algorithm to analyze Mr. A's condition. For example, it can be determined that he sends and receives many emails and attends many meetings, but that he continues to suffer from a lack of sleep.

[1666] The server calculates Person A's condition score based on the analysis results and classifies him / her as "high stress." The server then compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors then review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself / herself via the portal site, which helps support self-management.

[1667] The processing flow will be explained below.

[1668] Program processing steps

[1669] Step 1: Collect business data

[1670] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[1671] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[1672] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[1673] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[1674] Step 2: Collecting wearable device data

[1675] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[1676] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[1677] Step 3: Encrypt the data

[1678] The terminal encrypts the collected business data and wearable data using an encryption library.

[1679] Encryption library: Encrypts data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, the amount of sleep, and the amount of exercise, and stores the encrypted data in a local database.

[1680] Step 4: Sending data

[1681] The terminal sends the encrypted data to the server using the HTTPS protocol.

[1682] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[1683] Step 5: Receive and decrypt the data

[1684] The server receives the data sent from the terminal.

[1685] HTTP request: Temporarily store received data.

[1686] The server decrypts the received data.

[1687] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[1688] Step 6: Data analysis

[1689] The server analyzes the decrypted data.

[1690] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, and amount of exercise to evaluate employees' workload, activity level, and stress level.

[1691] Step 7: Calculating the Condition Score

[1692] The server calculates each employee's condition score based on the analysis results.

[1693] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[1694] Step 8: Generate and deliver reports

[1695] The server compiles each employee's condition score and analysis results into a report.

[1696] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[1697] The server provides the generated reports to managers and mentors.

[1698] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[1699] Step 9: Provide feedback

[1700] The server provides feedback to each employee.

[1701] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[1702] Example 1

[1703] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1704] In today's corporate environment, appropriately managing employees' workloads and stress levels and protecting their health are important issues. However, current methods make it difficult to collect and analyze individual work data, making it difficult to accurately assess their condition. Furthermore, there is no established method for integrating and analyzing data from wearable devices with work data. As a result, efficient health management and feedback for employees are currently not being provided.

[1705] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1706] In this invention, the server includes means for collecting the number of emails sent and received, the number of communications, and the number of meetings attended in the schedule management system from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side to calculate the workload and stress level of each employee, means for calculating a condition score based on the analysis results, means for compiling the condition score in report format and providing it to an appropriate manager or educational instructor, and means for using a generative artificial intelligence model to analyze the data. This enables integrated analysis of employee work data and individual health data, enabling accurate condition evaluation and effective feedback.

[1707] A "business terminal" is a computer or electronic device used to carry out business within a company or organization.

[1708] "Emails Sent and Received" means the total number of emails received and sent within a specified period of time.

[1709] "Number of communications" means the number of calls made using communication means such as telephone or voice chat.

[1710] A "schedule management system" is software or an electronic system for managing meeting schedules and task schedules.

[1711] "Number of meetings attended" means the total number of meetings attended within a specific period.

[1712] "Encryption" is a technique for converting data into a format that cannot be easily deciphered by third parties.

[1713] A "server" is a computer system that provides data and services to other computers and devices over a network.

[1714] "Decryption" is the technique of returning encrypted data to its original form.

[1715] "Analysis" is the process of analyzing data in detail and extracting specific information.

[1716] "Workload" refers to the total amount of work, difficulty, and time spent by an employee.

[1717] "Stress level" refers to the degree of mental and physical strain felt by employees.

[1718] A "condition score" is a score or index that comprehensively evaluates an employee's workload and stress level.

[1719] A "report" is a document or data that summarizes analysis results and evaluations using text and graphs.

[1720] A "manager" is a person in a company or organization who is responsible for managing the work and health of employees.

[1721] An "educational instructor" is a person who is responsible for improving the skills and providing guidance to employees.

[1722] "Generative artificial intelligence model" is a general term for algorithms or models designed to perform specific tasks using machine learning and deep learning techniques.

[1723] A "wearable device" is an electronic device worn on the body. Examples include smartwatches and fitness bands.

[1724] "Rest time" refers to the time spent sleeping or resting during the day.

[1725] "Physical activity" refers to the total amount of physical activity, such as exercise and movement, that occurs in a day.

[1726] A "portal site" is a website that provides information and services to specific users.

[1727] An "application" is a software program designed to accomplish a particular purpose.

[1728] This invention is a system that collects and analyzes data from employees' daily work to evaluate their workload and stress levels, and supports their health management. This system is primarily composed of business terminals, a server, and wearable devices used by users.

[1729] First, the device collects the following data from your business email client (e.g., Microsoft Outlook), phone application (e.g., Skype for Business), and calendar application (e.g., Google Calendar):

[1730] Number of emails sent and received

[1731] Number of communications

[1732] Number of meetings attended in the schedule management system

[1733] Additionally, if the user consents, the device will collect rest time and physical activity data from wearable devices (e.g., Fitbit, Apple Watch).

[1734] The collected data is encrypted by the device using an encryption library (e.g., OpenSSL) and sent to the server via the HTTPS protocol. The server then decrypts the received encrypted data to its original form using a decryption library.

