System

Abstract

A system is provided.SOLUTION: A system comprising means for collecting communication metadata, means for collecting business schedule information, means for transmitting the collected communication metadata and business schedule information to a server, means for estimating a busyness degree of each member using an AI generated based on the data in the server, means for visualizing the estimated busyness degree data, and means for proposing a redistribution of business based on the busyness degree data.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] With the spread of remote work in modern work styles, it has become difficult to grasp the workload and progress of each member. As a result, it is easy for work imbalances and unfair burdens to occur, leading to problems such as decreased productivity and increased employee stress. Furthermore, traditional methods require time-consuming information gathering and schedule creation, making it difficult to efficiently allocate work. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides a system including: means for collecting communication metadata, means for collecting work schedule information, means for transmitting the collected communication metadata and work schedule information to a server, means for estimating the busyness level of each member using a generation AI based on the data, means for visualizing the estimated busyness data, and means for proposing work redistribution based on the busyness data. The present invention makes it possible to grasp the workload and work progress of each member in real time, thereby realizing efficient and fair work distribution.

[0006] "Communication metadata" refers to data related to communication activities, such as email sending and receiving logs, number and frequency of chat messages, and duration of video conference calls.

[0007] "Work schedule information" refers to time allocation information related to work, such as each member's schedule and task schedule.

[0008] A "server" is a computer system that receives, stores, analyzes, and processes data over a network.

[0009] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to generate and analyze information based on collected data.

[0010] "Busyness level" is an indicator that shows each member's workload and the progress of their work.

[0011] "Visualization" means displaying analytical results in a visual format such as a graph or dashboard.

[0012] "Redistribution" means evaluating and reviewing the current division of labor and making adjustments such as transferring some of the work to other members. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention relates to a system for efficiently managing the workload of each member in a remote work environment and achieving fair work distribution. Specific embodiments of the present invention will be described in detail below.

[0035] Overall system picture

[0036] The system collects communication metadata and work schedule information for all employees and uses generative AI to automatically estimate each member's "busyness level." The estimated results are visualized, and if work needs to be reallocated, suggestions are made. The overall process is as follows:

[0037] Data collection

[0038] The devices periodically collect communication metadata, such as each employee's email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. They also collect each employee's work schedule. This data is sent to a server at regular intervals. The collected data includes the time each email was sent and received, the recipient and sender, the number and frequency of chat messages, and the start and end times of video conferences.

[0039] Data transmission and storage

[0040] The communication metadata and work schedule information sent from the device are stored on the server, which then stores this data in a database and prepares it for analysis by the generation AI.

[0041] Data analysis

[0042] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each member's "busyness level." For example, if a member sends and receives a lot of emails and spends a lot of time participating in video conferences, the member's busyness level will be evaluated as high.

[0043] Data Visualization

[0044] The server converts the busyness data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing users to understand at a glance the busyness of each member and the overall work balance of the team. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and the overall status of the team.

[0045] Proposal for business reallocation

[0046] The server determines whether work needs to be redistributed based on the busyness assessment. If necessary, it generates a proposal for work redistribution. For example, if work is concentrated on a specific member, it proposes distributing that member's tasks to other members who have more free time.

[0047] Implementation of reallocation

[0048] The administrator, who is the user, reviews the work reallocation proposals presented by the server and actually reallocates the tasks. This process results in a fair and efficient work distribution.

[0049] Specific examples

[0050] For example, if Employee A participates in many video conferences and processes a large number of emails, the system collects communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates Employee A's busyness level as high. The server then visualizes the evaluation results as a graph, making Employee A's workload clear. The manager can then view the graph and receive suggestions for redistributing tasks to other employees to reduce Employee A's workload, and redistribute work based on these suggestions.

[0051] This system enables efficient and fair distribution of work even in a remote work environment.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The device collects communication metadata. For example, an employee's device periodically records information such as email logs, chat message counts, and video conference participation time. Each employee's device is configured to run this process in the background.

[0055] Step 2:

[0056] The device sends communication metadata and work schedule information to the server. The collected data is sent to the server at regular intervals (e.g., every hour). The data is encrypted and reaches the server securely.

[0057] Step 3:

[0058] The server stores the received data in a database. The transmitted communication metadata and work schedule information are stored in the database and used for subsequent analysis.

[0059] Step 4:

[0060] The server analyzes communication metadata and work schedule information. Using a generative AI model, it evaluates each member's communication volume and the density of their work schedule, and calculates their "busyness level." For example, the AI ​​model can learn features such as the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences, and then predict the optimal busyness level.

[0061] Step 5:

[0062] The server visualizes the calculated busyness data, which is converted into graphs and dashboards, allowing users to see at a glance the workload of each member and the overall team balance.

[0063] Step 6:

[0064] Users can check their busyness data. Each member and administrator can access the data from their own device and visually check their own busyness level and the overall team status on a dashboard or graph.

[0065] Step 7:

[0066] The server generates proposals for work reallocation. Based on the analysis results of the generation AI, if work is concentrated on a specific member, a proposal for work reallocation is created.

[0067] Step 8:

[0068] The administrator, who is the user, checks and implements the redistribution proposal. The administrator reviews the work redistribution proposal presented by the server and instructs other members to reallocate tasks as necessary. As a result, a fair and efficient work balance is achieved.

[0069] Example 1

[0070] 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."

[0071] In a remote work environment, it is difficult to manage each member's workload efficiently and fairly. In particular, it is necessary to accurately grasp the level of workload and allocate tasks appropriately to each member, but current manual management has its limitations. In addition, since data collection and analysis are insufficient, it is difficult to propose appropriate task reallocation.

[0072] 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.

[0073] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for transmitting the collected communication metadata and work schedule information to the server, means for estimating the busyness level of each member using a generative AI model based on the data, means for visualizing the estimated busyness data, means for proposing work redistribution based on the busyness data, and means for a manager to implement the proposed work redistribution. This makes it possible to efficiently and fairly manage the workload of each member and appropriately redistribute work even in a remote work environment.

[0074] "Communication metadata" refers to data about communication activities, such as email sending and receiving logs, number of chat messages, and participation time in online meetings.

[0075] "Work schedule information" refers to information about the allocation of time related to work, such as each member's plans, tasks, and meeting schedules.

[0076] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and generate results that fit a specific purpose.

[0077] "Busyness" refers to the degree of workload of each member, and is an indicator evaluated based on factors such as communication volume and the density of work schedules.

[0078] "Visualization" refers to the visual representation of data and information and displaying it in the form of graphs, dashboards, etc.

[0079] "Redistribution of work" refers to reviewing the tasks and roles assigned to each member and reassigning them efficiently and fairly.

[0080] "Suggestion" refers to the actions or changes recommended by a generative AI model or system to achieve a specific goal.

[0081] "Administrator" refers to a person who is responsible for operating the system and coordinating business operations, and who is responsible for considering and implementing proposals for business reallocation.

[0082] In an embodiment of the present invention, a system for efficiently and fairly managing the workload of each member in a remote work environment includes the following configuration.

[0083] Hardware and software used

[0084] Device:

[0085] Terminals are devices such as computers and smartphones used by each employee. Email clients, chat tools, and video conferencing tools are installed on the terminals. Examples of tools used include Outlook, Slack, Zoom, and MICROSOFT (registered trademark) TEAMS (registered trademark).

[0086] server:

[0087] The server is a backend system for collecting, storing, analyzing, visualizing, and redistributing data. Specifically, it includes database software (e.g., PostgreSQL) and generative AI models (e.g., GPT-4 (registered trademark)). Programming languages ​​such as Python and Node.js are also used.

[0088] Specific operation of the system

[0089] The device has a means of collecting communication metadata (email sending and receiving logs, number of chat messages, participation time in online meetings, etc.) and work schedule information for each employee. For example, it uses Outlook API to obtain email data and Slack API to collect chat data. This allows the device to regularly monitor each employee's detailed communication activities.

[0090] The collected data is periodically sent to a server, which receives it using WebSockets or HTTP POST requests and stores it in a database, where it is checked for format and cleansed if necessary.

[0091] The server uses a generative AI model based on the stored communication metadata and work schedule information to analyze each employee's busyness level. Specifically, a Python script is executed to provide the generative AI model with the following prompt: "Please estimate this employee's busyness level based on their communication metadata." The generative AI then uses a machine learning algorithm to calculate the busyness level, and the server receives the results.

[0092] The received busyness data is visualized using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript (registered trademark) to display each employee's busyness as a bar graph or dashboard. This allows users (employees and managers) to access the visualized data from their own devices and check their own workload and that of their entire team.

[0093] Based on the results of the busyness analysis, the server determines whether work redistribution is necessary and generates a redistribution proposal. For example, if work is concentrated on a specific employee, it will propose distributing that employee's tasks to other members. The generative AI model uses the following prompt: "Please suggest how to distribute employee A's tasks to other members."

[0094] These proposals are presented to the user, the administrator, who reviews the proposed redistribution and actually reallocates the tasks as necessary.

[0095] Specific examples

[0096] For example, if employee A is participating in many video conferences and handling many emails, the following might happen:

[0097] 1. The device uses the Outlook API and Zoom API to collect email and video conference data from Employee A.

[0098] 2. The device sends the collected data to the server at regular intervals.

[0099] 3. The server stores the received data in a database.

[0100] 4. The server passes the saved data to the generation AI to analyze the busyness of Employee A. An example of a prompt for the generation AI model is: "Please estimate this employee's busyness level from their communication metadata."

[0101] 5. The server visualizes the analysis results as graphs so that managers and employees can check them.

[0102] 6. The server makes a proposal to reallocate employee A’s tasks to employees B and C. An example of a prompt for the generative AI model: “Please suggest how employee A’s tasks should be distributed to other members.”

[0103] 7. The user administrator reviews the proposal and reallocates the work.

[0104] This enables efficient and fair distribution of work even in a remote work environment.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1:

[0107] The device collects communication metadata such as each employee's email sending and receiving history, number of chat messages, and participation time in video conferences. Specifically, the device uses the Outlook API to obtain the time of sending and receiving emails and the sender and receiver, and the number and frequency of chat messages using the Slack API. The start and end times of video conferences are obtained from the Zoom API and Microsoft Teams API.

[0108] Input: User communication activity data

[0109] Output: Collected communication metadata

[0110] Step 2:

[0111] The device sends the collected communication metadata and work schedule information to the server at regular intervals (for example, every hour). The data is sent using WebSocket or HTTP POST requests. Specifically, the device uses HTTP POST requests to send metadata to the server in JSON format.

[0112] Input: Collected communication metadata and work schedule information

[0113] Output: Data sent to the server

[0114] Step 3:

[0115] The server saves the communication metadata and work schedule information sent from the terminal in a database (e.g., PostgreSQL). Before saving, it checks the data format and whether it contains any invalid data. The server parses the JSON data and inserts it into the database using the SQL INSERT statement.

[0116] Input: Communication metadata and work schedule information received from the terminal

[0117] Output: Data stored in the database

[0118] Step 4:

[0119] The server uses a generative AI model (e.g., GPT-4) to analyze each employee's busyness level based on the stored communication metadata and work schedule information. It runs a Python script and prompts the generative AI model, saying, "Please estimate this employee's busyness level based on this employee's communication metadata." The generative AI evaluates each employee's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each employee's busyness level.

[0120] Input: Communications metadata and work schedule information retrieved from the database

[0121] Output: Busyness evaluation results by generated AI

[0122] Step 5:

[0123] The server visualizes the busyness data calculated by the generation AI as graphs and dashboards. The data is displayed visually using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness level as a bar graph or dashboard.

[0124] Input: Busyness evaluation results by generated AI

[0125] Output: Visualized graphs and dashboards

[0126] Step 6:

[0127] The server determines the need for work reallocation based on the results of the busyness analysis and generates a reallocation proposal. It sends a prompt to the generative AI model saying, "Please suggest how employee A's tasks should be distributed to other members." The generative AI then generates an optimal work reallocation proposal.

[0128] Input: Busyness evaluation results by generated AI

[0129] Output: Task reallocation proposals by generative AI

[0130] Step 7:

[0131] The user, an administrator, receives and implements the work reallocation proposals presented by the server. The proposals are displayed on a dashboard, and the administrator confirms them before implementing them. Specifically, the administrator clicks a button on the dashboard to reallocate specific work to another employee.

[0132] Input: Task redistribution proposal from the server

[0133] Output: The reallocation of work performed

[0134] This enables efficient and fair distribution of work even in a remote work environment.

[0135] (Application example 1)

[0136] 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."

[0137] In today's remote work environment, it is necessary to efficiently manage each member's workload and ensure fair work distribution. However, collecting and analyzing communication metadata and work schedule information is time-consuming and labor-intensive, and there are limitations to manual management. Furthermore, in factories and production facilities, it is important to understand the operating status of each piece of equipment and line in real time and optimally reallocate work, but this is also not easy. A system that can solve these problems is needed.

[0138] 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.

[0139] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for estimating the busyness of each member using a generation AI based on the collected communication metadata and work schedule information, means for visualizing the estimated busyness data, means for proposing work reallocation based on the busyness data, means for collecting operation data and maintenance schedule information, means for estimating the operation load of each piece of equipment, etc. using a generation AI, means for visualizing the estimated operation load data, and means for proposing work reallocation based on the operation load data. This enables efficient and fair work allocation and operation management both in remote work environments and within factories.

[0140] "Communication metadata" refers to data about each member's communication activities, such as email sending and receiving logs, number of chat messages, and participation time in video conferences.

[0141] "Work schedule information" is data indicating the work content and timetable of each member's scheduled work.

[0142] "Server" means a device or system that stores and analyzes communication metadata and work schedule information and processes the data using generative AI.

[0143] "Generative AI" is an artificial intelligence technology used to estimate each member's workload and workload using collected data.

[0144] "Busyness level" is an indicator of each member's workload, calculated by comprehensively evaluating the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences.

[0145] "Visualization" refers to displaying estimated busyness and operating load data in a visually easy-to-understand format, such as a graph or dashboard.

[0146] "Redistribution" refers to the adjustment of tasks or workloads that are concentrated on specific members or equipment to other members or equipment.

[0147] "Operation data" refers to data related to the operating status of each piece of equipment and line within the factory, such as operating time and workload.

[0148] "Maintenance schedule information" is data showing the maintenance and repair schedule for each piece of equipment.

[0149] The present invention relates to a system for efficiently managing the load of each member and each piece of equipment and achieving fair distribution in a remote work environment and in factory operation management. Specific embodiments of the present invention will be described in detail below.

[0150] Overall system picture

[0151] The system consists of multiple terminals and servers, and collects and manages each member's communication metadata and work schedule information, as well as factory operation data and maintenance schedule information. Generative AI is used to estimate and visualize the workload and operating load of each member and each piece of equipment. It also makes suggestions for reallocation if necessary.

[0152] Data collection

[0153] The devices periodically collect communication metadata such as email logs, chat message counts, and video conference participation times for each member. They also collect information on each member's work schedule, operational data, and maintenance schedule. The collected data is then sent to a server at regular intervals.

[0154] Data transmission and storage

[0155] The collected communication metadata, work schedule information, operation data, and maintenance schedule information are sent to a server and stored in a database. The server performs pre-processing to prepare this data in a format that can be analyzed by the generation AI.

[0156] Data analysis

[0157] The server uses a generation AI to analyze data based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The generation AI evaluates each member's communication volume, the congestion of their work schedule, the operation status of their equipment, the frequency of their maintenance schedule, etc., and estimates each member's "busyness level" and each piece of equipment's "operational load."

[0158] Data Visualization

[0159] The server converts the busyness and operating load data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing the load status of each member and each piece of equipment to be understood at a glance. Users can access these graphs and dashboards from their own devices to check their own workload and the operating status of their equipment.

[0160] Proposal for reallocation of work and operations

[0161] The server determines whether reallocation is necessary based on the busyness level and workload assessment. If necessary, it generates a reallocation proposal. For example, if work is concentrated on a specific member, it will propose distributing that member's tasks to other members who have more leeway. Also, if a specific piece of equipment is overworked, it will propose distributing that work to other equipment.

[0162] Implementation of reallocation

[0163] The administrator, who is the user, reviews the reallocation proposals presented by the server and actually reallocates the tasks. This process ensures fair and efficient business and operation management.

[0164] Specific examples of program processing

[0165] For example, if member A participates in many video conferences and processes a large number of emails, the system collects their communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates member A's busyness level as high. The server then visualizes the evaluation results as a graph, making member A's workload clear. The administrator can view the graph and receive suggestions for redistributing tasks to other members to reduce member A's workload, and then redistribute work based on the suggestions.

[0166] Prompt Sentence Examples

[0167] Your task is to balance the load on factory robots. Analyze the given metadata and schedule data to estimate the load on each robot. Visualize the data and propose a redistribution plan if any robots are overloaded.

[0168] This system enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] The terminal collects communication metadata such as email sending and receiving logs, chat message counts, and video conference participation time for each member, as well as work schedule information. This collection process is carried out periodically. The input data is communication metadata and work schedule information, and the output is the collected data.

[0172] Step 2:

[0173] The terminal transmits the collected communication metadata and work schedule information to the server. The input data is the collection result of the communication metadata and work schedule information, and the output is the transmission of these data to the server.

[0174] Step 3:

[0175] The server stores the received communication metadata and work schedule information in a database. The input data are the communication metadata and work schedule information sent to the server, and the output is these data stored in the server's database.

[0176] Step 4:

[0177] The server uses a generation AI to estimate the busyness of each member and the operational load of each piece of equipment based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The input data are the communication metadata, work schedule information, operation data, and maintenance schedule information stored in the database, and the output is the busyness and operational load estimation results obtained by the generation AI.

[0178] Step 5:

[0179] The server converts the busyness and workload data calculated by the generation AI into a visually easy-to-understand format. Specifically, it visualizes it in the form of a dashboard or graph. The input data is the estimated busyness and workload calculated by the generation AI, and the output is a visualized graph or dashboard.

[0180] Step 6:

[0181] Users can access the server's dashboard and graphs from their own devices to check their workload and the operating status of each piece of equipment. The input data is the visualized graphs and dashboard display content, and the output is what the user checks.

