System

Abstract

A system is provided.SOLUTION: A system comprising means for collecting and aggregating data for each project using a generative AI, means for analyzing the collected data in real-time to understand progress and resource utilization, means for optimally assigning tasks and optimizing schedules using the generative AI, means for predicting risk based on past data and current progress data and presenting countermeasures, and means for presenting suggestions to users through notifications and user interfaces.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] This invention supports project novices who find it difficult to manage the overall project, manage resources, and identify stakeholders in project management tasks. Specifically, functions such as real-time monitoring of project progress, optimal task allocation, schedule optimization, risk prediction, and presentation of countermeasures are essential. The purpose of this is to enable project managers with little experience to efficiently progress projects. [Means for solving the problem]

[0005] The present invention is a system that includes a means for collecting and integrating project data using a generative AI, a means for analyzing the collected data in real time to understand progress and resource usage, a means for optimally allocating tasks and optimizing schedules using the generative AI, a means for predicting risks based on past and current progress data and proposing countermeasures, and a means for presenting suggestions to users through notifications and a user interface, thereby enabling even project novices to effectively manage projects and reduce risks.

[0006] "Generative AI" is a system that uses artificial intelligence technology to generate and analyze data.

[0007] "Project data" refers to all information related to project management, such as project progress, task details, and resource usage.

[0008] "Collection and integration" is the process of gathering information from disparate data sources and consolidating it into a single database.

[0009] "Real-time analysis" means processing and analyzing collected data immediately, enabling you to always be aware of the latest situation.

[0010] "Progress" is information that indicates the stage of the project and how much of each task has been completed.

[0011] "Resource usage status" is information that indicates how human, material, and time resources used in a project are being used.

[0012] "Optimal task allocation" is the process of assigning each task to the most suitable team member.

[0013] "Schedule optimization" means making adjustments to streamline the overall project schedule and prevent unnecessary delays.

[0014] "Risk prediction" means detecting potential problems or issues that may arise in the future based on past data and current progress data.

[0015] "Proposing countermeasures" means proposing appropriate measures for predicted risks.

[0016] "Notification" is a feature that notifies users of system-generated suggestions and warnings.

[0017] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0018] "Suggestions" are recommendations of optimal actions or measures that the system provides to users based on generated AI. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The project management support system of this invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the system is implemented by a server, terminal, and user, each with their own role.

[0041] Server Processing

[0042] 1. Data Collection and Integration

[0043] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and integrated through a formatting and cleansing process.

[0044] 2. Data analysis

[0045] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[0046] 3. Task allocation and schedule optimization

[0047] The server uses generative AI to assign optimal tasks based on the skill sets and work history of project members, and also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[0048] 4. Risk prediction and countermeasures

[0049] The server predicts risks based on past project data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific phase, it generates countermeasures to mitigate the risk and notifies the user.

[0050] Terminal handling

[0051] 1. Notification and interface updates

[0052] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0053] 2. Accepting and Sending User Input

[0054] The terminal accepts manual task assignments and schedule changes by the project manager and sends that information to the server, allowing the terminal to reassign new tasks to specific members, for example.

[0055] 3. Visualization of risk information

[0056] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0057] User interaction and feedback

[0058] 1. Review progress and risk information

[0059] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[0060] 2. Task assignment and schedule management

[0061] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of project progress.

[0062] 3. Implementation of risk countermeasures

[0063] Users receive risk prediction information and take countermeasures based on it. The server provides options for countermeasures and implements specific action plans to reduce project risks.

[0064] Specific examples

[0065] Task assignment

[0066] The server analyzes each member's skill set and work history and assigns new tasks to the most suitable member. For example, a member with strong design skills might be assigned the task of user interface design, while a member with strong development skills might be assigned the task of coding new features.

[0067] Risk prediction

[0068] The server analyzes past project data and detects when specific phases are prone to resource shortages. For example, based on the fact that past projects have experienced many delays in the database migration phase, the server will suggest adding resources or extending the time.

[0069] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[0070] The processing flow will be explained below.

[0071] Step 1: Data collection

[0072] The server collects progress data, task data, and resource data for each project through APIs. Specifically, it connects with project management tools and resource management systems to obtain the latest data.