[1735] The server then uses the decoded data to analyze each employee's workload and stress level using a generative artificial intelligence model (e.g., TensorFlow) and comprehensively evaluates the following factors:

[1736] Number of emails sent and received

[1737] Number of communications

[1738] Number of meetings attended

[1739] Wearable data (rest time, physical activity)

[1740] Each data indicator is weighted appropriately to produce a condition score, which is then categorized into "high stress," "medium stress," and "low stress."

[1741] The server compiles the condition scores for each employee based on the analysis results in the form of a report. The report contains details of the analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational instructors. Administrators and educational instructors are notified of the generation of the report via a notification function.

[1742] The server also provides feedback to employees based on their condition scores. This feedback is sent to employees via a portal site or dedicated application, and includes information that helps support self-management and improvement.

[1743] Specific examples

[1744] For example, in the case of Person A, the device will collect data on the number of emails sent and received (50), the number of communications (10), and the number of meetings attended (5) in Person A's daily work. In addition, with Person A's consent, the device will also obtain the amount of rest time (6 hours) and the amount of physical activity (5,000 steps) from the wearable device.

[1745] The device encrypts the collected data and sends it to a server. The server decrypts the data and uses a generative AI model to analyze Person A's condition. For example, it can be determined that although he sends and receives many emails and attends many meetings, he continues to lack rest.

[1746] Based on the analysis results, the server classifies Person A's condition score as "high stress." The analysis results are compiled in a report and provided to administrators and educational instructors. The administrators and educational instructors review the report and provide appropriate support and feedback to Person A. Feedback is also provided to Person A himself through the portal site, which helps support his self-management.

[1747] Example prompts for generative AI models

[1748] prompt:

[1749] Calculate your condition score based on the employee data below.

[1750] data:

[1751] Number of emails sent and received: 50

[1752] Number of communications: 10

[1753] Number of meetings attended: 5

[1754] Rest time: 6 hours

[1755] Physical activity: 5,000 steps

[1756] An example of the output produced:

[1757] Condition Score: High Load

[1758] Details: The workload was assessed as high due to the high volume of emails sent and received and the high number of meetings attended, as well as the continued lack of rest.

[1759] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1760] Step 1: Collect data

[1761] The device collects data from the user's daily work. Specifically, data on the number of emails sent and received from the business email client, the number of communications from the phone application, and the number of meetings attended from the calendar application are input. In addition, if the user consents, data on rest time and physical activity levels are also collected from the wearable device. This data is obtained using an API and stored in the device's local storage.

[1762] Input: Number of emails sent and received, number of communications, number of meetings attended, rest time, amount of physical activity

[1763] Output: Collected data (stored in local storage)

[1764] Specific operation: The device makes the following API request:

[1765] GET / api / mail / received?user_id=A

[1766] GET / api / calendar / meetings?user_id=A

[1767] GET / api / phone / calls?user_id=A

[1768] GET / api / wearable / data?user_id=A

[1769] Step 2: Encrypt the data and send it to the server

[1770] The device encrypts the collected data using an encryption library (e.g., OpenSSL), and the encrypted data is sent to the server via the HTTPS protocol to ensure security.

[1771] Input: Collected data

[1772] Output: Encrypted data (sent to server)

[1773] Specific operation: Encrypts the data in JSON format and sends a POST request to the server.

[1774] POST / api / data

[1775] Content-Type: application / json

[1776] {

[1777] "user_id": "A",

[1778] "data": "encryptedData"

[1779] }

[1780] Step 3: Receive and decrypt the data

[1781] The server receives the encrypted data sent from the device, and uses a decryption library to restore the data to its original format.

[1782] Input: Encrypted data

[1783] Output: Decrypted data

[1784] What happens: The server uses an encryption library to decrypt the data.

[1785] encryptedData = request.body.data;

[1786] rawData = OpenSSL::Decrypt(encryptedData);

[1787] Step 4: Analyze the data

[1788] The server uses the decoded data it receives to analyze each employee's workload and stress level. A generative AI model (e.g., TensorFlow) is used for the analysis, and a comprehensive evaluation is made of the number of emails sent and received, the number of communications, the number of meetings attended, and wearable data. An appropriate weighting is then assigned to each data indicator to calculate an overall condition score.

[1789] Input: Decrypted data

[1790] Output: Analysis results (work load and stress level, condition score)

[1791] What it does: It uses an AI model to analyze data and predict scores.

[1792] model = tf.keras.models.load_model('condition_model.h5')

[1793] data = {"emails": rawData["emails"], "calls": rawData["calls"], "meetings": rawData["meetings"], "sleep": rawData["sleep"], "steps": rawData["steps"]}

[1794] condition_score = model.predict(data)

[1795] Step 5: Calculating the Condition Score

[1796] Based on the results of the AI ​​algorithm analysis, the server calculates a condition score for each employee, which is categorized into "high load," "medium load," and "low load."

[1797] Input: Analysis results

[1798] Output: Condition Score

[1799] Specific Behavior: Evaluate condition scores and categorize them.