[0182] Step 7:

[0183] The server determines the need for reallocation based on the busyness and workload assessment, and generates a reallocation proposal as necessary. The input data is the busyness and workload estimation results by the generation AI, and the output is a reallocation proposal.

[0184] Step 8:

[0185] The user, the administrator, considers the redistribution proposals presented by the server and actually reallocates the tasks. The input data is the redistribution proposals presented by the server, and the output is the new configuration of the reallocated tasks.

[0186] This enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[0187] 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.

[0188] The present invention relates to a system that efficiently manages the workload of each member in a remote work environment and achieves fair work distribution, and further combines a function for recognizing user emotions. Specific embodiments of the present invention are described in detail below.

[0189] Overall system picture

[0190] This system collects communication metadata and work schedule information for each employee and uses generative AI to automatically estimate each member's "busyness level" and "emotional state." This makes the estimated results visible and suggests work redistribution and mental health care as needed. The overall process is as follows:

[0191] Data collection

[0192] The device periodically collects communication metadata and work schedule information, such as each employee's email sending and receiving logs, the number of chat messages, and the participation time in video conferences. It also uses an emotion engine to analyze the text content of users' emails and chats, as well as their voices and facial expressions during video conferences, to collect emotional data.

[0193] Data transmission and storage

[0194] The communication metadata, work schedule information, and emotion data collected by the device are sent to a server at regular intervals, where they are stored in a database for subsequent analysis.

[0195] Data analysis

[0196] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, and other factors to calculate each member's "busyness level." It also analyzes emotional data using an emotion engine to determine each member's "emotional state." For example, if text analysis reveals a high number of negative words, the member's emotional state is assessed as being highly stressed.

[0197] Data Visualization

[0198] The server converts the busyness data calculated by the generation AI and the emotional state determined by the emotion engine into a visually easy-to-understand format. This data is displayed in graph and dashboard format, allowing each member's workload and emotional state, as well as the overall team balance, to be understood at a glance. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and emotional state, as well as the overall team situation.

[0199] Work redistribution and mental health care proposals

[0200] The server generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or their emotional state is negative, the server will suggest distributing their tasks to other members who have more free time or suggest that they need mental care.

[0201] Reallocation and care delivery

[0202] The administrator, who is the user, considers the work redistribution and mental health care suggestions presented by the server and reallocates tasks to other members as necessary. For members who are recognized as being in a negative emotional state, the administrator takes appropriate mental health care measures, such as reducing their workload or providing access to mental health support.

[0203] Specific examples

[0204] For example, suppose Employee B is participating in many video conferences and processing a large number of emails. At the same time, if the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. The manager can then reallocate tasks to other members to reduce Employee B's burden and provide mental health support to Employee B as needed.

[0205] This system will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment, which is expected to improve overall productivity and employee satisfaction.

[0206] The processing flow will be explained below.

[0207] Step 1:

[0208] The devices collect communication metadata. Each employee's device periodically records information such as email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. Work schedule information is also collected. Data collection is performed in the background and is set up so as not to affect employees' normal work.

[0209] Step 2:

[0210] The device collects emotional data. It analyzes text content in emails and chats, as well as audio and video footage during video conferences, in real time and uses an emotion engine to estimate the user's emotional state. For example, text analysis can detect positive or negative words, and voice and facial expression analysis can assess signs of stress or fatigue.

[0211] Step 3:

[0212] The device sends communication metadata, work schedule information, and emotion data to a server. The collected data is securely sent to the server at regular intervals (e.g., every 30 minutes). The data is encrypted and protected from unauthorized access.

[0213] Step 4:

[0214] The server stores the received data in a database. The transmitted communication metadata, work schedule information, and emotion data are stored in the server's database and used for subsequent analysis. The data is indexed for efficient search.

[0215] Step 5:

[0216] The server analyzes the data and uses a generative AI model to calculate each member's "busyness level" and "emotional state" based on their communication volume, work schedule congestion, and emotional data. For example, the AI ​​model learns from past data and accurately predicts each member's workload and emotional state based on current data.

[0217] Step 6:

[0218] The server visualizes the analysis results. The generated busyness data and emotional state are converted into graphs and dashboards, visually displaying each member's status in an easy-to-understand manner. This allows managers and each member to understand their own workload and emotional state at a glance.

[0219] Step 7:

[0220] Users can check their workload data and emotional state. Each employee and manager can access the dashboard from their own device and visually check detailed analysis results. This allows them to quickly understand individual workloads, the overall team balance, and even the need for mental health care.

[0221] Step 8:

[0222] The server generates suggestions for work reallocation and mental care. Based on the analysis results of the generation AI and emotion engine, if work is concentrated on a specific member or if the emotional state is judged to be negative, the server automatically generates suggestions for work reallocation and mental care.

[0223] Step 9:

[0224] The administrator, who is the user, confirms and implements the proposals. Based on the work reallocation and mental care proposals presented by the server, the administrator reallocates tasks and provides mental care to each member. For example, they may reduce the tasks of members with a heavy workload, or refer members with negative emotional states to specialized mental health support.

[0225] In this way, this system aims to provide efficient and fair work distribution and appropriate mental care by integrating and analyzing communication metadata, work schedule information, and emotional data.

[0226] Example 2

[0227] 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."

[0228] In today's remote work environment, the challenge is to efficiently manage each member's workload, distribute work fairly, and provide appropriate mental health care. Direct observation is particularly difficult in a remote environment, making it difficult to accurately grasp each member's workload and emotional state. To address this issue, a system is needed that comprehensively analyzes not only communication metadata and work schedule information, but also emotional data, to appropriately reallocate work and provide mental health care.

[0229] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication metadata, work schedule information, and emotion data, means for estimating the busyness level and emotional state of each member using a generation algorithm based on the collected data, means for visualizing the estimated busyness data and emotional state data, and means for redistributing work and proposing mental care based on the data. This enables efficient and fair work distribution and appropriate mental care even in a remote work environment.

[0230] "Communication metadata" refers to various data related to communication, such as email sending and receiving logs, the number of chat messages, and the duration of video calls.

[0231] "Work schedule information" is schedule data related to work, such as each member's plans and tasks, and meeting schedules.

[0232] "Emotion data" is data that indicates the user's emotional state, and includes information analyzed from text, voice, and facial expressions.

[0233] The "server" is a computer system that collects, stores, and analyzes communication metadata, work schedule information, and emotion data, and visualizes and proposes the results.

[0234] A "generative algorithm" is a program that uses a machine learning algorithm to generate a specific output (such as busyness or emotional state) from input data.

[0235] "Busyness" is an index that indicates the workload of each member, and is calculated based on communication metadata and work schedule information.

[0236] "Emotional state" is an indicator that shows each member's emotional and psychological state, and is analyzed based on emotional data.

[0237] "Visualization" means converting the analysis results into graphs or dashboards and displaying them in a way that is visually easy to understand.

[0238] "Work reallocation" means reallocating tasks to other members in order to reduce or adjust the workload on a particular member.

[0239] "Mental care proposals" means presenting psychological support and mental health care measures based on each member's emotional state.

[0240] This invention is a system that manages workloads and distributes tasks fairly in a remote work environment, and also has the function of managing the user's emotional state. This system is characterized by comprehensively collecting and analyzing communication metadata, work schedule information, and emotional data, and proposing work redistribution and mental care.

[0241] First, the device collects data related to each member's daily work. Communication metadata includes email sending and receiving logs, the number of chat messages, and the duration of video calls. Work schedule information is also obtained from calendar systems and other sources. Furthermore, an emotion engine is used to collect user emotion data from text, voice, and facial expressions. Natural language processing algorithms and speech recognition technology are used for analysis by this emotion engine.

[0242] The collected communication metadata, work schedule information, and emotion data are temporarily stored and then sent to a server at regular intervals. The server receives this data and stores it in a database. Communication is carried out using the HTTPS protocol, and all data is encrypted.

[0243] The server then uses a generation algorithm to analyze the collected data. The generation algorithm uses a machine learning algorithm to calculate the "busyness level" based on each member's communication volume, work schedule congestion, frequency of meetings, etc. Furthermore, the emotion engine analyzes the user's "emotional state" from email and chat text and audio during video conferences to generate indicators.

[0244] The analysis results are visualized by the server in the form of graphs and dashboards using graph generation libraries such as D3.js and Chart.js. Users can access these graphs and dashboards from their own devices to check the workload and emotional state of themselves and their entire team.

[0245] The server also generates suggestions for work redistribution and mental health care based on the analysis results. For example, if a member is very busy and in a negative emotional state, it will suggest reassigning that member's tasks to another member. Furthermore, if mental health care is needed, it will provide specific actions and support information.

[0246] As a specific example, consider a case where Employee B participates in numerous video conferences and processes a lot of emails. If the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server then evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. To reduce Employee B's burden, the manager can reallocate tasks to other members and provide mental health support to Employee B as needed.

[0247] Example prompt: "Please explain your system for efficiently managing each member's workload and emotional state in a remote work environment. Please provide detailed information, including specific data collection methods, data transmission and storage methods, data analysis methods, data visualization methods, work redistribution and mental health care proposal methods, and implementation methods. Please also provide specific examples."

[0248] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0249] Step 1:

[0250] The device periodically collects communication metadata (email sending and receiving logs, number of chat messages, and participation time in video calls) and work schedule information for each member. It also uses an emotion engine to collect emotional data from the user's text, voice, and facial expressions. Specifically, the device records logs of each communication method during working hours, and the emotion engine performs text analysis in real time and uses speech recognition technology to analyze audio during video conferences.

[0251] Input: Each member's communication data, work schedule, user text, voice, and facial expressions

[0252] Output: communication metadata, work schedule information, emotion data

[0253] Step 2:

[0254] The device sends the collected communication metadata, work schedule information, and emotion data to the server at regular intervals (e.g., once a day). Specifically, the device encrypts the temporarily stored data and uploads it to the server using the HTTPS protocol.

[0255] Input: communication metadata, work schedule information, emotion data

[0256] Output: Data sent to the server

[0257] Step 3:

[0258] The server receives the transmitted communication metadata, work schedule information, and emotion data and stores them in a database. Specifically, the server decodes the received data and stores them in the corresponding databases (for communication metadata, work schedule data, and emotion data).

[0259] Input: Data sent from the terminal

[0260] Output: Data stored in the database

[0261] Step 4:

[0262] The server analyzes data using a generation algorithm based on the stored communication metadata and work schedule information. The generation algorithm evaluates each member's communication volume, schedule congestion, frequency of meetings, etc., and calculates their "busyness level." It also uses an emotion engine to analyze the "emotional state" from the emotional data and generate an index. Specifically, the server runs an automated script and inputs the data into the analysis algorithm.

[0263] Input: Communication metadata, work schedule information, and emotion data stored in the database

[0264] Output: Busyness and emotional state of each member

[0265] Step 5:

[0266] The server converts the busyness level calculated by the generation algorithm and the emotional state analyzed by the emotion engine into a visually easy-to-understand format. Specifically, the server uses a graph generation library (such as D3.js or Chart.js) to convert the analysis results into a graph or dashboard format and display them on a web dashboard.

[0267] Input: Each member's busyness and emotional state

[0268] Output: Visualized data in the form of graphs and dashboards

[0269] Step 6:

[0270] The administrator, who is the user, checks and implements work reallocation and mental care suggestions based on the visualized data displayed by the server. Specifically, the administrator accesses the web dashboard and clicks on a work reallocation instruction to reallocate tasks or provide mental care support information.

[0271] Input: Visualized data displayed on the web dashboard

[0272] Output: Actual tasks reallocated and mental health support provided

[0273] This will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment.

[0274] (Application example 2)

[0275] 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."

[0276] In remote work and factory environments, it is extremely important to efficiently manage the workload and emotional state of each member and operator. However, conventional systems have made it difficult to properly evaluate workload and emotional state, and to implement fair work distribution and mental care. In particular, there is a demand for a function that can analyze operator work data and communication logs in real time and immediately reflect the situation.

[0277] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0278] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for analyzing emotional data, means for estimating the busyness and emotional state of each member using a generating AI based on the collected communication metadata, work schedule information, and emotional data, means for visualizing the estimated busyness data and emotional state, means for proposing work redistribution and mental care based on the data, and means for displaying information in real time on a device worn by an operator. This makes it possible to efficiently and fairly manage the busyness and emotional state of each member and operator and to immediately implement improvement proposals.

[0279] "Communication metadata" refers to data such as email sending and receiving logs, number of chat messages, participation time in video conferences, operator work data and communication logs.

[0280] "Work schedule information" refers to schedule data such as work plans and meeting schedules for each member or operator.

[0281] "Server" refers to a central processing unit for receiving, storing, and analyzing data to estimate each member's busyness and emotional state.

[0282] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze each member's communication metadata, work schedule information, and emotional data.

[0283] "Busyness level" refers to an indicator that shows the amount of work and workload each member or operator is handling.

[0284] "Emotional state" refers to data used to assess the mental health and emotional fluctuations of each member or operator.

[0285] "Emotional data" refers to data about an individual's emotions analyzed from voice, facial expressions, verbal content, etc.

[0286] "Real-time display" refers to the function of instantly processing data and providing instant feedback to devices worn by each member or operator.

[0287] "Work reallocation" refers to a proposal to allocate work to other members in order to optimize the workload of each member or operator.

[0288] "Mental care suggestions" refer to suggestions based on emotional data to maintain and improve the mental health of each member or operator.

[0289] The system for implementing this invention is designed to enable employees and operators to efficiently manage their workload and emotional state. Its main components include a terminal that collects communication metadata and work schedule information, a server that analyzes, stores, and visualizes the data, and a user device that provides final suggestions and feedback.

[0290] Data collection

[0291] The device collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. Each member's work schedule information is also collected periodically. Furthermore, emotional data is analyzed from the operator's facial expressions and voice using a camera and microphone. Smart glasses or smartphones are used as the device.

[0292] Data transmission and storage

[0293] All data collected by the device is sent to the server at regular intervals. The server has a database where the received data is stored and used for subsequent analysis. Data is sent using the HTTP protocol.

[0294] Based on this data, the server analyzes each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., and estimates each member's "busyness level" and "emotional state."

[0295] Data analysis

[0296] The server first uses a generative AI model to analyze the collected communication metadata and work schedule information to calculate each member's busy level. It then uses an emotion engine to analyze the emotional data and determine each member's emotional state. Specifically, it uses natural language processing (NLP) technology and machine learning algorithms.

[0297] Data Visualization

[0298] The server converts the busyness data calculated by the generative AI and the emotional state identified by the emotion engine into a visually easy-to-understand format. This data is displayed in graphs and dashboards and fed back in real time to user devices such as smart glasses, smartphones, and PCs, allowing users and administrators to understand the situation at a glance.

[0299] Work redistribution and mental health care proposals

[0300] The server automatically generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or if that member's emotional state is negative, the server will suggest reallocating that work to other members who have more time. Furthermore, if mental care is needed, the server will suggest providing mental health support.

[0301] Reallocation and care delivery

[0302] The administrator, who is the user, can reallocate work based on this suggestion. Appropriate mental health care measures can also be taken for members whose emotional state is judged to be negative. For example, if employee B participates in many video conferences and handles a large number of emails, and the emotion engine detects high stress levels from employee B's chat messages and comments during video conferences, the server will suggest reallocating employee B's work to other members.

[0303] Examples of concrete examples and prompts

[0304] For example, if factory operator A works long hours on the day shift and data from smart glasses indicates that A's stress level is high, the following prompts can be input into the generative AI:

[0305] "Operator A's workload is high and his emotional state is negative. How would you redistribute his work and suggest appropriate mental health care?"

[0306] This allows the generative AI to propose specific work redistribution and mental care measures, making it possible to balance factory productivity with employee health.

[0307] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0308] Step 1:

[0309] The device periodically collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. In addition, it uses a camera and microphone to capture the operator's facial expressions and voice to obtain emotion data.

[0310] Input: communication metadata, facial expression data, voice data

[0311] Output: Collected communication metadata, emotion data

[0312] Step 2:

[0313] The device sends the collected communication metadata, emotion data, and work schedule information to a server via HTTP, which then receives and stores the data in a database.

[0314] Input: Collected communication metadata, emotion data, work schedule information

[0315] Output: Collected data stored in a database

[0316] Step 3:

[0317] The server uses a generative AI model to analyze communication metadata and work schedule information stored in the database to calculate each member's busy level, and an emotion engine to analyze emotion data and determine each member's emotional state.

[0318] Input: communication metadata, work schedule information, emotion data

[0319] Output: Calculated busyness data, emotional state data

[0320] Step 4:

[0321] The server converts the calculated busyness data and emotional state data into a visually easy-to-understand format and visualizes it in the form of graphs, dashboards, etc. This display information is sent in real time to user devices such as smart glasses, smartphones, and PCs.

[0322] Input: Busyness data, emotional state data

[0323] Output: Visualized graphs and dashboard information

[0324] Step 5:

[0325] The server then uses the analysis results to propose work redistribution and mental care, using a generative AI model to generate proposals for redistribution when a specific member's workload is high, or for mental care when the member's emotional state is negative.

[0326] Input: Busyness data, emotional state data

[0327] Output: Work reallocation proposals, mental care proposals

[0328] Step 6:

[0329] The administrator, who is the user, reviews the proposals sent from the server and reallocates work as necessary. Appropriate mental care measures are also taken for members with negative emotional states. For example, if high stress is detected in Operator A, a proposal is displayed based on a prompt from the generation AI: "Operator A's workload is high and his emotional state is negative. How would you reallocate work and suggest appropriate mental care?"

[0330] Input: Work reallocation proposals, mental care proposals

[0331] Output: Reallocated tasks, mental health measures implemented

[0332] 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.

[0333] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0334] 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.

[0335] [Second embodiment]

[0336] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0337] 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.

[0338] 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).

[0339] 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.

[0340] 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.

[0341] 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).

[0342] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0343] 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.

[0344] 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.

[0345] 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.

[0346] 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.

[0347] 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."

[0348] The present invention relates to a system for efficiently managing the workload of each member in a remote work environment and achieving fair work distribution. Specific embodiments of the present invention will be described in detail below.

