System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting work data; means for analyzing the collected work data; means for identifying a work imbalance based on an analysis result; means for issuing an alert when an imbalance is identified; means for recommending a work improvement measure based on the analysis result; means for monitoring implementation of the recommended work improvement measure; and means for reporting an analysis result and an improvement effect at regular intervals.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In many companies and organizations today, imbalances in employee workloads are a major problem. In particular, workloads tend to be concentrated in specific departments or positions, which can lead to feelings of unfairness and a decline in motivation among employees. Furthermore, managers themselves often have excessive workloads, which is one of the reasons why fewer employees aspire to managerial positions. Furthermore, the enormous amount of work required to manage overtime and the man-hours required to compile data makes efficient management difficult. The present invention aims to solve these problems and create a fair and comfortable working environment for all employees. [Means for solving the problem]

[0005] The present invention provides a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. Specifically, this is achieved by a system that includes a means for collecting work data, a means for analyzing the collected work data, a means for identifying imbalances in work based on the analysis results, a means for issuing an alert when an imbalance is identified, a means for proposing work improvement measures based on the analysis results, a means for monitoring the implementation of the proposed work improvement measures, and a means for periodically reporting the analysis results and the effectiveness of the improvements. This system makes it possible to equalize employee workloads, reduce the amount of time required to manage overtime, and increase the number of employees seeking managerial positions.

[0006] "Work data" refers to information related to an employee's work, such as the time they clock in and out, their break times, and the nature of their work.

[0007] "Means of collection" refers to methods or technologies that automatically obtain employee work data from each device.

[0008] "Means for analysis" refers to methods or technologies for using collected work data to detect each employee's workload, overtime hours, and imbalances.

[0009] "Means for identifying imbalances" refers to methods or techniques for identifying imbalances in employee workloads or working hours based on the results of analysis.

[0010] "Means for issuing alerts" refers to methods or technologies for notifying relevant parties when workload imbalances or abnormalities are detected.

[0011] "Means for proposing business improvement measures" refers to a method or technology for proposing improvement measures such as appropriate redistribution of work or review of shifts based on the analysis results.

[0012] "Monitoring measures" refers to methods or techniques for continuously monitoring and evaluating the effectiveness of proposed business improvement measures after they have been implemented.

[0013] "Means for generating reports" refers to a method or technology for creating reports summarizing analysis results and improvement effects at regular intervals. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[0036] Collection and analysis of work data

[0037] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[0038] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be sent to the server periodically. The server then sends the collected work data to the generation AI.

[0039] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates the total working hours and overtime hours for this month from the data of employee A and detects that the overtime hours exceed 80 hours.

[0040] Identifying and alerting on imbalances

[0041] The server receives the analysis results of the generative AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours.

[0042] Proposing business improvement measures and monitoring their implementation

[0043] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[0044] The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work among team members.

[0045] The server continues to monitor work data even after improvements are implemented and evaluates the effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased.

[0046] Generate and send reports

[0047] The server automatically generates a report of the analysis results and the improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of improvements made to Employee A's work is created.

[0048] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[0049] Streamlining overtime management

[0050] The server manages overtime data in real time in cooperation with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date.

[0051] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a graph of employee A's weekly overtime hours on the management panel, making it easy for managers to check.

[0052] This system will make the workload of employees fairer, reduce the amount of time required to manage overtime, and is expected to increase the number of employees who wish to become managers.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0056] Step 2:

[0057] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[0058] Step 3:

[0059] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI.

[0060] Step 4:

[0061] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. The generation AI aggregates "total monthly working hours," "overtime hours," and "break times" from employee A's data and identifies excessive overtime.

[0062] Step 5:

[0063] The server receives the analysis results of the generated AI and detects workload imbalances. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours."

[0064] Step 6:

[0065] The generative AI performs additional data analysis to propose measures to improve workloads. Specifically, it proposes measures such as redistributing work and reviewing shifts. For example, the generative AI might recommend "reviewing the division of work."

[0066] Step 7:

[0067] The server notifies the relevant parties of the generated AI's recommendations. For example, the server may notify employee A's team leader of the "redistribution of work proposals" by email.

[0068] Step 8:

[0069] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0070] Step 9:

[0071] The server will continue to monitor the work data even after the proposed improvement measures are implemented and evaluate the effectiveness of the improvements. For example, the server will collect the work data of employee A even after the redistribution and confirm the reduction in overtime hours.

[0072] Step 10:

[0073] The server periodically generates a report on the analysis results and the effects of the improvements. For example, at the end of the month, a report is created summarizing "Changes in working hours and overtime hours before and after improvements made by employee A."

[0074] Step 11:

[0075] The server provides the generated report to the relevant parties. For example, the server may email the report in PDF format to a team leader or manager.

[0076] Step 12:

[0077] The server manages overtime data in real time by linking with the AI ​​generator. For example, the AI ​​generator updates its analysis results every day and reflects the latest data on the management panel.

[0078] Step 13:

[0079] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph showing the weekly trend of employee A's overtime hours, making it easy for managers to check.

[0080] Example 1

[0081] 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."

[0082] Conventional work data management systems have had difficulty in detecting imbalances in employee workloads and overwork, and proposing and implementing improvement measures. As a result, improvements to employees' working environments have been delayed, leading to problems such as lower labor productivity and motivation. The purpose of this invention is to solve these problems and efficiently manage and improve workloads.

[0083] 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.

[0084] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for analyzing the work data with a generative AI model and proposing measures to improve workloads, means for notifying relevant parties when an imbalance is identified, means for users to implement the proposed work improvement measures, and means for continuously monitoring the effectiveness of the work improvement measures. This makes it possible to efficiently and fairly manage employee workloads and quickly implement appropriate improvement measures.

[0085] "Work data" refers to information about an employee's work, such as the employee's arrival time, departure time, break time, and job duties.

[0086] "Means of collection" refers to the hardware or software that employees use to record information about their work and transmit that data to a server.

[0087] "Means of analysis" refers to the method of using software to analyze collected work data and calculate indicators such as workload and overtime hours.

[0088] "Means for identifying imbalances" refers to the process of detecting imbalances or abnormalities in workload among employees based on analyzed work data.

[0089] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate results or recommendations tailored to a specific purpose.

[0090] "Means for proposing measures to improve workload" refers to a method in which the generative AI model derives specific improvement proposals, such as redistributing work or reviewing shifts, based on the analysis results.

[0091] "Means of notifying stakeholders" refers to the method of communicating identified imbalances and proposed remedial measures to stakeholders via email or notification systems.

[0092] "User implementation measures" refers to the process by which managers and team leaders actually apply the proposed improvements in their work environment.

[0093] "Monitoring measures" refers to methods for continuously monitoring and evaluating the effectiveness of proposed improvements after they have been implemented.

[0094] "Means of reporting" refers to the process of automatically generating reports that periodically summarize the analysis results and improvement effects and sending them to relevant parties.

[0095] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[0096] Collection and analysis of work data

[0097] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. The terminals used are attendance management devices with touch panels or card readers so that employees can easily operate them. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[0098] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be periodically sent to the server. The server is equipped with a high-performance database and communication interface, allowing for real-time data collection. The server then sends the collected work data to the generative AI model.

[0099] The generative AI model analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generative AI aggregates the total working hours and overtime hours for this month from Employee A's data and detects that the overtime hours exceed 80 hours. Machine learning algorithms are used in the analysis to recognize patterns and detect anomalies.

[0100] Identifying and alerting on imbalances

[0101] The server receives the analysis results of the generative AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server detects that employee A's overtime hours exceed 80 hours and notifies management by email. A template engine is used for the notification, and an automatically generated email body is sent.

[0102] Proposing business improvement measures and monitoring their implementation

[0103] The generative AI model continues its analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generative AI. For example, if the generative AI recommends "redistributing work," the server sends the recommendation to employee A's team leader. The notification is distributed via email or the internal messaging system.

[0104] The user (management) implements the proposed improvement measures. Specifically, the team leader holds a meeting to redistribute work among team members. For example, employee A's work is assigned to another member. The implementation status of the improvement measures is recorded using a task management tool.

[0105] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased. Statistical analysis software is used for the evaluation and effectiveness is measured.

[0106] Generate and send reports

[0107] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements on employee A is created. The generated report includes graphs and charts to visualize the effects.

[0108] The generated reports are automatically sent to the relevant parties. For example, the server emails the report in PDF format to management. An automation tool is used to send the emails, ensuring regular reporting.

[0109] Streamlining overtime management

[0110] The server manages overtime data in real time in cooperation with the generative AI model. For example, the server updates the analysis results of the generative AI model every day to keep the data up to date.

[0111] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check. The management panel is web-based and can be accessed from anywhere.

[0112] This will make it possible to distribute the workload of employees fairly and reduce the amount of time spent managing overtime. It is also expected that there will be an increase in employees who are desired by managers.

[0113] Prompt Sentence Examples

[0114] To provide a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[0115] "Please enter Employee A's work data and analyze the total hours worked and overtime for this month. In addition, please check whether any employees are working too much and recommend appropriate work improvement measures."

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1: Collect work data

[0118] The terminal receives input from employees (start time, end time, break time, work content) and records the work data. For example, if employee A starts work at 9:00 and leaves work at 18:00, the start and end times are recorded on the terminal. The output is the recorded work data, which is the information to be sent to the server.

[0119] Step 2: Send data to the server

[0120] The server receives work data collected from each terminal at regular intervals. For example, every hour the server retrieves the latest work data from the terminal and stores it in a database. The input is work data from the terminal, and the output is data stored in the database in the server. Specifically, the server receives and stores the attendance data of employee A at 9:00 at 10:00.

[0121] Step 3: Data analysis with generative AI

[0122] The server sends the collected work data to the generative AI model. The generative AI model analyzes the input work data and identifies each employee's total working hours, overtime hours, and imbalances. For example, calculate employee A's total working hours and overtime hours for this month and check whether they exceed 80 hours. The input is work data from the server, and the output is the analysis result of the generative AI model.

[0123] Step 4: Imbalance detection and alerting

[0124] The server receives the analysis results from the generation AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. Specifically, the server detects that employee A's overtime hours exceed 80 hours and sends an email notification to management. The input is the analysis results from the generation AI, and the output is an alert notification to the relevant parties.

[0125] Step 5: Proposal for business improvement

[0126] The generative AI model proposes measures to improve workloads based on the analysis results. The server notifies the relevant parties of the improvement measures received from the generative AI. Specifically, the generative AI model proposes "redistribution of work," and the server sends this proposal to employee A's team leader. The input is the improvement proposal from the generative AI, and the output is a notification to the relevant parties.

[0127] Step 6: Implement and monitor improvements

[0128] The user (management) implements the proposed improvement measures. For example, a team leader holds a meeting to redistribute work. The server then continuously monitors the work data and evaluates the effectiveness of the improvement measures. The input is the implementation status of work redistribution by the management, and the output is the measured results of the improvement measures. Specifically, the server analyzes employee A's work data after redistribution and evaluates the effectiveness.

[0129] Step 7: Generate and send the report

[0130] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to relevant parties. For example, at the end of the month, the server creates a report summarizing the effects of work improvements on employee A and sends it to management by email. The input is the analysis data from the generation AI and the server, and the output is an automatically generated report.

[0131] Step 8: Improve overtime management efficiency

[0132] The server manages overtime data in real time by working in conjunction with the generated AI model. The terminal displays the latest data and predictions in real time on the management panel. For example, the server updates the analysis results of the generated AI model every day and displays a "weekly trend graph of employee A's overtime hours" on the terminal. The input is real-time data from the generated AI, and the output is the content displayed on the management panel.

[0133] (Application example 1)

[0134] 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."

[0135] At logistics centers, imbalances in employee workloads often occur, resulting in problems such as overwork and reduced production efficiency. Conventional systems make it difficult to detect workload imbalances in real time and quickly implement countermeasures. Furthermore, it is difficult to propose appropriate work improvement measures, and there is a lack of effective means for monitoring the implementation status of these measures. This leads to problems such as inappropriate work style measures not being implemented, resulting in a significant drop in productivity.

[0136] 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.

[0137] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for issuing an alert when an imbalance is identified, means for proposing work improvement measures based on the analysis results, means for monitoring the implementation of the proposed work improvement measures, means for periodically reporting the analysis results and the effects of the improvements, means for providing real-time alerts and improvement measures to employees via a smart device, means for managing the work status at the logistics center in real time and detecting workload imbalances, means for displaying the detected imbalance on the smart device, and means for displaying improvement suggestions on the smart device. This makes it possible to identify workload imbalances at the logistics center in real time and quickly propose and implement appropriate improvement measures.

[0138] "Work data" refers to work-related information such as employees' arrival and departure times, break times, and job duties.

[0139] "Analysis" is the process of analyzing collected work data to detect specific patterns or imbalances.

[0140] "Imbalance" refers to an unequal situation in terms of workload, working hours, etc., and means that certain employees are placed under an excessive burden.

[0141] An "alert" is a means of sending warnings or notifications to relevant parties when an imbalance occurs.

[0142] "Business improvement measures" are recommendations and procedures for balancing workloads and improving efficiency.

[0143] "Monitoring" is the process of overseeing the implementation of business improvement measures and evaluating their effectiveness.

[0144] A "report" is a document that summarizes the analysis results and improvement effects for a certain period of time.

[0145] "Smart devices" are electronic devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[0146] A "logistics center" is a facility that stores, organizes, and distributes goods and materials.

[0147] "Real-time" refers to the ability to collect, analyze, and notify data almost simultaneously.

[0148] "Improvement proposals" are specific methods or means proposed by the generative AI model to improve work efficiency or reduce workload.

[0149] A "generative AI model" is a system that uses artificial intelligence to analyze data and generate patterns and suggestions.

[0150] The present invention is a system that detects imbalances in the workloads of employees at a logistics center in real time and promptly proposes appropriate remedial measures. This system operates in cooperation with a server, terminals, and users.

[0151] Collection and analysis of work data

[0152] The terminal records attendance data when an employee arrives at work, and clocks out when they leave. Break times and work content are also recorded in the same way. For example, employee A clocks in on his terminal when he arrives at work, and "9:00" is recorded as his arrival time. The server collects the latest work data from each terminal at regular intervals. For example, if the server collects work data every hour, employee A's arrival, clock out, and break data are periodically sent to the server. The server then sends the collected work data to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generation AI tallys up the total working hours and overtime hours for this month from employee A's data and detects that overtime hours exceed 80 hours.

[0153] Identifying and alerting on imbalances

[0154] The server receives the analysis results of the generation AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours. It may also display a real-time alert to employees wearing smart glasses.

[0155] Proposing business improvement measures and monitoring their implementation

[0156] The generation AI continues its analysis and proposes measures to improve the workload. Specifically, it proposes improvements such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures it receives from the generation AI. For example, the generation AI recommends "redistributing work," and the server sends the proposal to employee A's team leader. The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work with team members. The server continues to monitor work data even after the improvement is implemented and evaluates its effectiveness. For example, the server checks employee A's work data after the work has been redistributed, and evaluates whether overtime has decreased.

[0157] Generate and send reports

[0158] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements made to employee A is created. The generated report is automatically sent to the relevant parties. For example, the server may email a PDF report to a manager.

[0159] Streamlining overtime management

[0160] The server manages overtime data in real time by working in conjunction with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date. The terminal displays the latest data and predictions on the management panel in real time. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check.

[0161] Examples of specific examples and prompts

[0162] For example, if a logistics center employee is working more than eight hours a day, an imbalance will be detected and an alert will be displayed on the smart glasses. An example of a prompt sentence for the generative AI model is as follows:

[0163] Prompt Sentence Examples

[0164] Based on current employee work data, analyze workload imbalances, issue alerts if any, and suggest appropriate remedial measures.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] The terminal records attendance data when an employee arrives at work, and records attendance data when the employee leaves work. Break times and work details are also recorded in the same way. Inputs include employee time-stamping information (times of arrival and departure) and selected work details. This allows employee work data to be collected in real time. The output is sent to the server as work data.

[0168] Step 2:

[0169] The server collects the latest work data from each device at regular intervals. The input is work data from the device. The server collects this data in a fixed format and stores it in a database. This allows the server to centrally manage employee work status. The output is the organized work data sent to the generation AI.

[0170] Step 3:

[0171] The server sends work data to the generation AI for analysis. The input is work data collected and organized by the server. The generation AI analyzes this data and identifies each employee's workload, imbalances, and overtime hours. The output is the analysis results, which are sent back to the server.

[0172] Step 4:

[0173] The server receives the analysis results from the generation AI and detects workload imbalances and anomalies. The input is the analysis results returned by the generation AI. The server checks the analysis results and issues an alert if an imbalance is detected. The output is alert information, which is sent to relevant parties and smart devices.

[0174] Step 5:

[0175] The server notifies the relevant parties of the improvement measures received from the generation AI. The input is the business improvement measures proposed by the generation AI. The server analyzes the contents of the proposal and notifies the appropriate relevant parties (e.g., team leader). The output is a notification of the business improvement proposal.

[0176] Step 6:

[0177] The user (management) implements the proposed improvement measures. The input is the business improvement proposal notified by the server. The user takes specific action (for example, redistributing work or reviewing shifts) based on the improvement measures. The output is the results of implementing the improvement measures.

[0178] Step 7:

[0179] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. The input is new work data and the results of the improvements. The server analyzes the data and evaluates the effectiveness of the improvements. The output is an evaluation report.

[0180] Step 8:

[0181] The server automatically generates reports of analysis results and improvement effects at regular intervals. The input is the accumulated analysis results and improvement effect data. The server automatically generates reports and sends them to the relevant parties. The output is a PDF report.