[1800] thresholds = {"low": 0.3, "medium": 0.7, "high": 1.0}

[1801] condition_value = condition_score[0]

[1802] if condition_value < thresholds["low"]:

[1803] condition_category = "Low load"

[1804] elif condition_value < thresholds["medium"]:

[1805] condition_category = "Medium load"

[1806] else:

[1807] condition_category = "High load"

[1808] Step 6: Generate and deliver reports

[1809] The server generates a report based on the calculated condition score. The report contains detailed analysis results and specific indicators. The generated report is saved in a database and provided to administrators and educational leaders. Administrators and educational leaders are notified of the generation of the report via a notification function.

[1810] Input: Condition score, analysis results

[1811] Output: Report (Saved to database, Notification)

[1812] Specific actions: Generate a report, save it in a database, and notify the administrator.

[1813] report = {

[1814] "user_id": "A",

[1815] "condition_score": condition_category,

[1816] "details": rawData,

[1817] "analysis_time": datetime.now()

[1818] }

[1819] db.save(report)

[1820] notification.send("Report generated", user_id="A")

[1821] Step 7: Provide feedback

[1822] The server provides feedback to employees based on their condition scores. The feedback is sent to employees via a portal site or dedicated application, and includes information useful for supporting self-management and improvement.

[1823] Input: Condition Score

[1824] Output: Feedback (notification)

[1825] Specific behavior: Generate feedback and communicate it through portals and applications.

[1826] feedback = f"{condition_category}:Due to the increased workload recently, we recommend that you take a proper rest."

[1827] notification.send(feedback, user_id="A")

[1828] (Application example 1)

[1829] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1830] In recent years, there has been growing emphasis on managing the health and workload of factory workers, but conventional systems only collect and analyze data from office work, making it difficult to accurately grasp the condition of factory workers. For this reason, there is a need for a new system that can detect worker fatigue and stress early and provide appropriate feedback.

[1831] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1832] In this invention, the server includes: means for collecting the number of emails sent and received, the number of outgoing and incoming calls, and the number of calendar meetings attended from business terminals; means for encrypting the collected data and sending it to the server; means for decrypting and analyzing the data on the server side to calculate each employee's workload and stress level; means for calculating a condition score based on the analysis results; means for compiling the condition score in report format and providing it to an appropriate manager or mentor; means for collecting the body temperature, heart rate, and work log of factory workers using smart glasses, encrypting the data in the same way, and sending it to the server; and means for evaluating the fatigue and stress levels of factory workers based on the collected data and providing breaks and feedback at appropriate times. This allows for real-time monitoring of the health status of factory workers, improving work efficiency, and ensuring safety.

[1833] A "business terminal" is an information processing device such as a computer used by a company or organization.

[1834] "Number of emails sent and received" is the total number of emails sent and received during a certain period of time.

[1835] "Number of calls made and received" refers to the total number of calls made and received via telephone or communication apps over a certain period of time.

[1836] "Number of meetings attended in calendar" refers to the number of times a person has attended a conference or meeting registered in an electronic calendar.

[1837] A "collection means" is a method or device used to obtain and store particular data.

[1838] An "encryption means" is a method or device that converts data from a readable form to an obfuscated form in order to protect it.

[1839] A "server" is a computer system that stores data and provides services to other computers and devices over a network.

[1840] A "decryption means" is a method or device that returns encrypted data to its original, readable form.

[1841] An "analyzing means" is a method or device for processing collected data and extracting meaningful information.

[1842] "Workload" refers to the amount of tasks or work that an employee handles as part of their job during a specific period of time.

[1843] "Stress level" refers to the degree of mental and physical stress felt by employees over a specific period of time.

[1844] A "condition score" is a numerical indicator that represents an employee's health status and workload.

[1845] A "report format" is a document format that summarizes collected and analyzed information in an easy-to-understand format.

[1846] A "management position" is a person in a position responsible for management or leadership within an organization.

[1847] A "mentor" is someone whose role is to provide guidance and advice on specific knowledge and skills.

[1848] "Smart glasses" are a wearable device in the form of glasses that displays visual information on a screen and can be connected to a computer or network.

[1849] "Body temperature" is an indicator of the worker's body temperature.

[1850] "Heart rate" is the number of times the heart beats within a certain period of time.

[1851] A "work log" is a detailed record of the work performed by a worker.

[1852] "Fatigue level" refers to the degree of physical and mental fatigue felt during work.

[1853] "Real-time" means that information is updated and processed almost immediately.

[1854] The present invention is a system for monitoring the health and workload of factory workers in real time and providing appropriate feedback. The system includes a business terminal, smart glasses, a wearable device, and a server.

[1855] Data collection

[1856] The business devices collect business data such as the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended. In addition, smart glasses are used to collect the factory workers' body temperature, heart rate, and work logs. This data is encrypted immediately upon collection. The encryption uses the OpenSSL library to protect the data.

[1857] Data Encryption and Transmission

[1858] The data is encrypted and then securely transmitted to the server using the HTTPS protocol, using the standard SSL / TLS protocol to ensure secure communication.