[0349] Overall system picture

[0350] The system collects communication metadata and work schedule information for all employees and uses generative AI to automatically estimate each member's "busyness level." The estimated results are visualized, and if work needs to be reallocated, suggestions are made. The overall process is as follows:

[0351] Data collection

[0352] The devices periodically collect communication metadata, such as each employee's email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. They also collect each employee's work schedule. This data is sent to a server at regular intervals. The collected data includes the time each email was sent and received, the recipient and sender, the number and frequency of chat messages, and the start and end times of video conferences.

[0353] Data transmission and storage

[0354] The communication metadata and work schedule information sent from the device are stored on the server, which then stores this data in a database and prepares it for analysis by the generation AI.

[0355] Data analysis

[0356] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each member's "busyness level." For example, if a member sends and receives a lot of emails and spends a lot of time participating in video conferences, the member's busyness level will be evaluated as high.

[0357] Data Visualization

[0358] The server converts the busyness data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing users to understand at a glance the busyness of each member and the overall work balance of the team. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and the overall status of the team.

[0359] Proposal for business reallocation

[0360] The server determines whether work needs to be redistributed based on the busyness assessment. If necessary, it generates a proposal for work redistribution. For example, if work is concentrated on a specific member, it proposes distributing that member's tasks to other members who have more free time.

[0361] Implementation of reallocation

[0362] The administrator, who is the user, reviews the work reallocation proposals presented by the server and actually reallocates the tasks. This process results in a fair and efficient work distribution.

[0363] Specific examples

[0364] For example, if Employee A participates in many video conferences and processes a large number of emails, the system collects communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates Employee A's busyness level as high. The server then visualizes the evaluation results as a graph, making Employee A's workload clear. The manager can then view the graph and receive suggestions for redistributing tasks to other employees to reduce Employee A's workload, and redistribute work based on these suggestions.

[0365] This system enables efficient and fair distribution of work even in a remote work environment.

[0366] The processing flow will be explained below.

[0367] Step 1:

[0368] The device collects communication metadata. For example, an employee's device periodically records information such as email logs, chat message counts, and video conference participation time. Each employee's device is configured to run this process in the background.

[0369] Step 2:

[0370] The device sends communication metadata and work schedule information to the server. The collected data is sent to the server at regular intervals (e.g., every hour). The data is encrypted and reaches the server securely.

[0371] Step 3:

[0372] The server stores the received data in a database. The transmitted communication metadata and work schedule information are stored in the database and used for subsequent analysis.

[0373] Step 4:

[0374] The server analyzes communication metadata and work schedule information. Using a generative AI model, it evaluates each member's communication volume and the density of their work schedule, and calculates their "busyness level." For example, the AI ​​model can learn features such as the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences, and then predict the optimal busyness level.

[0375] Step 5:

[0376] The server visualizes the calculated busyness data, which is converted into graphs and dashboards, allowing users to see at a glance the workload of each member and the overall team balance.

[0377] Step 6:

[0378] Users can check their busyness data. Each member and administrator can access the data from their own device and visually check their own busyness level and the overall team status on a dashboard or graph.

[0379] Step 7:

[0380] The server generates proposals for work reallocation. Based on the analysis results of the generation AI, if work is concentrated on a specific member, a proposal for work reallocation is created.

[0381] Step 8:

[0382] The administrator, who is the user, checks and implements the redistribution proposal. The administrator reviews the work redistribution proposal presented by the server and instructs other members to reallocate tasks as necessary. As a result, a fair and efficient work balance is achieved.

[0383] Example 1

[0384] 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."

[0385] In a remote work environment, it is difficult to manage each member's workload efficiently and fairly. In particular, it is necessary to accurately grasp the level of workload and allocate tasks appropriately to each member, but current manual management has its limitations. In addition, since data collection and analysis are insufficient, it is difficult to propose appropriate task reallocation.

[0386] 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.

[0387] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for transmitting the collected communication metadata and work schedule information to the server, means for estimating the busyness level of each member using a generative AI model based on the data, means for visualizing the estimated busyness data, means for proposing work redistribution based on the busyness data, and means for a manager to implement the proposed work redistribution. This makes it possible to efficiently and fairly manage the workload of each member and appropriately redistribute work even in a remote work environment.

[0388] "Communication metadata" refers to data about communication activities, such as email sending and receiving logs, number of chat messages, and participation time in online meetings.

[0389] "Work schedule information" refers to information about the allocation of time related to work, such as each member's plans, tasks, and meeting schedules.

[0390] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and generate results that fit a specific purpose.

[0391] "Busyness" refers to the degree of workload of each member, and is an indicator evaluated based on factors such as communication volume and the density of work schedules.

[0392] "Visualization" refers to the visual representation of data and information and displaying it in the form of graphs, dashboards, etc.

[0393] "Redistribution of work" refers to reviewing the tasks and roles assigned to each member and reassigning them efficiently and fairly.

[0394] "Suggestion" refers to the actions or changes recommended by a generative AI model or system to achieve a specific goal.

[0395] "Administrator" refers to a person who is responsible for operating the system and coordinating business operations, and who is responsible for considering and implementing proposals for business reallocation.

[0396] In an embodiment of the present invention, a system for efficiently and fairly managing the workload of each member in a remote work environment includes the following configuration.

[0397] Hardware and software used

[0398] Device:

[0399] Terminals are devices such as computers and smartphones used by each employee. Email clients, chat tools, and video conferencing tools are installed on the terminals. Examples of tools used include Outlook, Slack, Zoom, and Microsoft Teams.

[0400] server:

[0401] The server is a backend system for collecting, storing, analyzing, visualizing, and redistributing data. Specifically, it includes database software (e.g., PostgreSQL) and generative AI models (e.g., GPT-4). Programming languages ​​such as Python and Node.js are also used.

[0402] Specific operation of the system

[0403] The device has a means of collecting communication metadata (email sending and receiving logs, number of chat messages, participation time in online meetings, etc.) and work schedule information for each employee. For example, it uses Outlook API to obtain email data and Slack API to collect chat data. This allows the device to regularly monitor each employee's detailed communication activities.

[0404] The collected data is periodically sent to a server, which receives it using WebSockets or HTTP POST requests and stores it in a database, where it is checked for format and cleansed if necessary.

[0405] The server uses a generative AI model based on the stored communication metadata and work schedule information to analyze each employee's busyness level. Specifically, a Python script is executed to provide the generative AI model with the following prompt: "Please estimate this employee's busyness level based on their communication metadata." The generative AI then uses a machine learning algorithm to calculate the busyness level, and the server receives the results.

[0406] The received busyness data is visualized using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness as a bar graph or dashboard. This allows users (individual employees and managers) to access the visualized data from their own devices and check their own workload and that of the entire team.

[0407] Based on the results of the busyness analysis, the server determines whether work redistribution is necessary and generates a redistribution proposal. For example, if work is concentrated on a specific employee, it will propose distributing that employee's tasks to other members. The generative AI model uses the following prompt: "Please suggest how to distribute employee A's tasks to other members."

[0408] These proposals are presented to the user, the administrator, who reviews the proposed redistribution and actually reallocates the tasks as necessary.

[0409] Specific examples

[0410] For example, if employee A is participating in many video conferences and handling many emails, the following might happen:

[0411] 1. The device uses the Outlook API and Zoom API to collect email and video conference data from Employee A.

[0412] 2. The device sends the collected data to the server at regular intervals.

[0413] 3. The server stores the received data in a database.

[0414] 4. The server passes the saved data to the generation AI to analyze the busyness of Employee A. An example of a prompt for the generation AI model is: "Please estimate this employee's busyness level from their communication metadata."

[0415] 5. The server visualizes the analysis results as graphs so that managers and employees can check them.

[0416] 6. The server makes a proposal to reallocate employee A’s tasks to employees B and C. An example of a prompt for the generative AI model: “Please suggest how employee A’s tasks should be distributed to other members.”

[0417] 7. The user administrator reviews the proposal and reallocates the work.

[0418] This enables efficient and fair distribution of work even in a remote work environment.

[0419] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0420] Step 1:

[0421] The device collects communication metadata such as each employee's email sending and receiving history, number of chat messages, and participation time in video conferences. Specifically, the device uses the Outlook API to obtain the time of sending and receiving emails and the sender and receiver, and the number and frequency of chat messages using the Slack API. The start and end times of video conferences are obtained from the Zoom API and Microsoft Teams API.

[0422] Input: User communication activity data

[0423] Output: Collected communication metadata

[0424] Step 2:

[0425] The device sends the collected communication metadata and work schedule information to the server at regular intervals (for example, every hour). The data is sent using WebSocket or HTTP POST requests. Specifically, the device uses HTTP POST requests to send metadata to the server in JSON format.

[0426] Input: Collected communication metadata and work schedule information

[0427] Output: Data sent to the server

[0428] Step 3:

[0429] The server saves the communication metadata and work schedule information sent from the terminal in a database (e.g., PostgreSQL). Before saving, it checks the data format and whether it contains any invalid data. The server parses the JSON data and inserts it into the database using the SQL INSERT statement.

[0430] Input: Communication metadata and work schedule information received from the terminal

[0431] Output: Data stored in the database

[0432] Step 4:

[0433] The server uses a generative AI model (e.g., GPT-4) to analyze each employee's busyness level based on the stored communication metadata and work schedule information. It runs a Python script and prompts the generative AI model, saying, "Please estimate this employee's busyness level based on this employee's communication metadata." The generative AI evaluates each employee's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each employee's busyness level.

[0434] Input: Communications metadata and work schedule information retrieved from the database

[0435] Output: Busyness evaluation results by generated AI

[0436] Step 5:

[0437] The server visualizes the busyness data calculated by the generation AI as graphs and dashboards. The data is displayed visually using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness level as a bar graph or dashboard.

[0438] Input: Busyness evaluation results by generated AI

[0439] Output: Visualized graphs and dashboards

[0440] Step 6:

[0441] The server determines the need for work reallocation based on the results of the busyness analysis and generates a reallocation proposal. It sends a prompt to the generative AI model saying, "Please suggest how employee A's tasks should be distributed to other members." The generative AI then generates an optimal work reallocation proposal.

[0442] Input: Busyness evaluation results by generated AI

[0443] Output: Task reallocation proposals by generative AI

[0444] Step 7:

[0445] The user, an administrator, receives and implements the work reallocation proposals presented by the server. The proposals are displayed on a dashboard, and the administrator confirms them before implementing them. Specifically, the administrator clicks a button on the dashboard to reallocate specific work to another employee.

[0446] Input: Task redistribution proposal from the server

[0447] Output: The reallocation of work performed

[0448] This enables efficient and fair distribution of work even in a remote work environment.

[0449] (Application example 1)

[0450] 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."

[0451] In today's remote work environment, it is necessary to efficiently manage each member's workload and ensure fair work distribution. However, collecting and analyzing communication metadata and work schedule information is time-consuming and labor-intensive, and there are limitations to manual management. Furthermore, in factories and production facilities, it is important to understand the operating status of each piece of equipment and line in real time and optimally reallocate work, but this is also not easy. A system that can solve these problems is needed.

[0452] 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.

[0453] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for estimating the busyness of each member using a generation AI based on the collected communication metadata and work schedule information, means for visualizing the estimated busyness data, means for proposing work reallocation based on the busyness data, means for collecting operation data and maintenance schedule information, means for estimating the operation load of each piece of equipment, etc. using a generation AI, means for visualizing the estimated operation load data, and means for proposing work reallocation based on the operation load data. This enables efficient and fair work allocation and operation management both in remote work environments and within factories.

[0454] "Communication metadata" refers to data about each member's communication activities, such as email sending and receiving logs, number of chat messages, and participation time in video conferences.

[0455] "Work schedule information" is data indicating the work content and timetable of each member's scheduled work.

[0456] "Server" means a device or system that stores and analyzes communication metadata and work schedule information and processes the data using generative AI.

[0457] "Generative AI" is an artificial intelligence technology used to estimate each member's workload and workload using collected data.

[0458] "Busyness level" is an indicator of each member's workload, calculated by comprehensively evaluating the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences.

[0459] "Visualization" refers to displaying estimated busyness and operating load data in a visually easy-to-understand format, such as a graph or dashboard.

[0460] "Redistribution" refers to the adjustment of tasks or workloads that are concentrated on specific members or equipment to other members or equipment.

[0461] "Operation data" refers to data related to the operating status of each piece of equipment and line within the factory, such as operating time and workload.

[0462] "Maintenance schedule information" is data showing the maintenance and repair schedule for each piece of equipment.

[0463] The present invention relates to a system for efficiently managing the load of each member and each piece of equipment and achieving fair distribution in a remote work environment and in factory operation management. Specific embodiments of the present invention will be described in detail below.

[0464] Overall system picture

[0465] The system consists of multiple terminals and servers, and collects and manages each member's communication metadata and work schedule information, as well as factory operation data and maintenance schedule information. Generative AI is used to estimate and visualize the workload and operating load of each member and each piece of equipment. It also makes suggestions for reallocation if necessary.

[0466] Data collection

[0467] The devices periodically collect communication metadata such as email logs, chat message counts, and video conference participation times for each member. They also collect information on each member's work schedule, operational data, and maintenance schedule. The collected data is then sent to a server at regular intervals.

[0468] Data transmission and storage

[0469] The collected communication metadata, work schedule information, operation data, and maintenance schedule information are sent to a server and stored in a database. The server performs pre-processing to prepare this data in a format that can be analyzed by the generation AI.

[0470] Data analysis

[0471] The server uses a generation AI to analyze data based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The generation AI evaluates each member's communication volume, the congestion of their work schedule, the operation status of their equipment, the frequency of their maintenance schedule, etc., and estimates each member's "busyness level" and each piece of equipment's "operational load."

[0472] Data Visualization

[0473] The server converts the busyness and operating load data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing the load status of each member and each piece of equipment to be understood at a glance. Users can access these graphs and dashboards from their own devices to check their own workload and the operating status of their equipment.

[0474] Proposal for reallocation of work and operations

[0475] The server determines whether reallocation is necessary based on the busyness level and workload assessment. If necessary, it generates a reallocation proposal. For example, if work is concentrated on a specific member, it will propose distributing that member's tasks to other members who have more leeway. Also, if a specific piece of equipment is overworked, it will propose distributing that work to other equipment.

[0476] Implementation of reallocation

[0477] The administrator, who is the user, reviews the reallocation proposals presented by the server and actually reallocates the tasks. This process ensures fair and efficient business and operation management.

[0478] Specific examples of program processing

[0479] For example, if member A participates in many video conferences and processes a large number of emails, the system collects their communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates member A's busyness level as high. The server then visualizes the evaluation results as a graph, making member A's workload clear. The administrator can view the graph and receive suggestions for redistributing tasks to other members to reduce member A's workload, and then redistribute work based on the suggestions.

[0480] Prompt Sentence Examples

[0481] Your task is to balance the load on factory robots. Analyze the given metadata and schedule data to estimate the load on each robot. Visualize the data and propose a redistribution plan if any robots are overloaded.

[0482] This system enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[0483] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0484] Step 1:

[0485] The terminal collects communication metadata such as email sending and receiving logs, chat message counts, and video conference participation time for each member, as well as work schedule information. This collection process is carried out periodically. The input data is communication metadata and work schedule information, and the output is the collected data.

[0486] Step 2:

[0487] The terminal transmits the collected communication metadata and work schedule information to the server. The input data is the collection result of the communication metadata and work schedule information, and the output is the transmission of these data to the server.

[0488] Step 3:

[0489] The server stores the received communication metadata and work schedule information in a database. The input data are the communication metadata and work schedule information sent to the server, and the output is these data stored in the server's database.

[0490] Step 4:

[0491] The server uses a generation AI to estimate the busyness of each member and the operational load of each piece of equipment based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The input data are the communication metadata, work schedule information, operation data, and maintenance schedule information stored in the database, and the output is the busyness and operational load estimation results obtained by the generation AI.

[0492] Step 5:

[0493] The server converts the busyness and workload data calculated by the generation AI into a visually easy-to-understand format. Specifically, it visualizes it in the form of a dashboard or graph. The input data is the estimated busyness and workload calculated by the generation AI, and the output is a visualized graph or dashboard.

[0494] Step 6:

[0495] Users can access the server's dashboard and graphs from their own devices to check their workload and the operating status of each piece of equipment. The input data is the visualized graphs and dashboard display content, and the output is what the user checks.

[0496] Step 7:

[0497] The server determines the need for reallocation based on the busyness and workload assessment, and generates a reallocation proposal as necessary. The input data is the busyness and workload estimation results by the generation AI, and the output is a reallocation proposal.

[0498] Step 8:

[0499] The user, the administrator, considers the redistribution proposals presented by the server and actually reallocates the tasks. The input data is the redistribution proposals presented by the server, and the output is the new configuration of the reallocated tasks.

[0500] This enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[0501] 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.

[0502] The present invention relates to a system that efficiently manages the workload of each member in a remote work environment and achieves fair work distribution, and further combines a function for recognizing user emotions. Specific embodiments of the present invention are described in detail below.

[0503] Overall system picture

[0504] This system collects communication metadata and work schedule information for each employee and uses generative AI to automatically estimate each member's "busyness level" and "emotional state." This makes the estimated results visible and suggests work redistribution and mental health care as needed. The overall process is as follows:

[0505] Data collection

[0506] The device periodically collects communication metadata and work schedule information, such as each employee's email sending and receiving logs, the number of chat messages, and the participation time in video conferences. It also uses an emotion engine to analyze the text content of users' emails and chats, as well as their voices and facial expressions during video conferences, to collect emotional data.

[0507] Data transmission and storage

[0508] The communication metadata, work schedule information, and emotion data collected by the device are sent to a server at regular intervals, where they are stored in a database for subsequent analysis.

[0509] Data analysis

[0510] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, and other factors to calculate each member's "busyness level." It also analyzes emotional data using an emotion engine to determine each member's "emotional state." For example, if text analysis reveals a high number of negative words, the member's emotional state is assessed as being highly stressed.

[0511] Data Visualization

[0512] The server converts the busyness data calculated by the generation AI and the emotional state determined by the emotion engine into a visually easy-to-understand format. This data is displayed in graph and dashboard format, allowing each member's workload and emotional state, as well as the overall team balance, to be understood at a glance. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and emotional state, as well as the overall team situation.