[0182] Step 9:

[0183] The terminal displays the latest data and forecasts on the management panel in real time. The input is the latest data and forecast information sent from the server. The terminal displays this as graphs and charts so that the administrator can easily check it. The output is the visualization on the management panel.

[0184] In this way, it becomes possible to identify workload imbalances in logistics centers in real time and quickly propose and implement appropriate improvement measures.

[0185] 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.

[0186] This system collects and analyzes work data and user emotion data, identifies workload imbalances, and automatically proposes and implements appropriate remedial measures. This system operates in cooperation with the server, terminals, emotion engine, and users.

[0187] Collection and analysis of work data

[0188] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0189] The server periodically collects work data from each device. For example, a schedule can be set up so that the server collects work data from each device every hour. This allows employee A's arrival, departure, and break data to be collected on the server.

[0190] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. The generation AI tallys up the total working hours and overtime hours for this month from Employee A's data and identifies excessive overtime.

[0191] Emotion data collection and analysis

[0192] The emotion engine collects and analyzes the user's emotions. For example, the camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to collect emotion data. Emotion data includes information such as stress level and happiness level.

[0193] The server periodically collects emotional data from the emotion engine. For example, the server obtains employee A's emotional data every day. The emotion engine analyzes the collected emotional data and evaluates the employee's emotional state. The generative AI performs a comprehensive analysis combining the work data and emotional data to detect imbalances in workload and stress levels.

[0194] Identifying and alerting on imbalances

[0195] The server receives the analysis results of the generated AI and detects imbalances in workload or emotional states. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours and his emotional data indicates high stress."

[0196] Proposing business improvement measures and monitoring their implementation

[0197] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[0198] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0199] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[0200] Generate and send reports

[0201] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, it creates a report summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[0202] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[0203] Improved efficiency of overtime management and emotion monitoring

[0204] The server manages overtime data and emotion data in real time by linking with the generation AI and emotion engine. For example, it updates the analysis results of the generation AI and emotion engine every day and reflects the latest data on the management panel.

[0205] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[0206] This system will help to distribute the workload of employees fairly and monitor their emotional state, creating a comfortable working environment and reducing the amount of work required to manage overtime, which is expected to increase the number of employees who wish to become managers.

[0207] The processing flow will be explained below.

[0208] Step 1:

[0209] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0210] Step 2:

[0211] The server periodically collects work data from each device. For example, a schedule can be set up so that the server collects work data from each device every hour. This allows employee A's arrival, departure, and break data to be collected on the server.

[0212] Step 3:

[0213] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for one month" to the generation AI.

[0214] Step 4:

[0215] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates "total monthly working hours," "overtime hours," "break times," etc. from employee A's data and identifies excessive overtime.

[0216] Step 5:

[0217] The emotion engine collects and analyzes the user's emotions. The camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to obtain emotion data. For example, the emotion engine measures Employee A's stress level and happiness.

[0218] Step 6:

[0219] The server collects emotion data from the emotion engine and sends it to the generation AI along with work data. For example, the server sends employee A's emotion data to the generation AI every day.

[0220] Step 7:

[0221] The generative AI integrates and analyzes work data and emotional data to detect imbalances in workload and emotional states. For example, the generative AI detects a high stress state from employee A's emotional data and correlates it with an imbalance in workload.

[0222] Step 8:

[0223] The server receives the analysis results of the generating AI and sends an alert to relevant parties if an imbalance is identified. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours, and his emotional data indicates high stress."

[0224] Step 9:

[0225] The Generative AI performs additional analysis to recommend measures to improve workloads. Recommendations include redistributing work and reviewing shifts. For example, the Generative AI might recommend "redistributing Employee A's work to other members."

[0226] Step 10:

[0227] The server notifies the relevant parties of the improvement measures received from the generation AI. For example, the server sends an email to the team leader with a "work reallocation proposal."

[0228] Step 11:

[0229] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0230] Step 12:

[0231] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[0232] Step 13:

[0233] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, a report is created summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[0234] Step 14:

[0235] The server automatically sends the generated report to the relevant parties. For example, the server may email the report in PDF format to a manager.

[0236] Step 15:

[0237] The server manages overtime data and emotion data in real time by linking with the generation AI and emotion engine. For example, it updates the analysis results of the generation AI and emotion engine every day and reflects the latest data on the management panel.

[0238] Step 16:

[0239] The device displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[0240] Example 2

[0241] 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."

[0242] In today's work environment, it is difficult to accurately collect and analyze employee work data and emotional data to identify imbalances in workload and emotional state. When employees experience excessive stress or have uneven workloads, it is necessary to identify the issue early and propose and implement appropriate improvement measures. However, conventional systems do not adequately analyze work data and emotional data comprehensively, making it difficult to propose efficient work improvement measures and monitor their effectiveness.

[0243] 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.

[0244] In this invention, the server includes means for collecting work data, means for collecting emotion data, means for analyzing using a generative AI model, means for identifying imbalances, means for issuing alerts, means for proposing business improvement measures, means for monitoring the implementation of the proposed business improvement measures, and means for reporting the analysis results and improvement effects at regular intervals. This enables integrated and real-time analysis of employee work data and emotion data, early identification of imbalances in workload or emotional states, and the proposing and implementation of appropriate improvement measures.

[0245] "Work data" refers to data related to working hours and work conditions, such as an employee's arrival time, departure time, break time, and job content.

[0246] "Emotional data" refers to data that indicates psychological states such as stress levels and happiness obtained from employees' facial expressions, voice, behavior, etc.

[0247] A "generative AI model" is an artificial intelligence model that analyzes collected data and performs advanced data processing such as recognizing patterns and providing insights.

[0248] The "analyzing means" is a processing device or software that uses the collected data to evaluate and analyze workload, emotional state, and the like.

[0249] The "means for identifying imbalances" is an algorithm or device for identifying imbalances or imbalances in workload or emotional states based on the analysis results.

[0250] An "alert mechanism" is a communications device or software that notifies relevant parties when an imbalance is detected.

[0251] "Means for proposing business improvement measures" refers to a processing device or software that proposes improvement measures, such as adjusting workloads or redistributing work, based on the analysis results of the generative AI model.

[0252] "Means for monitoring proposed improvement measures" refers to devices or software for continuously evaluating the implementation status and effectiveness of proposed business improvement measures.

[0253] "Means for reporting analysis results and improvement effects at regular intervals" refers to a device or software that periodically generates reports on the analysis results and the effects of implementing business improvement measures, and provides them to relevant parties.

[0254] "Server" means a central processing unit for collecting data, analyzing, identifying imbalances, issuing alerts, recommending business improvements, monitoring, and generating reports.

[0255] "Terminal" means a device used by an employee to input and collect work data and emotion data.

[0256] This invention is a system that collects and analyzes work data and employee emotion data, identifies imbalances in workload and emotional states, and proposes and implements improvement measures. This system operates in cooperation with a server, terminals, and an emotion engine.

[0257] Collection of work data

[0258] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00." Break times and work details are also recorded at the same time.

[0259] Collection and analysis of work data

[0260] The server periodically collects work data from each device. For example, the server processes data on clock-in, clock-out, and breaks from each device every hour. The server then sends the collected work data to the generative AI model. The generative AI model then analyzes the data using the following prompt:

[0261] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[0262] A generative AI model analyzes the data it receives, calculates each employee's total working hours and overtime hours, and identifies imbalances.

[0263] Emotion data collection and analysis

[0264] The emotion engine collects the user's emotion data. While Employee A is working in front of the terminal, the terminal's camera analyzes facial expressions and the microphone collects emotion data from voice. The server collects the emotion data and sends it to the generative AI model. The generative AI model analyzes the emotion data using the following prompt sentence:

[0265] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[0266] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[0267] Identifying and alerting on imbalances

[0268] The server integrates the results of analyzing work data and emotional data to detect imbalances. For example, if the server detects that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an email alert to management.

[0269] Proposing business improvement measures and monitoring their implementation

[0270] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotion data. For example, the generative AI model recommends "redistribution of work," and the server notifies the manager of the proposal. The user (manager) then implements the proposed improvement measures. For example, the manager holds a meeting and decides to distribute employee A's work to other members.

[0271] Monitoring the effectiveness of improvements

[0272] The server continues to monitor work data and emotion data even after the implementation of improvement measures and evaluates their effectiveness. For example, even after redistribution, the server checks the work data and emotion data of employee A and evaluates whether overtime hours have been reduced and stress has been alleviated.

[0273] Generate and send reports

[0274] The server automatically generates a report of the analysis results and improvement effects at regular intervals and sends it to the relevant parties. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management.

[0275] Real-time management of overtime and emotion data

[0276] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The terminal displays a real-time graph of employee A's weekly overtime hours and emotion data trends on the management panel, making it easy for managers to check. This system enables the integrated analysis of employee work data and emotion data, making it possible to create a comfortable working environment and reduce the workload of managing overtime.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] The terminal records the employee's arrival time. The input is the employee's ID card information, which is stamped when they arrive at work. Specifically, when an employee holds their ID card over the terminal, the data "Arrival time: 9:00" is generated. This data is temporarily stored in the terminal.

[0280] Step 2:

[0281] The terminal records the employee's time of leaving work. The input is again the employee's ID card information, which is punched in when they leave work. Specifically, when an employee swipes their ID card at the desk to leave work, the data "Leave work time: 18:00" is generated. This data is also temporarily stored in the terminal.

[0282] Step 3:

[0283] The server periodically collects work data from each terminal. The input is the work data sent from each terminal, and the output is the work data consolidated in the server. For example, the server runs a collection script every hour to obtain data on arrival, departure, and breaks from each terminal.

[0284] Step 4:

[0285] The server sends the collected work data to the generative AI model. The input is the work data integrated by the server, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[0286] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[0287] The generative AI model analyzes work data, calculates total hours worked and overtime, and identifies imbalances.

[0288] Step 5:

[0289] The emotion engine collects the user's emotional data. The input is real-time facial and voice data obtained from the device's camera and microphone, and the output is the analysis results by the emotion engine. For example, while an employee is working in front of a device, the camera analyzes their facial expressions and the microphone collects their voice.

[0290] Step 6:

[0291] The server collects emotion data from the emotion engine and sends it to the generative AI model. The input is the emotion data obtained from the emotion engine, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[0292] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[0293] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[0294] Step 7:

[0295] The server integrates the results of work data and emotion data analysis to detect imbalances. The input is the analysis results of work data and emotion data obtained from the generative AI model, and the output is an alert indicating imbalances. For example, if the server finds that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an alert to management by email.

[0296] Step 8:

[0297] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotional data. The input is the analyzed work data and emotional data, and the output is a proposal for improvement measures. Specifically, the generative AI model recommends "work redistribution," and the server notifies the proposal to managers.

[0298] Step 9:

[0299] The user (management) implements the proposed improvement measures. The input is the improvement proposal from the generative AI model, and the output is the result of work redistribution after implementation. For example, the manager holds a meeting to allocate Employee A's work to other members.

[0300] Step 10:

[0301] The server continues to monitor work data and emotion data even after the implementation of improvement measures, and evaluates their effectiveness. The input is the collected work data and emotion data again, and the output is an evaluation of the effectiveness of the improvement. For example, even after redistribution, the server checks the work data and emotion data of employee A, and evaluates whether overtime hours have been reduced and stress has been alleviated.

[0302] Step 11:

[0303] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to the relevant parties. The input is the analysis results and improvement effect data, and the output is the generated report. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management by email.

[0304] Step 12:

[0305] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The input is the latest data from the generative AI model and emotion engine, and the output is the data for each employee displayed on the management panel. The terminal displays a weekly graph of employee A's overtime hours and emotion data trends on the management panel in real time, making it easy for managers to check.

[0306] (Application example 2)

[0307] 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."

[0308] In factory work environments, workload imbalances between employees and robots can occur, resulting in reduced production efficiency and increased employee stress. Identifying workload imbalances and proposing improvements requires a significant amount of time and effort. Even if improvements are proposed, there is a lack of efficient means for monitoring the effectiveness of their implementation. A solution to these issues is needed.

[0309] The identification processing by the identification 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 work data and emotional data, means for analyzing the collected work data and emotional data, and means for identifying imbalances in work load and emotional state based on the analysis results. This makes it possible to automatically propose improvements and improve implementation efficiency in order to maintain an appropriate balance between workload and emotional state.

[0310] "Work data" refers to information about the working habits of employees and machines, such as their arrival and departure times, work content, and break times.

[0311] "Emotional data" refers to information about the psychological state and emotions of employees and workers obtained by analyzing their facial expressions, voice, physical movements, etc.

[0312] A "collection means" is a device or system that has the function of acquiring data using an input device such as a sensor, camera, or microphone.

[0313] The "analysis method" is a process that uses algorithms and machine learning models to evaluate working patterns and emotional states based on collected data and detect imbalances and anomalies.

[0314] The "means for identifying" is a device or system that has the function of identifying and clearly indicating imbalances in workload or emotional state from the analysis results.

[0315] An "alert means" is a device or system that has the capability to notify administrators and other relevant parties of relevant information when an imbalance is identified.

[0316] The "means for making recommendations" refers to a device or system that has the function of automatically generating and proposing appropriate business improvement measures and shift readjustment measures based on the analysis results.

[0317] "Monitoring means" refers to a device or system that has the function of continuously monitoring and evaluating how effectively a proposed business improvement measure or shift readjustment measure is functioning after it has been implemented.

[0318] "Reporting means" refers to a device or system that has the function of creating and distributing reports on the analysis results and the effects of improvements based on data collected and analyzed at regular intervals.

[0319] "Imbalance" refers to a situation in which workload and emotional state are not equal, i.e., the existence of problems such as excessive workload or high stress.

[0320] "Business improvement measures" are specific action plans and measures to resolve problems identified through the analysis results and to improve business efficiency and the working environment.

[0321] The system that realizes this invention has a means for collecting and analyzing work data and emotional data from employees and machines, identifying imbalances in workload and emotional states, and proposing measures to improve them. The specific configuration and operation of this system are described below.

[0322] Data collection methods

[0323] The server has a means for collecting work data and emotional data. Work data is automatically collected from sensors and terminals and includes employees' arrival and departure times, work tasks, break times, etc. Emotional data is acquired using cameras and microphones through facial recognition and voice analysis.

[0324] Data Analysis Methods

[0325] The collected work data and emotional data are analyzed by a server. A generative AI model using TensorFlow is used for the analysis, and data processing is performed to identify imbalances. Specifically, the data is preprocessed (missing value correction and normalization), and then the AI ​​model is used to evaluate workload and emotional state.

[0326] Imbalance identification means

[0327] The server has a means for identifying imbalances in work and emotional states based on the analysis results. For example, if the total working hours, overtime hours, or stress level of employee A are high, these are identified as imbalances.

[0328] Alert method

[0329] If an imbalance is identified, the server has the means to raise an alert, specifically by sending an email notification to the relevant administrator or stakeholders.

[0330] Business improvement proposal methods

[0331] The server has a means to propose work improvement measures and shift reallocation measures based on the analysis results. The proposed contents are automatically sent to the manager, who will suggest work reallocation and shift review.

[0332] Implementation monitoring measures

[0333] Even after the proposed work improvement measures and shift reallocation measures are implemented, the server has a means for continuously monitoring the work data and emotion data, thereby evaluating the effectiveness of the implemented improvement measures.

[0334] Report Generation Method

[0335] The server has a means to periodically report the analysis results and improvement effects, and the generated reports are automatically sent to the relevant parties.

[0336] Hardware and software used

[0337] Sensor: Device for measuring operating time

[0338] Camera and microphone: a device for collecting emotional data

[0339] TensorFlow: for analyzing generative AI models

[0340] EmotionEngine: for emotional data analysis

[0341] smtplib: for email notifications

[0342] Prompt Sentence Examples

[0343] Example of sending work data: "Employee A's work data for May"

[0344] Example of sending emotional data: "Employee A's emotional data"

[0345] This enables automated improvement suggestions and improved implementation efficiency to properly balance workload and emotional states in factories and other large workplaces.

[0346] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0347] Step 1:

[0348] The server collects work data and emotional data. Specifically, the terminal records the arrival and departure times, break times, and work details of employees and machines, and acquires emotional data from sensors, cameras, and microphones. This data is sent from the terminal to the server. The input is the operating status and emotional state of each employee and machine, and the output is the collected data.

[0349] Step 2:

[0350] The server preprocesses the collected work data and emotion data, imputing missing values ​​and normalizing the data. Specifically, missing values ​​for each data point are imputed with zeros and all data is standardized. The input is the data collected in step 1, and the output is the preprocessed data.

[0351] Step 3:

[0352] The server analyzes the preprocessed data. Using TensorFlow, the preprocessed data is fed into a generative AI model to identify imbalances in workload and emotional states. Specifically, the model detects excessive working hours and high stress levels. The input is the preprocessed data, and the output is an analysis showing the imbalances.

[0353] Step 4:

[0354] The server notifies administrators of imbalances based on the analysis results. Specifically, it uses the smtplib library to send alerts by email. The notifications describe excessive workloads and stress levels of employees and machines. The input is the analysis results, and the output is the sent alert email.

[0355] Step 5:

[0356] The server recommends business improvement measures and shift reallocation measures based on the analysis results. It uses a generative AI model to calculate the optimal reallocation and generate recommendations. The recommendations are automatically sent to the administrator. The inputs are the analysis results and performance data, and the output is the recommendations.

[0357] Step 6:

[0358] The user (manager) implements the proposed business improvement measures and shift reallocation measures. Specifically, team meetings and shift adjustments are held, and the proposed improvement measures are implemented. The input is the proposal, and the output is the implemented improvement measures.

[0359] Step 7:

[0360] The server continues to monitor work data and emotion data even after the proposed improvement measures are implemented. It again collects and analyzes data from sensors, cameras, and microphones. This allows the effectiveness of the improvement measures to be evaluated. The input is the updated work data and emotion data, and the output is the reevaluation results.