[1859] Data Reception and Decryption

[1860] The server then decrypts the received data using the PyCrypto library, which returns the data to its original, readable form for analysis.

[1861] Data analysis

[1862] The server calculates the workload and stress level of workers based on the decoded data. The analysis uses TensorFlow and PyTorch and utilizes a generative AI model. Specifically, the server comprehensively analyzes the number of emails sent and received, the number of meetings attended, body temperature, heart rate, and work logs, and assigns appropriate weights to the data indicators.

[1863] Calculating condition scores and providing feedback

[1864] Based on the analysis results, a condition score is calculated for each employee. The condition score is a comprehensive assessment of the employee's workload and stress level. This score is provided to the worker in real time via the smart glasses' built-in display. The analysis results are then compiled into a report and provided to managers and mentors.

[1865] Specific examples

[1866] For example, suppose a factory worker has a body temperature of 37.2°C, a heart rate of 85 bpm, and has not taken a break in the past hour. Based on this data, the system determines that the worker is highly fatigued and displays an alert on the smart glasses display urging the worker to take a break. The system also notifies managers that the worker's condition score is "high strain."

[1867] Prompt Sentence Examples

[1868] "Collect daily work data (body temperature, heart rate, break times) from factory workers and create an AI model that evaluates their condition from the analysis results. Design an application that provides feedback and alerts based on the condition score."

[1869] This will not only enable factory workers to properly manage their health, but also enable managers and mentors to understand the health of workers and provide appropriate support. By using this system, it will be possible to improve work efficiency and safety.

[1870] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1871] Step 1:

[1872] The business device collects the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee. This data is obtained using the business device's API. The input data is employee activity information, and the output is business data before encryption. Specifically, this includes operations that make API calls from email clients, phone apps, and calendar apps.

[1873] Step 2:

[1874] The terminal encrypts the data collected in step 1 using the OpenSSL library. The input data is the business data described above, and the output data is the encrypted business data. Specifically, this includes the operation of performing encryption processing using AES encryption.

[1875] Step 3:

[1876] The terminal sends encrypted data to the server using the HTTPS protocol. The input data is encrypted business data, and the output is the data sent to the server. Specifically, this includes the operation of creating and sending an HTTPS request.

[1877] Step 4:

[1878] The server decrypts the data sent from the terminal using the PyCrypto library. The input data is encrypted business data, and the output is decrypted business data. Specifically, it includes the operation of performing decryption processing using AES decryption.

[1879] Step 5:

[1880] The server inputs the decoded data into a generative AI model using TensorFlow or PyTorch to analyze workload and stress levels. The input data is the decoded workload data, and the output is the evaluation results of workload and stress levels. Specifically, this includes the operation of performing data analysis processing using the AI ​​model.

[1881] Step 6:

[1882] The server calculates a condition score for each employee based on the analysis results. The input data are the evaluation results of workload and stress level, and the output is a condition score for each employee. Specifically, it includes operations for weighting and score calculation based on the evaluation results.

[1883] Step 7:

[1884] The server compiles the condition scores into a report and provides it to the appropriate manager or mentor. The input data is the condition score, and the output is a report that is delivered to the manager or mentor. Specifically, it uses a report generation algorithm and includes operations such as email and dashboard notifications.

[1885] Step 8:

[1886] The smart glasses collect the body temperature, heart rate, and work logs (such as working hours and break times) of factory workers. This data is acquired using the smart glasses' sensors and API. The input data is sensor information, and the output is work data before encryption. Specifically, this includes operations that utilize the body temperature sensor, heart rate sensor, and work log recording function.

[1887] Step 9:

[1888] The smart glasses encrypt the collected data using the OpenSSL library and send it to the server. The input data is sensor information, and the output is encrypted working data. Specifically, the glasses perform operations including encryption using AES encryption and sending HTTPS requests.

[1889] Step 10:

[1890] The server decrypts the data sent from the smart glasses and analyzes the condition of the factory workers. The input data is encrypted work data, and the output is the worker condition evaluation results. Specifically, the server performs operations such as decryption processing and evaluation processing using a data analysis model.

[1891] Step 11:

[1892] The smart glasses display break and feedback alerts to workers in real time. The input data is the condition assessment results from the server, and the output is the alerts displayed on the smart glasses display. Specifically, it includes the operation of displaying feedback messages on the display.

[1893] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1894] This invention is a system that accurately assesses an employee's condition by collecting and analyzing data such as the number of emails sent and received, the number of calendar meetings attended, and combining it with user emotional data, allowing managers and mentors to effectively monitor and support the health of their employees.

[1895] Program processing

[1896] Data collection

[1897] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of meetings attended from the email client, phone application, and calendar application installed on the work device. If the employee consents, the device also collects data on sleep time and exercise volume from wearable devices (e.g., smartwatches). Furthermore, the device uses an emotion engine to analyze the user's emotional state from their voice data and facial expression data.

[1898] Data Encryption and Transmission

[1899] The device encrypts the collected business data, wearable data, and emotion data and transmits them securely to the server using an encryption library and the HTTPS protocol.