[0513] Work redistribution and mental health care proposals

[0514] The server generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or their emotional state is negative, the server will suggest distributing their tasks to other members who have more free time or suggest that they need mental care.

[0515] Reallocation and care delivery

[0516] The administrator, who is the user, considers the work redistribution and mental health care suggestions presented by the server and reallocates tasks to other members as necessary. For members who are recognized as being in a negative emotional state, the administrator takes appropriate mental health care measures, such as reducing their workload or providing access to mental health support.

[0517] Specific examples

[0518] For example, suppose Employee B is participating in many video conferences and processing a large number of emails. At the same time, if the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. The manager can then reallocate tasks to other members to reduce Employee B's burden and provide mental health support to Employee B as needed.

[0519] This system will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment, which is expected to improve overall productivity and employee satisfaction.

[0520] The processing flow will be explained below.

[0521] Step 1:

[0522] The devices collect communication metadata. Each employee's device periodically records information such as email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. Work schedule information is also collected. Data collection is performed in the background and is set up so as not to affect employees' normal work.

[0523] Step 2:

[0524] The device collects emotional data. It analyzes text content in emails and chats, as well as audio and video footage during video conferences, in real time and uses an emotion engine to estimate the user's emotional state. For example, text analysis can detect positive or negative words, and voice and facial expression analysis can assess signs of stress or fatigue.

[0525] Step 3:

[0526] The device sends communication metadata, work schedule information, and emotion data to a server. The collected data is securely sent to the server at regular intervals (e.g., every 30 minutes). The data is encrypted and protected from unauthorized access.

[0527] Step 4:

[0528] The server stores the received data in a database. The transmitted communication metadata, work schedule information, and emotion data are stored in the server's database and used for subsequent analysis. The data is indexed for efficient search.

[0529] Step 5:

[0530] The server analyzes the data and uses a generative AI model to calculate each member's "busyness level" and "emotional state" based on their communication volume, work schedule congestion, and emotional data. For example, the AI ​​model learns from past data and accurately predicts each member's workload and emotional state based on current data.

[0531] Step 6:

[0532] The server visualizes the analysis results. The generated busyness data and emotional state are converted into graphs and dashboards, visually displaying each member's status in an easy-to-understand manner. This allows managers and each member to understand their own workload and emotional state at a glance.

[0533] Step 7:

[0534] Users can check their workload data and emotional state. Each employee and manager can access the dashboard from their own device and visually check detailed analysis results. This allows them to quickly understand individual workloads, the overall team balance, and even the need for mental care.

[0535] Step 8:

[0536] The server generates suggestions for work reallocation and mental care. Based on the analysis results of the generation AI and emotion engine, if work is concentrated on a specific member or if the emotional state is judged to be negative, the server automatically generates suggestions for work reallocation and mental care.

[0537] Step 9:

[0538] The administrator, who is the user, confirms and implements the proposals. Based on the work reallocation and mental care proposals presented by the server, the administrator reassigns tasks and provides mental care to each member. For example, they may reduce the tasks of members with a heavy workload, or refer members with negative emotional states to specialized mental health support.

[0539] In this way, this system aims to provide efficient and fair work distribution and appropriate mental care by integrating and analyzing communication metadata, work schedule information, and emotional data.

[0540] Example 2

[0541] 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."

[0542] In today's remote work environment, the challenge is to efficiently manage each member's workload, distribute work fairly, and provide appropriate mental health care. Direct observation is particularly difficult in a remote environment, making it difficult to accurately grasp each member's workload and emotional state. To address this issue, a system is needed that comprehensively analyzes not only communication metadata and work schedule information, but also emotional data, to appropriately reallocate work and provide mental health care.

[0543] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication metadata, work schedule information, and emotion data, means for estimating the busyness level and emotional state of each member using a generation algorithm based on the collected data, means for visualizing the estimated busyness data and emotional state data, and means for redistributing work and proposing mental care based on the data. This enables efficient and fair work distribution and appropriate mental care even in a remote work environment.

[0544] "Communication metadata" refers to various data related to communication, such as email sending and receiving logs, the number of chat messages, and the duration of video calls.

[0545] "Work schedule information" is schedule data related to work, such as each member's plans and tasks, and meeting schedules.

[0546] "Emotion data" is data that indicates the user's emotional state, and includes information analyzed from text, voice, and facial expressions.

[0547] The "server" is a computer system that collects, stores, and analyzes communication metadata, work schedule information, and emotion data, and visualizes and proposes the results.

[0548] A "generative algorithm" is a program that uses a machine learning algorithm to generate a specific output (such as busyness or emotional state) from input data.

[0549] "Busyness" is an index that indicates the workload of each member, and is calculated based on communication metadata and work schedule information.

[0550] "Emotional state" is an indicator that shows each member's emotional and psychological state, and is analyzed based on emotional data.

[0551] "Visualization" means converting the analysis results into graphs or dashboards and displaying them in a way that is visually easy to understand.

[0552] "Work reallocation" means reallocating tasks to other members in order to reduce or adjust the workload on a particular member.

[0553] "Mental care proposals" means presenting psychological support and mental health care measures based on each member's emotional state.

[0554] This invention is a system that manages workloads and distributes tasks fairly in a remote work environment, and also has the function of managing the user's emotional state. This system is characterized by comprehensively collecting and analyzing communication metadata, work schedule information, and emotional data, and proposing work redistribution and mental care.

[0555] First, the device collects data related to each member's daily work. Communication metadata includes email sending and receiving logs, the number of chat messages, and the duration of video calls. Work schedule information is also obtained from calendar systems and other sources. Furthermore, an emotion engine is used to collect user emotion data from text, voice, and facial expressions. Natural language processing algorithms and speech recognition technology are used for analysis by this emotion engine.

[0556] The collected communication metadata, work schedule information, and emotion data are temporarily stored and then sent to a server at regular intervals. The server receives this data and stores it in a database. Communication is carried out using the HTTPS protocol, and all data is encrypted.

[0557] The server then uses a generation algorithm to analyze the collected data. The generation algorithm uses a machine learning algorithm to calculate the "busyness level" based on each member's communication volume, work schedule congestion, frequency of meetings, etc. Furthermore, the emotion engine analyzes the user's "emotional state" from email and chat text and audio during video conferences to generate indicators.

[0558] The analysis results are visualized by the server in the form of graphs and dashboards using graph generation libraries such as D3.js and Chart.js. Users can access these graphs and dashboards from their own devices to check the workload and emotional state of themselves and their entire team.

[0559] The server also generates suggestions for work redistribution and mental health care based on the analysis results. For example, if a member is very busy and in a negative emotional state, it will suggest reassigning that member's tasks to another member. Furthermore, if mental health care is needed, it will provide specific actions and support information.

[0560] As a specific example, consider a case where Employee B participates in numerous video conferences and processes a lot of emails. If the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server then evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. To reduce Employee B's burden, the manager can reallocate tasks to other members and provide mental health support to Employee B as needed.

[0561] Example prompt: "Please explain your system for efficiently managing each member's workload and emotional state in a remote work environment. Please provide detailed information, including specific data collection methods, data transmission and storage methods, data analysis methods, data visualization methods, work redistribution and mental health care proposal methods, and implementation methods. Please also provide specific examples."

[0562] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0563] Step 1:

[0564] The device periodically collects communication metadata (email sending and receiving logs, number of chat messages, and participation time in video calls) and work schedule information for each member. It also uses an emotion engine to collect emotional data from the user's text, voice, and facial expressions. Specifically, the device records logs of each communication method during working hours, and the emotion engine performs text analysis in real time and uses speech recognition technology to analyze audio during video conferences.

[0565] Input: Each member's communication data, work schedule, user text, voice, and facial expressions

[0566] Output: communication metadata, work schedule information, emotion data

[0567] Step 2:

[0568] The device sends the collected communication metadata, work schedule information, and emotion data to the server at regular intervals (e.g., once a day). Specifically, the device encrypts the data temporarily stored and uploads it to the server using the HTTPS protocol.

[0569] Input: communication metadata, work schedule information, emotion data

[0570] Output: Data sent to the server

[0571] Step 3:

[0572] The server receives the transmitted communication metadata, work schedule information, and emotion data and stores them in a database. Specifically, the server decodes the received data and stores them in the corresponding databases (for communication metadata, work schedule data, and emotion data).

[0573] Input: Data sent from the terminal

[0574] Output: Data stored in the database

[0575] Step 4:

[0576] The server analyzes data using a generation algorithm based on the stored communication metadata and work schedule information. The generation algorithm evaluates each member's communication volume, schedule congestion, frequency of meetings, etc., and calculates their "busyness level." It also uses an emotion engine to analyze the "emotional state" from the emotional data and generate an index. Specifically, the server runs an automated script and inputs the data into the analysis algorithm.

[0577] Input: Communication metadata, work schedule information, and emotion data stored in the database

[0578] Output: Busyness and emotional state of each member

[0579] Step 5:

[0580] The server converts the busyness level calculated by the generation algorithm and the emotional state analyzed by the emotion engine into a visually easy-to-understand format. Specifically, the server uses a graph generation library (such as D3.js or Chart.js) to convert the analysis results into a graph or dashboard format and display them on a web dashboard.

[0581] Input: Each member's busyness and emotional state

[0582] Output: Visualized data in the form of graphs and dashboards

[0583] Step 6:

[0584] The administrator, who is the user, checks and implements work reallocation and mental care suggestions based on the visualized data displayed by the server. Specifically, the administrator accesses the web dashboard and clicks on a work reallocation instruction to reallocate tasks or provide mental care support information.

[0585] Input: Visualized data displayed on the web dashboard

[0586] Output: Actual tasks reallocated and mental health support provided

[0587] This will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment.

[0588] (Application example 2)

[0589] 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."

[0590] In remote work and factory environments, it is extremely important to efficiently manage the workload and emotional state of each member and operator. However, conventional systems have made it difficult to properly evaluate workload and emotional state, and to implement fair work distribution and mental care. In particular, there is a demand for a function that can analyze operator work data and communication logs in real time and immediately reflect the situation.

[0591] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0592] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for analyzing emotional data, means for estimating the busyness and emotional state of each member using a generating AI based on the collected communication metadata, work schedule information, and emotional data, means for visualizing the estimated busyness data and emotional state, means for proposing work redistribution and mental care based on the data, and means for displaying information in real time on a device worn by an operator. This makes it possible to efficiently and fairly manage the busyness and emotional state of each member and operator and to immediately implement improvement proposals.

[0593] "Communication metadata" refers to data such as email sending and receiving logs, number of chat messages, participation time in video conferences, operator work data, and communication logs.

[0594] "Work schedule information" refers to schedule data such as work plans and meeting schedules for each member or operator.

[0595] "Server" refers to a central processing unit for receiving, storing, and analyzing data to estimate each member's busyness and emotional state.

[0596] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze each member's communication metadata, work schedule information, and emotional data.

[0597] "Busyness level" refers to an indicator that shows the amount of work and workload each member or operator is handling.

[0598] "Emotional state" refers to data used to assess the mental health and emotional fluctuations of each member or operator.

[0599] "Emotional data" refers to data about an individual's emotions analyzed from voice, facial expressions, verbal content, etc.

[0600] "Real-time display" refers to the function of instantly processing data and providing instant feedback to devices worn by each member or operator.

[0601] "Work reallocation" refers to a proposal to allocate work to other members in order to optimize the workload of each member or operator.

[0602] "Mental care suggestions" refer to suggestions based on emotional data to maintain and improve the mental health of each member or operator.

[0603] The system for implementing this invention is designed to enable employees and operators to efficiently manage their workload and emotional state. Its main components include a terminal that collects communication metadata and work schedule information, a server that analyzes, stores, and visualizes the data, and a user device that provides final suggestions and feedback.

[0604] Data collection

[0605] The device collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. Each member's work schedule information is also collected periodically. Furthermore, emotional data is analyzed from the operator's facial expressions and voice using a camera and microphone. Smart glasses or smartphones are used as the device.

[0606] Data transmission and storage

[0607] All data collected by the device is sent to the server at regular intervals. The server has a database where the received data is stored and used for subsequent analysis. Data is sent using the HTTP protocol.

[0608] Based on this data, the server analyzes each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., and estimates each member's "busyness level" and "emotional state."

[0609] Data analysis

[0610] The server first uses a generative AI model to analyze the collected communication metadata and work schedule information to calculate each member's busy level. It then uses an emotion engine to analyze the emotional data and determine each member's emotional state. Specifically, it uses natural language processing (NLP) technology and machine learning algorithms.

[0611] Data Visualization

[0612] The server converts the busyness data calculated by the generative AI and the emotional state identified by the emotion engine into a visually easy-to-understand format. This data is displayed in graphs and dashboards and fed back in real time to user devices such as smart glasses, smartphones, and PCs, allowing users and administrators to understand the situation at a glance.

[0613] Work redistribution and mental health care proposals

[0614] The server automatically generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or if that member's emotional state is negative, the server will suggest reallocating that work to other members who have more time. Furthermore, if mental care is needed, the server will suggest providing mental health support.

[0615] Reallocation and care delivery

[0616] The administrator, who is the user, can reallocate work based on this suggestion. Appropriate mental health care measures can also be taken for members whose emotional state is judged to be negative. For example, if Employee B participates in many video conferences and handles a large number of emails, and the emotion engine detects high stress levels from Employee B's chat messages and comments during video conferences, the server will suggest reallocating Employee B's work to other members.

[0617] Examples of concrete examples and prompts

[0618] For example, if factory operator A works long hours on the day shift and data from smart glasses indicates that A's stress level is high, the following prompts can be input into the generative AI:

[0619] "Operator A's workload is high and his emotional state is negative. How would you redistribute his work and suggest appropriate mental health care?"

[0620] This allows the generative AI to propose specific work redistribution and mental care measures, making it possible to balance factory productivity with employee health.

[0621] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0622] Step 1:

[0623] The device periodically collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. In addition, it uses a camera and microphone to capture the operator's facial expressions and voice to obtain emotion data.

[0624] Input: communication metadata, facial expression data, voice data

[0625] Output: Collected communication metadata, emotion data

[0626] Step 2:

[0627] The device sends the collected communication metadata, emotion data, and work schedule information to a server via HTTP, which then receives and stores the data in a database.

[0628] Input: Collected communication metadata, emotion data, work schedule information

[0629] Output: Collected data stored in a database

[0630] Step 3:

[0631] The server uses a generative AI model to analyze communication metadata and work schedule information stored in the database to calculate each member's busy level, and an emotion engine to analyze emotion data and determine each member's emotional state.

[0632] Input: communication metadata, work schedule information, emotion data

[0633] Output: Calculated busyness data, emotional state data

[0634] Step 4:

[0635] The server converts the calculated busyness data and emotional state data into a visually easy-to-understand format and visualizes it in the form of graphs, dashboards, etc. This display information is sent in real time to user devices such as smart glasses, smartphones, and PCs.

[0636] Input: Busyness data, emotional state data

[0637] Output: Visualized graphs and dashboard information

[0638] Step 5:

[0639] The server then uses the analysis results to propose work redistribution and mental care, using a generative AI model to generate proposals for redistribution when a specific member's workload is high, or for mental care when the member's emotional state is negative.

[0640] Input: Busyness data, emotional state data

[0641] Output: Work reallocation proposals, mental care proposals

[0642] Step 6:

[0643] The administrator, who is the user, reviews the proposals sent from the server and reallocates work as necessary. Appropriate mental care measures are also taken for members with negative emotional states. For example, if high stress is detected in Operator A, a proposal is displayed based on a prompt from the generation AI: "Operator A's workload is high and his emotional state is negative. How would you reallocate work and suggest appropriate mental care?"

[0644] Input: Work reallocation proposals, mental care proposals

[0645] Output: Reallocated tasks, mental health measures implemented

[0646] 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.

[0647] 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.

[0648] 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.

[0649] [Third embodiment]

[0650] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0651] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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).

[0656] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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."

[0662] The present invention relates to a system for efficiently managing the workload of each member in a remote work environment and achieving fair work distribution. Specific embodiments of the present invention will be described in detail below.

[0663] Overall system picture

[0664] The system collects communication metadata and work schedule information for all employees and uses generative AI to automatically estimate each member's "busyness level." The estimated results are visualized, and if work needs to be reallocated, suggestions are made. The overall process is as follows:

[0665] Data collection

[0666] The devices periodically collect communication metadata, such as each employee's email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. They also collect each employee's work schedule. This data is sent to a server at regular intervals. The collected data includes the time each email was sent and received, the recipient and sender, the number and frequency of chat messages, and the start and end times of video conferences.

[0667] Data transmission and storage

[0668] The communication metadata and work schedule information sent from the device are stored on the server, which then stores this data in a database and prepares it for analysis by the generation AI.

[0669] Data analysis

[0670] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each member's "busyness level." For example, if a member sends and receives a lot of emails and spends a lot of time participating in video conferences, the member's busyness level will be evaluated as high.

[0671] Data Visualization

[0672] The server converts the busyness data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing users to understand at a glance the busyness of each member and the overall work balance of the team. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and the overall status of the team.

[0673] Proposal for business reallocation

[0674] The server determines whether work needs to be redistributed based on the busyness assessment. If necessary, it generates a proposal for work redistribution. For example, if work is concentrated on a specific member, it proposes distributing that member's tasks to other members who have more free time.

[0675] Implementation of reallocation

[0676] The administrator, who is the user, reviews the work reallocation proposals presented by the server and actually reallocates the tasks. This process results in a fair and efficient work distribution.

[0677] Specific examples

[0678] For example, if Employee A participates in many video conferences and processes a large number of emails, the system collects communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates Employee A's busyness level as high. The server then visualizes the evaluation results as a graph, making Employee A's workload clear. The manager can then view the graph and receive suggestions for redistributing tasks to other employees to reduce Employee A's workload, and redistribute work based on these suggestions.

[0679] This system enables efficient and fair distribution of work even in a remote work environment.

[0680] The processing flow will be explained below.

[0681] Step 1:

[0682] The device collects communication metadata. For example, an employee's device periodically records information such as email logs, chat message counts, and video conference participation time. Each employee's device is configured to run this process in the background.

[0683] Step 2:

[0684] The device sends communication metadata and work schedule information to the server. The collected data is sent to the server at regular intervals (e.g., every hour). The data is encrypted and reaches the server securely.