[0361] Step 8:

[0362] The server periodically compiles the analysis results and improvement effects into a report. The report is automatically generated and distributed to relevant parties. The input is the data and analysis results obtained at each step, and the output is data in report format.

[0363] 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.

[0364] 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.

[0365] 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.

[0366] [Second embodiment]

[0367] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0368] 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.

[0369] 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).

[0370] 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.

[0371] 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.

[0372] 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).

[0373] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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."

[0379] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[0380] Collection and analysis of work data

[0381] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[0382] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be sent to the server periodically. The server then sends the collected work data to the generation AI.

[0383] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates the total working hours and overtime hours for this month from the data of employee A and detects that the overtime hours exceed 80 hours.

[0384] Identifying and alerting on imbalances

[0385] The server receives the analysis results of the generative AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours.

[0386] Proposing business improvement measures and monitoring their implementation

[0387] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[0388] The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work among team members.

[0389] The server continues to monitor work data even after improvements are implemented and evaluates the effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased.

[0390] Generate and send reports

[0391] The server automatically generates a report of the analysis results and the improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of improvements made to Employee A's work is created.

[0392] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[0393] Streamlining overtime management

[0394] The server manages overtime data in real time in cooperation with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date.

[0395] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a graph of employee A's weekly overtime hours on the management panel, making it easy for managers to check.

[0396] This system will make the workload of employees fairer, reduce the amount of time required to manage overtime, and is expected to increase the number of employees who wish to become managers.

[0397] The processing flow will be explained below.

[0398] Step 1:

[0399] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0400] Step 2:

[0401] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[0402] Step 3:

[0403] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI.

[0404] Step 4:

[0405] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. The generation AI aggregates "total monthly working hours," "overtime hours," and "break times" from employee A's data and identifies excessive overtime.

[0406] Step 5:

[0407] The server receives the analysis results of the generated AI and detects workload imbalances. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours."

[0408] Step 6:

[0409] The generative AI performs additional data analysis to propose measures to improve workloads. Specifically, it proposes measures such as redistributing work and reviewing shifts. For example, the generative AI might recommend "reviewing the division of work."

[0410] Step 7:

[0411] The server notifies the relevant parties of the generated AI's recommendations. For example, the server may notify employee A's team leader of the "redistribution of work proposals" by email.

[0412] Step 8:

[0413] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0414] Step 9:

[0415] The server continues to monitor the work data even after the implementation of the proposed improvement measures and evaluates the effectiveness of the improvements. For example, the server collects the work data of employee A even after the redistribution to confirm the reduction in overtime hours.

[0416] Step 10:

[0417] The server periodically generates a report on the analysis results and the effects of the improvements. For example, at the end of the month, a report is created summarizing the changes in working hours and overtime hours of employee A before and after the improvements.

[0418] Step 11:

[0419] The server provides the generated report to the relevant parties. For example, the server may email the report in PDF format to a team leader or manager.

[0420] Step 12:

[0421] The server manages overtime data in real time by linking with the AI ​​generator. For example, the AI ​​generator updates its analysis results every day and reflects the latest data on the management panel.

[0422] Step 13:

[0423] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph showing the weekly trend of employee A's overtime hours, making it easy for managers to check.

[0424] Example 1

[0425] 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."

[0426] Conventional work data management systems have had difficulty in detecting imbalances in employee workloads and overwork, and proposing and implementing improvement measures. As a result, improvements to employees' working environments have been delayed, leading to problems such as lower labor productivity and motivation. The purpose of this invention is to solve these problems and efficiently manage and improve workloads.

[0427] 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.

[0428] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for analyzing the work data with a generative AI model and proposing measures to improve workloads, means for notifying relevant parties when an imbalance is identified, means for users to implement the proposed work improvement measures, and means for continuously monitoring the effectiveness of the work improvement measures. This makes it possible to efficiently and fairly manage employee workloads and quickly implement appropriate improvement measures.

[0429] "Work data" refers to information about an employee's work, such as the employee's arrival time, departure time, break time, and job duties.

[0430] "Means of collection" refers to the hardware or software that employees use to record information about their work and transmit that data to a server.

[0431] "Means of analysis" refers to the method of using software to analyze collected work data and calculate indicators such as workload and overtime hours.

[0432] "Means for identifying imbalances" refers to the process of detecting imbalances or abnormalities in workload among employees based on analyzed work data.

[0433] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate results or recommendations tailored to a specific purpose.

[0434] "Means for proposing measures to improve workload" refers to a method in which the generative AI model derives specific improvement proposals, such as redistributing work or reviewing shifts, based on the analysis results.

[0435] "Means of notifying stakeholders" refers to the method of communicating identified imbalances and proposed remedial measures to stakeholders via email or notification systems.

[0436] "User implementation measures" refers to the process by which managers and team leaders actually apply the proposed improvements in their work environment.

[0437] "Monitoring measures" refers to methods for continuously monitoring and evaluating the effectiveness of proposed improvements after they have been implemented.

[0438] "Means of reporting" refers to the process of automatically generating reports that periodically summarize the analysis results and improvement effects and sending them to relevant parties.

[0439] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[0440] Collection and analysis of work data

[0441] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. The terminals used are attendance management devices with touch panels or card readers so that employees can easily operate them. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[0442] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be periodically sent to the server. The server is equipped with a high-performance database and communication interface, allowing for real-time data collection. The server then sends the collected work data to the generative AI model.

[0443] The generative AI model analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generative AI aggregates the total working hours and overtime hours for this month from Employee A's data and detects that the overtime hours exceed 80 hours. Machine learning algorithms are used in the analysis to recognize patterns and detect anomalies.

[0444] Identifying and alerting on imbalances

[0445] The server receives the analysis results of the generative AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server detects that employee A's overtime hours exceed 80 hours and notifies management by email. A template engine is used for the notification, and an automatically generated email body is sent.

[0446] Proposing business improvement measures and monitoring their implementation

[0447] The generative AI model continues its analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generative AI. For example, if the generative AI recommends "redistributing work," the server sends the recommendation to employee A's team leader. The notification is distributed via email or the internal messaging system.

[0448] The user (management) implements the proposed improvement measures. Specifically, the team leader holds a meeting to redistribute work among team members. For example, employee A's work is assigned to another member. The implementation status of the improvement measures is recorded using a task management tool.

[0449] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased. Statistical analysis software is used for the evaluation and effectiveness is measured.

[0450] Generate and send reports

[0451] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements on employee A is created. The generated report includes graphs and charts to visualize the effects.

[0452] The generated reports are automatically sent to the relevant parties. For example, the server emails the report in PDF format to management. An automation tool is used to send the emails, ensuring regular reporting.

[0453] Streamlining overtime management

[0454] The server manages overtime data in real time in cooperation with the generative AI model. For example, the server updates the analysis results of the generative AI model every day to keep the data up to date.

[0455] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check. The management panel is web-based and can be accessed from anywhere.

[0456] This will make it possible to distribute the workload of employees fairly and reduce the amount of time spent managing overtime. It is also expected that the number of employees desired by managers will increase.

[0457] Prompt Sentence Examples

[0458] To provide a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[0459] "Please enter Employee A's work data and analyze the total hours worked and overtime for this month. In addition, please check whether any employees are working too much and recommend appropriate work improvement measures."

[0460] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0461] Step 1: Collect work data

[0462] The terminal receives input from employees (start time, end time, break time, work content) and records the work data. For example, if employee A starts work at 9:00 and leaves work at 18:00, the start and end times are recorded on the terminal. The output is the recorded work data, which is the information to be sent to the server.

[0463] Step 2: Send data to the server

[0464] The server receives work data collected from each terminal at regular intervals. For example, every hour the server retrieves the latest work data from the terminal and stores it in a database. The input is work data from the terminal, and the output is data stored in the database in the server. Specifically, the server receives and stores the attendance data of employee A at 9:00 at 10:00.

[0465] Step 3: Data analysis with generative AI

[0466] The server sends the collected work data to the generative AI model. The generative AI model analyzes the input work data and identifies each employee's total working hours, overtime hours, and imbalances. For example, calculate employee A's total working hours and overtime hours for this month and check whether they exceed 80 hours. The input is work data from the server, and the output is the analysis result of the generative AI model.

[0467] Step 4: Imbalance detection and alerting

[0468] The server receives the analysis results from the generation AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. Specifically, the server detects that employee A's overtime hours exceed 80 hours and sends an email notification to management. The input is the analysis results from the generation AI, and the output is an alert notification to the relevant parties.

[0469] Step 5: Proposing business improvement measures

[0470] The generative AI model proposes measures to improve workloads based on the analysis results. The server notifies the relevant parties of the improvement measures received from the generative AI. Specifically, the generative AI model proposes "redistribution of work," and the server sends this proposal to employee A's team leader. The input is the improvement proposal from the generative AI, and the output is a notification to the relevant parties.

[0471] Step 6: Implement and monitor improvements

[0472] The user (management) implements the proposed improvement measures. For example, a team leader holds a meeting to redistribute work. The server then continuously monitors the work data and evaluates the effectiveness of the improvement measures. The input is the implementation status of work redistribution by the management, and the output is the measured results of the improvement measures. Specifically, the server analyzes employee A's work data after redistribution and evaluates the effectiveness.

[0473] Step 7: Generate and send the report

[0474] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to relevant parties. For example, at the end of the month, the server creates a report summarizing the effects of work improvements on employee A and sends it to management by email. The input is the analysis data from the generation AI and the server, and the output is an automatically generated report.

[0475] Step 8: Improve overtime management efficiency

[0476] The server manages overtime data in real time by working in conjunction with the generated AI model. The terminal displays the latest data and predictions in real time on the management panel. For example, the server updates the analysis results of the generated AI model every day and displays a "weekly trend graph of employee A's overtime hours" on the terminal. The input is real-time data from the generated AI, and the output is the content displayed on the management panel.

[0477] (Application example 1)

[0478] 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."

[0479] At logistics centers, imbalances in employee workloads often occur, resulting in problems such as overwork and reduced production efficiency. Conventional systems make it difficult to detect workload imbalances in real time and quickly implement countermeasures. Furthermore, it is difficult to propose appropriate work improvement measures, and there is a lack of effective means for monitoring the implementation status of these measures. This leads to problems such as inappropriate work style measures not being implemented, resulting in a significant drop in productivity.

[0480] 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.

[0481] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for issuing an alert when an imbalance is identified, means for proposing work improvement measures based on the analysis results, means for monitoring the implementation of the proposed work improvement measures, means for periodically reporting the analysis results and the effects of the improvements, means for providing real-time alerts and improvement measures to employees via a smart device, means for managing the work status at the logistics center in real time and detecting workload imbalances, means for displaying the detected imbalance on the smart device, and means for displaying improvement suggestions on the smart device. This makes it possible to identify workload imbalances at the logistics center in real time and quickly propose and implement appropriate improvement measures.

[0482] "Work data" refers to work-related information such as employees' arrival and departure times, break times, and job duties.

[0483] "Analysis" is the process of analyzing collected work data to detect specific patterns or imbalances.

[0484] "Imbalance" refers to an unequal situation in terms of workload, working hours, etc., and means that certain employees are placed under an excessive burden.

[0485] An "alert" is a means of sending warnings or notifications to relevant parties when an imbalance occurs.

[0486] "Business improvement measures" are recommendations and procedures for balancing workloads and improving efficiency.

[0487] "Monitoring" is the process of overseeing the implementation of business improvement measures and evaluating their effectiveness.

[0488] A "report" is a document that summarizes the analysis results and improvement effects for a certain period of time.

[0489] "Smart devices" are electronic devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[0490] A "logistics center" is a facility that stores, organizes, and distributes goods and materials.

[0491] "Real-time" refers to the ability to collect, analyze, and notify data almost simultaneously.

[0492] "Improvement proposals" are specific methods or means proposed by the generative AI model to improve work efficiency or reduce workload.

[0493] A "generative AI model" is a system that uses artificial intelligence to analyze data and generate patterns and suggestions.

[0494] The present invention is a system that detects imbalances in the workloads of employees at a logistics center in real time and promptly proposes appropriate remedial measures. This system operates in cooperation with a server, terminals, and users.

[0495] Collection and analysis of work data

[0496] The terminal records attendance data when an employee arrives at work, and clocks out when they leave. Break times and work content are also recorded in the same way. For example, employee A clocks in on his terminal when he arrives at work, and "9:00" is recorded as his arrival time. The server collects the latest work data from each terminal at regular intervals. For example, if the server collects work data every hour, employee A's arrival, clock out, and break data are periodically sent to the server. The server then sends the collected work data to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generation AI tallys up the total working hours and overtime hours for this month from employee A's data and detects that overtime hours exceed 80 hours.

[0497] Identifying and alerting on imbalances

[0498] The server receives the analysis results of the generation AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours. It may also display a real-time alert to employees wearing smart glasses.

[0499] Proposing business improvement measures and monitoring their implementation

[0500] The generation AI continues its analysis and proposes measures to improve the workload. Specifically, it proposes improvements such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures it receives from the generation AI. For example, the generation AI recommends "redistributing work," and the server sends the proposal to employee A's team leader. The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work with team members. The server continues to monitor work data even after the improvement is implemented and evaluates its effectiveness. For example, the server checks employee A's work data after the work has been redistributed, and evaluates whether overtime has decreased.

[0501] Generate and send reports

[0502] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements made to employee A is created. The generated report is automatically sent to the relevant parties. For example, the server may email a PDF report to a manager.

[0503] Streamlining overtime management

[0504] The server manages overtime data in real time by working with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date. The terminal displays the latest data and predictions on the management panel in real time. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check.

[0505] Examples of concrete examples and prompts

[0506] For example, if a logistics center employee is working more than eight hours a day, an imbalance will be detected and an alert will be displayed on the smart glasses. An example of a prompt sentence for the generative AI model is as follows:

[0507] Prompt Sentence Examples

[0508] Based on current employee work data, analyze workload imbalances, issue alerts if any, and suggest appropriate remedial measures.

[0509] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0510] Step 1:

[0511] The terminal records attendance data when an employee arrives at work, and records attendance data when the employee leaves work. Break times and work details are also recorded in the same way. Inputs include employee time-stamping information (times of arrival and departure) and selected work details. This allows employee work data to be collected in real time. The output is sent to the server as work data.

[0512] Step 2:

[0513] The server collects the latest work data from each device at regular intervals. The input is work data from the device. The server collects this data in a fixed format and stores it in a database. This allows the server to centrally manage employee work status. The output is the organized work data sent to the generation AI.

[0514] Step 3:

[0515] The server sends work data to the generation AI for analysis. The input is work data collected and organized by the server. The generation AI analyzes this data and identifies each employee's workload, imbalances, and overtime hours. The output is the analysis results, which are sent back to the server.

[0516] Step 4:

[0517] The server receives the analysis results from the generation AI and detects workload imbalances and anomalies. The input is the analysis results returned by the generation AI. The server checks the analysis results and issues an alert if an imbalance is detected. The output is alert information, which is sent to relevant parties and smart devices.

[0518] Step 5:

[0519] The server notifies the relevant parties of the improvement measures received from the generation AI. The input is the business improvement measures proposed by the generation AI. The server analyzes the contents of the proposal and notifies the appropriate relevant parties (e.g., team leader). The output is a notification of the business improvement proposal.

[0520] Step 6:

[0521] The user (management) implements the proposed improvement measures. The input is the business improvement proposal notified by the server. The user takes specific action (for example, redistributing work or reviewing shifts) based on the improvement measures. The output is the results of implementing the improvement measures.

[0522] Step 7:

[0523] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. The input is new work data and the results of the improvements. The server analyzes the data and evaluates the effectiveness of the improvements. The output is an evaluation report.

[0524] Step 8:

[0525] The server automatically generates reports of analysis results and improvement effects at regular intervals. The input is the accumulated analysis results and improvement effect data. The server automatically generates reports and sends them to the relevant parties. The output is a PDF report.

[0526] Step 9:

[0527] The terminal displays the latest data and forecasts on the management panel in real time. The input is the latest data and forecast information sent from the server. The terminal displays this as graphs and charts so that the administrator can easily check it. The output is the visualization on the management panel.

[0528] In this way, it becomes possible to identify workload imbalances in logistics centers in real time and quickly propose and implement appropriate improvement measures.

[0529] 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.

[0530] This system collects and analyzes work data and user emotion data, identifies workload imbalances, and automatically proposes and implements appropriate remedial measures. This system operates in cooperation with the server, terminals, emotion engine, and users.

[0531] Collection and analysis of work data

[0532] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0533] The server periodically collects work data from each device. For example, a schedule can be set up so that the server collects work data from each device every hour. This allows employee A's arrival, departure, and break data to be collected on the server.

[0534] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. The generation AI tallys up the total working hours and overtime hours for this month from Employee A's data and identifies excessive overtime.

[0535] Emotion data collection and analysis

[0536] The emotion engine collects and analyzes the user's emotions. For example, the camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to collect emotion data. Emotion data includes information such as stress level and happiness level.

[0537] The server periodically collects emotional data from the emotion engine. For example, the server obtains employee A's emotional data every day. The emotion engine analyzes the collected emotional data and evaluates the employee's emotional state. The generative AI performs a comprehensive analysis combining the work data and emotional data to detect imbalances in workload and stress levels.

[0538] Identifying and alerting on imbalances

[0539] The server receives the analysis results of the generated AI and detects imbalances in workload or emotional states. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours and his emotional data indicates high stress."