[1900] Data Reception and Decryption

[1901] The server receives the data sent from the device, decrypts the encrypted data, and stores it in a database, ready for analysis.

[1902] Data analysis

[1903] The server analyzes the decrypted data, integrating data such as the number of emails sent and received, the number of meetings attended, sleep time, exercise level, and emotional data. An AI algorithm is used for the analysis, weighting each data indicator appropriately to assess the employee's workload and stress level.

[1904] Calculating the Condition Score

[1905] The server calculates a condition score for each employee based on the analysis results. By combining this with emotional data, stress levels can be corrected to provide a more accurate condition score. Scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[1906] Report generation and delivery

[1907] The server compiles each employee's condition score and analysis results into a report. The generated report is saved in a database and notified to managers and mentors. A notification function also encourages employees to check the report.

[1908] Providing feedback

[1909] The server provides feedback to each employee, who is then notified of the feedback via a portal site or dedicated application, providing support for self-management and improvement.

[1910] Specific examples

[1911] In the case of person B

[1912] The device collects data on the number of emails sent and received (30), the number of calls made and received (15), and the number of meetings attended (3) during B's daily work. With B's consent, the device also collects the amount of sleep (7 hours) and exercise (6,000 steps) per day from the wearable device (smartwatch).

[1913] In addition, the device uses an emotion engine to analyze B's voice and facial expression data to determine his / her stress level. For example, it may detect that B is under high stress based on his / her voice tone and facial expression.

[1914] The device encrypts all collected data and sends it to the server. The server decrypts the data and analyzes Mr. B's condition using an AI algorithm. Based on the analysis results, Mr. B's condition score is classified as "medium load."

[1915] The server compiles the analysis results into a report and provides it to managers and mentors. The managers and mentors review the report and provide appropriate support and feedback to Person B. Feedback is also provided to Person B himself via the portal site, which helps support his self-management.

[1916] The processing flow will be explained below.

[1917] MODE FOR CARRYING OUT THE INVENTION

[1918] This invention is a system that collects and analyzes work data, wearable data, and emotional data to assess an employee's condition, allowing managers and mentors to gain a detailed understanding of their employees' health status and provide appropriate support.

[1919] Program processing steps

[1920] Step 1: Collect business data

[1921] The device collects data from email clients, phone applications, and calendar applications installed on business devices.

[1922] Email client: Uses the API to obtain the number of emails sent and received on the day and saves them in a local database.

[1923] Phone application: Uses API to obtain the number of calls made and received and stores it in a local database.

[1924] Calendar application: Uses API to obtain the number of meetings attended and stores it in a local database.

[1925] Step 2: Collecting wearable device data

[1926] The device collects data from wearable devices (e.g., smartwatches) if the employee consents.

[1927] Wearable device: Uses API to obtain sleep time and exercise volume (e.g., number of steps) and stores them in a local database.

[1928] Step 3: Collecting emotion data

[1929] The device uses an emotion engine to analyze the user's voice data and facial expression data to determine the user's stress level and emotional state.

[1930] Emotion Engine: Using voice recordings and camera data, it analyzes changes in voice tone and facial expressions to generate emotion data, which is then stored in a local database.

[1931] Step 4: Encrypt the data

[1932] The device encrypts the collected business data, wearable data, and emotion data using an encryption library.

[1933] Encryption library: Encrypts data such as the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, exercise amount, and emotional data, and stores the encrypted data in a local database.

[1934] Step 5: Sending data

[1935] The terminal sends the encrypted data to the server using the HTTPS protocol.

[1936] HTTPS protocol: Encrypts data over an encrypted channel to a server endpoint.

[1937] Step 6: Receive and decrypt data

[1938] The server receives the data sent from the terminal.

[1939] HTTP request: Temporarily store received data.

[1940] The server decrypts the received data.

[1941] Decryption library: Returns the encrypted data to its original form and stores it in the database.

[1942] Step 7: Data analysis

[1943] The server analyzes the decrypted data.

[1944] AI algorithm: Comprehensively analyzes data on the number of emails sent and received, the number of calls made and received, the number of meetings attended, sleep time, amount of exercise, and emotional data to evaluate employees' workload, activity level, and stress level.

[1945] Analysis results: Based on the analysis results, the workload and stress level of each employee are evaluated and expressed as a numerical value.

[1946] Step 8: Calculating the Condition Score

[1947] The server calculates each employee's condition score based on the analysis results.

[1948] Scoring algorithm: Each data metric is weighted appropriately to calculate an overall score, which is then categorized into categories such as "high impact," "medium impact," and "low impact."

[1949] Step 9: Generate and deliver reports

[1950] The server compiles each employee's condition score and analysis results into a report.

[1951] Report Generation Module: Use templates to embed analysis results and scores and create reports.

[1952] The server provides the generated reports to managers and mentors.

[1953] Notification system: Notifies reports when they are generated and allows managers and mentors to review the reports.

[1954] Step 10: Provide feedback

[1955] The server provides feedback to each employee.

[1956] Feedback system: Advice and guidance are provided based on condition scores and analysis results, and are communicated to employees via a portal site or application.