[0685] Step 3:

[0686] The server stores the received data in a database. The transmitted communication metadata and work schedule information are stored in the database and used for subsequent analysis.

[0687] Step 4:

[0688] The server analyzes communication metadata and work schedule information. Using a generative AI model, it evaluates each member's communication volume and the density of their work schedule, and calculates their "busyness level." For example, the AI ​​model can learn features such as the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences, and then predict the optimal busyness level.

[0689] Step 5:

[0690] The server visualizes the calculated busyness data, which is converted into graphs and dashboards, allowing users to see at a glance the workload of each member and the overall team balance.

[0691] Step 6:

[0692] Users can check their busyness data. Each member and administrator can access the data from their own device and visually check their own busyness level and the overall team status on a dashboard or graph.

[0693] Step 7:

[0694] The server generates proposals for work reallocation. Based on the analysis results of the generation AI, if work is concentrated on a specific member, a proposal for work reallocation is created.

[0695] Step 8:

[0696] The administrator, who is the user, checks and implements the redistribution proposal. The administrator reviews the work redistribution proposal presented by the server and instructs other members to reallocate tasks as necessary. As a result, a fair and efficient work balance is achieved.

[0697] Example 1

[0698] 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."

[0699] In a remote work environment, it is difficult to manage each member's workload efficiently and fairly. In particular, it is necessary to accurately grasp the level of workload and allocate tasks appropriately to each member, but current manual management has its limitations. In addition, since data collection and analysis are insufficient, it is difficult to propose appropriate task reallocation.

[0700] 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.

[0701] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for transmitting the collected communication metadata and work schedule information to the server, means for estimating the busyness level of each member using a generative AI model based on the data, means for visualizing the estimated busyness data, means for proposing work redistribution based on the busyness data, and means for a manager to implement the proposed work redistribution. This makes it possible to efficiently and fairly manage the workload of each member and appropriately redistribute work even in a remote work environment.

[0702] "Communication metadata" refers to data about communication activities, such as email sending and receiving logs, number of chat messages, and participation time in online meetings.

[0703] "Work schedule information" refers to information about the allocation of time related to work, such as each member's plans, tasks, and meeting schedules.

[0704] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and generate results that fit a specific purpose.

[0705] "Busyness" refers to the degree of workload of each member, and is an indicator evaluated based on factors such as communication volume and the density of work schedules.

[0706] "Visualization" refers to the visual representation of data and information and displaying it in the form of graphs, dashboards, etc.

[0707] "Redistribution of work" refers to reviewing the tasks and roles assigned to each member and reassigning them efficiently and fairly.

[0708] "Suggestion" refers to the actions or changes recommended by a generative AI model or system to achieve a specific goal.

[0709] "Administrator" refers to a person who is responsible for operating the system and coordinating business operations, and who is responsible for considering and implementing proposals for business reallocation.

[0710] In an embodiment of the present invention, a system for efficiently and fairly managing the workload of each member in a remote work environment includes the following configuration.

[0711] Hardware and software used

[0712] Device:

[0713] Terminals are devices such as computers and smartphones used by each employee. Email clients, chat tools, and video conferencing tools are installed on the terminals. Examples of tools used include Outlook, Slack, Zoom, and Microsoft Teams.

[0714] server:

[0715] The server is a backend system for collecting, storing, analyzing, visualizing, and redistributing data. Specifically, it includes database software (e.g., PostgreSQL) and generative AI models (e.g., GPT-4). Programming languages ​​such as Python and Node.js are also used.

[0716] Specific operation of the system

[0717] The device has a means of collecting communication metadata (email sending and receiving logs, number of chat messages, participation time in online meetings, etc.) and work schedule information for each employee. For example, it uses Outlook API to obtain email data and Slack API to collect chat data. This allows the device to regularly monitor each employee's detailed communication activities.

[0718] The collected data is periodically sent to a server, which receives it using WebSockets or HTTP POST requests and stores it in a database, where it is checked for format and cleansed if necessary.

[0719] The server uses a generative AI model based on the stored communication metadata and work schedule information to analyze each employee's busyness level. Specifically, a Python script is executed to provide the generative AI model with the following prompt: "Please estimate this employee's busyness level based on their communication metadata." The generative AI then uses a machine learning algorithm to calculate the busyness level, and the server receives the results.

[0720] The received busyness data is visualized using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness as a bar graph or dashboard. This allows users (individual employees and managers) to access the visualized data from their own devices and check their own workload and that of the entire team.

[0721] Based on the results of the busyness analysis, the server determines whether work redistribution is necessary and generates a redistribution proposal. For example, if work is concentrated on a specific employee, it will propose distributing that employee's tasks to other members. The generative AI model uses the following prompt: "Please suggest how to distribute employee A's tasks to other members."

[0722] These proposals are presented to the user, the administrator, who reviews the proposed redistribution and actually reallocates the tasks as necessary.

[0723] Specific examples

[0724] For example, if employee A is participating in many video conferences and handling many emails, the following might happen:

[0725] 1. The device uses the Outlook API and Zoom API to collect email and video conference data from Employee A.

[0726] 2. The device sends the collected data to the server at regular intervals.

[0727] 3. The server stores the received data in a database.

[0728] 4. The server passes the saved data to the generation AI to analyze the busyness of Employee A. An example of a prompt for the generation AI model is: "Please estimate this employee's busyness level from their communication metadata."

[0729] 5. The server visualizes the analysis results as graphs so that managers and employees can check them.

[0730] 6. The server makes a proposal to reallocate employee A’s tasks to employees B and C. An example of a prompt for the generative AI model: “Please suggest how employee A’s tasks should be distributed to other members.”

[0731] 7. The user administrator reviews the proposal and reallocates the work.

[0732] This enables efficient and fair distribution of work even in a remote work environment.

[0733] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0734] Step 1:

[0735] The device collects communication metadata such as each employee's email sending and receiving history, number of chat messages, and participation time in video conferences. Specifically, the device uses the Outlook API to obtain the time of sending and receiving emails and the sender and receiver, and the number and frequency of chat messages using the Slack API. The start and end times of video conferences are obtained from the Zoom API and Microsoft Teams API.

[0736] Input: User communication activity data

[0737] Output: Collected communication metadata

[0738] Step 2:

[0739] The device sends the collected communication metadata and work schedule information to the server at regular intervals (for example, every hour). The data is sent using WebSocket or HTTP POST requests. Specifically, the device uses HTTP POST requests to send metadata to the server in JSON format.

[0740] Input: Collected communication metadata and work schedule information

[0741] Output: Data sent to the server

[0742] Step 3:

[0743] The server saves the communication metadata and work schedule information sent from the terminal in a database (e.g., PostgreSQL). Before saving, it checks the data format and whether it contains any invalid data. The server parses the JSON data and inserts it into the database using the SQL INSERT statement.

[0744] Input: Communication metadata and work schedule information received from the terminal

[0745] Output: Data stored in the database

[0746] Step 4:

[0747] The server uses a generative AI model (e.g., GPT-4) to analyze each employee's busyness level based on the stored communication metadata and work schedule information. It runs a Python script and prompts the generative AI model, saying, "Please estimate this employee's busyness level based on this employee's communication metadata." The generative AI evaluates each employee's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each employee's busyness level.

[0748] Input: Communications metadata and work schedule information retrieved from the database

[0749] Output: Busyness evaluation results by generated AI

[0750] Step 5:

[0751] The server visualizes the busyness data calculated by the generation AI as graphs and dashboards. The data is displayed visually using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness level as a bar graph or dashboard.

[0752] Input: Busyness evaluation results by generated AI

[0753] Output: Visualized graphs and dashboards

[0754] Step 6:

[0755] The server determines the need for work reallocation based on the results of the busyness analysis and generates a reallocation proposal. It sends a prompt to the generative AI model saying, "Please suggest how employee A's tasks should be distributed to other members." The generative AI then generates an optimal work reallocation proposal.

[0756] Input: Busyness evaluation results by generated AI

[0757] Output: Task reallocation proposals by generative AI

[0758] Step 7:

[0759] The user, an administrator, receives and implements the work reallocation proposals presented by the server. The proposals are displayed on a dashboard, and the administrator confirms them before implementing them. Specifically, the administrator clicks a button on the dashboard to reallocate specific work to another employee.

[0760] Input: Task redistribution proposal from the server

[0761] Output: The reallocation of work performed

[0762] This enables efficient and fair distribution of work even in a remote work environment.

[0763] (Application example 1)

[0764] 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."

[0765] In today's remote work environment, it is necessary to efficiently manage each member's workload and ensure fair work distribution. However, collecting and analyzing communication metadata and work schedule information is time-consuming and labor-intensive, and there are limitations to manual management. Furthermore, in factories and production facilities, it is important to understand the operating status of each piece of equipment and line in real time and optimally reallocate work, but this is also not easy. A system that can solve these problems is needed.

[0766] 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.

[0767] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for estimating the busyness of each member using a generation AI based on the collected communication metadata and work schedule information, means for visualizing the estimated busyness data, means for proposing work reallocation based on the busyness data, means for collecting operation data and maintenance schedule information, means for estimating the operation load of each piece of equipment, etc. using a generation AI, means for visualizing the estimated operation load data, and means for proposing work reallocation based on the operation load data. This enables efficient and fair work allocation and operation management both in remote work environments and within factories.

[0768] "Communication metadata" refers to data about each member's communication activities, such as email sending and receiving logs, number of chat messages, and participation time in video conferences.

[0769] "Work schedule information" is data indicating the work content and timetable of each member's scheduled work.

[0770] "Server" means a device or system that stores and analyzes communication metadata and work schedule information and processes the data using generative AI.

[0771] "Generative AI" is an artificial intelligence technology used to estimate each member's workload and workload using collected data.

[0772] "Busyness level" is an indicator of each member's workload, calculated by comprehensively evaluating the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences.

[0773] "Visualization" refers to displaying estimated busyness and operating load data in a visually easy-to-understand format, such as a graph or dashboard.

[0774] "Redistribution" refers to the adjustment of tasks or workloads that are concentrated on specific members or equipment to other members or equipment.

[0775] "Operation data" refers to data related to the operating status of each piece of equipment and line within the factory, such as operating time and workload.

[0776] "Maintenance schedule information" is data showing the maintenance and repair schedule for each piece of equipment.

[0777] The present invention relates to a system for efficiently managing the load of each member and each piece of equipment and achieving fair distribution in a remote work environment and in factory operation management. Specific embodiments of the present invention will be described in detail below.

[0778] Overall system picture

[0779] The system consists of multiple terminals and servers, and collects and manages each member's communication metadata and work schedule information, as well as factory operation data and maintenance schedule information. Generative AI is used to estimate and visualize the workload and operating load of each member and each piece of equipment. It also makes suggestions for reallocation if necessary.

[0780] Data collection

[0781] The devices periodically collect communication metadata such as email logs, chat message counts, and video conference participation times for each member. They also collect information on each member's work schedule, operational data, and maintenance schedule. The collected data is then sent to a server at regular intervals.

[0782] Data transmission and storage

[0783] The collected communication metadata, work schedule information, operation data, and maintenance schedule information are sent to a server and stored in a database. The server performs pre-processing to prepare this data in a format that can be analyzed by the generation AI.

[0784] Data analysis

[0785] The server uses a generation AI to analyze data based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The generation AI evaluates each member's communication volume, the congestion of their work schedule, the operation status of their equipment, the frequency of their maintenance schedule, etc., and estimates each member's "busyness level" and each piece of equipment's "operational load."

[0786] Data Visualization

[0787] The server converts the busyness and operating load data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing the load status of each member and each piece of equipment to be understood at a glance. Users can access these graphs and dashboards from their own devices to check their own workload and the operating status of their equipment.

[0788] Proposal for reallocation of work and operations

[0789] The server determines whether reallocation is necessary based on the busyness level and workload assessment. If necessary, it generates a reallocation proposal. For example, if work is concentrated on a specific member, it will propose distributing that member's tasks to other members who have more leeway. Also, if a specific piece of equipment is overworked, it will propose distributing that work to other equipment.

[0790] Implementation of reallocation

[0791] The administrator, who is the user, reviews the reallocation proposals presented by the server and actually reallocates the tasks. This process ensures fair and efficient business and operation management.

[0792] Specific examples of program processing

[0793] For example, if member A participates in many video conferences and processes a large number of emails, the system collects their communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates member A's busyness level as high. The server then visualizes the evaluation results as a graph, making member A's workload clear. The administrator can view the graph and receive suggestions for redistributing tasks to other members to reduce member A's workload, and then redistribute work based on the suggestions.

[0794] Prompt Sentence Examples

[0795] Your task is to balance the load on factory robots. Analyze the given metadata and schedule data to estimate the load on each robot. Visualize the data and propose a redistribution plan if any robots are overloaded.

[0796] This system enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[0797] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0798] Step 1:

[0799] The terminal collects communication metadata such as email sending and receiving logs, chat message counts, and video conference participation time for each member, as well as work schedule information. This collection process is carried out periodically. The input data is communication metadata and work schedule information, and the output is the collected data.

[0800] Step 2:

[0801] The terminal transmits the collected communication metadata and work schedule information to the server. The input data is the collection result of the communication metadata and work schedule information, and the output is the transmission of these data to the server.

[0802] Step 3:

[0803] The server stores the received communication metadata and work schedule information in a database. The input data are the communication metadata and work schedule information sent to the server, and the output is these data stored in the server's database.

[0804] Step 4:

[0805] The server uses a generation AI to estimate the busyness of each member and the operational load of each piece of equipment based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The input data are the communication metadata, work schedule information, operation data, and maintenance schedule information stored in the database, and the output is the busyness and operational load estimation results obtained by the generation AI.

[0806] Step 5:

[0807] The server converts the busyness and workload data calculated by the generation AI into a visually easy-to-understand format. Specifically, it visualizes it in the form of a dashboard or graph. The input data is the estimated busyness and workload calculated by the generation AI, and the output is a visualized graph or dashboard.

[0808] Step 6:

[0809] Users can access the server's dashboard and graphs from their own devices to check their workload and the operating status of each piece of equipment. The input data is the visualized graphs and dashboard display content, and the output is what the user checks.

[0810] Step 7:

[0811] The server determines the need for reallocation based on the busyness and workload assessment, and generates a reallocation proposal as necessary. The input data is the busyness and workload estimation results by the generation AI, and the output is a reallocation proposal.

[0812] Step 8:

[0813] The user, the administrator, considers the redistribution proposals presented by the server and actually reallocates the tasks. The input data is the redistribution proposals presented by the server, and the output is the new configuration of the reallocated tasks.

[0814] This enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[0815] 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.

[0816] The present invention relates to a system that efficiently manages the workload of each member in a remote work environment and achieves fair work distribution, and further combines it with a function to recognize user emotions. Specific embodiments of the present invention are described in detail below.

[0817] Overall system picture

[0818] This system collects communication metadata and work schedule information for each employee and uses generative AI to automatically estimate each member's "busyness level" and "emotional state." This makes the estimated results visible and suggests work redistribution and mental health care as needed. The overall process is as follows:

[0819] Data collection

[0820] The device periodically collects communication metadata and work schedule information, such as each employee's email sending and receiving logs, the number of chat messages, and the participation time in video conferences. It also uses an emotion engine to analyze the text content of users' emails and chats, as well as their voices and facial expressions during video conferences, to collect emotional data.

[0821] Data transmission and storage

[0822] The communication metadata, work schedule information, and emotion data collected by the device are sent to a server at regular intervals, where they are stored in a database for subsequent analysis.

[0823] Data analysis

[0824] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, and other factors to calculate each member's "busyness level." It also analyzes emotional data using an emotion engine to determine each member's "emotional state." For example, if text analysis reveals a high number of negative words, the member's emotional state is assessed as being highly stressed.

[0825] Data Visualization

[0826] The server converts the busyness data calculated by the generation AI and the emotional state determined by the emotion engine into a visually easy-to-understand format. This data is displayed in graph and dashboard format, allowing each member's workload and emotional state, as well as the overall team balance, to be understood at a glance. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and emotional state, as well as the overall team situation.

[0827] Work redistribution and mental health care proposals

[0828] The server generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or their emotional state is negative, the server will suggest distributing their tasks to other members who have more free time or suggest that they need mental care.

[0829] Reallocation and care delivery

[0830] The administrator, who is the user, considers the work redistribution and mental health care suggestions presented by the server and reallocates tasks to other members as necessary. For members who are recognized as being in a negative emotional state, the administrator takes appropriate mental health care measures, such as reducing their workload or providing access to mental health support.

[0831] Specific examples

[0832] For example, suppose Employee B is participating in many video conferences and processing a large number of emails. At the same time, if the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. The manager can then reallocate tasks to other members to reduce Employee B's burden and provide mental health support to Employee B as needed.

[0833] This system will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment, which is expected to improve overall productivity and employee satisfaction.

[0834] The processing flow will be explained below.

[0835] Step 1:

[0836] The devices collect communication metadata. Each employee's device periodically records information such as email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. Work schedule information is also collected. Data collection is performed in the background and is set up so as not to affect employees' normal work.

[0837] Step 2:

[0838] The device collects emotional data. It analyzes text content in emails and chats, as well as audio and video footage during video conferences, in real time and uses an emotion engine to estimate the user's emotional state. For example, text analysis can detect positive or negative words, and voice and facial expression analysis can assess signs of stress or fatigue.

[0839] Step 3:

[0840] The device sends communication metadata, work schedule information, and emotion data to a server. The collected data is securely sent to the server at regular intervals (e.g., every 30 minutes). The data is encrypted and protected from unauthorized access.

[0841] Step 4:

[0842] The server stores the received data in a database. The transmitted communication metadata, work schedule information, and emotion data are stored in the server's database and used for subsequent analysis. The data is indexed for efficient search.

[0843] Step 5:

[0844] The server analyzes the data and uses a generative AI model to calculate each member's "busyness level" and "emotional state" based on their communication volume, work schedule congestion, and emotional data. For example, the AI ​​model learns from past data and accurately predicts each member's workload and emotional state based on current data.

[0845] Step 6:

[0846] The server visualizes the analysis results. The generated busyness data and emotional state are converted into graphs and dashboards, visually displaying each member's status in an easy-to-understand manner. This allows managers and each member to understand their own workload and emotional state at a glance.