[0540] Proposing business improvement measures and monitoring their implementation

[0541] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[0542] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0543] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[0544] Generate and send reports

[0545] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, it creates a report summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[0546] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[0547] Improved efficiency of overtime management and emotion monitoring

[0548] The server manages overtime data and emotion data in real time by linking with the generation AI and emotion engine. For example, it updates the analysis results of the generation AI and emotion engine every day and reflects the latest data on the management panel.

[0549] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[0550] This system will help to distribute the workload of employees fairly and monitor their emotional state, creating a comfortable working environment and reducing the amount of work required to manage overtime, which is expected to increase the number of employees who wish to become managers.

[0551] The processing flow will be explained below.

[0552] Step 1:

[0553] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0554] Step 2:

[0555] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[0556] Step 3:

[0557] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for one month" to the generation AI.

[0558] Step 4:

[0559] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates "total monthly working hours," "overtime hours," "break times," etc. from employee A's data and identifies excessive overtime.

[0560] Step 5:

[0561] The emotion engine collects and analyzes the user's emotions. The camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to obtain emotion data. For example, the emotion engine measures Employee A's stress level and happiness.

[0562] Step 6:

[0563] The server collects emotion data from the emotion engine and sends it to the generation AI along with work data. For example, the server sends employee A's emotion data to the generation AI every day.

[0564] Step 7:

[0565] The generative AI integrates and analyzes work data and emotional data to detect imbalances in workload and emotional states. For example, the generative AI detects a high stress state from employee A's emotional data and correlates it with an imbalance in workload.

[0566] Step 8:

[0567] The server receives the analysis results of the generating AI and sends an alert to relevant parties if an imbalance is identified. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours, and his emotional data indicates high stress."

[0568] Step 9:

[0569] The Generative AI performs additional analysis to recommend measures to improve workloads. Recommendations include redistributing work and reviewing shifts. For example, the Generative AI might recommend "redistributing Employee A's work to other members."

[0570] Step 10:

[0571] The server notifies the relevant parties of the improvement measures received from the generation AI. For example, the server sends an email to the team leader with a "work reallocation proposal."

[0572] Step 11:

[0573] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0574] Step 12:

[0575] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[0576] Step 13:

[0577] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, a report is created summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[0578] Step 14:

[0579] The server automatically sends the generated report to the relevant parties. For example, the server may email the report in PDF format to a manager.

[0580] Step 15:

[0581] The server manages real-time overtime data and emotion data in cooperation with the generation AI and emotion engine. For example, the analysis results of the generation AI and emotion engine are updated daily, and the latest data is reflected in the management panel.

[0582] Step 16:

[0583] The device displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[0584] Example 2

[0585] 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."

[0586] In today's work environment, it is difficult to accurately collect and analyze employee work data and emotional data to identify imbalances in workload and emotional state. When employees experience excessive stress or have uneven workloads, it is necessary to identify the issue early and propose and implement appropriate improvement measures. However, conventional systems do not adequately analyze work data and emotional data comprehensively, making it difficult to propose efficient work improvement measures and monitor their effectiveness.

[0587] 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.

[0588] In this invention, the server includes means for collecting work data, means for collecting emotion data, means for analyzing using a generative AI model, means for identifying imbalances, means for issuing alerts, means for proposing business improvement measures, means for monitoring the implementation of the proposed business improvement measures, and means for reporting the analysis results and improvement effects at regular intervals. This enables integrated and real-time analysis of employee work data and emotion data, early identification of imbalances in workload or emotional states, and the proposing and implementation of appropriate improvement measures.

[0589] "Work data" refers to data related to working hours and work conditions, such as an employee's arrival time, departure time, break time, and job content.

[0590] "Emotional data" refers to data that indicates psychological states such as stress levels and happiness obtained from employees' facial expressions, voice, behavior, etc.

[0591] A "generative AI model" is an artificial intelligence model that analyzes collected data and performs advanced data processing such as recognizing patterns and providing insights.

[0592] The "analyzing means" is a processing device or software that uses the collected data to evaluate and analyze workload, emotional state, and the like.

[0593] The "means for identifying imbalances" is an algorithm or device for identifying imbalances or imbalances in workload or emotional states based on the analysis results.

[0594] An "alert mechanism" is a communications device or software that notifies relevant parties when an imbalance is detected.

[0595] "Means for proposing business improvement measures" refers to a processing device or software that proposes improvement measures such as adjusting workloads or redistributing work based on the analysis results of the generative AI model.

[0596] "Means for monitoring proposed improvement measures" refers to devices or software for continuously evaluating the implementation status and effects of proposed business improvement measures.

[0597] "Means for reporting analysis results and improvement effects at regular intervals" refers to a device or software that periodically generates reports on the analysis results and the effects of implementing business improvement measures, and provides them to those involved.

[0598] "Server" means a central processing unit for collecting data, analyzing, identifying imbalances, issuing alerts, recommending business improvements, monitoring, and generating reports.

[0599] "Terminal" means a device used by an employee to input and collect work data and emotion data.

[0600] This invention is a system that collects and analyzes work data and employee emotional data, identifies imbalances in workload and emotional states, and proposes and implements improvement measures. This system operates in cooperation with a server, terminals, and an emotion engine.

[0601] Collection of work data

[0602] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00." Break times and work details are also recorded at the same time.

[0603] Collection and analysis of work data

[0604] The server periodically collects work data from each device. For example, the server processes data on clock-in, clock-out, and breaks from each device every hour. The server then sends the collected work data to the generative AI model. The generative AI model then analyzes the data using the following prompt:

[0605] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[0606] A generative AI model analyzes the data it receives, calculates each employee's total working hours and overtime hours, and identifies imbalances.

[0607] Emotion data collection and analysis

[0608] The emotion engine collects the user's emotion data. While Employee A is working in front of the terminal, the terminal's camera analyzes facial expressions and the microphone collects emotion data from voice. The server collects the emotion data and sends it to the generative AI model. The generative AI model analyzes the emotion data using the following prompt sentence:

[0609] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[0610] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[0611] Identifying and alerting on imbalances

[0612] The server integrates the results of analyzing work data and emotional data to detect imbalances. For example, if the server detects that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an email alert to management.

[0613] Proposing business improvement measures and monitoring their implementation

[0614] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotion data. For example, the generative AI model recommends "redistribution of work," and the server notifies the manager of the proposal. The user (manager) then implements the proposed improvement measures. For example, the manager holds a meeting and decides to distribute employee A's work to other members.

[0615] Monitoring the effectiveness of improvements

[0616] The server continues to monitor work data and emotion data even after the implementation of improvement measures and evaluates their effectiveness. For example, even after redistribution, the server checks the work data and emotion data of employee A and evaluates whether overtime hours have been reduced and stress has been alleviated.

[0617] Generate and send reports

[0618] The server automatically generates a report of the analysis results and improvement effects at regular intervals and sends it to the relevant parties. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management.

[0619] Real-time management of overtime and emotion data

[0620] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The terminal displays a real-time graph of employee A's weekly overtime hours and emotion data trends on the management panel, making it easy for managers to check. This system enables the integrated analysis of employee work data and emotion data, making it possible to create a comfortable working environment and reduce the workload of managing overtime.

[0621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] The terminal records the employee's arrival time. The input is the employee's ID card information, which is stamped when they arrive at work. Specifically, when an employee holds their ID card over the terminal, the data "Arrival time: 9:00" is generated. This data is temporarily stored in the terminal.

[0624] Step 2:

[0625] The terminal records the employee's time of leaving work. The input is again the employee's ID card information, which is punched in when they leave work. Specifically, when an employee swipes their ID card at the desk to leave work, the data "Leave work time: 18:00" is generated. This data is also temporarily stored in the terminal.

[0626] Step 3:

[0627] The server periodically collects work data from each terminal. The input is the work data sent from each terminal, and the output is the work data consolidated in the server. For example, the server runs a collection script every hour to obtain data on arrival, departure, and breaks from each terminal.

[0628] Step 4:

[0629] The server sends the collected work data to the generative AI model. The input is the work data integrated by the server, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[0630] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[0631] The generative AI model analyzes work data, calculates total hours worked and overtime, and identifies imbalances.

[0632] Step 5:

[0633] The emotion engine collects the user's emotional data. The input is real-time facial and voice data obtained from the device's camera and microphone, and the output is the analysis results by the emotion engine. For example, while an employee is working in front of a device, the camera analyzes their facial expressions and the microphone collects their voice.

[0634] Step 6:

[0635] The server collects emotion data from the emotion engine and sends it to the generative AI model. The input is the emotion data obtained from the emotion engine, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[0636] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[0637] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[0638] Step 7:

[0639] The server integrates the results of work data and emotion data analysis to detect imbalances. The input is the analysis results of work data and emotion data obtained from the generative AI model, and the output is an alert indicating imbalances. For example, if the server finds that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an alert to management by email.

[0640] Step 8:

[0641] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotional data. The input is the analyzed work data and emotional data, and the output is a proposal for improvement measures. Specifically, the generative AI model recommends "work redistribution," and the server notifies the proposal to managers.

[0642] Step 9:

[0643] The user (manager) implements the proposed improvement measures. The input is the improvement proposal from the generative AI model, and the output is the work redistribution results after implementation. For example, the manager holds a meeting to allocate Employee A's work to other members.

[0644] Step 10:

[0645] The server continues to monitor work data and emotion data even after the implementation of improvement measures, and evaluates their effectiveness. The input is the collected work data and emotion data again, and the output is an evaluation of the effectiveness of the improvement. For example, even after redistribution, the server checks the work data and emotion data of employee A, and evaluates whether overtime hours have been reduced and stress has been alleviated.

[0646] Step 11:

[0647] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to the relevant parties. The input is the analysis results and improvement effect data, and the output is the generated report. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management by email.

[0648] Step 12:

[0649] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The input is the latest data from the generative AI model and emotion engine, and the output is the data for each employee displayed on the management panel. The terminal displays a weekly graph of employee A's overtime hours and emotion data trends on the management panel in real time, making it easy for managers to check.

[0650] (Application example 2)

[0651] 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."

[0652] In factory work environments, workload imbalances between employees and robots can occur, resulting in reduced production efficiency and increased employee stress. Identifying workload imbalances and proposing improvements requires a significant amount of time and effort. Even if improvements are proposed, there is a lack of efficient means for monitoring the effectiveness of their implementation. A solution to these issues is needed.

[0653] The identification processing by the identification 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 work data and emotional data, means for analyzing the collected work data and emotional data, and means for identifying imbalances in work load and emotional state based on the analysis results. This makes it possible to automatically propose improvements and improve implementation efficiency in order to maintain an appropriate balance between workload and emotional state.

[0654] "Work data" refers to information about the working habits of employees and machines, such as their arrival and departure times, work content, and break times.

[0655] "Emotional data" refers to information about the psychological state and emotions of employees and workers obtained by analyzing their facial expressions, voice, physical movements, etc.

[0656] A "collection means" is a device or system that has the function of acquiring data using an input device such as a sensor, camera, or microphone.

[0657] The "analysis method" is a process that uses algorithms and machine learning models to evaluate working patterns and emotional states based on collected data and detect imbalances and anomalies.

[0658] The "means for identifying" is a device or system that has the function of identifying and clearly indicating imbalances in workload or emotional state from the analysis results.

[0659] An "alert means" is a device or system that has the capability to notify administrators and other relevant parties of relevant information when an imbalance is identified.

[0660] The "means for making recommendations" refers to a device or system that has the function of automatically generating and proposing appropriate business improvement measures and shift readjustment measures based on the analysis results.

[0661] "Monitoring means" refers to a device or system that has the function of continuously monitoring and evaluating how effectively a proposed business improvement measure or shift readjustment measure is functioning after it has been implemented.

[0662] "Reporting means" refers to a device or system that has the function of creating and distributing reports on the analysis results and the effects of improvements based on data collected and analyzed at regular intervals.

[0663] "Imbalance" refers to a situation in which workload and emotional state are not equal, i.e., the existence of problems such as excessive workload or high stress.

[0664] "Business improvement measures" are specific action plans and measures to resolve problems identified through the analysis results and to improve business efficiency and the working environment.

[0665] The system that realizes this invention has a means for collecting and analyzing work data and emotional data from employees and machines, identifying imbalances in workload and emotional states, and proposing measures to improve them. The specific configuration and operation of this system are described below.

[0666] Data collection methods

[0667] The server has a means for collecting work data and emotional data. Work data is automatically collected from sensors and terminals and includes employees' arrival and departure times, work tasks, break times, etc. Emotional data is acquired using cameras and microphones through facial recognition and voice analysis.

[0668] Data Analysis Methods

[0669] The collected work data and emotional data are analyzed by a server. A generative AI model using TensorFlow is used for the analysis, and data processing is performed to identify imbalances. Specifically, the data is preprocessed (missing value correction and normalization), and then the AI ​​model is used to evaluate workload and emotional state.

[0670] Imbalance identification means

[0671] The server has a means for identifying imbalances in work and emotional states based on the analysis results. For example, if the total working hours, overtime hours, or stress level of employee A are high, these are identified as imbalances.

[0672] Alert method

[0673] If an imbalance is identified, the server has the means to raise an alert, specifically by sending an email notification to the relevant administrator or stakeholders.

[0674] Business improvement proposal methods

[0675] The server has a means to propose work improvement measures and shift reallocation measures based on the analysis results. The proposed contents are automatically sent to the manager, who will suggest work reallocation and shift review.

[0676] Implementation monitoring measures

[0677] Even after the proposed work improvement measures and shift reallocation measures are implemented, the server has a means for continuously monitoring the work data and emotion data, thereby evaluating the effectiveness of the implemented improvement measures.

[0678] Report Generation Method

[0679] The server has a means to periodically report the analysis results and improvement effects, and the generated reports are automatically sent to the relevant parties.

[0680] Hardware and software used

[0681] Sensor: Device for measuring operating time

[0682] Camera and microphone: a device for collecting emotional data

[0683] TensorFlow: for analyzing generative AI models

[0684] EmotionEngine: for emotional data analysis

[0685] smtplib: for email notifications

[0686] Prompt Sentence Examples

[0687] Example of sending work data: "Employee A's work data for May"

[0688] Example of sending emotional data: "Employee A's emotional data"

[0689] This enables automated improvement suggestions and implementation efficiencies to properly balance workload and emotional states in factories and other large workplaces.

[0690] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0691] Step 1:

[0692] The server collects work data and emotional data. Specifically, the terminal records the arrival and departure times, break times, and work details of employees and machines, and acquires emotional data from sensors, cameras, and microphones. This data is sent from the terminal to the server. The input is the operating status and emotional state of each employee and machine, and the output is the collected data.

[0693] Step 2:

[0694] The server preprocesses the collected work data and emotion data, imputing missing values ​​and normalizing the data. Specifically, missing values ​​for each data point are imputed with zeros and all data is standardized. The input is the data collected in step 1, and the output is the preprocessed data.

[0695] Step 3:

[0696] The server analyzes the preprocessed data. Using TensorFlow, the preprocessed data is fed into a generative AI model to identify imbalances in workload and emotional states. Specifically, the model detects excessive working hours and high stress levels. The input is the preprocessed data, and the output is an analysis showing the imbalances.

[0697] Step 4:

[0698] The server notifies the administrator of imbalances based on the analysis results. Specifically, it uses the smtplib library to send alerts by email. The notifications describe excessive workloads and stress levels of employees and machines. The input is the analysis results, and the output is the sent alert email.

[0699] Step 5:

[0700] The server recommends business improvement measures and shift reallocation measures based on the analysis results. It uses a generative AI model to calculate the optimal reallocation and generate recommendations. The recommendations are automatically sent to the administrator. The inputs are the analysis results and performance data, and the output is the recommendations.

[0701] Step 6:

[0702] The user (manager) implements the proposed business improvement measures and shift reallocation measures. Specifically, team meetings and shift adjustments are held, and the proposed improvement measures are implemented. The input is the proposal, and the output is the implemented improvement measures.

[0703] Step 7:

[0704] The server continues to monitor work data and emotion data even after the proposed improvement measures are implemented. It again collects and analyzes data from sensors, cameras, and microphones. This allows the effectiveness of the improvement measures to be evaluated. The input is the updated work data and emotion data, and the output is the reevaluation results.

[0705] Step 8:

[0706] The server periodically compiles the analysis results and improvement effects into a report. The report is automatically generated and distributed to relevant parties. The input is the data and analysis results obtained at each step, and the output is data in report format.

[0707] 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.

[0708] 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.

[0709] 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.

[0710] [Third embodiment]

[0711] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0712] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0713] 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).

[0714] 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.

[0715] 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.

[0716] 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).

[0717] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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.

[0722] 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."

[0723] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[0724] Collection and analysis of work data

[0725] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[0726] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be sent to the server periodically. The server then sends the collected work data to the generation AI.

[0727] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates the total working hours and overtime hours for this month from the data of employee A and detects that the overtime hours exceed 80 hours.

[0728] Identifying and alerting on imbalances

[0729] The server receives the analysis results of the generative AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours.

[0730] Proposing business improvement measures and monitoring their implementation

[0731] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[0732] The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work among team members.

[0733] The server continues to monitor work data even after improvements are implemented and evaluates the effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased.

[0734] Generate and send reports

[0735] The server automatically generates a report of the analysis results and the improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of improvements made to Employee A's work is created.

[0736] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[0737] Streamlining overtime management

[0738] The server manages overtime data in real time in cooperation with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date.

[0739] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a graph of employee A's weekly overtime hours on the management panel, making it easy for managers to check.

[0740] This system will make the workload of employees fairer, reduce the amount of time required to manage overtime, and is expected to increase the number of employees who wish to become managers.

[0741] The processing flow will be explained below.

[0742] Step 1:

[0743] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0744] Step 2:

[0745] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[0746] Step 3:

[0747] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI.