[0073] Step 2: Data integration

[0074] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[0075] Step 3: Real-time analytics

[0076] The server analyzes the consolidated data in real time, instantly understanding the progress of each task and resource usage, and generates information to display on a dashboard.

[0077] Step 4: Progress forecast

[0078] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data and current progress, it calculates future progress and the possibility of resource shortages.

[0079] Step 5: Task assignment

[0080] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set and work history. Specifically, it assigns the most appropriate work to each member, improving the efficiency of the entire project.

[0081] Step 6: Schedule optimization

[0082] The server optimizes the schedule for the entire project, using techniques such as the critical path method (CPM) to reconstruct the schedule to prevent unnecessary delays.

[0083] Step 7: Risk prediction

[0084] The server predicts risks based on past and current progress data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[0085] Step 8: Generate countermeasures

[0086] The server generates countermeasures to address risks and notifies the project manager, suggesting additional resources or rescheduling the project.

[0087] Step 9: Notifications and User Interface Updates

[0088] The device receives notifications and suggestions from the server and displays them in a user interface designed to help users intuitively understand important information.

[0089] Step 10: Accepting User Input

[0090] The terminal accepts manual task assignments and schedule changes made by the project manager, and sends that information to the server, which then reanalyzes the data based on the new information.

[0091] Step 11: Visualize risk information

[0092] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly implement specific countermeasures.

[0093] Step 12: Review progress and risk information

[0094] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[0095] Step 13: Task assignment and scheduling

[0096] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary. This operation is done through the terminal, and the information is again processed by the server.

[0097] Step 14: Implement risk responses

[0098] The user receives risk prediction information and takes countermeasures based on it. The server implements the countermeasures suggested by the user to reduce the risk of the project.

[0099] Step 15: Feedback Loop

[0100] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[0101] Example 1

[0102] 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."

[0103] In conventional project management systems, data collection and integration, progress management, and resource management are all performed separately, limiting overall efficiency and effectiveness. Risk prediction and countermeasure proposals are often performed manually, creating problems that are prone to human error and delays. This increases the risk of project delays and raises concerns about a lower overall project success rate. Furthermore, the system requires sufficient management skills, making it technically challenging, especially for project novices.

[0104] 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.

[0105] In this invention, the server includes a means for collecting and integrating data for each project using a data collection device, a means for analyzing the collected data in real time to grasp the project's progress and resource usage, and a means for optimally allocating tasks and optimizing the schedule using generative AI. This enables centralized management and real-time analysis of project data, significantly improving the efficiency of project progress management and resource management, and automating risk prediction and countermeasure proposals, thereby increasing the project success rate. It also provides support for even project beginners to effectively manage projects.

[0106] A "data collection device" is a device that can automatically collect data for each project and integrate it as needed.

[0107] "Real-time analytics" is the process of processing and analyzing data immediately at the moment it is collected.

[0108] "Generative AI" is a technology that uses artificial intelligence to analyze and predict data, and then generates optimal suggestions and actions based on the results.

[0109] "Optimal task allocation" is the process of efficiently assigning each project task to the most suitable member.

[0110] "Schedule optimization" is the process of managing the time schedule of all tasks in a project in the most efficient and effective way.

[0111] "Risk prediction" is the process of predicting potential problems and risks in the progress of a project in advance based on past data and current progress data.

[0112] "Proposing countermeasures" refers to proposing optimal countermeasures for predicted risks.

[0113] A "notification system" is a mechanism for quickly communicating important information and offers to users.

[0114] The "user interface" is the visual and operational part through which a user directly interacts with a system.

[0115] A "project manager" is a person responsible for planning, managing progress, and allocating resources for a project.

[0116] The project management support system of the present invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures.

[0117] Server Processing

[0118] First, the server collects progress data, task data, and resource data from each project management tool via its API and stores it in a database. Specifically, data is collected from tools such as JIRA, Trello, and Asana. This data is then formatted and cleansed using the Python pandas library and stored in a MySQL database.