[1957] Example 2

[1958] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1959] In today's corporate environment, it is important to accurately understand employees' workloads and stress levels and provide appropriate support. However, conventional systems only collect operational data such as the number of emails sent and received, phone calls made and received, and number of meetings attended, which is not enough to accurately assess an employee's condition. Furthermore, relying solely on numerical data makes it difficult to consider an employee's mental state or physical health. To solve this problem, a more diversified and comprehensive method of data collection and analysis is needed.

[1960] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1961] In this invention, the server includes means for collecting the number of emails sent and received, the number of phone calls made and received, and the number of calendar meetings attended from the business terminals, means for encrypting the collected data and sending it to the server, means for decrypting and analyzing the data on the server side, means for analyzing the emotional state of employees from their voice data and facial expression data, means for calculating the workload and stress level of each employee, means for calculating a condition score based on the analysis results, and means for compiling the condition score in report format and providing it to an appropriate manager or instructor. This allows for an integrated analysis of employee work data as well as emotional and physical data, enabling more accurate condition evaluations.

[1962] "Business terminals" are computers and smart devices used by employees within a company to carry out their work.

[1963] "Emails Sent and Received" means the total number of emails sent and received by an employee within a specified period of time.

[1964] "Number of calls made and received" is the total number of calls made and received by an employee during a specified period.

[1965] "Calendar Meeting Attendance" is the total number of meetings that an employee has registered to attend in scheduling software.

[1966] "Encryption" is a technology that converts data into a format that cannot be read by third parties, and is a means of ensuring security.

[1967] A "server" is a computer system that provides data or services to multiple clients over a network.

[1968] "Decryption" is the process of returning encrypted data to its original, readable form.

[1969] "Analysis" is the process of using collected data to extract and evaluate information for a specific purpose.

[1970] "Emotional state" is the result of judging an individual's mental state obtained through voice and facial expression data.

[1971] "Workload" is a measure of the amount of work and difficulty an employee feels when performing their job.

[1972] "Stress level" is a measure of the degree of psychological and physiological stress felt by an individual.

[1973] A "Condition Score" is a comprehensive score calculated to assess an employee's overall work situation and health.

[1974] A "report format" is a document format that visually organizes analysis results and presents them in an easy-to-understand manner.

[1975] A "manager" is someone who supervises and supports the work of employees within an organization.

[1976] A "leader" is someone whose role is to educate and support employees within an organization.

[1977] "Wearable devices" are small electronic devices and related technologies that can be worn by a user.

[1978] "Sleep time" is the total time an employee was asleep.

[1979] "Amount of exercise" is the cumulative amount of physical activity an employee engages in within a specific period of time.

[1980] This invention is a system that accurately assesses the condition of employees by collecting and analyzing data from various angles related to their daily work. The system analyzes data collected from business terminals on a server and provides useful information to managers and instructors, aiming to effectively monitor and support employees' health and stress levels.

[1981] Data collection

[1982] The device collects data from the email client, phone application, and calendar application installed on the work device. Specifically, it uses an API to obtain the number of emails sent and received, the number of phone calls made and received, and the number of meetings attended. If the employee consents, the device also collects data on sleep time and exercise volume from a wearable device (e.g., a smartwatch). Furthermore, an emotion engine is used to analyze the user's voice data and facial expression data to evaluate their emotional state. This makes it possible to collect data that can be used to comprehensively evaluate not only employees' work performance, but also their mental and health states.

[1983] Data Encryption and Transmission

[1984] The device encrypts the collected and analyzed data and transmits it to the server with a high level of security. The encryption is performed using the AES encryption library and the HTTPS protocol for data transmission, ensuring confidentiality and integrity of the data.

[1985] Data Reception and Decryption

[1986] The server receives the encrypted data sent from the device and decrypts it in a secure environment, where it is stored in a database until it is ready to be analyzed.

[1987] Data analysis

[1988] The server performs an integrated analysis of data collected from various data sources. First, it integrates business data (emails, phone calls, meeting participation), wearable data, and emotional data, and then analyzes them using an AI algorithm. The specific algorithm assigns appropriate weights to each data indicator to evaluate employees' workload and stress levels.

[1989] Calculating the Condition Score

[1990] Based on the analysis results, the server calculates a condition score for each employee. This score can be combined with emotional data to correct for stress levels, enabling more accurate assessments. Condition scores are categorized into categories such as "high stress," "medium stress," and "low stress."

[1991] Report generation and delivery

[1992] The server compiles the analysis results and condition scores into a report. The generated report is saved in a database and notified to the appropriate administrator or instructor. Notifications are sent via email or the alert function on the portal site.

[1993] Providing feedback

[1994] Finally, the server provides feedback to each employee, which is then communicated to the employee via a portal site or dedicated application, and used as a guide for self-management and improvement.