[0748] Step 4:

[0749] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. The generation AI aggregates "total monthly working hours," "overtime hours," and "break times" from employee A's data and identifies excessive overtime.

[0750] Step 5:

[0751] The server receives the analysis results of the generated AI and detects workload imbalances. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours."

[0752] Step 6:

[0753] The generative AI performs additional data analysis to propose measures to improve workloads. Specifically, it proposes measures such as redistributing work and reviewing shifts. For example, the generative AI might recommend "reviewing the division of work."

[0754] Step 7:

[0755] The server notifies the relevant parties of the generated AI's recommendations. For example, the server may notify employee A's team leader of the "redistribution of work proposals" by email.

[0756] Step 8:

[0757] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0758] Step 9:

[0759] The server continues to monitor the work data even after the implementation of the proposed improvement measures and evaluates the effectiveness of the improvements. For example, the server collects the work data of employee A even after the redistribution to confirm the reduction in overtime hours.

[0760] Step 10:

[0761] The server periodically generates a report on the analysis results and the effects of the improvements. For example, at the end of the month, a report is created summarizing the changes in working hours and overtime hours of employee A before and after the improvements.

[0762] Step 11:

[0763] The server provides the generated report to the relevant parties. For example, the server may email the report in PDF format to a team leader or manager.

[0764] Step 12:

[0765] The server manages overtime data in real time by linking with the AI ​​generator. For example, the AI ​​generator updates its analysis results every day and reflects the latest data on the management panel.

[0766] Step 13:

[0767] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph showing the weekly trend of employee A's overtime hours, making it easy for managers to check.

[0768] Example 1

[0769] 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."

[0770] Conventional work data management systems have had difficulty in detecting imbalances in employee workloads and overwork, and proposing and implementing improvement measures. As a result, improvements to employees' working environments have been delayed, leading to problems such as lower labor productivity and motivation. The purpose of this invention is to solve these problems and efficiently manage and improve workloads.

[0771] 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.

[0772] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for analyzing the work data with a generative AI model and proposing measures to improve workloads, means for notifying relevant parties when an imbalance is identified, means for users to implement the proposed work improvement measures, and means for continuously monitoring the effectiveness of the work improvement measures. This makes it possible to efficiently and fairly manage employee workloads and quickly implement appropriate improvement measures.

[0773] "Work data" refers to information about an employee's work, such as the employee's arrival time, departure time, break time, and job duties.

[0774] "Means of collection" refers to the hardware or software that employees use to record information about their work and transmit that data to a server.

[0775] "Means of analysis" refers to the method of using software to analyze collected work data and calculate indicators such as workload and overtime hours.

[0776] "Means for identifying imbalances" refers to the process of detecting imbalances or abnormalities in workload among employees based on analyzed work data.

[0777] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate results or recommendations tailored to a specific purpose.

[0778] "Means for proposing measures to improve workload" refers to a method in which the generative AI model derives specific improvement proposals, such as redistributing work or reviewing shifts, based on the analysis results.

[0779] "Means of notifying stakeholders" refers to the method of communicating identified imbalances and proposed remedial measures to stakeholders via email or notification systems.

[0780] "User implementation measures" refers to the process by which managers and team leaders actually apply the proposed improvements in their work environment.

[0781] "Monitoring measures" refers to methods for continuously monitoring and evaluating the effectiveness of proposed improvements after they have been implemented.

[0782] "Means of reporting" refers to the process of automatically generating reports that periodically summarize the analysis results and improvement effects and sending them to relevant parties.

[0783] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[0784] Collection and analysis of work data

[0785] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. The terminals used are attendance management devices with touch panels or card readers so that employees can easily operate them. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[0786] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be periodically sent to the server. The server is equipped with a high-performance database and communication interface, allowing for real-time data collection. The server then sends the collected work data to the generative AI model.

[0787] The generative AI model analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generative AI aggregates the total working hours and overtime hours for this month from Employee A's data and detects that the overtime hours exceed 80 hours. Machine learning algorithms are used in the analysis to recognize patterns and detect anomalies.

[0788] Identifying and alerting on imbalances

[0789] The server receives the analysis results of the generative AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server detects that employee A's overtime hours exceed 80 hours and notifies management by email. A template engine is used for the notification, and an automatically generated email body is sent.

[0790] Proposing business improvement measures and monitoring their implementation

[0791] The generative AI model continues its analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generative AI. For example, if the generative AI recommends "redistributing work," the server sends the recommendation to employee A's team leader. The notification is distributed via email or the internal messaging system.

[0792] The user (management) implements the proposed improvement measures. Specifically, the team leader holds a meeting to redistribute work among team members. For example, employee A's work is assigned to another member. The implementation status of the improvement measures is recorded using a task management tool.

[0793] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased. Statistical analysis software is used for the evaluation and effectiveness is measured.

[0794] Generate and send reports

[0795] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements on employee A is created. The generated report includes graphs and charts to visualize the effects.

[0796] The generated reports are automatically sent to the relevant parties. For example, the server emails the report in PDF format to management. An automation tool is used to send the emails, ensuring regular reporting.

[0797] Streamlining overtime management

[0798] The server manages overtime data in real time in cooperation with the generative AI model. For example, the server updates the analysis results of the generative AI model every day to keep the data up to date.

[0799] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check. The management panel is web-based and can be accessed from anywhere.

[0800] This will make it possible to distribute the workload of employees fairly and reduce the amount of time spent managing overtime. It is also expected that the number of employees desired by managers will increase.

[0801] Prompt Sentence Examples

[0802] To provide a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[0803] "Please enter Employee A's work data and analyze the total hours worked and overtime for this month. In addition, please check whether any employees are working too much and recommend appropriate work improvement measures."

[0804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0805] Step 1: Collect work data

[0806] The terminal receives input from employees (start time, end time, break time, work content) and records the work data. For example, if employee A starts work at 9:00 and leaves work at 18:00, the start and end times are recorded on the terminal. The output is the recorded work data, which is the information to be sent to the server.

[0807] Step 2: Send data to the server

[0808] The server receives work data collected from each terminal at regular intervals. For example, every hour the server retrieves the latest work data from the terminal and stores it in a database. The input is work data from the terminal, and the output is data stored in the database in the server. Specifically, the server receives and stores the attendance data of employee A at 9:00 at 10:00.

[0809] Step 3: Data analysis with generative AI

[0810] The server sends the collected work data to the generative AI model. The generative AI model analyzes the input work data and identifies each employee's total working hours, overtime hours, and imbalances. For example, calculate employee A's total working hours and overtime hours for this month and check whether they exceed 80 hours. The input is work data from the server, and the output is the analysis result of the generative AI model.

[0811] Step 4: Imbalance detection and alerting

[0812] The server receives the analysis results from the generation AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. Specifically, the server detects that employee A's overtime hours exceed 80 hours and sends an email notification to management. The input is the analysis results from the generation AI, and the output is an alert notification to the relevant parties.

[0813] Step 5: Proposing business improvement measures

[0814] The generative AI model proposes measures to improve workloads based on the analysis results. The server notifies the relevant parties of the improvement measures received from the generative AI. Specifically, the generative AI model proposes "redistribution of work," and the server sends this proposal to employee A's team leader. The input is the improvement proposal from the generative AI, and the output is a notification to the relevant parties.

[0815] Step 6: Implement and monitor improvements

[0816] The user (management) implements the proposed improvement measures. For example, a team leader holds a meeting to redistribute work. The server then continuously monitors the work data and evaluates the effectiveness of the improvement measures. The input is the implementation status of work redistribution by the management, and the output is the measured results of the improvement measures. Specifically, the server analyzes employee A's work data after redistribution and evaluates the effectiveness.

[0817] Step 7: Generate and send the report

[0818] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to relevant parties. For example, at the end of the month, the server creates a report summarizing the effects of work improvements on employee A and sends it to management by email. The input is the analysis data from the generation AI and the server, and the output is an automatically generated report.

[0819] Step 8: Improve overtime management efficiency

[0820] The server manages overtime data in real time by working in conjunction with the generated AI model. The terminal displays the latest data and predictions in real time on the management panel. For example, the server updates the analysis results of the generated AI model every day and displays a "weekly trend graph of employee A's overtime hours" on the terminal. The input is real-time data from the generated AI, and the output is the content displayed on the management panel.

[0821] (Application example 1)

[0822] 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."

[0823] At logistics centers, imbalances in employee workloads often occur, resulting in problems such as overwork and reduced production efficiency. Conventional systems make it difficult to detect workload imbalances in real time and quickly implement countermeasures. Furthermore, it is difficult to propose appropriate work improvement measures, and there is a lack of effective means for monitoring the implementation status of these measures. This leads to problems such as inappropriate work style measures not being implemented, resulting in a significant drop in productivity.

[0824] 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.

[0825] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for issuing an alert when an imbalance is identified, means for proposing work improvement measures based on the analysis results, means for monitoring the implementation of the proposed work improvement measures, means for periodically reporting the analysis results and the effects of the improvements, means for providing real-time alerts and improvement measures to employees via a smart device, means for managing the work status at the logistics center in real time and detecting workload imbalances, means for displaying the detected imbalance on the smart device, and means for displaying improvement suggestions on the smart device. This makes it possible to identify workload imbalances at the logistics center in real time and quickly propose and implement appropriate improvement measures.

[0826] "Work data" refers to work-related information such as employees' arrival and departure times, break times, and job duties.

[0827] "Analysis" is the process of analyzing collected work data to detect specific patterns or imbalances.

[0828] "Imbalance" refers to an unequal situation in terms of workload, working hours, etc., and means that certain employees are placed under an excessive burden.

[0829] An "alert" is a means of sending warnings or notifications to relevant parties when an imbalance occurs.

[0830] "Business improvement measures" are recommendations and procedures for balancing workloads and improving efficiency.

[0831] "Monitoring" is the process of overseeing the implementation of business improvement measures and evaluating their effectiveness.

[0832] A "report" is a document that summarizes the analysis results and improvement effects for a certain period of time.

[0833] "Smart devices" are electronic devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[0834] A "logistics center" is a facility that stores, organizes, and distributes goods and materials.

[0835] "Real-time" refers to the ability to collect, analyze, and notify data almost simultaneously.

[0836] "Improvement proposals" are specific methods or means proposed by the generative AI model to improve work efficiency or reduce workload.

[0837] A "generative AI model" is a system that uses artificial intelligence to analyze data and generate patterns and suggestions.

[0838] The present invention is a system that detects imbalances in the workloads of employees at a logistics center in real time and promptly proposes appropriate remedial measures. This system operates in cooperation with a server, terminals, and users.

[0839] Collection and analysis of work data

[0840] The terminal records attendance data when an employee arrives at work, and clocks out when they leave. Break times and work content are also recorded in the same way. For example, employee A clocks in on his terminal when he arrives at work, and "9:00" is recorded as his arrival time. The server collects the latest work data from each terminal at regular intervals. For example, if the server collects work data every hour, employee A's arrival, clock out, and break data are periodically sent to the server. The server then sends the collected work data to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generation AI tallys up the total working hours and overtime hours for this month from employee A's data and detects that overtime hours exceed 80 hours.

[0841] Identifying and alerting on imbalances

[0842] The server receives the analysis results of the generation AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours. It may also display a real-time alert to employees wearing smart glasses.

[0843] Proposing business improvement measures and monitoring their implementation

[0844] The generation AI continues its analysis and proposes measures to improve the workload. Specifically, it proposes improvements such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures it receives from the generation AI. For example, the generation AI recommends "redistributing work," and the server sends the proposal to employee A's team leader. The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work with team members. The server continues to monitor work data even after the improvement is implemented and evaluates its effectiveness. For example, the server checks employee A's work data after the work has been redistributed, and evaluates whether overtime has decreased.

[0845] Generate and send reports

[0846] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements made to employee A is created. The generated report is automatically sent to the relevant parties. For example, the server may email a PDF report to a manager.

[0847] Streamlining overtime management

[0848] The server manages overtime data in real time by working with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date. The terminal displays the latest data and predictions on the management panel in real time. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check.

[0849] Examples of concrete examples and prompts

[0850] For example, if a logistics center employee is working more than eight hours a day, an imbalance will be detected and an alert will be displayed on the smart glasses. An example of a prompt sentence for the generative AI model is as follows:

[0851] Prompt Sentence Examples

[0852] Based on current employee work data, analyze workload imbalances, issue alerts if any, and suggest appropriate remedial measures.

[0853] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0854] Step 1:

[0855] The terminal records attendance data when an employee arrives at work, and records attendance data when the employee leaves work. Break times and work details are also recorded in the same way. Inputs include employee time-stamping information (times of arrival and departure) and selected work details. This allows employee work data to be collected in real time. The output is sent to the server as work data.

[0856] Step 2:

[0857] The server collects the latest work data from each device at regular intervals. The input is work data from the device. The server collects this data in a fixed format and stores it in a database. This allows the server to centrally manage employee work status. The output is the organized work data sent to the generation AI.

[0858] Step 3:

[0859] The server sends work data to the generation AI for analysis. The input is work data collected and organized by the server. The generation AI analyzes this data and identifies each employee's workload, imbalances, and overtime hours. The output is the analysis results, which are sent back to the server.

[0860] Step 4:

[0861] The server receives the analysis results from the generation AI and detects workload imbalances and anomalies. The input is the analysis results returned by the generation AI. The server checks the analysis results and issues an alert if an imbalance is detected. The output is alert information, which is sent to relevant parties and smart devices.

[0862] Step 5:

[0863] The server notifies the relevant parties of the improvement measures received from the generation AI. The input is the business improvement measures proposed by the generation AI. The server analyzes the contents of the proposal and notifies the appropriate relevant parties (e.g., team leader). The output is a notification of the business improvement proposal.

[0864] Step 6:

[0865] The user (management) implements the proposed improvement measures. The input is the business improvement proposal notified by the server. The user takes specific action (for example, redistributing work or reviewing shifts) based on the improvement measures. The output is the results of implementing the improvement measures.

[0866] Step 7:

[0867] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. The input is new work data and the results of the improvements. The server analyzes the data and evaluates the effectiveness of the improvements. The output is an evaluation report.

[0868] Step 8:

[0869] The server automatically generates reports of analysis results and improvement effects at regular intervals. The input is the accumulated analysis results and improvement effect data. The server automatically generates reports and sends them to the relevant parties. The output is a PDF report.

[0870] Step 9:

[0871] The terminal displays the latest data and forecasts on the management panel in real time. The input is the latest data and forecast information sent from the server. The terminal displays this as graphs and charts so that the administrator can easily check it. The output is the visualization on the management panel.

[0872] In this way, it becomes possible to identify workload imbalances in logistics centers in real time and quickly propose and implement appropriate improvement measures.

[0873] 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.

[0874] This system collects and analyzes work data and user emotion data, identifies workload imbalances, and automatically proposes and implements appropriate remedial measures. This system operates in cooperation with the server, terminals, emotion engine, and users.

[0875] Collection and analysis of work data

[0876] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0877] The server periodically collects work data from each device. For example, a schedule can be set up so that the server collects work data from each device every hour. This allows employee A's arrival, departure, and break data to be collected on the server.

[0878] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. The generation AI tallys up the total working hours and overtime hours for this month from Employee A's data and identifies excessive overtime.

[0879] Emotion data collection and analysis

[0880] The emotion engine collects and analyzes the user's emotions. For example, the camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to collect emotion data. Emotion data includes information such as stress level and happiness level.

[0881] The server periodically collects emotional data from the emotion engine. For example, the server obtains employee A's emotional data every day. The emotion engine analyzes the collected emotional data and evaluates the employee's emotional state. The generative AI performs a comprehensive analysis combining the work data and emotional data to detect imbalances in workload and stress levels.

[0882] Identifying and alerting on imbalances

[0883] The server receives the analysis results of the generated AI and detects imbalances in workload or emotional states. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours and his emotional data indicates high stress."

[0884] Proposing business improvement measures and monitoring their implementation

[0885] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[0886] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0887] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[0888] Generate and send reports

[0889] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, it creates a report summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[0890] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[0891] Improved efficiency of overtime management and emotion monitoring

[0892] The server manages overtime data and emotion data in real time by linking with the generation AI and emotion engine. For example, it updates the analysis results of the generation AI and emotion engine every day and reflects the latest data on the management panel.

[0893] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[0894] This system will help to distribute the workload of employees fairly and monitor their emotional state, creating a comfortable working environment and reducing the amount of work required to manage overtime, which is expected to increase the number of employees who wish to become managers.

[0895] The processing flow will be explained below.

[0896] Step 1:

[0897] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[0898] Step 2:

[0899] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[0900] Step 3:

[0901] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for one month" to the generation AI.

[0902] Step 4:

[0903] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates "total monthly working hours," "overtime hours," "break times," etc. from employee A's data and identifies excessive overtime.

[0904] Step 5:

[0905] The emotion engine collects and analyzes the user's emotions. The camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to obtain emotion data. For example, the emotion engine measures Employee A's stress level and happiness.

[0906] Step 6:

[0907] The server collects emotion data from the emotion engine and sends it to the generation AI along with work data. For example, the server sends employee A's emotion data to the generation AI every day.

[0908] Step 7:

[0909] The generative AI integrates and analyzes work data and emotional data to detect imbalances in workload and emotional states. For example, the generative AI detects a high stress state from employee A's emotional data and correlates it with an imbalance in workload.

[0910] Step 8:

[0911] The server receives the analysis results of the generating AI and sends an alert to relevant parties if an imbalance is identified. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours, and his emotional data indicates high stress."

[0912] Step 9:

[0913] The Generative AI performs additional analysis to recommend measures to improve workloads. Recommendations include redistributing work and reviewing shifts. For example, the Generative AI might recommend "redistributing Employee A's work to other members."