[0119] The server then analyzes the stored data in real time, using generative AI models (e.g., GPT-3 and BERT) to forecast progress and resource demand and supply, and immediately updates the results, allowing project managers to understand the progress of their projects in real time.

[0120] Furthermore, the server uses generative AI to assign tasks and optimize the schedule. It considers each member's skill set and work history to assign optimal tasks. It also utilizes the critical path method to efficiently optimize the schedule. At this time, the server queries the generative AI model using a prompt such as, "What tasks should be assigned to members with high design skills?"

[0121] Finally, the server predicts risks based on past project data and current progress data and suggests countermeasures. For example, it sends a prompt such as, "Please tell me the predicted risks in the database migration phase and the countermeasures," to the generative AI model, and displays the results on the user interface to notify the project manager.

[0122] Terminal handling

[0123] The device receives notifications and suggestions from the server and displays that information in a user interface. The UI is designed to be intuitive and easy to use, allowing users to easily understand important information. Specifically, a dashboard built using React.js and Vue.js is used.

[0124] The terminal also has a function that allows project managers to manually assign tasks and change schedules. This allows project managers to reassign tasks and adjust schedules. In this case, the input data is sent to the server using the JavaScript fetch API.

[0125] Furthermore, the device visualizes risk and countermeasure information provided by the server and presents details and recommended actions to the user. Risk information is drawn as a graph using D3.js, and details are displayed in tooltips, making it easy for users to understand the risks.

[0126] User interaction and feedback

[0127] Project managers can check project progress and risk information through a dashboard on their devices. Real-time updates are available to reassign tasks and change schedules. They can also take appropriate countermeasures based on risk information and send feedback to the server.

[0128] Specifically, users can check real-time charts and graphs displayed on the dashboard and flexibly manage the progress of the project as needed. Risk response options are presented, and users can select and implement the appropriate response to effectively reduce project risks.

[0129] As a result, the system of the present invention will significantly improve the efficiency of project management work and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1: Data collection and integration

[0132] The server sends API requests to each project management tool (e.g., JIRA, Trello, Asana) to collect progress data, task data, and resource data. The retrieved data is temporarily saved in JSON format, and then reformatted and cleansed using Python's pandas library. Specifically, unnecessary columns are removed, leaving only the necessary information. The reformatted data is imported into a MySQL database and consolidated in a unified format. This creates a dataset for each project.

[0133] Input: API request (project management tool)

[0134] Output: Consolidated dataset (MySQL database)

[0135] Step 2: Real-time analysis

[0136] The server retrieves the latest project data from the database using SQL queries. It then sends prompts to a generative AI model (e.g., GPT-3 or BERT) to predict progress and resource supply and demand. The analysis results are immediately sent via WebSocket to a front-end built with React.js and displayed in the UI in real time. Specifically, metrics such as progress rate and resource usage are visualized.

[0137] Input: Latest project data (SQL query)

[0138] Output: Progress forecast, resource supply and demand forecast (WebSocket)

[0139] Step 3: Task allocation and schedule optimization

[0140] The server retrieves each member's skill set and work history from the database and sends prompts to the generative AI model. The optimal task assignment and schedule is received from the generative AI model and updated in the database. For example, a prompt such as "What tasks should be assigned to members with high design skills?" is used. The critical path method (CPM) is also used to optimize the overall project schedule.

[0141] Input: Member skill set, work history (SQL query)

[0142] Output: Optimal task assignment, optimized schedule (database update)

[0143] Step 4: Risk prediction and countermeasure proposal

[0144] The server predicts risks based on past and current project data. It sends prompts such as "Please tell us the risks predicted for the database migration phase and their countermeasures" to the generative AI model, and receives the risk predictions and countermeasures. The information based on this is displayed on the device's user interface and notified to the project management personnel.

[0145] Input: Past and current project data (SQL query)

[0146] Output: Risk prediction, countermeasures (user interface)

[0147] Step 5: Update notifications and interface

[0148] The device receives WebSocket notifications from the server, analyzes the content, and updates the user interface. Specifically, the UI, built with React.js and Vue.js, displays risk predictions and task assignment information in real time, allowing project managers to instantly grasp the latest situation.