[1995] Specific examples

[1996] For example, in the case of Person B, the device collects data on the number of emails sent and received (30), the number of phone calls made and received (15), and the number of meetings attended (3) in Person B's daily work. Furthermore, with Person B's consent, data on the amount of sleep per day (7 hours) and the amount of exercise (6,000 steps) is also collected from the wearable device. Person B's voice data and facial expression data are analyzed using an emotion engine to determine their stress level. For example, it can detect that Person B is feeling increasingly stressed from their voice tone and facial expression.

[1997] The device encrypts all of this data and sends it to the server. The server decrypts the data and uses an AI algorithm to analyze Person B's condition. Based on the results of this analysis, Person B's condition score is classified as "medium load." The server compiles the analysis results into a report and provides it to the manager or coach. The manager or coach reviews the report and provides appropriate support and feedback to Person B. Person B also receives feedback via a portal site, which can be used to help with self-management.

[1998] Prompt Sentence Examples

[1999] "Please explain in detail the specific steps you take to collect data on Mr. B's daily work and analyze his condition."

[2000] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2001] Program processing steps

[2002] Step 1: Start collecting data

[2003] The device accesses the email client, phone application, and calendar application on the business device according to a specific time schedule.

[2004] Input: Each application on the user's work computer.

[2005] Output: Raw data obtained from each application.

[2006] Specific operation:

[2007] The device calls the email client's API and collects the number of emails sent and received.

[2008] The device calls the API of the phone application and collects the number of calls made and received.

[2009] The device calls the calendar application API to collect the number of meetings attended.

[2010] Step 2: Wearable data collection

[2011] The device works in conjunction with a wearable device (e.g., a smartwatch) to obtain the user's sleep time and exercise volume.

[2012] Input: Sensor data from wearable devices.

[2013] Output: Data on sleep duration and exercise.

[2014] Specific operation:

[2015] The device retrieves the data via the wearable device's API and stores it locally.

[2016] Sleep duration is obtained from the wearable device's activity tracker, and exercise volume is obtained from the pedometer sensor.

[2017] Step 3: Sentiment Data Analysis

[2018] The device uses an emotion engine to analyze the user's voice data and facial expression data to evaluate their emotional state.

[2019] Input: User's voice and facial expression data.

[2020] Output: Parsed emotion data.

[2021] Specific operation:

[2022] The device uses a voice recognition engine to analyze voice tone and pitch.

[2023] Using a facial expression recognition engine, facial images acquired from a camera are analyzed to determine the emotional state.

[2024] Step 4: Data Encryption

[2025] The device encrypts all collected data and prepares it for transmission to the server.

[2026] Input: Each dataset collected and analyzed.

[2027] Output: Encrypted data bundle.

[2028] Specific operation:

[2029] The terminal uses the AES encryption library to encrypt the data set.

[2030] Create a batch to send encrypted data to the server via HTTPS protocol.

[2031] Step 5: Send data

[2032] The terminal transmits the encrypted data to the server.

[2033] Input: Encrypted data bundle.

[2034] Output: The data sent to the server.

[2035] Specific operation:

[2036] The device uses the HTTPS protocol to send encrypted data to the server.

[2037] A manual or automated submission process sends the data to an endpoint where the server can receive it.

[2038] Step 6: Data Reception and Decryption

[2039] The server receives and decrypts the data sent from the terminal.

[2040] Input: The received encrypted data.

[2041] Output: Decoded raw data.

[2042] Specific operation:

[2043] The server uses a secure endpoint to receive encrypted data.

[2044] The received data is decrypted to restore it to its original data format.

[2045] Step 7: Data integration and analysis

[2046] The server integrates and analyzes business data, wearable data, and emotional data.

[2047] Input: The decoded dataset.

[2048] Output: Analysis results.

[2049] Specific operation:

[2050] The server uses a data management system to integrate each dataset.

[2051] AI algorithms are applied to analyze data and evaluate workload and stress levels.

[2052] Step 8: Calculating the Condition Score

[2053] Based on the analysis results, the server calculates each employee's condition score.

[2054] Input: Analysis results.

[2055] Output: Condition score.

[2056] Specific operation:

[2057] The condition score is calculated based on an AI algorithm.

[2058] The calculation results are classified into specific score categories (high load, medium load, low load).

[2059] Step 9: Reporting and Notifications

[2060] The server compiles each employee's condition score and analysis data into a report format and provides it to managers and instructors.

[2061] Input: Condition score and analysis data.

[2062] Output: The generated report.

[2063] Specific operation:

[2064] The server organizes and structures the analysis results using report generation templates.

[2065] The completed reports are stored in a database and notifications are sent to managers and leaders through a notification system.

[2066] Step 10: Provide feedback

[2067] The server provides individual feedback to each employee.

[2068] Input: Condition score and analysis results.

[2069] Output: The feedback provided.

[2070] Specific operation:

[2071] The server automatically generates feedback content and notifies employees via a portal site or dedicated application.

[2072] Employees can refer to the feedback provided to help them self-manage and improve.

[2073] (Application example 2)

[2074] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2075] In many modern business situations, it is important to properly manage employee workload and stress. However, conventional systems assess employee health based solely on work data, making it difficult to accurately assess workload. Furthermore, systems lacked the mechanisms for combining emotional data and data from wearable devices, resulting in delayed or inaccurate feedback. This can lead to a deterioration in employee health and a drop in productivity.