[0914] Step 10:

[0915] The server notifies the relevant parties of the improvement measures received from the generation AI. For example, the server sends an email to the team leader with a "work reallocation proposal."

[0916] Step 11:

[0917] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[0918] Step 12:

[0919] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[0920] Step 13:

[0921] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, a report is created summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[0922] Step 14:

[0923] The server automatically sends the generated report to the relevant parties. For example, the server may email the report in PDF format to a manager.

[0924] Step 15:

[0925] The server manages real-time overtime data and emotion data in cooperation with the generation AI and emotion engine. For example, the analysis results of the generation AI and emotion engine are updated daily, and the latest data is reflected in the management panel.

[0926] Step 16:

[0927] The device displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[0928] Example 2

[0929] 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."

[0930] In today's work environment, it is difficult to accurately collect and analyze employee work data and emotional data to identify imbalances in workload and emotional state. When employees experience excessive stress or have uneven workloads, it is necessary to identify the issue early and propose and implement appropriate improvement measures. However, conventional systems do not adequately analyze work data and emotional data comprehensively, making it difficult to propose efficient work improvement measures and monitor their effectiveness.

[0931] 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.

[0932] In this invention, the server includes means for collecting work data, means for collecting emotion data, means for analyzing using a generative AI model, means for identifying imbalances, means for issuing alerts, means for proposing business improvement measures, means for monitoring the implementation of the proposed business improvement measures, and means for reporting the analysis results and improvement effects at regular intervals. This enables integrated and real-time analysis of employee work data and emotion data, early identification of imbalances in workload or emotional states, and the proposing and implementation of appropriate improvement measures.

[0933] "Work data" refers to data related to working hours and work conditions, such as an employee's arrival time, departure time, break time, and job content.

[0934] "Emotional data" refers to data that indicates psychological states such as stress levels and happiness obtained from employees' facial expressions, voice, behavior, etc.

[0935] A "generative AI model" is an artificial intelligence model that analyzes collected data and performs advanced data processing such as recognizing patterns and providing insights.

[0936] The "analyzing means" is a processing device or software that uses the collected data to evaluate and analyze workload, emotional state, and the like.

[0937] The "means for identifying imbalances" is an algorithm or device for identifying imbalances or imbalances in workload or emotional states based on the analysis results.

[0938] An "alert mechanism" is a communications device or software that notifies relevant parties when an imbalance is detected.

[0939] "Means for proposing business improvement measures" refers to a processing device or software that proposes improvement measures such as adjusting workloads or redistributing work based on the analysis results of the generative AI model.

[0940] "Means for monitoring proposed improvement measures" refers to devices or software for continuously evaluating the implementation status and effects of proposed business improvement measures.

[0941] "Means for reporting analysis results and improvement effects at regular intervals" refers to a device or software that periodically generates reports on the analysis results and the effects of implementing business improvement measures, and provides them to those involved.

[0942] "Server" means a central processing unit for collecting data, analyzing, identifying imbalances, issuing alerts, recommending business improvements, monitoring, and generating reports.

[0943] "Terminal" means a device used by an employee to input and collect work data and emotion data.

[0944] This invention is a system that collects and analyzes work data and employee emotional data, identifies imbalances in workload and emotional states, and proposes and implements improvement measures. This system operates in cooperation with a server, terminals, and an emotion engine.

[0945] Collection of work data

[0946] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00." Break times and work details are also recorded at the same time.

[0947] Collection and analysis of work data

[0948] The server periodically collects work data from each device. For example, the server processes data on clock-in, clock-out, and breaks from each device every hour. The server then sends the collected work data to the generative AI model. The generative AI model then analyzes the data using the following prompt:

[0949] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[0950] A generative AI model analyzes the data it receives, calculates each employee's total working hours and overtime hours, and identifies imbalances.

[0951] Emotion data collection and analysis

[0952] The emotion engine collects the user's emotion data. While Employee A is working in front of the terminal, the terminal's camera analyzes facial expressions and the microphone collects emotion data from voice. The server collects the emotion data and sends it to the generative AI model. The generative AI model analyzes the emotion data using the following prompt sentence:

[0953] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[0954] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[0955] Identifying and alerting on imbalances

[0956] The server integrates the results of analyzing work data and emotional data to detect imbalances. For example, if the server detects that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an email alert to management.

[0957] Proposing business improvement measures and monitoring their implementation

[0958] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotion data. For example, the generative AI model recommends "redistribution of work," and the server notifies the manager of the proposal. The user (manager) then implements the proposed improvement measures. For example, the manager holds a meeting and decides to distribute employee A's work to other members.

[0959] Monitoring the effectiveness of improvements

[0960] The server continues to monitor work data and emotion data even after the implementation of improvement measures and evaluates their effectiveness. For example, even after redistribution, the server checks the work data and emotion data of employee A and evaluates whether overtime hours have been reduced and stress has been alleviated.

[0961] Generate and send reports

[0962] The server automatically generates a report of the analysis results and improvement effects at regular intervals and sends it to the relevant parties. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management.

[0963] Real-time management of overtime and emotion data

[0964] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The terminal displays a real-time graph of employee A's weekly overtime hours and emotion data trends on the management panel, making it easy for managers to check. This system enables the integrated analysis of employee work data and emotion data, making it possible to create a comfortable working environment and reduce the workload of managing overtime.

[0965] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0966] Step 1:

[0967] The terminal records the employee's arrival time. The input is the employee's ID card information, which is stamped when they arrive at work. Specifically, when an employee holds their ID card over the terminal, the data "Arrival time: 9:00" is generated. This data is temporarily stored in the terminal.

[0968] Step 2:

[0969] The terminal records the employee's time of leaving work. The input is again the employee's ID card information, which is punched in when they leave work. Specifically, when an employee swipes their ID card at the desk to leave work, the data "Leave work time: 18:00" is generated. This data is also temporarily stored in the terminal.

[0970] Step 3:

[0971] The server periodically collects work data from each terminal. The input is the work data sent from each terminal, and the output is the work data consolidated in the server. For example, the server runs a collection script every hour to obtain data on arrival, departure, and breaks from each terminal.

[0972] Step 4:

[0973] The server sends the collected work data to the generative AI model. The input is the work data integrated by the server, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[0974] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[0975] The generative AI model analyzes work data, calculates total hours worked and overtime, and identifies imbalances.

[0976] Step 5:

[0977] The emotion engine collects the user's emotional data. The input is real-time facial and voice data obtained from the device's camera and microphone, and the output is the analysis results by the emotion engine. For example, while an employee is working in front of a device, the camera analyzes their facial expressions and the microphone collects their voice.

[0978] Step 6:

[0979] The server collects emotion data from the emotion engine and sends it to the generative AI model. The input is the emotion data obtained from the emotion engine, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[0980] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[0981] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[0982] Step 7:

[0983] The server integrates the results of work data and emotion data analysis to detect imbalances. The input is the analysis results of work data and emotion data obtained from the generative AI model, and the output is an alert indicating imbalances. For example, if the server finds that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an alert to management by email.

[0984] Step 8:

[0985] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotional data. The input is the analyzed work data and emotional data, and the output is a proposal for improvement measures. Specifically, the generative AI model recommends "work redistribution," and the server notifies the proposal to managers.

[0986] Step 9:

[0987] The user (manager) implements the proposed improvement measures. The input is the improvement proposal from the generative AI model, and the output is the work redistribution results after implementation. For example, the manager holds a meeting to allocate Employee A's work to other members.

[0988] Step 10:

[0989] The server continues to monitor work data and emotion data even after the implementation of improvement measures, and evaluates their effectiveness. The input is the collected work data and emotion data again, and the output is an evaluation of the effectiveness of the improvement. For example, even after redistribution, the server checks the work data and emotion data of employee A, and evaluates whether overtime hours have been reduced and stress has been alleviated.

[0990] Step 11:

[0991] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to the relevant parties. The input is the analysis results and improvement effect data, and the output is the generated report. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management by email.

[0992] Step 12:

[0993] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The input is the latest data from the generative AI model and emotion engine, and the output is the data for each employee displayed on the management panel. The terminal displays a weekly graph of employee A's overtime hours and emotion data trends on the management panel in real time, making it easy for managers to check.

[0994] (Application example 2)

[0995] 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."

[0996] In factory work environments, workload imbalances between employees and robots can occur, resulting in reduced production efficiency and increased employee stress. Identifying workload imbalances and proposing improvements requires a significant amount of time and effort. Even if improvements are proposed, there is a lack of efficient means for monitoring the effectiveness of their implementation. A solution to these issues is needed.

[0997] The identification processing by the identification 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 work data and emotional data, means for analyzing the collected work data and emotional data, and means for identifying imbalances in work load and emotional state based on the analysis results. This makes it possible to automatically propose improvements and improve implementation efficiency in order to maintain an appropriate balance between workload and emotional state.

[0998] "Work data" refers to information about the working habits of employees and machines, such as their arrival and departure times, work content, and break times.

[0999] "Emotional data" refers to information about the psychological state and emotions of employees and workers obtained by analyzing their facial expressions, voice, physical movements, etc.

[1000] A "collection means" is a device or system that has the function of acquiring data using an input device such as a sensor, camera, or microphone.

[1001] The "analysis method" is a process that uses algorithms and machine learning models to evaluate working patterns and emotional states based on collected data and detect imbalances and anomalies.

[1002] The "means for identifying" is a device or system that has the function of identifying and clearly indicating imbalances in workload or emotional state from the analysis results.

[1003] An "alert means" is a device or system that has the capability to notify administrators and other relevant parties of relevant information when an imbalance is identified.

[1004] The "means for making recommendations" refers to a device or system that has the function of automatically generating and proposing appropriate business improvement measures and shift readjustment measures based on the analysis results.

[1005] "Monitoring means" refers to a device or system that has the function of continuously monitoring and evaluating how effectively a proposed business improvement measure or shift readjustment measure is functioning after it has been implemented.

[1006] "Reporting means" refers to a device or system that has the function of creating and distributing reports on the analysis results and the effects of improvements based on data collected and analyzed at regular intervals.

[1007] "Imbalance" refers to a situation in which workload and emotional state are not equal, i.e., the existence of problems such as excessive workload or high stress.

[1008] "Business improvement measures" are specific action plans and measures to resolve problems identified through the analysis results and to improve business efficiency and the working environment.

[1009] The system that realizes this invention has a means for collecting and analyzing work data and emotional data from employees and machines, identifying imbalances in workload and emotional states, and proposing measures to improve them. The specific configuration and operation of this system are described below.

[1010] Data collection methods

[1011] The server has a means for collecting work data and emotional data. Work data is automatically collected from sensors and terminals and includes employees' arrival and departure times, work tasks, break times, etc. Emotional data is acquired using cameras and microphones through facial recognition and voice analysis.

[1012] Data Analysis Methods

[1013] The collected work data and emotional data are analyzed by a server. A generative AI model using TensorFlow is used for the analysis, and data processing is performed to identify imbalances. Specifically, the data is preprocessed (missing value correction and normalization), and then the AI ​​model is used to evaluate workload and emotional state.

[1014] Imbalance identification means

[1015] The server has a means for identifying imbalances in work and emotional states based on the analysis results. For example, if the total working hours, overtime hours, or stress level of employee A are high, these are identified as imbalances.

[1016] Alert method

[1017] If an imbalance is identified, the server has the means to raise an alert, specifically by sending an email notification to the relevant administrator or stakeholders.

[1018] Business improvement proposal methods

[1019] The server has a means to propose work improvement measures and shift reallocation measures based on the analysis results. The proposed contents are automatically sent to the manager, who will suggest work reallocation and shift review.

[1020] Implementation monitoring measures

[1021] Even after the proposed work improvement measures and shift reallocation measures are implemented, the server has a means for continuously monitoring the work data and emotion data, thereby evaluating the effectiveness of the implemented improvement measures.

[1022] Report Generation Method

[1023] The server has a means to periodically report the analysis results and improvement effects, and the generated reports are automatically sent to the relevant parties.

[1024] Hardware and software used

[1025] Sensor: Device for measuring operating time

[1026] Camera and microphone: a device for collecting emotional data

[1027] TensorFlow: for analyzing generative AI models

[1028] EmotionEngine: for emotional data analysis

[1029] smtplib: for email notifications

[1030] Prompt Sentence Examples

[1031] Example of sending work data: "Employee A's work data for May"

[1032] Example of sending emotional data: "Employee A's emotional data"

[1033] This enables automated improvement suggestions and implementation efficiencies to properly balance workload and emotional states in factories and other large workplaces.

[1034] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1035] Step 1:

[1036] The server collects work data and emotional data. Specifically, the terminal records the arrival and departure times, break times, and work details of employees and machines, and acquires emotional data from sensors, cameras, and microphones. This data is sent from the terminal to the server. The input is the operating status and emotional state of each employee and machine, and the output is the collected data.

[1037] Step 2:

[1038] The server preprocesses the collected work data and emotion data, imputing missing values ​​and normalizing the data. Specifically, missing values ​​for each data point are imputed with zeros and all data is standardized. The input is the data collected in step 1, and the output is the preprocessed data.

[1039] Step 3:

[1040] The server analyzes the preprocessed data. Using TensorFlow, the preprocessed data is fed into a generative AI model to identify imbalances in workload and emotional states. Specifically, the model detects excessive working hours and high stress levels. The input is the preprocessed data, and the output is an analysis showing the imbalances.

[1041] Step 4:

[1042] The server notifies the administrator of imbalances based on the analysis results. Specifically, it uses the smtplib library to send alerts by email. The notifications describe excessive workloads and stress levels of employees and machines. The input is the analysis results, and the output is the sent alert email.

[1043] Step 5:

[1044] The server recommends business improvement measures and shift reallocation measures based on the analysis results. It uses a generative AI model to calculate the optimal reallocation and generate recommendations. The recommendations are automatically sent to the administrator. The inputs are the analysis results and performance data, and the output is the recommendations.

[1045] Step 6:

[1046] The user (manager) implements the proposed business improvement measures and shift reallocation measures. Specifically, team meetings and shift adjustments are held, and the proposed improvement measures are implemented. The input is the proposal, and the output is the implemented improvement measures.

[1047] Step 7:

[1048] The server continues to monitor work data and emotion data even after the proposed improvement measures are implemented. It again collects and analyzes data from sensors, cameras, and microphones. This allows the effectiveness of the improvement measures to be evaluated. The input is the updated work data and emotion data, and the output is the reevaluation results.

[1049] Step 8:

[1050] The server periodically compiles the analysis results and improvement effects into a report. The report is automatically generated and distributed to relevant parties. The input is the data and analysis results obtained at each step, and the output is data in report format.

[1051] 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.

[1052] 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.

[1053] 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.

[1054] [Fourth embodiment]

[1055] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1056] 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.

[1057] 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).

[1058] 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.

[1059] 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.

[1060] 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).

[1061] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] 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.

[1067] 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."

[1068] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[1069] Collection and analysis of work data

[1070] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[1071] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be sent to the server periodically. The server then sends the collected work data to the generation AI.

[1072] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates the total working hours and overtime hours for this month from the data of employee A and detects that the overtime hours exceed 80 hours.

[1073] Identifying and alerting on imbalances

[1074] The server receives the analysis results of the generative AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours.

[1075] Proposing business improvement measures and monitoring their implementation

[1076] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[1077] The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work among team members.

[1078] The server continues to monitor work data even after improvements are implemented and evaluates the effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased.

[1079] Generate and send reports

[1080] The server automatically generates a report of the analysis results and the improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of improvements made to Employee A's work is created.

[1081] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[1082] Streamlining overtime management

[1083] The server manages overtime data in real time in cooperation with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date.

[1084] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a graph of employee A's weekly overtime hours on the management panel, making it easy for managers to check.

[1085] This system will make the workload of employees fairer, reduce the amount of time required to manage overtime, and is expected to increase the number of employees who wish to become managers.

[1086] The processing flow will be explained below.

[1087] Step 1:

[1088] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[1089] Step 2:

[1090] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[1091] Step 3:

[1092] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI.

[1093] Step 4:

[1094] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. The generation AI aggregates "total monthly working hours," "overtime hours," and "break times" from employee A's data and identifies excessive overtime.

[1095] Step 5:

[1096] The server receives the analysis results of the generated AI and detects workload imbalances. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours."

[1097] Step 6:

[1098] The generative AI performs additional data analysis to propose measures to improve workloads. Specifically, it proposes measures such as redistributing work and reviewing shifts. For example, the generative AI might recommend "reviewing the division of work."

[1099] Step 7:

[1100] The server notifies the relevant parties of the generated AI's recommendations. For example, the server may notify employee A's team leader of the "redistribution of work proposals" by email.

[1101] Step 8:

[1102] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[1103] Step 9:

[1104] The server continues to monitor the work data even after the implementation of the proposed improvement measures and evaluates the effectiveness of the improvements. For example, the server collects the work data of employee A even after the redistribution to confirm the reduction in overtime hours.

[1105] Step 10:

[1106] The server periodically generates a report on the analysis results and the effects of the improvements. For example, at the end of the month, a report is created summarizing the changes in working hours and overtime hours of employee A before and after the improvements.

[1107] Step 11:

[1108] The server provides the generated report to the relevant parties. For example, the server may email the report in PDF format to a team leader or manager.

[1109] Step 12:

[1110] The server manages overtime data in real time by linking with the AI ​​generator. For example, the AI ​​generator updates its analysis results every day and reflects the latest data on the management panel.

[1111] Step 13:

[1112] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph showing the weekly trend of employee A's overtime hours, making it easy for managers to check.

[1113] Example 1

[1114] 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."

[1115] Conventional work data management systems have had difficulty in detecting imbalances in employee workloads and overwork, and proposing and implementing improvement measures. As a result, improvements to employees' working environments have been delayed, leading to problems such as lower labor productivity and motivation. The purpose of this invention is to solve these problems and efficiently manage and improve workloads.