[0149] Input: WebSocket notification (from server)

[0150] Output: Updated user interface (real-time information display)

[0151] Step 6: Accepting and Sending User Input

[0152] The terminal accepts operations from project managers. Specifically, it provides an input form for manual task assignment and schedule changes, and sends the input data to the server using the JavaScript fetch API. This allows task and schedule adjustments to be reflected in real time.

[0153] Input: User operations (task assignment, schedule change)

[0154] Output: Send data to the server (fetch API)

[0155] Step 7: Visualize risk information

[0156] The device receives risk information and countermeasure information provided by the server and visualizes it using D3.js. Specifically, the risk information is drawn as graphs and charts, and detailed information is displayed in tooltips. This allows users to easily understand the details of the risks and recommended actions.

[0157] Input: Risk information, countermeasure information (notification from the server)

[0158] Output: Visualized risk information (graphs, charts)

[0159] Step 8: Review progress and risk information

[0160] Users can access the dashboard on their device to check project progress and risk information in real time. By clicking on a specific graph, further details will be displayed in a modal window, allowing users to gain a detailed understanding of the project's status.

[0161] Input: Dashboard access

[0162] Output: Display of real-time information (modal window)

[0163] Step 9: Task assignment and scheduling

[0164] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary by using the drag-and-drop functionality to reassign tasks and clicking the save button to submit the changes to the server.

[0165] Input: Task assignment, schedule proposal (from server)

[0166] Output: Send manual correction data (to server)

[0167] Step 10: Implement risk responses

[0168] The user selects an action to be taken from the list of risk countermeasures displayed on the dashboard and clicks the execute button. The selected action is recorded on the server, and the execution results are also fed back.

[0169] Input: Risk Response Selection (Dashboard)

[0170] Output: Execution and feedback (notification to the server)

[0171] As a result, this system can improve the efficiency of project management operations and increase the success rate of projects.

[0172] (Application example 1)

[0173] 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."

[0174] In current factory operations, production planning, task allocation, resource optimization, risk prediction, and countermeasure presentation are often not adequately handled. This can lead to reduced efficiency and delayed troubleshooting, raising concerns about a decline in overall factory productivity. It is also difficult to integrate data from different devices and systems and analyze it in real time. Solving these issues will significantly improve factory operational efficiency.

[0175] 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.

[0176] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time and understanding progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting proposals to users through notifications and a user interface; means for collecting data in real time from each device in the factory and integrating it into a central server; means for analyzing and reporting resource usage in the production process in real time; means for optimally allocating tasks based on the specialized skills and past work history of each device; and means for predicting risks in the production process and proposing countermeasures to mitigate the risks, thereby significantly improving the operational efficiency of the entire factory and maximizing productivity.

[0177] "Generative AI" is artificial intelligence that uses machine learning techniques to collect, analyze, predict, and make suggestions about data.

[0178] "Data collection and integration" refers to collecting data from different systems and devices, formatting and cleansing that data, and integrating it into a single database.

[0179] "Real-time analysis" means instantly analyzing collected data to understand current progress and resource usage, and immediately reflecting the results.

[0180] "Task allocation" is the act of automatically specifying the most suitable task, taking into consideration the skill sets and work history of project members and equipment.

[0181] "Schedule optimization" refers to adjusting the overall project plan to proceed efficiently and deriving the optimal schedule using methods such as the critical path method (CPM).

[0182] "Risk prediction" is the act of predicting future risks based on past data and current conditions.

[0183] "Countermeasures" refer to specific actions or measures that should be taken in response to predicted risks.

[0184] "Notification" is the act of conveying important information or suggestions from the system to the user.

[0185] "User interface" refers to the screens and operating methods that users use to exchange information with a system.

[0186] "Each piece of equipment in the factory" refers to all the equipment and facilities used to carry out production activities.

[0187] A "central server" is a server that is responsible for integrating and managing all collected data and performing analysis and optimization.

[0188] "Specialized skills" refers to the knowledge and techniques required to perform a specific task or work.

[0189] "Work history" refers to a record of tasks and work done in the past.