[0847] Step 7:

[0848] Users can check their workload data and emotional state. Each employee and manager can access the dashboard from their own device and visually check detailed analysis results. This allows them to quickly understand individual workloads, the overall team balance, and even the need for mental health care.

[0849] Step 8:

[0850] The server generates suggestions for work reallocation and mental care. Based on the analysis results of the generation AI and emotion engine, if work is concentrated on a specific member or if the emotional state is judged to be negative, the server automatically generates suggestions for work reallocation and mental care.

[0851] Step 9:

[0852] The administrator, who is the user, confirms and implements the proposals. Based on the work reallocation and mental care proposals presented by the server, the administrator reallocates tasks and provides mental care to each member. For example, they may reduce the tasks of members with a heavy workload, or refer members with negative emotional states to specialized mental health support.

[0853] In this way, this system aims to provide efficient and fair work distribution and appropriate mental care by integrating and analyzing communication metadata, work schedule information, and emotional data.

[0854] Example 2

[0855] 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."

[0856] In today's remote work environment, the challenge is to efficiently manage each member's workload, distribute work fairly, and provide appropriate mental health care. Direct observation is particularly difficult in a remote environment, making it difficult to accurately grasp each member's workload and emotional state. To address this issue, a system is needed that comprehensively analyzes not only communication metadata and work schedule information, but also emotional data, to appropriately reallocate work and provide mental health care.

[0857] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication metadata, work schedule information, and emotion data, means for estimating the busyness level and emotional state of each member using a generation algorithm based on the collected data, means for visualizing the estimated busyness data and emotional state data, and means for redistributing work and proposing mental care based on the data. This enables efficient and fair work distribution and appropriate mental care even in a remote work environment.

[0858] "Communication metadata" refers to various data related to communication, such as email sending and receiving logs, the number of chat messages, and the duration of video calls.

[0859] "Work schedule information" is schedule data related to work, such as each member's plans and tasks, and meeting schedules.

[0860] "Emotion data" is data that indicates the user's emotional state, and includes information analyzed from text, voice, and facial expressions.

[0861] The "server" is a computer system that collects, stores, and analyzes communication metadata, work schedule information, and emotion data, and visualizes and proposes the results.

[0862] A "generative algorithm" is a program that uses a machine learning algorithm to generate a specific output (such as busyness or emotional state) from input data.

[0863] "Busyness" is an index that indicates the workload of each member, and is calculated based on communication metadata and work schedule information.

[0864] "Emotional state" is an indicator that shows each member's emotional and psychological state, and is analyzed based on emotional data.

[0865] "Visualization" means converting the analysis results into graphs or dashboards and displaying them in a way that is visually easy to understand.

[0866] "Work reallocation" means reallocating tasks to other members in order to reduce or adjust the workload on a particular member.

[0867] "Mental care proposals" means presenting psychological support and mental health care measures based on each member's emotional state.

[0868] This invention is a system that manages workloads and distributes tasks fairly in a remote work environment, and also has the function of managing the user's emotional state. This system is characterized by comprehensively collecting and analyzing communication metadata, work schedule information, and emotional data, and proposing work redistribution and mental care.

[0869] First, the device collects data related to each member's daily work. Communication metadata includes email sending and receiving logs, the number of chat messages, and the duration of video calls. Work schedule information is also obtained from calendar systems and other sources. Furthermore, an emotion engine is used to collect user emotion data from text, voice, and facial expressions. Natural language processing algorithms and speech recognition technology are used for analysis by this emotion engine.

[0870] The collected communication metadata, work schedule information, and emotion data are temporarily stored and then sent to a server at regular intervals. The server receives this data and stores it in a database. Communication is carried out using the HTTPS protocol, and all data is encrypted.

[0871] The server then uses a generation algorithm to analyze the collected data. The generation algorithm uses a machine learning algorithm to calculate the "busyness level" based on each member's communication volume, work schedule congestion, frequency of meetings, etc. Furthermore, the emotion engine analyzes the user's "emotional state" from email and chat text and audio during video conferences to generate indicators.

[0872] The analysis results are visualized by the server in the form of graphs and dashboards using graph generation libraries such as D3.js and Chart.js. Users can access these graphs and dashboards from their own devices to check the workload and emotional state of themselves and their entire team.

[0873] The server also generates suggestions for work redistribution and mental health care based on the analysis results. For example, if a member is very busy and in a negative emotional state, it will suggest reassigning that member's tasks to another member. Furthermore, if mental health care is needed, it will provide specific actions and support information.

[0874] As a specific example, consider a case where Employee B participates in numerous video conferences and processes a lot of emails. If the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server then evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. To reduce Employee B's burden, the manager can reallocate tasks to other members and provide mental health support to Employee B as needed.

[0875] Example prompt: "Please explain your system for efficiently managing each member's workload and emotional state in a remote work environment. Please provide detailed information, including specific data collection methods, data transmission and storage methods, data analysis methods, data visualization methods, work redistribution and mental health care proposal methods, and implementation methods. Please also provide specific examples."

[0876] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0877] Step 1:

[0878] The device periodically collects communication metadata (email sending and receiving logs, number of chat messages, and participation time in video calls) and work schedule information for each member. It also uses an emotion engine to collect emotional data from the user's text, voice, and facial expressions. Specifically, the device records logs of each communication method during working hours, and the emotion engine performs text analysis in real time and uses speech recognition technology to analyze audio during video conferences.

[0879] Input: Each member's communication data, work schedule, user text, voice, and facial expressions

[0880] Output: communication metadata, work schedule information, emotion data

[0881] Step 2:

[0882] The device sends the collected communication metadata, work schedule information, and emotion data to the server at regular intervals (e.g., once a day). Specifically, the device encrypts the temporarily stored data and uploads it to the server using the HTTPS protocol.

[0883] Input: communication metadata, work schedule information, emotion data

[0884] Output: Data sent to the server

[0885] Step 3:

[0886] The server receives the transmitted communication metadata, work schedule information, and emotion data and stores them in a database. Specifically, the server decodes the received data and stores them in the corresponding databases (for communication metadata, work schedule data, and emotion data).

[0887] Input: Data sent from the terminal

[0888] Output: Data stored in the database

[0889] Step 4:

[0890] The server analyzes data using a generation algorithm based on the stored communication metadata and work schedule information. The generation algorithm evaluates each member's communication volume, schedule congestion, frequency of meetings, etc., and calculates their "busyness level." It also uses an emotion engine to analyze the "emotional state" from the emotional data and generate an index. Specifically, the server runs an automated script and inputs the data into the analysis algorithm.

[0891] Input: Communication metadata, work schedule information, and emotion data stored in the database

[0892] Output: Busyness and emotional state of each member

[0893] Step 5:

[0894] The server converts the busyness level calculated by the generation algorithm and the emotional state analyzed by the emotion engine into a visually easy-to-understand format. Specifically, the server uses a graph generation library (such as D3.js or Chart.js) to convert the analysis results into a graph or dashboard format and display them on a web dashboard.

[0895] Input: Each member's busyness and emotional state

[0896] Output: Visualized data in the form of graphs and dashboards

[0897] Step 6:

[0898] The administrator, who is the user, checks and implements work reallocation and mental care suggestions based on the visualized data displayed by the server. Specifically, the administrator accesses the web dashboard and clicks on a work reallocation instruction to reallocate tasks or provide mental care support information.

[0899] Input: Visualized data displayed on the web dashboard

[0900] Output: Actual tasks reallocated and mental health support provided

[0901] This will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment.

[0902] (Application example 2)

[0903] 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."

[0904] In remote work and factory environments, it is extremely important to efficiently manage the workload and emotional state of each member and operator. However, conventional systems have made it difficult to properly evaluate workload and emotional state, and to implement fair work distribution and mental care. In particular, there is a demand for a function that can analyze operator work data and communication logs in real time and immediately reflect the situation.

[0905] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0906] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for analyzing emotional data, means for estimating the busyness and emotional state of each member using a generating AI based on the collected communication metadata, work schedule information, and emotional data, means for visualizing the estimated busyness data and emotional state, means for proposing work redistribution and mental care based on the data, and means for displaying information in real time on a device worn by an operator. This makes it possible to efficiently and fairly manage the busyness and emotional state of each member and operator and to immediately implement improvement proposals.

[0907] "Communication metadata" refers to data such as email sending and receiving logs, number of chat messages, participation time in video conferences, operator work data and communication logs.

[0908] "Work schedule information" refers to schedule data such as work plans and meeting schedules for each member or operator.

[0909] "Server" refers to a central processing unit for receiving, storing, and analyzing data to estimate each member's busyness and emotional state.

[0910] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze each member's communication metadata, work schedule information, and emotional data.

[0911] "Busyness level" refers to an indicator that shows the amount of work and workload each member or operator is handling.

[0912] "Emotional state" refers to data used to assess the mental health and emotional fluctuations of each member or operator.

[0913] "Emotional data" refers to data about an individual's emotions analyzed from voice, facial expressions, verbal content, etc.

[0914] "Real-time display" refers to the function of instantly processing data and providing instant feedback to devices worn by each member or operator.

[0915] "Work reallocation" refers to a proposal to allocate work to other members in order to optimize the workload of each member or operator.

[0916] "Mental care suggestions" refer to suggestions based on emotional data to maintain and improve the mental health of each member or operator.

[0917] The system for implementing this invention is designed to enable employees and operators to efficiently manage their workload and emotional state. Its main components include a terminal that collects communication metadata and work schedule information, a server that analyzes, stores, and visualizes the data, and a user device that provides final suggestions and feedback.

[0918] Data collection

[0919] The device collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. Each member's work schedule information is also collected periodically. Furthermore, emotional data is analyzed from the operator's facial expressions and voice using a camera and microphone. Smart glasses or smartphones are used as the device.

[0920] Data transmission and storage

[0921] All data collected by the device is sent to the server at regular intervals. The server has a database where the received data is stored and used for subsequent analysis. Data is sent using the HTTP protocol.

[0922] Based on this data, the server analyzes each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., and estimates each member's "busyness level" and "emotional state."

[0923] Data analysis

[0924] The server first uses a generative AI model to analyze the collected communication metadata and work schedule information to calculate each member's busy level. It then uses an emotion engine to analyze the emotional data and determine each member's emotional state. Specifically, it uses natural language processing (NLP) technology and machine learning algorithms.

[0925] Data Visualization

[0926] The server converts the busyness data calculated by the generative AI and the emotional state identified by the emotion engine into a visually easy-to-understand format. This data is displayed in graphs and dashboards and fed back in real time to user devices such as smart glasses, smartphones, and PCs, allowing users and administrators to understand the situation at a glance.

[0927] Work redistribution and mental health care proposals

[0928] The server automatically generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or if that member's emotional state is negative, the server will suggest reallocating that work to other members who have more time. Furthermore, if mental care is needed, the server will suggest providing mental health support.

[0929] Reallocation and care delivery

[0930] The administrator, who is the user, can reallocate work based on this suggestion. Appropriate mental health care measures can also be taken for members whose emotional state is judged to be negative. For example, if employee B participates in many video conferences and handles a large number of emails, and the emotion engine detects high stress levels from employee B's chat messages and comments during video conferences, the server will suggest reallocating employee B's work to other members.

[0931] Examples of concrete examples and prompts

[0932] For example, if factory operator A works long hours on the day shift and data from smart glasses indicates that A's stress level is high, the following prompts can be input into the generative AI:

[0933] "Operator A's workload is high and his emotional state is negative. How would you redistribute his work and suggest appropriate mental health care?"

[0934] This allows the generative AI to propose specific work redistribution and mental care measures, making it possible to balance factory productivity with employee health.

[0935] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0936] Step 1:

[0937] The device periodically collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. In addition, it uses a camera and microphone to capture the operator's facial expressions and voice to obtain emotion data.

[0938] Input: communication metadata, facial expression data, voice data

[0939] Output: Collected communication metadata, emotion data

[0940] Step 2:

[0941] The device sends the collected communication metadata, emotion data, and work schedule information to a server via HTTP, which then receives and stores the data in a database.

[0942] Input: Collected communication metadata, emotion data, work schedule information

[0943] Output: Collected data stored in a database

[0944] Step 3:

[0945] The server uses a generative AI model to analyze communication metadata and work schedule information stored in the database to calculate each member's busy level, and an emotion engine to analyze emotion data and determine each member's emotional state.

[0946] Input: communication metadata, work schedule information, emotion data

[0947] Output: Calculated busyness data, emotional state data

[0948] Step 4:

[0949] The server converts the calculated busyness data and emotional state data into a visually easy-to-understand format and visualizes it in the form of graphs, dashboards, etc. This display information is sent in real time to user devices such as smart glasses, smartphones, and PCs.

[0950] Input: Busyness data, emotional state data

[0951] Output: Visualized graphs and dashboard information

[0952] Step 5:

[0953] The server then uses the analysis results to propose work redistribution and mental care, using a generative AI model to generate proposals for redistribution when a specific member's workload is high, or for mental care when the member's emotional state is negative.

[0954] Input: Busyness data, emotional state data

[0955] Output: Work reallocation proposals, mental care proposals

[0956] Step 6:

[0957] The administrator, who is the user, reviews the proposals sent from the server and reallocates work as necessary. Appropriate mental care measures are also taken for members with negative emotional states. For example, if high stress is detected in Operator A, a proposal is displayed based on a prompt from the generation AI: "Operator A's workload is high and his emotional state is negative. How would you reallocate work and suggest appropriate mental care?"

[0958] Input: Work reallocation proposals, mental care proposals

[0959] Output: Reallocated tasks, mental health measures implemented

[0960] 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.

[0961] 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.

[0962] 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.

[0963] [Fourth embodiment]

[0964] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0965] 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.

[0966] 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).

[0967] 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.

[0968] 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.

[0969] 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).

[0970] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0971] 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.

[0972] 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.

[0973] 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.

[0974] 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.

[0975] 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.

[0976] 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."

[0977] The present invention relates to a system for efficiently managing the workload of each member in a remote work environment and achieving fair work distribution. Specific embodiments of the present invention will be described in detail below.

[0978] Overall system picture

[0979] The system collects communication metadata and work schedule information for all employees and uses generative AI to automatically estimate each member's "busyness level." The estimated results are visualized, and if work needs to be reallocated, suggestions are made. The overall process is as follows:

[0980] Data collection

[0981] The devices periodically collect communication metadata, such as each employee's email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. They also collect each employee's work schedule. This data is sent to a server at regular intervals. The collected data includes the time each email was sent and received, the recipient and sender, the number and frequency of chat messages, and the start and end times of video conferences.

[0982] Data transmission and storage

[0983] The communication metadata and work schedule information sent from the device are stored on the server, which then stores this data in a database and prepares it for analysis by the generation AI.

[0984] Data analysis

[0985] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each member's "busyness level." For example, if a member sends and receives a lot of emails and spends a lot of time participating in video conferences, the member's busyness level will be evaluated as high.

[0986] Data Visualization

[0987] The server converts the busyness data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing users to understand at a glance the busyness of each member and the overall work balance of the team. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and the overall status of the team.

[0988] Proposal for business reallocation

[0989] The server determines whether work needs to be redistributed based on the busyness assessment. If necessary, it generates a proposal for work redistribution. For example, if work is concentrated on a specific member, it proposes distributing that member's tasks to other members who have more free time.

[0990] Implementation of reallocation

[0991] The administrator, who is the user, reviews the work reallocation proposals presented by the server and actually reallocates the tasks. This process results in a fair and efficient work distribution.

[0992] Specific examples

[0993] For example, if Employee A participates in many video conferences and processes a large number of emails, the system collects communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates Employee A's busyness level as high. The server then visualizes the evaluation results as a graph, making Employee A's workload clear. The manager can then view the graph and receive suggestions for redistributing tasks to other employees to reduce Employee A's workload, and redistribute work based on these suggestions.

[0994] This system enables efficient and fair distribution of work even in a remote work environment.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] The device collects communication metadata. For example, an employee's device periodically records information such as email logs, chat message counts, and video conference participation time. Each employee's device is configured to run this process in the background.

[0998] Step 2:

[0999] The device sends communication metadata and work schedule information to the server. The collected data is sent to the server at regular intervals (e.g., every hour). The data is encrypted and reaches the server securely.

[1000] Step 3:

[1001] The server stores the received data in a database. The transmitted communication metadata and work schedule information are stored in the database and used for subsequent analysis.

[1002] Step 4:

[1003] The server analyzes communication metadata and work schedule information. Using a generative AI model, it evaluates each member's communication volume and the density of their work schedule, and calculates their "busyness level." For example, the AI ​​model can learn features such as the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences, and then predict the optimal busyness level.

[1004] Step 5:

[1005] The server visualizes the calculated busyness data, which is converted into graphs and dashboards, allowing users to see at a glance the workload of each member and the overall team balance.

[1006] Step 6:

[1007] Users can check their busyness data. Each member and administrator can access the data from their own device and visually check their own busyness level and the overall team status on the dashboard and in graphs.

[1008] Step 7:

[1009] The server generates proposals for work reallocation. Based on the analysis results of the generation AI, if work is concentrated on a specific member, a proposal for work reallocation is created.

[1010] Step 8:

[1011] The administrator, who is the user, checks and implements the redistribution proposal. The administrator reviews the work redistribution proposal presented by the server and instructs other members to reallocate tasks as necessary. As a result, a fair and efficient work balance is achieved.

[1012] Example 1

[1013] 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."

[1014] In a remote work environment, it is difficult to manage each member's workload efficiently and fairly. In particular, it is necessary to accurately grasp the level of workload and allocate tasks appropriately to each member, but current manual management has its limitations. In addition, since data collection and analysis are insufficient, it is difficult to propose appropriate task reallocation.

[1015] 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.

[1016] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for transmitting the collected communication metadata and work schedule information to the server, means for estimating the busyness level of each member using a generative AI model based on the data, means for visualizing the estimated busyness data, means for proposing work redistribution based on the busyness data, and means for a manager to implement the proposed work redistribution. This makes it possible to efficiently and fairly manage the workload of each member and appropriately redistribute work even in a remote work environment.

[1017] "Communication metadata" refers to data about communication activities, such as email sending and receiving logs, number of chat messages, and participation time in online meetings.