[1116] 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.

[1117] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for analyzing the work data with a generative AI model and proposing measures to improve workloads, means for notifying relevant parties when an imbalance is identified, means for users to implement the proposed work improvement measures, and means for continuously monitoring the effectiveness of the work improvement measures. This makes it possible to efficiently and fairly manage employee workloads and quickly implement appropriate improvement measures.

[1118] "Work data" refers to information about an employee's work, such as the employee's arrival time, departure time, break time, and job duties.

[1119] "Means of collection" refers to the hardware or software that employees use to record information about their work and transmit that data to a server.

[1120] "Means of analysis" refers to the method of using software to analyze collected work data and calculate indicators such as workload and overtime hours.

[1121] "Means for identifying imbalances" refers to the process of detecting imbalances or abnormalities in workload among employees based on analyzed work data.

[1122] A "generative AI model" refers to an algorithm that uses artificial intelligence to analyze data and generate results or recommendations tailored to a specific purpose.

[1123] "Means for proposing measures to improve workload" refers to a method in which the generative AI model derives specific improvement proposals, such as redistributing work or reviewing shifts, based on the analysis results.

[1124] "Means of notifying stakeholders" refers to the method of communicating identified imbalances and proposed remedial measures to stakeholders via email or notification systems.

[1125] "User implementation measures" refers to the process by which managers and team leaders actually apply the proposed improvements in their work environment.

[1126] "Monitoring measures" refers to methods for continuously monitoring and evaluating the effectiveness of proposed improvements after they have been implemented.

[1127] "Means of reporting" refers to the process of automatically generating reports that periodically summarize the analysis results and improvement effects and sending them to relevant parties.

[1128] This invention is a system that collects and analyzes work data to identify imbalances in employee workloads and automatically proposes and implements appropriate improvement measures. This system operates in cooperation with the server, terminals, and users.

[1129] Collection and analysis of work data

[1130] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. Break times and work details are also recorded in the same way. The terminals used are attendance management devices with touch panels or card readers so that employees can easily operate them. For example, employee A clocks in on the terminal when he comes to work, and "9:00" is recorded as his clock-in time.

[1131] The server collects the latest work data from each device at regular intervals. For example, if the server collects work data every hour, employee A's arrival, departure, and break data will be periodically sent to the server. The server is equipped with a high-performance database and communication interface, allowing for real-time data collection. The server then sends the collected work data to the generative AI model.

[1132] The generative AI model analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generative AI aggregates the total working hours and overtime hours for this month from Employee A's data and detects that the overtime hours exceed 80 hours. Machine learning algorithms are used in the analysis to recognize patterns and detect anomalies.

[1133] Identifying and alerting on imbalances

[1134] The server receives the analysis results of the generative AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server detects that employee A's overtime hours exceed 80 hours and notifies management by email. A template engine is used for the notification, and an automatically generated email body is sent.

[1135] Proposing business improvement measures and monitoring their implementation

[1136] The generative AI model continues its analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generative AI. For example, if the generative AI recommends "redistributing work," the server sends the recommendation to employee A's team leader. The notification is distributed via email or the internal messaging system.

[1137] The user (management) implements the proposed improvement measures. Specifically, the team leader holds a meeting to redistribute work among team members. For example, employee A's work is assigned to another member. The implementation status of the improvement measures is recorded using a task management tool.

[1138] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. For example, the server checks the work data of employee A after his work has been redistributed and evaluates whether his overtime has decreased. Statistical analysis software is used for the evaluation and effectiveness is measured.

[1139] Generate and send reports

[1140] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements on employee A is created. The generated report includes graphs and charts to visualize the effects.

[1141] The generated reports are automatically sent to the relevant parties. For example, the server emails the report in PDF format to management. An automation tool is used to send the emails, ensuring regular reporting.

[1142] Streamlining overtime management

[1143] The server manages overtime data in real time in cooperation with the generative AI model. For example, the server updates the analysis results of the generative AI model every day to keep the data up to date.

[1144] The terminal displays the latest data and forecasts in real time on the management panel. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check. The management panel is web-based and can be accessed from anywhere.

[1145] This will make it possible to distribute the workload of employees fairly and reduce the amount of time spent managing overtime. It is also expected that the number of employees desired by managers will increase.

[1146] Prompt Sentence Examples

[1147] To provide a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[1148] "Please enter Employee A's work data and analyze the total hours worked and overtime for this month. In addition, please check whether any employees are working too much and recommend appropriate work improvement measures."

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

[1150] Step 1: Collect work data

[1151] The terminal receives input from employees (start time, end time, break time, work content) and records the work data. For example, if employee A starts work at 9:00 and leaves work at 18:00, the start and end times are recorded on the terminal. The output is the recorded work data, which is the information to be sent to the server.

[1152] Step 2: Send data to the server

[1153] The server receives work data collected from each terminal at regular intervals. For example, every hour the server retrieves the latest work data from the terminal and stores it in a database. The input is work data from the terminal, and the output is data stored in the database in the server. Specifically, the server receives and stores the attendance data of employee A at 9:00 at 10:00.

[1154] Step 3: Data analysis with generative AI

[1155] The server sends the collected work data to the generative AI model. The generative AI model analyzes the input work data and identifies each employee's total working hours, overtime hours, and imbalances. For example, calculate employee A's total working hours and overtime hours for this month and check whether they exceed 80 hours. The input is work data from the server, and the output is the analysis result of the generative AI model.

[1156] Step 4: Imbalance detection and alerting

[1157] The server receives the analysis results from the generation AI and detects imbalances or abnormalities in workload. If an imbalance is identified, the server sends an alert to the relevant parties. Specifically, the server detects that employee A's overtime hours exceed 80 hours and sends an email notification to management. The input is the analysis results from the generation AI, and the output is an alert notification to the relevant parties.

[1158] Step 5: Proposing business improvement measures

[1159] The generative AI model proposes measures to improve workloads based on the analysis results. The server notifies the relevant parties of the improvement measures received from the generative AI. Specifically, the generative AI model proposes "redistribution of work," and the server sends this proposal to employee A's team leader. The input is the improvement proposal from the generative AI, and the output is a notification to the relevant parties.

[1160] Step 6: Implement and monitor improvements

[1161] The user (management) implements the proposed improvement measures. For example, a team leader holds a meeting to redistribute work. The server then continuously monitors the work data and evaluates the effectiveness of the improvement measures. The input is the implementation status of work redistribution by the management, and the output is the measured results of the improvement measures. Specifically, the server analyzes employee A's work data after redistribution and evaluates the effectiveness.

[1162] Step 7: Generate and send the report

[1163] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to relevant parties. For example, at the end of the month, the server creates a report summarizing the effects of work improvements on employee A and sends it to management by email. The input is the analysis data from the generation AI and the server, and the output is an automatically generated report.

[1164] Step 8: Improve overtime management efficiency

[1165] The server manages overtime data in real time by working in conjunction with the generated AI model. The terminal displays the latest data and predictions in real time on the management panel. For example, the server updates the analysis results of the generated AI model every day and displays a "weekly trend graph of employee A's overtime hours" on the terminal. The input is real-time data from the generated AI, and the output is the content displayed on the management panel.

[1166] (Application example 1)

[1167] 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."

[1168] At logistics centers, imbalances in employee workloads often occur, resulting in problems such as overwork and reduced production efficiency. Conventional systems make it difficult to detect workload imbalances in real time and quickly implement countermeasures. Furthermore, it is difficult to propose appropriate work improvement measures, and there is a lack of effective means for monitoring the implementation status of these measures. This leads to problems such as inappropriate work style measures not being implemented, resulting in a significant drop in productivity.

[1169] 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.

[1170] In this invention, the server includes means for collecting work data, means for analyzing the collected work data, means for identifying work imbalances based on the analysis results, means for issuing an alert when an imbalance is identified, means for proposing work improvement measures based on the analysis results, means for monitoring the implementation of the proposed work improvement measures, means for periodically reporting the analysis results and the effects of the improvements, means for providing real-time alerts and improvement measures to employees via a smart device, means for managing the work status at the logistics center in real time and detecting workload imbalances, means for displaying the detected imbalance on the smart device, and means for displaying improvement suggestions on the smart device. This makes it possible to identify workload imbalances at the logistics center in real time and quickly propose and implement appropriate improvement measures.

[1171] "Work data" refers to work-related information such as employees' arrival and departure times, break times, and job duties.

[1172] "Analysis" is the process of analyzing collected work data to detect specific patterns or imbalances.

[1173] "Imbalance" refers to an unequal situation in terms of workload, working hours, etc., and means that certain employees are placed under an excessive burden.

[1174] An "alert" is a means of sending warnings or notifications to relevant parties when an imbalance occurs.

[1175] "Business improvement measures" are recommendations and procedures for balancing workloads and improving efficiency.

[1176] "Monitoring" is the process of overseeing the implementation of business improvement measures and evaluating their effectiveness.

[1177] A "report" is a document that summarizes the analysis results and improvement effects for a certain period of time.

[1178] "Smart devices" are electronic devices with internet connectivity, such as smartphones, smart glasses, and head-mounted displays.

[1179] A "logistics center" is a facility that stores, organizes, and distributes goods and materials.

[1180] "Real-time" refers to the ability to collect, analyze, and notify data almost simultaneously.

[1181] "Improvement proposals" are specific methods or means proposed by the generative AI model to improve work efficiency or reduce workload.

[1182] A "generative AI model" is a system that uses artificial intelligence to analyze data and generate patterns and suggestions.

[1183] The present invention is a system that detects imbalances in the workloads of employees at a logistics center in real time and promptly proposes appropriate remedial measures. This system operates in cooperation with a server, terminals, and users.

[1184] Collection and analysis of work data

[1185] The terminal records attendance data when an employee arrives at work, and clocks out when they leave. Break times and work content are also recorded in the same way. For example, employee A clocks in on his terminal when he arrives at work, and "9:00" is recorded as his arrival time. The server collects the latest work data from each terminal at regular intervals. For example, if the server collects work data every hour, employee A's arrival, clock out, and break data are periodically sent to the server. The server then sends the collected work data to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. For example, the generation AI tallys up the total working hours and overtime hours for this month from employee A's data and detects that overtime hours exceed 80 hours.

[1186] Identifying and alerting on imbalances

[1187] The server receives the analysis results of the generation AI and detects workload imbalances and anomalies. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that Employee A's overtime hours exceed 80 hours. It may also display a real-time alert to employees wearing smart glasses.

[1188] Proposing business improvement measures and monitoring their implementation

[1189] The generation AI continues its analysis and proposes measures to improve the workload. Specifically, it proposes improvements such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures it receives from the generation AI. For example, the generation AI recommends "redistributing work," and the server sends the proposal to employee A's team leader. The user (management) implements the proposed improvement measures. For example, the team leader holds a meeting to redistribute work with team members. The server continues to monitor work data even after the improvement is implemented and evaluates its effectiveness. For example, the server checks employee A's work data after the work has been redistributed, and evaluates whether overtime has decreased.

[1190] Generate and send reports

[1191] The server automatically generates reports on the analysis results and improvement effects at regular intervals. For example, at the end of the month, a report summarizing the effects of work improvements made to employee A is created. The generated report is automatically sent to the relevant parties. For example, the server may email a PDF report to a manager.

[1192] Streamlining overtime management

[1193] The server manages overtime data in real time by working with the generation AI. For example, it updates the analysis results of the generation AI every day to keep the data up to date. The terminal displays the latest data and predictions on the management panel in real time. For example, the terminal displays a "weekly trend graph of employee A's overtime hours" on the management panel, making it easy for managers to check.

[1194] Examples of concrete examples and prompts

[1195] For example, if a logistics center employee is working more than eight hours a day, an imbalance will be detected and an alert will be displayed on the smart glasses. An example of a prompt sentence for the generative AI model is as follows:

[1196] Prompt Sentence Examples

[1197] Based on current employee work data, analyze workload imbalances, issue alerts if any, and suggest appropriate remedial measures.

[1198] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1199] Step 1:

[1200] The terminal records attendance data when an employee arrives at work, and records attendance data when the employee leaves work. Break times and work details are also recorded in the same way. Inputs include employee time-stamping information (times of arrival and departure) and selected work details. This allows employee work data to be collected in real time. The output is sent to the server as work data.

[1201] Step 2:

[1202] The server collects the latest work data from each device at regular intervals. The input is work data from the device. The server collects this data in a fixed format and stores it in a database. This allows the server to centrally manage employee work status. The output is the organized work data sent to the generation AI.

[1203] Step 3:

[1204] The server sends work data to the generation AI for analysis. The input is work data collected and organized by the server. The generation AI analyzes this data and identifies each employee's workload, imbalances, and overtime hours. The output is the analysis results, which are sent back to the server.

[1205] Step 4:

[1206] The server receives the analysis results from the generation AI and detects workload imbalances and anomalies. The input is the analysis results returned by the generation AI. The server checks the analysis results and issues an alert if an imbalance is detected. The output is alert information, which is sent to relevant parties and smart devices.

[1207] Step 5:

[1208] The server notifies the relevant parties of the improvement measures received from the generation AI. The input is the business improvement measures proposed by the generation AI. The server analyzes the contents of the proposal and notifies the appropriate relevant parties (e.g., team leader). The output is a notification of the business improvement proposal.

[1209] Step 6:

[1210] The user (management) implements the proposed improvement measures. The input is the business improvement proposal notified by the server. The user takes specific action (for example, redistributing work or reviewing shifts) based on the improvement measures. The output is the results of implementing the improvement measures.

[1211] Step 7:

[1212] The server continues to monitor work data even after improvements are implemented and evaluates their effectiveness. The input is new work data and the results of the improvements. The server analyzes the data and evaluates the effectiveness of the improvements. The output is an evaluation report.

[1213] Step 8:

[1214] The server automatically generates reports of analysis results and improvement effects at regular intervals. The input is the accumulated analysis results and improvement effect data. The server automatically generates reports and sends them to the relevant parties. The output is a PDF report.

[1215] Step 9:

[1216] The terminal displays the latest data and forecasts on the management panel in real time. The input is the latest data and forecast information sent from the server. The terminal displays this as graphs and charts so that the administrator can easily check it. The output is the visualization on the management panel.

[1217] In this way, it becomes possible to identify workload imbalances in logistics centers in real time and quickly propose and implement appropriate improvement measures.

[1218] 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.

[1219] This system collects and analyzes work data and user emotion data, identifies workload imbalances, and automatically proposes and implements appropriate remedial measures. This system operates in cooperation with the server, terminals, emotion engine, and users.

[1220] Collection and analysis of work data

[1221] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[1222] The server periodically collects work data from each device. For example, a schedule can be set up so that the server collects work data from each device every hour. This allows employee A's arrival, departure, and break data to be collected on the server.

[1223] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for May" to the generation AI. The generation AI analyzes the received work data and identifies each employee's workload, overtime hours, and imbalances. The generation AI tallys up the total working hours and overtime hours for this month from Employee A's data and identifies excessive overtime.

[1224] Emotion data collection and analysis

[1225] The emotion engine collects and analyzes the user's emotions. For example, the camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to collect emotion data. Emotion data includes information such as stress level and happiness level.

[1226] The server periodically collects emotional data from the emotion engine. For example, the server obtains employee A's emotional data every day. The emotion engine analyzes the collected emotional data and evaluates the employee's emotional state. The generative AI performs a comprehensive analysis combining the work data and emotional data to detect imbalances in workload and stress levels.

[1227] Identifying and alerting on imbalances

[1228] The server receives the analysis results of the generated AI and detects imbalances in workload or emotional states. If an imbalance is identified, the server sends an alert to the relevant parties. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours and his emotional data indicates high stress."

[1229] Proposing business improvement measures and monitoring their implementation

[1230] The generating AI then conducts further analysis and proposes measures to improve the workload. Specifically, it proposes measures such as redistributing work and reviewing shifts. The server notifies the relevant parties of the improvement measures received from the generating AI. For example, the generating AI proposes "redistributing work," and the server sends the proposal to employee A's team leader.

[1231] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[1232] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[1233] Generate and send reports

[1234] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, it creates a report summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[1235] The generated report is automatically sent to the relevant parties, for example, the server can email the report in PDF format to a manager.

[1236] Improved efficiency of overtime management and emotion monitoring

[1237] The server manages overtime data and emotion data in real time by linking with the generation AI and emotion engine. For example, it updates the analysis results of the generation AI and emotion engine every day and reflects the latest data on the management panel.

[1238] The terminal displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[1239] This system will help to distribute the workload of employees fairly and monitor their emotional state, creating a comfortable working environment and reducing the amount of work required to manage overtime, which is expected to increase the number of employees who wish to become managers.

[1240] The processing flow will be explained below.

[1241] Step 1:

[1242] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. It also records break times and work details. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00."

[1243] Step 2:

[1244] The server periodically collects work data from each device. For example, a schedule is set up so that the server collects work data from each device every hour. This allows employee A's clock-in, clock-out, and break data to be collected on the server.

[1245] Step 3:

[1246] The server sends the collected work data to the generation AI. For example, the server sends "Employee A's work data for one month" to the generation AI.

[1247] Step 4:

[1248] The generation AI analyzes the received work data and identifies the workload, overtime hours, and imbalances for each employee. For example, the generation AI aggregates "total monthly working hours," "overtime hours," "break times," etc. from employee A's data and identifies excessive overtime.

[1249] Step 5:

[1250] The emotion engine collects and analyzes the user's emotions. The camera and microphone installed on Employee A's device analyze the employee's facial expressions and voice to obtain emotion data. For example, the emotion engine measures Employee A's stress level and happiness.