[0190] MODE FOR CARRYING OUT THE INVENTION

[0191] The factory management system of this invention aims to maximize productivity by streamlining factory operations through generative AI. This system provides a series of functions including data collection and integration, real-time analysis, task assignment, schedule optimization, risk prediction, and countermeasure proposals.

[0192] Server Processing

[0193] 1. Data Collection and Integration

[0194] The server collects data in real time from each device in the factory and consolidates it into a central server. It uses APIs for data collection and the pandas library for data formatting and cleansing. This process allows data from different systems and devices to be managed centrally.

[0195] 2. Real-time analysis

[0196] The server instantly analyzes the collected data to understand the current progress and resource usage. This process uses a generative AI model to analyze the data and predict progress and resource supply and demand. The generative AI model makes it possible to understand the situation in real time.

[0197] 3. Task allocation and schedule optimization

[0198] The server uses generative AI to optimally allocate tasks, taking into account the specialized skills and past work history of each device. It also optimizes the overall project schedule for efficient progress. It optimizes the schedule using techniques such as the critical path method (CPM).

[0199] 4. Risk prediction and countermeasures

[0200] The server predicts risks based on past data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific production process, it generates countermeasures to mitigate the risk and notifies the user.

[0201] Terminal handling

[0202] 1. Notification and interface updates

[0203] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0204] 2. Accepting and Sending User Input

[0205] The terminal accepts manual task assignments and schedule changes by factory managers and sends the information to the server, allowing them to, for example, reassign new tasks to specific equipment.

[0206] 3. Visualization of risk information

[0207] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0208] User interaction and feedback

[0209] 1. Review progress and risk information

[0210] The user (factory manager) can check real-time updates of progress and risk information through the terminal interface, and all necessary information is displayed on the dashboard.

[0211] 2. Task assignment and schedule management

[0212] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of factory operations.

[0213] 3. Implementation of risk countermeasures

[0214] The user receives risk prediction information and takes specific countermeasures based on it. Based on the countermeasures proposed by the server, the user takes action to reduce risks throughout the factory.

[0215] Specific examples

[0216] For example, let's consider data collection and management when Robot A is performing welding work in a factory in real time. Data on Robot A's work efficiency and the materials used is automatically collected via API. The collected data is formatted and stored in a database using the pandas library. When a generative AI model analyzes this data and finds that Robot A is consuming more materials than usual, that information is immediately sent to the terminal and the necessary countermeasures are presented.

[0217] Example prompt for a generative AI model:

[0218] "Based on progress and resource usage, predict the process where risks are most likely to occur next and propose countermeasures."

[0219] The above is an embodiment of the present invention, which makes it possible to improve the efficiency of factory operations and maximize productivity.

[0220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0221] Step 1:

[0222] The server collects data in real time from each device in the factory. The input is data from each device via API, and the output is formatted and cleansed data. This data is then stored in a database through pipeline processing.

[0223] Step 2:

[0224] The server analyzes the collected data in real time using a generative AI model. The input is formatted and cleansed data, and the output is a visualization of each device's progress and resource usage. The AI ​​model analyzes the data and detects anomalies and patterns.

[0225] Step 3:

[0226] The server uses a generation AI to optimally allocate tasks. The input is data including the specialized skills and past work history of each device, and the output is the optimal task allocation for each device. The generation AI automatically generates the allocation by taking into account the relationship between skills and tasks.

[0227] Step 4:

[0228] The server optimizes the schedule for the entire project. The input is current progress and resource usage data, and the output is an optimized schedule. It uses the critical path method (CPM) to create an efficient production plan.

[0229] Step 5:

[0230] The server predicts risks based on past data and current progress data and proposes countermeasures. The input is past project data and current progress data, and the output is predicted risks and proposed countermeasures. The AI ​​model analyzes risks and generates countermeasures.

[0231] Step 6:

[0232] The terminal displays notifications and suggestions from the server on a user interface. The input is notification data and suggestion data from the server, and the output is an intuitive presentation of information on a UI. The interface displays important information visually and clearly.

[0233] Step 7:

[0234] The terminal accepts user input and sends that information to the server. The input is the user's task assignment or schedule change operation, and the output is updated data to the server. The user operates the interface and inputs information.