[2076] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting the number of emails sent and received, the number of calls made and received, and the number of meetings attended on the calendar from the business terminals, means for encrypting the collected data and sending it to the server, and means for decrypting and analyzing the data on the server side and calculating the workload and stress level of each employee. This enables detailed data collection and analysis.

[2077] Furthermore, the server includes means for collecting data on sleep duration and exercise volume from the smartphone and wearable device, analyzing voice and facial expressions using an emotion recognition engine, means for classifying condition scores into categories such as high, medium, and low stress based on the analysis results, and means for notifying managers and leaders of the analysis results through a notification function, thereby enabling real-time evaluation of the overall health status of employees and providing prompt feedback.

[2078] "Business terminals" are electronic devices such as computers and smartphones used in companies and organizations.

[2079] "Emails Sent and Received" means the total number of emails sent and received within a specified period of time.

[2080] "Number of outgoing and incoming calls" refers to the total number of outgoing and incoming voice calls made within a specific period of time.

[2081] "Calendar meeting attendance count" refers to the number of scheduled meetings attended within a specific period.

[2082] A "collection means" is a method or device for obtaining and recording data.

[2083] "Encryption" is the process of transforming data using a specific algorithm in order to secure it.

[2084] A "server" is a computer system that stores, manages, and analyzes data.

[2085] "Decryption" is the process of restoring encrypted data to its original state.

[2086] "Analysis" is the process of examining data in detail to derive useful information.

[2087] "Workload" refers to the amount of work an employee handles in a given period of time.

[2088] "Stress level" is the degree of mental or emotional strain experienced by an employee.

[2089] The "condition score" is a numerical representation of an employee's health status and workload calculated based on the analysis results.

[2090] A "report" is a report that summarizes and organizes the results of analysis.

[2091] A "smartphone" is a mobile phone that can connect to the Internet and use applications in addition to making calls.

[2092] A "wearable device" is an electronic device that can be worn and used.

[2093] "Sleep time" refers to the actual time spent asleep within a specific period of time.

[2094] "Movement" is the amount of physical activity performed within a specific period of time.

[2095] An "emotion recognition engine" is software or a system for analyzing emotional states from voice, facial expressions, etc.

[2096] "Analysis of voice and facial expressions" is the process of extracting specific information from voice and facial expressions and making judgments based on that information.

[2097] "High workload, medium workload, low workload" refers to the level of workload and stress classified based on the condition score.

[2098] The "notification function" is a function for notifying the user of specific information.

[2099] "Managers and leaders" are people in positions that involve managing and guiding employees.

[2100] This invention is a system for accurately assessing the health status and workload of employees in a corporate environment such as a factory. The system collects data using smartphones and wearable devices, analyzes the data on a server, and provides the results to managers and instructors.

[2101] System Configuration

[2102] The system consists of the following hardware and software:

[2103] Smartphones (e.g. iPhone, Android devices)

[2104] Wearable devices (e.g., Apple Watch, Fitbit)

[2105] Server (e.g. Amazon Web Services (AWS), Google Cloud Platform)

[2106] Data collection

[2107] The device collects data on the number of emails sent and received, the number of calls made and received, and the number of calendar meetings attended by each employee during their daily work. It also collects data on sleep time and exercise volume from smartphones and wearable devices. Furthermore, it uses an emotion recognition engine to analyze voice and facial expression data.

[2108] Data Encryption and Transmission

[2109] The device encrypts the collected data and sends it to a server using the HTTPS protocol, for example using the PyCryptodome library.

[2110] Data Reception and Decryption

[2111] The server receives the encrypted data, decrypts it, and stores it in a database, ready for analysis. Databases used include MySQL and PostgreSQL.

[2112] Data analysis

[2113] The server analyzes the decoded data using AI algorithms (e.g., TensorFlow, PyTorch), which quantify each employee's workload and stress level and calculate a condition score based on that data.

[2114] Calculating the Condition Score

[2115] Based on the analysis results, the server classifies each employee's condition score into "high load," "medium load," "low load," etc. This score is calculated by integrating the collected work data, wearable data, and emotional data.

[2116] Report generation and delivery

[2117] The server compiles each employee's condition score and analysis results into a report and notifies the appropriate manager or leader via email or a dedicated application.

[2118] Providing feedback ...

Claims

1. A means of collecting the number of emails sent and received, the number of calls made and received, and the number of meetings attended on the calendar from business terminals; A means for encrypting the collected data and transmitting it to a server; A means for decoding and analyzing the data on the server side to calculate the workload and stress level of each employee; A means for calculating a condition score based on the analysis results; A way to compile condition scores into a report and provide it to appropriate managers and mentors, and A system including:

2. A means for collecting sleep time and exercise amount from a wearable device; A means of integrating and analyzing collected wearable data with business data to improve the accuracy of judgments; The system of claim 1 further comprising:

3. A means of providing feedback to employees based on their condition scores; A means to display the feedback content through a portal site or application, The system of claim 1 further comprising:

Images