[1018] "Work schedule information" refers to information about the allocation of time related to work, such as each member's plans, tasks, and meeting schedules.

[1019] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze data and generate results that fit a specific purpose.

[1020] "Busyness" refers to the degree of workload of each member, and is an indicator evaluated based on factors such as communication volume and the density of work schedules.

[1021] "Visualization" refers to the visual representation of data and information and displaying it in the form of graphs, dashboards, etc.

[1022] "Redistribution of work" refers to reviewing the tasks and roles assigned to each member and reassigning them efficiently and fairly.

[1023] "Suggestion" refers to the actions or changes recommended by a generative AI model or system to achieve a specific goal.

[1024] "Administrator" refers to a person who is responsible for operating the system and coordinating business operations, and who is responsible for considering and implementing proposals for business reallocation.

[1025] In an embodiment of the present invention, a system for efficiently and fairly managing the workload of each member in a remote work environment includes the following configuration.

[1026] Hardware and software used

[1027] Device:

[1028] Terminals are devices such as computers and smartphones used by each employee. Email clients, chat tools, and video conferencing tools are installed on the terminals. Examples of tools used include Outlook, Slack, Zoom, and Microsoft Teams.

[1029] server:

[1030] The server is a backend system for collecting, storing, analyzing, visualizing, and redistributing data. Specifically, it includes database software (e.g., PostgreSQL) and generative AI models (e.g., GPT-4). Programming languages ​​such as Python and Node.js are also used.

[1031] Specific operation of the system

[1032] The device has a means of collecting communication metadata (email sending and receiving logs, number of chat messages, participation time in online meetings, etc.) and work schedule information for each employee. For example, it uses Outlook API to obtain email data and Slack API to collect chat data. This allows the device to regularly monitor each employee's detailed communication activities.

[1033] The collected data is periodically sent to a server, which receives it using WebSockets or HTTP POST requests and stores it in a database, where it is checked for format and cleansed if necessary.

[1034] The server uses a generative AI model to analyze each employee's busy level based on the stored communication metadata and work schedule information. Specifically, a Python script is executed to provide the generative AI model with the following prompt: "Please estimate this employee's busy level based on their communication metadata." The generative AI then uses a machine learning algorithm to calculate the busy level, and the server receives the results.

[1035] The received busyness data is visualized using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness as a bar graph or dashboard. This allows users (individual employees and managers) to access the visualized data from their own devices and check their own workload and that of the entire team.

[1036] Based on the results of the busyness analysis, the server determines whether work redistribution is necessary and generates a redistribution proposal. For example, if work is concentrated on a specific employee, it will propose distributing that employee's tasks to other members. The generative AI model uses the following prompt: "Please suggest how to distribute employee A's tasks to other members."

[1037] These proposals are presented to the user, the administrator, who reviews the proposed redistribution and actually reallocates the tasks as necessary.

[1038] Specific examples

[1039] For example, if employee A is participating in many video conferences and handling many emails, the following might happen:

[1040] 1. The device uses the Outlook API and Zoom API to collect email and video conference data from Employee A.

[1041] 2. The device sends the collected data to the server at regular intervals.

[1042] 3. The server stores the received data in a database.

[1043] 4. The server passes the saved data to the generation AI to analyze the busyness of Employee A. An example of a prompt for the generation AI model is: "Please estimate this employee's busyness level from their communication metadata."

[1044] 5. The server visualizes the analysis results as graphs so that managers and employees can check them.

[1045] 6. The server makes a proposal to reallocate employee A’s tasks to employees B and C. An example of a prompt for the generative AI model: “Please suggest how employee A’s tasks should be distributed to other members.”

[1046] 7. The user administrator reviews the proposal and reallocates the work.

[1047] This enables efficient and fair distribution of work even in a remote work environment.

[1048] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1049] Step 1:

[1050] The device collects communication metadata such as each employee's email sending and receiving history, number of chat messages, and participation time in video conferences. Specifically, the device uses the Outlook API to obtain the time of sending and receiving emails and the sender and receiver, and the number and frequency of chat messages using the Slack API. The start and end times of video conferences are obtained from the Zoom API and Microsoft Teams API.

[1051] Input: User communication activity data

[1052] Output: Collected communication metadata

[1053] Step 2:

[1054] The device sends the collected communication metadata and work schedule information to the server at regular intervals (for example, every hour). The data is sent using WebSocket or HTTP POST requests. Specifically, the device uses HTTP POST requests to send metadata to the server in JSON format.

[1055] Input: Collected communication metadata and work schedule information

[1056] Output: Data sent to the server

[1057] Step 3:

[1058] The server saves the communication metadata and work schedule information sent from the terminal in a database (e.g., PostgreSQL). Before saving, it checks the data format and whether it contains any invalid data. The server parses the JSON data and inserts it into the database using the SQL INSERT statement.

[1059] Input: Communication metadata and work schedule information received from the terminal

[1060] Output: Data stored in the database

[1061] Step 4:

[1062] The server uses a generative AI model (e.g., GPT-4) to analyze each employee's busyness level based on the stored communication metadata and work schedule information. It runs a Python script and prompts the generative AI model, saying, "Please estimate this employee's busyness level based on this employee's communication metadata." The generative AI evaluates each employee's communication volume, the busyness of their work schedule, the frequency of meetings, etc., to estimate each employee's busyness level.

[1063] Input: Communications metadata and work schedule information retrieved from the database

[1064] Output: Busyness evaluation results by generated AI

[1065] Step 5:

[1066] The server visualizes the busyness data calculated by the generation AI as graphs and dashboards. The data is displayed visually using data visualization tools such as D3.js and Chart.js. Specifically, the server generates HTML and JavaScript to display each employee's busyness level as a bar graph or dashboard.

[1067] Input: Busyness evaluation results by generated AI

[1068] Output: Visualized graphs and dashboards

[1069] Step 6:

[1070] The server determines the need for work reallocation based on the results of the busyness analysis and generates a reallocation proposal. It sends a prompt to the generative AI model saying, "Please suggest how employee A's tasks should be distributed to other members." The generative AI then generates an optimal work reallocation proposal.

[1071] Input: Busyness evaluation results by generated AI

[1072] Output: Task reallocation proposals by generative AI

[1073] Step 7:

[1074] The user, an administrator, receives and implements the work reallocation proposals presented by the server. The proposals are displayed on a dashboard, and the administrator confirms them before implementing them. Specifically, the administrator clicks a button on the dashboard to reallocate specific work to another employee.

[1075] Input: Task redistribution proposal from the server

[1076] Output: The reallocation of work performed

[1077] This enables efficient and fair distribution of work even in a remote work environment.

[1078] (Application example 1)

[1079] 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."

[1080] In today's remote work environment, it is necessary to efficiently manage each member's workload and ensure fair work distribution. However, collecting and analyzing communication metadata and work schedule information is time-consuming and labor-intensive, and there are limitations to manual management. Furthermore, in factories and production facilities, it is important to understand the operating status of each piece of equipment and line in real time and optimally reallocate work, but this is also not easy. A system that can solve these problems is needed.

[1081] 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.

[1082] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for estimating the busyness of each member using a generation AI based on the collected communication metadata and work schedule information, means for visualizing the estimated busyness data, means for proposing work reallocation based on the busyness data, means for collecting operation data and maintenance schedule information, means for estimating the operation load of each piece of equipment, etc. using a generation AI, means for visualizing the estimated operation load data, and means for proposing work reallocation based on the operation load data. This enables efficient and fair work allocation and operation management both in remote work environments and within factories.

[1083] "Communication metadata" refers to data about each member's communication activities, such as email sending and receiving logs, number of chat messages, and participation time in video conferences.

[1084] "Work schedule information" is data indicating the work content and timetable of each member's scheduled work.

[1085] "Server" means a device or system that stores and analyzes communication metadata and work schedule information and processes the data using generative AI.

[1086] "Generative AI" is an artificial intelligence technology used to estimate each member's workload and workload using collected data.

[1087] "Busyness level" is an indicator of each member's workload, calculated by comprehensively evaluating the number of emails sent and received, the number of chat messages, and the time spent participating in video conferences.

[1088] "Visualization" refers to displaying estimated busyness and operating load data in a visually easy-to-understand format, such as a graph or dashboard.

[1089] "Redistribution" refers to the adjustment of tasks or workloads that are concentrated on specific members or equipment to other members or equipment.

[1090] "Operation data" refers to data related to the operating status of each piece of equipment and line within the factory, such as operating time and workload.

[1091] "Maintenance schedule information" is data showing the maintenance and repair schedule for each piece of equipment.

[1092] The present invention relates to a system for efficiently managing the load of each member and each piece of equipment and achieving fair distribution in a remote work environment and in factory operation management. Specific embodiments of the present invention will be described in detail below.

[1093] Overall system picture

[1094] The system consists of multiple terminals and servers, and collects and manages each member's communication metadata and work schedule information, as well as factory operation data and maintenance schedule information. Generative AI is used to estimate and visualize the workload and operating load of each member and each piece of equipment. It also makes suggestions for reallocation if necessary.

[1095] Data collection

[1096] The devices periodically collect communication metadata such as email logs, chat message counts, and video conference participation times for each member. They also collect information on each member's work schedule, operational data, and maintenance schedule. The collected data is then sent to a server at regular intervals.

[1097] Data transmission and storage

[1098] The collected communication metadata, work schedule information, operation data, and maintenance schedule information are sent to a server and stored in a database. The server performs preprocessing to prepare this data in a format that can be analyzed by the generation AI.

[1099] Data analysis

[1100] The server uses a generation AI to analyze data based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The generation AI evaluates each member's communication volume, the congestion of their work schedule, the operation status of their equipment, the frequency of their maintenance schedule, etc., and estimates each member's "busyness level" and each piece of equipment's "operational load."

[1101] Data Visualization

[1102] The server converts the busyness and operating load data calculated by the generation AI into a visually easy-to-understand format. At this stage, it is displayed as graphs and dashboards, allowing the load status of each member and each piece of equipment to be understood at a glance. Users can access these graphs and dashboards from their own devices to check their own workload and the operating status of their equipment.

[1103] Proposal for reallocation of work and operations

[1104] The server determines whether reallocation is necessary based on the busyness level and workload assessment. If necessary, it generates a reallocation proposal. For example, if work is concentrated on a specific member, it will propose distributing that member's tasks to other members who have more leeway. Also, if a specific piece of equipment is overworked, it will propose distributing that work to other equipment.

[1105] Implementation of reallocation

[1106] The administrator, who is the user, reviews the reallocation proposals presented by the server and actually reallocates the tasks. This process ensures fair and efficient business and operation management.

[1107] Specific examples of program processing

[1108] For example, if member A participates in many video conferences and processes a large number of emails, the system collects their communication metadata and work schedule information. The collected data is sent to the server, and the generating AI evaluates member A's busyness level as high. The server then visualizes the evaluation results as a graph, making member A's workload clear. The administrator can view the graph and receive suggestions for redistributing tasks to other members to reduce member A's workload, and then redistribute work based on the suggestions.

[1109] Prompt Sentence Examples

[1110] Your task is to balance the load on factory robots. Analyze the given metadata and schedule data to estimate the load on each robot. Visualize the data and propose a redistribution plan if any robots are overloaded.

[1111] This system enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[1112] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1113] Step 1:

[1114] The terminal collects communication metadata such as email sending and receiving logs, chat message counts, and video conference participation time for each member, as well as work schedule information. This collection process is carried out periodically. The input data is communication metadata and work schedule information, and the output is the collected data.

[1115] Step 2:

[1116] The terminal transmits the collected communication metadata and work schedule information to the server. The input data is the collection result of the communication metadata and work schedule information, and the output is the transmission of these data to the server.

[1117] Step 3:

[1118] The server stores the received communication metadata and work schedule information in a database. The input data are the communication metadata and work schedule information sent to the server, and the output is these data stored in the server's database.

[1119] Step 4:

[1120] The server uses a generation AI to estimate the busyness of each member and the operational load of each piece of equipment based on the stored communication metadata, work schedule information, operation data, and maintenance schedule information. The input data are the communication metadata, work schedule information, operation data, and maintenance schedule information stored in the database, and the output is the busyness and operational load estimation results obtained by the generation AI.

[1121] Step 5:

[1122] The server converts the busyness and workload data calculated by the generation AI into a visually easy-to-understand format. Specifically, it visualizes it in the form of a dashboard or graph. The input data is the estimated busyness and workload calculated by the generation AI, and the output is a visualized graph or dashboard.

[1123] Step 6:

[1124] Users can access the server's dashboard and graphs from their own devices to check their workload and the operating status of each piece of equipment. The input data is the visualized graphs and dashboard display content, and the output is what the user checks.

[1125] Step 7:

[1126] The server determines the need for reallocation based on the busyness and workload assessment, and generates a reallocation proposal as necessary. The input data is the busyness and workload estimation results by the generation AI, and the output is a reallocation proposal.

[1127] Step 8:

[1128] The user, the administrator, considers the redistribution proposals presented by the server and actually reallocates the tasks. The input data is the redistribution proposals presented by the server, and the output is the new configuration of the reallocated tasks.

[1129] This enables efficient and fair work distribution and operation management both in remote work environments and within factories.

[1130] 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.

[1131] The present invention relates to a system that efficiently manages the workload of each member in a remote work environment and achieves fair work distribution, and further combines a function for recognizing user emotions. Specific embodiments of the present invention are described in detail below.

[1132] Overall system picture

[1133] This system collects communication metadata and work schedule information for each employee and uses generative AI to automatically estimate each member's "busyness level" and "emotional state." This makes the estimated results visible and suggests work redistribution and mental health care as needed. The overall process is as follows:

[1134] Data collection

[1135] The device periodically collects communication metadata and work schedule information, such as each employee's email sending and receiving logs, the number of chat messages, and the participation time in video conferences. It also uses an emotion engine to analyze the text content of users' emails and chats, as well as their voices and facial expressions during video conferences, to collect emotional data.

[1136] Data transmission and storage

[1137] The communication metadata, work schedule information, and emotion data collected by the device are sent to a server at regular intervals, where they are stored in a database for subsequent analysis.

[1138] Data analysis

[1139] The server uses a generation AI to analyze data based on the stored communication metadata and work schedule information. The generation AI evaluates each member's communication volume, the busyness of their work schedule, the frequency of meetings, and other factors to calculate each member's "busyness level." It also analyzes emotional data using an emotion engine to determine each member's "emotional state." For example, if text analysis reveals a high number of negative words, the member's emotional state is assessed as being highly stressed.

[1140] Data Visualization

[1141] The server converts the busyness data calculated by the generation AI and the emotional state determined by the emotion engine into a visually easy-to-understand format. This data is displayed in graph and dashboard format, allowing each member's workload and emotional state, as well as the overall team balance, to be understood at a glance. Users, i.e., individual employees and managers, can access these graphs and dashboards from their own devices to check their own workload and emotional state, as well as the overall team situation.

[1142] Work redistribution and mental health care proposals

[1143] The server generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or their emotional state is negative, the server will suggest distributing their tasks to other members who have more free time or suggest that they need mental care.

[1144] Reallocation and care delivery

[1145] The administrator, who is the user, considers the work redistribution and mental health care suggestions presented by the server and reallocates tasks to other members as necessary. For members who are recognized as being in a negative emotional state, the administrator takes appropriate mental health care measures, such as reducing their workload or providing access to mental health support.

[1146] Specific examples

[1147] For example, suppose Employee B is participating in many video conferences and processing a large number of emails. At the same time, if the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. The manager can then reallocate tasks to other members to reduce Employee B's burden and provide mental health support to Employee B as needed.

[1148] This system will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment, which is expected to improve overall productivity and employee satisfaction.

[1149] The processing flow will be explained below.

[1150] Step 1:

[1151] The devices collect communication metadata. Each employee's device periodically records information such as email sending and receiving logs, the number of chat messages, and the time spent participating in video conferences. Work schedule information is also collected. Data collection is performed in the background and is set up so as not to affect employees' normal work.

[1152] Step 2:

[1153] The device collects emotional data. It analyzes text content in emails and chats, as well as audio and video footage during video conferences, in real time and uses an emotion engine to estimate the user's emotional state. For example, text analysis can detect positive or negative words, and voice and facial expression analysis can assess signs of stress or fatigue.

[1154] Step 3:

[1155] The device sends communication metadata, work schedule information, and emotion data to a server. The collected data is securely sent to the server at regular intervals (e.g., every 30 minutes). The data is encrypted and protected from unauthorized access.

[1156] Step 4:

[1157] The server stores the received data in a database. The transmitted communication metadata, work schedule information, and emotion data are stored in the server's database and used for subsequent analysis. The data is indexed for efficient search.

[1158] Step 5:

[1159] The server analyzes the data and uses a generative AI model to calculate each member's "busyness level" and "emotional state" based on their communication volume, work schedule congestion, and emotional data. For example, the AI ​​model learns from past data and accurately predicts each member's workload and emotional state based on current data.

[1160] Step 6:

[1161] The server visualizes the analysis results. The generated busyness data and emotional state are converted into graphs and dashboards, visually displaying each member's status in an easy-to-understand manner. This allows managers and each member to understand their own workload and emotional state at a glance.

[1162] Step 7:

[1163] Users can check their workload data and emotional state. Each employee and manager can access the dashboard from their own device and visually check detailed analysis results. This allows them to quickly understand individual workloads, the overall team balance, and even the need for mental health care.

[1164] Step 8:

[1165] The server generates suggestions for work reallocation and mental care. Based on the analysis results of the generation AI and emotion engine, if work is concentrated on a specific member or if the emotional state is judged to be negative, the server automatically generates suggestions for work reallocation and mental care.

[1166] Step 9:

[1167] The administrator, who is the user, confirms and implements the proposals. Based on the work reallocation and mental care proposals presented by the server, the administrator reassigns tasks and provides mental care to each member. For example, they may reduce the tasks of members with a heavy workload, or refer members with negative emotional states to specialized mental health support.

[1168] In this way, this system aims to provide efficient and fair work distribution and appropriate mental care by integrating and analyzing communication metadata, work schedule information, and emotional data.

[1169] Example 2

[1170] 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."