[1251] Step 6:

[1252] The server collects emotion data from the emotion engine and sends it to the generation AI along with work data. For example, the server sends employee A's emotion data to the generation AI every day.

[1253] Step 7:

[1254] The generative AI integrates and analyzes work data and emotional data to detect imbalances in workload and emotional states. For example, the generative AI detects a high stress state from employee A's emotional data and correlates it with an imbalance in workload.

[1255] Step 8:

[1256] The server receives the analysis results of the generating AI and sends an alert to relevant parties if an imbalance is identified. For example, the server may notify a manager by email that "Employee A's overtime hours exceed 80 hours, and his emotional data indicates high stress."

[1257] Step 9:

[1258] The Generative AI performs additional analysis to recommend measures to improve workloads. Recommendations include redistributing work and reviewing shifts. For example, the Generative AI might recommend "redistributing Employee A's work to other members."

[1259] Step 10:

[1260] The server notifies the relevant parties of the improvement measures received from the generation AI. For example, the server sends an email to the team leader with a "work reallocation proposal."

[1261] Step 11:

[1262] The user (management) implements the proposed improvement measures. The team leader holds a meeting to redistribute work among the team members. For example, the team leader assigns Employee A's work to other members.

[1263] Step 12:

[1264] Even after the implementation of the proposed improvement measures, the server continues to monitor the work data and emotional data and evaluates their effectiveness. For example, even after the redistribution, the server checks the work data and emotional data of employee A and evaluates the reduction in overtime hours and improvement in stress levels.

[1265] Step 13:

[1266] The server automatically generates a report of the analysis results and the effects of the improvements at regular intervals. For example, at the end of the month, a report is created summarizing "changes in working hours, overtime hours, and emotional data for employee A before and after the improvements."

[1267] Step 14:

[1268] The server automatically sends the generated report to the relevant parties. For example, the server may email the report in PDF format to a manager.

[1269] Step 15:

[1270] The server manages real-time overtime data and emotion data in cooperation with the generation AI and emotion engine. For example, the analysis results of the generation AI and emotion engine are updated daily, and the latest data is reflected in the management panel.

[1271] Step 16:

[1272] The device displays the latest data and forecasts in real time on the management panel. For example, the management panel can display a graph of employee A's weekly overtime hours and trends in employee emotion data, making them easy for managers to check.

[1273] Example 2

[1274] 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."

[1275] In today's work environment, it is difficult to accurately collect and analyze employee work data and emotional data to identify imbalances in workload and emotional state. When employees experience excessive stress or have uneven workloads, it is necessary to identify the issue early and propose and implement appropriate improvement measures. However, conventional systems do not adequately analyze work data and emotional data comprehensively, making it difficult to propose efficient work improvement measures and monitor their effectiveness.

[1276] 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.

[1277] In this invention, the server includes means for collecting work data, means for collecting emotion data, means for analyzing using a generative AI model, means for identifying imbalances, means for issuing alerts, means for proposing business improvement measures, means for monitoring the implementation of the proposed business improvement measures, and means for reporting the analysis results and improvement effects at regular intervals. This enables integrated and real-time analysis of employee work data and emotion data, early identification of imbalances in workload or emotional states, and the proposing and implementation of appropriate improvement measures.

[1278] "Work data" refers to data related to working hours and work conditions, such as an employee's arrival time, departure time, break time, and job content.

[1279] "Emotional data" refers to data that indicates psychological states such as stress levels and happiness obtained from employees' facial expressions, voice, behavior, etc.

[1280] A "generative AI model" is an artificial intelligence model that analyzes collected data and performs advanced data processing such as recognizing patterns and providing insights.

[1281] The "analyzing means" is a processing device or software that uses the collected data to evaluate and analyze workload, emotional state, and the like.

[1282] The "means for identifying imbalances" is an algorithm or device for identifying imbalances or imbalances in workload or emotional states based on the analysis results.

[1283] An "alert mechanism" is a communications device or software that notifies relevant parties when an imbalance is detected.

[1284] "Means for proposing business improvement measures" refers to a processing device or software that proposes improvement measures such as adjusting workloads or redistributing work based on the analysis results of the generative AI model.

[1285] "Means for monitoring proposed improvement measures" refers to devices or software for continuously evaluating the implementation status and effects of proposed business improvement measures.

[1286] "Means for reporting analysis results and improvement effects at regular intervals" refers to a device or software that periodically generates reports on the analysis results and the effects of implementing business improvement measures, and provides them to those involved.

[1287] "Server" means a central processing unit for collecting data, analyzing, identifying imbalances, issuing alerts, recommending business improvements, monitoring, and generating reports.

[1288] "Terminal" means a device used by an employee to input and collect work data and emotion data.

[1289] This invention is a system that collects and analyzes work data and employee emotional data, identifies imbalances in workload and emotional states, and proposes and implements improvement measures. This system operates in cooperation with a server, terminals, and an emotion engine.

[1290] Collection of work data

[1291] The terminal records the employee's clock-in data when they come to work, and clock-out data when they leave. For example, when employee A clocks in, the terminal records "Clock-in time: 9:00." Break times and work details are also recorded at the same time.

[1292] Collection and analysis of work data

[1293] The server periodically collects work data from each device. For example, the server processes data on clock-in, clock-out, and breaks from each device every hour. The server then sends the collected work data to the generative AI model. The generative AI model then analyzes the data using the following prompt:

[1294] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[1295] A generative AI model analyzes the data it receives, calculates each employee's total working hours and overtime hours, and identifies imbalances.

[1296] Emotion data collection and analysis

[1297] The emotion engine collects the user's emotion data. While Employee A is working in front of the terminal, the terminal's camera analyzes facial expressions and the microphone collects emotion data from voice. The server collects the emotion data and sends it to the generative AI model. The generative AI model analyzes the emotion data using the following prompt sentence:

[1298] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[1299] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[1300] Identifying and alerting on imbalances

[1301] The server integrates the results of analyzing work data and emotional data to detect imbalances. For example, if the server detects that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an email alert to management.

[1302] Proposing business improvement measures and monitoring their implementation

[1303] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotion data. For example, the generative AI model recommends "redistribution of work," and the server notifies the manager of the proposal. The user (manager) then implements the proposed improvement measures. For example, the manager holds a meeting and decides to distribute employee A's work to other members.

[1304] Monitoring the effectiveness of improvements

[1305] The server continues to monitor work data and emotion data even after the implementation of improvement measures and evaluates their effectiveness. For example, even after redistribution, the server checks the work data and emotion data of employee A and evaluates whether overtime hours have been reduced and stress has been alleviated.

[1306] Generate and send reports

[1307] The server automatically generates a report of the analysis results and improvement effects at regular intervals and sends it to the relevant parties. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management.

[1308] Real-time management of overtime and emotion data

[1309] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The terminal displays a real-time graph of employee A's weekly overtime hours and emotion data trends on the management panel, making it easy for managers to check. This system enables the integrated analysis of employee work data and emotion data, making it possible to create a comfortable working environment and reduce the workload of managing overtime.

[1310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] The terminal records the employee's arrival time. The input is the employee's ID card information, which is stamped when they arrive at work. Specifically, when an employee holds their ID card over the terminal, the data "Arrival time: 9:00" is generated. This data is temporarily stored in the terminal.

[1313] Step 2:

[1314] The terminal records the employee's time of leaving work. The input is again the employee's ID card information, which is punched in when they leave work. Specifically, when an employee swipes their ID card at the desk to leave work, the data "Leave work time: 18:00" is generated. This data is also temporarily stored in the terminal.

[1315] Step 3:

[1316] The server periodically collects work data from each terminal. The input is the work data sent from each terminal, and the output is the work data consolidated in the server. For example, the server runs a collection script every hour to obtain data on arrival, departure, and breaks from each terminal.

[1317] Step 4:

[1318] The server sends the collected work data to the generative AI model. The input is the work data integrated by the server, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[1319] Prompt: "Analyze employee A's work data and identify workload, overtime hours, and imbalances."

[1320] The generative AI model analyzes work data, calculates total hours worked and overtime, and identifies imbalances.

[1321] Step 5:

[1322] The emotion engine collects the user's emotional data. The input is real-time facial and voice data obtained from the device's camera and microphone, and the output is the analysis results by the emotion engine. For example, while an employee is working in front of a device, the camera analyzes their facial expressions and the microphone collects their voice.

[1323] Step 6:

[1324] The server collects emotion data from the emotion engine and sends it to the generative AI model. The input is the emotion data obtained from the emotion engine, and the output is the analysis result by the generative AI model. The server sends the following prompt to the generative AI model:

[1325] Prompt: "Analyze employee A's emotional data and assess their stress levels and happiness."

[1326] The generative AI model analyzes the data received from the emotion engine and calculates employee stress levels and happiness.

[1327] Step 7:

[1328] The server integrates the results of work data and emotion data analysis to detect imbalances. The input is the analysis results of work data and emotion data obtained from the generative AI model, and the output is an alert indicating imbalances. For example, if the server finds that "Employee A's overtime hours exceed 80 hours, indicating high stress," it will send an alert to management by email.

[1329] Step 8:

[1330] The generative AI model proposes measures to improve workloads based on the results of analyzing work data and emotional data. The input is the analyzed work data and emotional data, and the output is a proposal for improvement measures. Specifically, the generative AI model recommends "work redistribution," and the server notifies the proposal to managers.

[1331] Step 9:

[1332] The user (manager) implements the proposed improvement measures. The input is the improvement proposal from the generative AI model, and the output is the work redistribution results after implementation. For example, the manager holds a meeting to allocate Employee A's work to other members.

[1333] Step 10:

[1334] The server continues to monitor work data and emotion data even after the implementation of improvement measures, and evaluates their effectiveness. The input is the collected work data and emotion data again, and the output is an evaluation of the effectiveness of the improvement. For example, even after redistribution, the server checks the work data and emotion data of employee A, and evaluates whether overtime hours have been reduced and stress has been alleviated.

[1335] Step 11:

[1336] The server automatically generates reports of analysis results and improvement effects at regular intervals and sends them to the relevant parties. The input is the analysis results and improvement effect data, and the output is the generated report. For example, at the end of the month, a report summarizing "Changes in employee A's working hours and emotional data before and after improvement" is created in PDF format and sent to management by email.

[1337] Step 12:

[1338] The server manages real-time data from the generative AI model and emotion engine, and displays the latest data and predictions on the management panel. The input is the latest data from the generative AI model and emotion engine, and the output is the data for each employee displayed on the management panel. The terminal displays a weekly graph of employee A's overtime hours and emotion data trends on the management panel in real time, making it easy for managers to check.

[1339] (Application example 2)

[1340] 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."

[1341] In factory work environments, workload imbalances between employees and robots can occur, resulting in reduced production efficiency and increased employee stress. Identifying workload imbalances and proposing improvements requires a significant amount of time and effort. Even if improvements are proposed, there is a lack of efficient means for monitoring the effectiveness of their implementation. A solution to these issues is needed.

[1342] The identification processing by the identification 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 work data and emotional data, means for analyzing the collected work data and emotional data, and means for identifying imbalances in work load and emotional state based on the analysis results. This makes it possible to automatically propose improvements and improve implementation efficiency in order to maintain an appropriate balance between workload and emotional state.

[1343] "Work data" refers to information about the working habits of employees and machines, such as their arrival and departure times, work content, and break times.

[1344] "Emotional data" refers to information about the psychological state and emotions of employees and workers obtained by analyzing their facial expressions, voice, physical movements, etc.

[1345] A "collection means" is a device or system that has the function of acquiring data using an input device such as a sensor, camera, or microphone.

[1346] The "analysis method" is a process that uses algorithms and machine learning models to evaluate working patterns and emotional states based on collected data and detect imbalances and anomalies.

[1347] The "means for identifying" is a device or system that has the function of identifying and clearly indicating imbalances in workload or emotional state from the analysis results.

[1348] An "alert means" is a device or system that has the capability to notify administrators and other relevant parties of relevant information when an imbalance is identified.

[1349] The "means for making recommendations" refers to a device or system that has the function of automatically generating and proposing appropriate business improvement measures and shift readjustment measures based on the analysis results.

[1350] "Monitoring means" refers to a device or system that has the function of continuously monitoring and evaluating how effectively a proposed business improvement measure or shift readjustment measure is functioning after it has been implemented.

[1351] "Reporting means" refers to a device or system that has the function of creating and distributing reports on the analysis results and the effects of improvements based on data collected and analyzed at regular intervals.

[1352] "Imbalance" refers to a situation in which workload and emotional state are not equal, i.e., the existence of problems such as excessive workload or high stress.

[1353] "Business improvement measures" are specific action plans and measures to resolve problems identified through the analysis results and to improve business efficiency and the working environment.

[1354] The system that realizes this invention has a means for collecting and analyzing work data and emotional data from employees and machines, identifying imbalances in workload and emotional states, and proposing measures to improve them. The specific configuration and operation of this system are described below.

[1355] Data collection methods

[1356] The server has a means for collecting work data and emotional data. Work data is automatically collected from sensors and terminals and includes employees' arrival and departure times, work tasks, break times, etc. Emotional data is acquired using cameras and microphones through facial recognition and voice analysis.

[1357] Data Analysis Methods

[1358] The collected work data and emotional data are analyzed by a server. A generative AI model using TensorFlow is used for the analysis, and data processing is performed to identify imbalances. Specifically, the data is preprocessed (missing value correction and normalization), and then the AI ​​model is used to evaluate workload and emotional state.

[1359] Imbalance identification means

[1360] The server has a means for identifying imbalances in work and emotional states based on the analysis results. For example, if the total working hours, overtime hours, or stress level of employee A are high, these are identified as imbalances.

[1361] Alert method

[1362] If an imbalance is identified, the server has the means to raise an alert, specifically by sending an email notification to the relevant administrator or stakeholders.

[1363] Business improvement proposal methods

[1364] The server has a means to propose work improvement measures and shift reallocation measures based on the analysis results. The proposed contents are automatically sent to the manager, who will suggest work reallocation and shift review.

[1365] Implementation monitoring measures

[1366] Even after the proposed work improvement measures and shift reallocation measures are implemented, the server has a means for continuously monitoring the work data and emotion data, thereby evaluating the effectiveness of the implemented improvement measures.

[1367] Report Generation Method

[1368] The server has a means to periodically report the analysis results and improvement effects, and the generated reports are automatically sent to the relevant parties.

[1369] Hardware and software used

[1370] Sensor: Device for measuring operating time

[1371] Camera and microphone: a device for collecting emotional data

[1372] TensorFlow: for analyzing generative AI models

[1373] EmotionEngine: for emotional data analysis

[1374] smtplib: for email notifications

[1375] Prompt Sentence Examples

[1376] Example of sending work data: "Employee A's work data for May"

[1377] Example of sending emotional data: "Employee A's emotional data"

[1378] This enables automated improvement suggestions and implementation efficiencies to properly balance workload and emotional states in factories and other large workplaces.

[1379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1380] Step 1:

[1381] The server collects work data and emotional data. Specifically, the terminal records the arrival and departure times, break times, and work details of employees and machines, and acquires emotional data from sensors, cameras, and microphones. This data is sent from the terminal to the server. The input is the operating status and emotional state of each employee and machine, and the output is the collected data.

[1382] Step 2:

[1383] The server preprocesses the collected work data and emotion data, imputing missing values ​​and normalizing the data. Specifically, missing values ​​for each data point are imputed with zeros and all data is standardized. The input is the data collected in step 1, and the output is the preprocessed data.

[1384] Step 3:

[1385] The server analyzes the preprocessed data. Using TensorFlow, the preprocessed data is fed into a generative AI model to identify imbalances in workload and emotional states. Specifically, the model detects excessive working hours and high stress levels. The input is the preprocessed data, and the output is an analysis showing the imbalances.

[1386] Step 4:

[1387] The server notifies the administrator of imbalances based on the analysis results. Specifically, it uses the smtplib library to send alerts by email. The notifications describe excessive workloads and stress levels of employees and machines. The input is the analysis results, and the output is the sent alert email.

[1388] Step 5:

[1389] The server recommends business improvement measures and shift reallocation measures based on the analysis results. It uses a generative AI model to calculate the optimal reallocation and generate recommendations. The recommendations are automatically sent to the administrator. The inputs are the analysis results and performance data, and the output is the recommendations.

[1390] Step 6:

[1391] The user (manager) implements the proposed business improvement measures and shift reallocation measures. Specifically, team meetings and shift adjustments are held, and the proposed improvement measures are implemented. The input is the proposal, and the output is the implemented improvement measures.

[1392] Step 7:

[1393] The server continues to monitor work data and emotion data even after the proposed improvement measures are implemented. It again collects and analyzes data from sensors, cameras, and microphones. This allows the effectiveness of the improvement measures to be evaluated. The input is the updated work data and emotion data, and the output is the reevaluation results.

[1394] Step 8:

[1395] The server periodically compiles the analysis results and improvement effects into a report. The report is automatically generated and distributed to relevant parties. The input is the data and analysis results obtained at each step, and the output is data in report format.

[1396] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice 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 voice data.

[1397] 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.

[1398] 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 robot 414.

[1399] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1400] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1401] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1402] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1403] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1404] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1405] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1406] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1407] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1408] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1409] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1410] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1411] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1412] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1413] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1414] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1415] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of...

Claims

1. a means of collecting work data; A means of analyzing the collected work data; A means of identifying work imbalances based on the analysis results; and A means of issuing alerts when imbalances are identified; and A means of proposing business improvement measures based on the analysis results, A means of monitoring the implementation of the recommended business improvements; and A means to report analysis results and improvement effects at regular intervals, A system including:

2. The system of claim 1 , wherein work data is automatically collected from employee terminals.

3. The system of claim 1 , further comprising: automatically transmitting the generated report to interested parties.

Images