[1171] In today's remote work environment, the challenge is to efficiently manage each member's workload, distribute work fairly, and provide appropriate mental health care. Direct observation is particularly difficult in a remote environment, making it difficult to accurately grasp each member's workload and emotional state. To address this issue, a system is needed that comprehensively analyzes not only communication metadata and work schedule information, but also emotional data, to appropriately reallocate work and provide mental health care.

[1172] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting communication metadata, work schedule information, and emotion data, means for estimating the busyness level and emotional state of each member using a generation algorithm based on the collected data, means for visualizing the estimated busyness data and emotional state data, and means for redistributing work and proposing mental care based on the data. This enables efficient and fair work distribution and appropriate mental care even in a remote work environment.

[1173] "Communication metadata" refers to various data related to communication, such as email sending and receiving logs, the number of chat messages, and the duration of video calls.

[1174] "Work schedule information" is schedule data related to work, such as each member's plans and tasks, and meeting schedules.

[1175] "Emotion data" is data that indicates the user's emotional state, and includes information analyzed from text, voice, and facial expressions.

[1176] The "server" is a computer system that collects, stores, and analyzes communication metadata, work schedule information, and emotion data, and visualizes and proposes the results.

[1177] A "generative algorithm" is a program that uses a machine learning algorithm to generate a specific output (such as busyness or emotional state) from input data.

[1178] "Busyness" is an index that indicates the workload of each member, and is calculated based on communication metadata and work schedule information.

[1179] "Emotional state" is an indicator that shows each member's emotional and psychological state, and is analyzed based on emotional data.

[1180] "Visualization" means converting the analysis results into graphs or dashboards and displaying them in a way that is visually easy to understand.

[1181] "Work reallocation" means reallocating tasks to other members in order to reduce or adjust the workload on a particular member.

[1182] "Mental care proposals" means presenting psychological support and mental health care measures based on each member's emotional state.

[1183] This invention is a system that manages workloads and distributes tasks fairly in a remote work environment, and also has the function of managing the user's emotional state. This system is characterized by comprehensively collecting and analyzing communication metadata, work schedule information, and emotional data, and proposing work redistribution and mental care.

[1184] First, the device collects data related to each member's daily work. Communication metadata includes email sending and receiving logs, the number of chat messages, and the duration of video calls. Work schedule information is also obtained from calendar systems and other sources. Furthermore, an emotion engine is used to collect user emotion data from text, voice, and facial expressions. Natural language processing algorithms and speech recognition technology are used for analysis by this emotion engine.

[1185] The collected communication metadata, work schedule information, and emotion data are temporarily stored and then sent to a server at regular intervals. The server receives this data and stores it in a database. Communication is carried out using the HTTPS protocol, and all data is encrypted.

[1186] The server then uses a generation algorithm to analyze the collected data. The generation algorithm uses a machine learning algorithm to calculate the "busyness level" based on each member's communication volume, work schedule congestion, frequency of meetings, etc. Furthermore, the emotion engine analyzes the user's "emotional state" from email and chat text and audio during video conferences to generate indicators.

[1187] The analysis results are visualized by the server in the form of graphs and dashboards using graph generation libraries such as D3.js and Chart.js. Users can access these graphs and dashboards from their own devices to check the workload and emotional state of themselves and their entire team.

[1188] The server also generates suggestions for work redistribution and mental health care based on the analysis results. For example, if a member is very busy and in a negative emotional state, it will suggest reassigning that member's tasks to another member. Furthermore, if mental health care is needed, it will provide specific actions and support information.

[1189] As a specific example, consider a case where Employee B participates in numerous video conferences and processes a lot of emails. If the emotion engine detects signs of stress from Employee B's chat messages and comments during video conferences, this information is sent to the server. The server then evaluates Employee B's busyness as high and his emotional state as negative. These evaluation results are visualized as graphs, allowing the manager to check the situation at a glance. To reduce Employee B's burden, the manager can reallocate tasks to other members and provide mental health support to Employee B as needed.

[1190] Example prompt: "Please explain your system for efficiently managing each member's workload and emotional state in a remote work environment. Please provide detailed information, including specific data collection methods, data transmission and storage methods, data analysis methods, data visualization methods, work redistribution and mental health care proposal methods, and implementation methods. Please also provide specific examples."

[1191] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1192] Step 1:

[1193] The device periodically collects communication metadata (email sending and receiving logs, number of chat messages, and participation time in video calls) and work schedule information for each member. It also uses an emotion engine to collect emotional data from the user's text, voice, and facial expressions. Specifically, the device records logs of each communication method during working hours, and the emotion engine performs text analysis in real time and uses speech recognition technology to analyze audio during video conferences.

[1194] Input: Each member's communication data, work schedule, user text, voice, and facial expressions

[1195] Output: communication metadata, work schedule information, emotion data

[1196] Step 2:

[1197] The device sends the collected communication metadata, work schedule information, and emotion data to the server at regular intervals (e.g., once a day). Specifically, the device encrypts the data temporarily stored and uploads it to the server using the HTTPS protocol.

[1198] Input: communication metadata, work schedule information, emotion data

[1199] Output: Data sent to the server

[1200] Step 3:

[1201] The server receives the transmitted communication metadata, work schedule information, and emotion data and stores them in a database. Specifically, the server decodes the received data and stores them in the corresponding databases (for communication metadata, work schedule data, and emotion data).

[1202] Input: Data sent from the terminal

[1203] Output: Data stored in the database

[1204] Step 4:

[1205] The server analyzes data using a generation algorithm based on the stored communication metadata and work schedule information. The generation algorithm evaluates each member's communication volume, schedule congestion, frequency of meetings, etc., and calculates their "busyness level." It also uses an emotion engine to analyze the "emotional state" from the emotional data and generate an index. Specifically, the server runs an automated script and inputs the data into the analysis algorithm.

[1206] Input: Communication metadata, work schedule information, and emotion data stored in the database

[1207] Output: Busyness and emotional state of each member

[1208] Step 5:

[1209] The server converts the busyness level calculated by the generation algorithm and the emotional state analyzed by the emotion engine into a visually easy-to-understand format. Specifically, the server uses a graph generation library (such as D3.js or Chart.js) to convert the analysis results into a graph or dashboard format and display them on a web dashboard.

[1210] Input: Each member's busyness and emotional state

[1211] Output: Visualized data in the form of graphs and dashboards

[1212] Step 6:

[1213] The administrator, who is the user, checks and implements work reallocation and mental care suggestions based on the visualized data displayed by the server. Specifically, the administrator accesses the web dashboard and clicks on a work reallocation instruction to reallocate tasks or provide mental care support information.

[1214] Input: Visualized data displayed on the web dashboard

[1215] Output: Actual tasks reallocated and mental health support provided

[1216] This will enable efficient and fair distribution of work and appropriate mental care even in a remote work environment.

[1217] (Application example 2)

[1218] 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."

[1219] In remote work and factory environments, it is extremely important to efficiently manage the workload and emotional state of each member and operator. However, conventional systems have made it difficult to properly evaluate workload and emotional state, and to implement fair work distribution and mental care. In particular, there is a demand for a function that can analyze operator work data and communication logs in real time and immediately reflect the situation.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1221] In this invention, the server includes means for collecting communication metadata, means for collecting work schedule information, means for analyzing emotional data, means for estimating the busyness and emotional state of each member using a generating AI based on the collected communication metadata, work schedule information, and emotional data, means for visualizing the estimated busyness data and emotional state, means for proposing work redistribution and mental care based on the data, and means for displaying information in real time on a device worn by an operator. This makes it possible to efficiently and fairly manage the busyness and emotional state of each member and operator and to immediately implement improvement proposals.

[1222] "Communication metadata" refers to data such as email sending and receiving logs, number of chat messages, participation time in video conferences, operator work data and communication logs.

[1223] "Work schedule information" refers to schedule data such as work plans and meeting schedules for each member or operator.

[1224] "Server" refers to a central processing unit for receiving, storing, and analyzing data to estimate each member's busyness and emotional state.

[1225] "Generative AI" refers to artificial intelligence that uses machine learning algorithms to analyze each member's communication metadata, work schedule information, and emotional data.

[1226] "Busyness level" refers to an indicator that shows the amount of work and workload each member or operator is handling.

[1227] "Emotional state" refers to data used to assess the mental health and emotional fluctuations of each member or operator.

[1228] "Emotional data" refers to data about an individual's emotions analyzed from voice, facial expressions, verbal content, etc.

[1229] "Real-time display" refers to the function of instantly processing data and providing instant feedback to devices worn by each member or operator.

[1230] "Work reallocation" refers to a proposal to allocate work to other members in order to optimize the workload of each member or operator.

[1231] "Mental care suggestions" refer to suggestions based on emotional data to maintain and improve the mental health of each member or operator.

[1232] The system for implementing this invention is designed to enable employees and operators to efficiently manage their workload and emotional state. Its main components include a terminal that collects communication metadata and work schedule information, a server that analyzes, stores, and visualizes the data, and a user device that provides final suggestions and feedback.

[1233] Data collection

[1234] The device collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. Each member's work schedule information is also collected periodically. Furthermore, emotional data is analyzed from the operator's facial expressions and voice using a camera and microphone. Smart glasses or smartphones are used as the device.

[1235] Data transmission and storage

[1236] All data collected by the device is sent to the server at regular intervals. The server has a database where the received data is stored and used for subsequent analysis. Data is sent using the HTTP protocol.

[1237] Based on this data, the server analyzes each member's communication volume, the busyness of their work schedule, the frequency of meetings, etc., and estimates each member's "busyness level" and "emotional state."

[1238] Data analysis

[1239] The server first uses a generative AI model to analyze the collected communication metadata and work schedule information to calculate each member's busy level. It then uses an emotion engine to analyze the emotional data and determine each member's emotional state. Specifically, it uses natural language processing (NLP) technology and machine learning algorithms.

[1240] Data Visualization

[1241] The server converts the busyness data calculated by the generative AI and the emotional state identified by the emotion engine into a visually easy-to-understand format. This data is displayed in graphs and dashboards and fed back in real time to user devices such as smart glasses, smartphones, and PCs, allowing users and administrators to understand the situation at a glance.

[1242] Work redistribution and mental health care proposals

[1243] The server automatically generates suggestions for reallocating work and providing mental care based on the busyness assessment and emotional state. For example, if a specific member is overwhelmed with work or if that member's emotional state is negative, the server will suggest reallocating that work to other members who have more time. Furthermore, if mental care is needed, the server will suggest providing mental health support.

[1244] Reallocation and care delivery

[1245] The administrator, who is the user, can reallocate work based on this suggestion. Appropriate mental health care measures can also be taken for members whose emotional state is judged to be negative. For example, if employee B participates in many video conferences and handles a large number of emails, and the emotion engine detects high stress levels from employee B's chat messages and comments during video conferences, the server will suggest reallocating employee B's work to other members.

[1246] Examples of concrete examples and prompts

[1247] For example, if factory operator A works long hours on the day shift and data from smart glasses indicates that A's stress level is high, the following prompts can be input into the generative AI:

[1248] "Operator A's workload is high and his emotional state is negative. How would you redistribute his work and suggest appropriate mental health care?"

[1249] This allows the generative AI to propose specific work redistribution and mental care measures, making it possible to balance factory productivity with employee health.

[1250] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1251] Step 1:

[1252] The device periodically collects communication metadata such as email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs. In addition, it uses a camera and microphone to capture the operator's facial expressions and voice to obtain emotion data.

[1253] Input: communication metadata, facial expression data, voice data

[1254] Output: Collected communication metadata, emotion data

[1255] Step 2:

[1256] The device sends the collected communication metadata, emotion data, and work schedule information to a server via HTTP, which then receives and stores the data in a database.

[1257] Input: Collected communication metadata, emotion data, work schedule information

[1258] Output: Collected data stored in a database

[1259] Step 3:

[1260] The server uses a generative AI model to analyze communication metadata and work schedule information stored in the database to calculate each member's busy level, and an emotion engine to analyze emotion data and determine each member's emotional state.

[1261] Input: communication metadata, work schedule information, emotion data

[1262] Output: Calculated busyness data, emotional state data

[1263] Step 4:

[1264] The server converts the calculated busyness data and emotional state data into a visually easy-to-understand format and visualizes it in the form of graphs, dashboards, etc. This display information is sent in real time to user devices such as smart glasses, smartphones, and PCs.

[1265] Input: Busyness data, emotional state data

[1266] Output: Visualized graphs and dashboard information

[1267] Step 5:

[1268] The server then uses the analysis results to propose work redistribution and mental care, using a generative AI model to generate proposals for redistribution when a specific member's workload is high, or for mental care when the member's emotional state is negative.

[1269] Input: Busyness data, emotional state data

[1270] Output: Work reallocation proposals, mental care proposals

[1271] Step 6:

[1272] The administrator, who is the user, reviews the proposals sent from the server and reallocates work as necessary. Appropriate mental care measures are also taken for members with negative emotional states. For example, if high stress is detected in Operator A, a proposal is displayed based on a prompt from the generation AI: "Operator A's workload is high and his emotional state is negative. How would you reallocate work and suggest appropriate mental care?"

[1273] Input: Work reallocation proposals, mental care proposals

[1274] Output: Reallocated tasks, mental health measures implemented

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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).

[1282] 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.

[1283] 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."

[1284] 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.

[1285] 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).

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] 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.

[1294] 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 the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1295] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1296] The following is further disclosed regarding the above embodiment.

[1297] (Claim 1)

[1298] a means for collecting communication metadata;

[1299] a means for collecting work schedule information;

[1300] means for transmitting the collected communication metadata and work schedule information to a server;

[1301] A means for estimating the busyness of each member using a generating AI based on the data in the server;

[1302] A means for visualizing the estimated busyness data;

[1303] The system includes a means for proposing a reallocation of work based on the busyness data.

[1304] (Claim 2)

[1305] 2. The system of claim 1, wherein the communication metadata includes email sending and receiving logs, chat message counts, and video conference participation times.

[1306] (Claim 3)

[1307] The system of claim 1, wherein the generating AI calculates the busyness level using a machine learning algorithm based on each member's communication metadata and work schedule information.

[1308] "Example 1"

[1309] (Claim 1)

[1310] a means for collecting communication metadata;

[1311] a means for collecting work schedule information;

[1312] means for transmitting the collected communication metadata and work schedule information to a server;

[1313] A means for estimating the busyness of each member using a generated AI model based on the data in the server;

[1314] A means for visualizing the estimated busyness data;

[1315] means for proposing a reallocation of work based on the busyness data;

[1316] A system that includes a means for management to implement proposed work reallocations.

[1317] (Claim 2)

[1318] 2. The system of claim 1, wherein the communication metadata includes email sending and receiving logs, chat message counts, and online conference participation times.

[1319] (Claim 3)

[1320] The system of claim 1, wherein the generative AI model calculates busyness levels using a machine learning algorithm based on each member's communication metadata and work schedule information.

[1321] "Application Example 1"

[1322] (Claim 1)

[1323] a means for collecting communication metadata;

[1324] a means for collecting work schedule information;

[1325] means for transmitting the collected communication metadata and work schedule information to a server;

[1326] A means for estimating the busyness of each member using a generating AI based on the data in the server;

[1327] A means for visualizing the estimated busyness data;

[1328] means for proposing a reallocation of work based on the busyness data;

[1329] a means for collecting operational data and maintenance schedule information;

[1330] A means for estimating the operating load of each piece of equipment using generation AI;

[1331] A means for visualizing the estimated operational load data;

[1332] The system includes means for suggesting a reallocation of workload based on the workload data.

[1333] (Claim 2)

[1334] 2. The system of claim 1, wherein the communication metadata includes email sending and receiving logs, chat message counts, and video conference participation times.

[1335] (Claim 3)

[1336] The system of claim 1, wherein the generation AI calculates busyness and operational load using a machine learning algorithm based on each member's communication metadata, work schedule information, operation data, and maintenance schedule information.

[1337] "Example 2: Combining Emotion Engines"

[1338] (Claim 1)

[1339] a means for collecting communication metadata;

[1340] a means for collecting work schedule information;

[1341] means for collecting user emotion data;

[1342] means for transmitting the collected communication metadata, work schedule information, and emotion data to a server;

[1343] In the server, a means for estimating the busyness level and emotional state of each member using a generation algorithm based on the data;

[1344] a means for visualizing the estimated busyness data and emotional state data;

[1345] a means for reallocating work and proposing mental care based on the busyness data and emotional state data;

[1346] A system including:

[1347] (Claim 2)

[1348] 2. The system of claim 1, wherein the communication metadata includes email sending and receiving logs, chat message counts, and video call participation times.

[1349] (Claim 3)

[1350] The system of claim 1, wherein the generation algorithm calculates the busyness level and emotional state of each member based on communication metadata and work schedule information using a machine learning algorithm.

[1351] "Application example 2 when combining emotion engines"

[1352] (Claim 1)

[1353] a means for collecting communication metadata;

[1354] a means for collecting work schedule information;

[1355] means for transmitting the collected communication metadata and work schedule information to a server;

[1356] A means for estimating the busyness of each member using a generating AI based on the data in the server;

[1357] A means for visualizing the estimated busyness data;

[1358] means for proposing a reallocation of work based on the busyness data;

[1359] a means for analyzing emotion data;

[1360] A means for suggesting mental care based on the estimated emotional state;

[1361] A system including a means for displaying information in real time on an operator-worn device.

[1362] (Claim 2)

[1363] 2. The system of claim 1, wherein the communication metadata includes email sending and receiving logs, chat message counts, video conference participation time, operator work data, and communication logs.

[1364] (Claim 3)

[1365] The system of claim 1, wherein the generating AI calculates the busyness level and emotional state of each member using a machine learning algorithm based on communication metadata, work schedule information, and emotional data. [Explanation of symbols]

[1366] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting communication metadata; a means for collecting work schedule information; means for transmitting the collected communication metadata and work schedule information to a server; A means for estimating the busyness of each member using a generating AI based on the data in the server; A means for visualizing the estimated busyness data; The system includes a means for proposing a reallocation of work based on the busyness data.

2. The system of claim 1 , wherein the communication metadata includes email sending and receiving logs, chat message counts, and video conference participation times.

3. The system of claim 1, wherein the generating AI calculates the busyness level using a machine learning algorithm based on each member's communication metadata and work schedule information.

Images