[0235] Step 8:

[0236] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents it to the user. The input is risk prediction data and countermeasure data, and the output is detailed risk information and recommended actions. The user checks the risk information and takes specific countermeasures.

[0237] Step 9:

[0238] Users can view progress and risk information through a device interface. The input is real-time data on the device, and the output is understanding the current situation and taking action. Users can view the information on the dashboard and select the necessary actions.

[0239] Step 10:

[0240] The user implements the risk countermeasures presented by the server. The input is the countermeasures proposed by the server, and the output is a specific action plan for risk reduction. Measures are then taken promptly based on the countermeasures.

[0241] Step 11:

[0242] Users can input prompt statements into the generative AI model to request additional analysis, such as "Based on progress and resource usage, please predict the next process where a risk is most likely to occur and propose countermeasures," to obtain more detailed analysis results.

[0243] 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.

[0244] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. This provides advanced support for improving project efficiency and risk management. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[0245] Server Processing

[0246] 1. Data Collection and Integration

[0247] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process.

[0248] 2. Data analysis

[0249] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[0250] 3. Task allocation and schedule optimization

[0251] The server uses generative AI to optimally assign tasks based on the skill sets and work history of project members, as well as emotional data provided by the emotion engine. It also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[0252] 4. Risk prediction and countermeasures

[0253] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that are likely to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[0254] Terminal handling

[0255] 1. Notification and interface updates

[0256] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0257] 2. Accepting and Sending User Input

[0258] The terminal accepts manual task assignments and schedule changes by the project manager, as well as emotional input, and sends that information to the server, allowing it to, for example, reassign new tasks to specific members.

[0259] 3. Visualization of risk information

[0260] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[0261] User interaction and feedback

[0262] 1. Review progress and risk information

[0263] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[0264] 2. Task assignment and schedule management

[0265] The user can review the task assignments and schedules proposed by the server, manually revise them as needed, and provide feedback on emotional data, which is then used for further optimization.

[0266] 3. Implementation of risk countermeasures

[0267] Users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[0268] Emotion engine integration

[0269] 1. Collecting Emotional Data

[0270] The emotion engine recognizes emotions in real time from the user's facial expressions, voice, text data, etc., and sends that data to the server.

[0271] 2. Emotional Data Integration and Analysis

[0272] The server combines the data sent by the emotion engine with project data and uses it for analysis, for example, adjusting task assignments to take into account a user's increased stress level.

[0273] 3. Improving risk prediction and countermeasures

[0274] The server uses the emotion data to more accurately predict risks and propose countermeasures, such as reducing the task load of users who show signs of stress or fatigue.

[0275] Specific examples

[0276] Task assignment

[0277] The server analyzes each member's skill set, work history, and emotional data and assigns tasks to the most suitable member. For example, if a member with strong design skills is confirmed to have not been feeling stressed recently, he or she will be assigned the task of user interface design.

[0278] Risk prediction and countermeasures

[0279] The server predicts project risks based on past project data, current progress data, and emotional data. For example, it can determine that a particular phase is prone to resource shortages, while also detecting rising stress levels from the emotional data of current team members and suggesting countermeasures.

[0280] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI and an emotion engine, even beginners can improve their project management skills.

[0281] The processing flow will be explained below.

[0282] Step 1: Data collection

[0283] The server collects progress data, task data, and resource data for each project through APIs. It connects with project management tools and resource management systems and obtains emotion data from the emotion engine.

[0284] Step 2: Data integration

[0285] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[0286] Step 3: Real-time analytics

[0287] The server analyzes the integrated data in real time, instantly understanding the progress of each task, resource usage, and user sentiment data.

[0288] Step 4: Progress forecast

[0289] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data, current progress, and emotion data, it calculates future progress and the possibility of resource shortages.

[0290] Step 5: Task assignment

[0291] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set, work history, and emotional data. For example, it assigns important tasks to members with low stress levels.

[0292] Step 6: Schedule optimization

[0293] The server optimizes the schedule for the entire project, using the critical path method (CPM) to prevent unnecessary delays.

[0294] Step 7: Risk prediction

[0295] The server predicts risks based on past and current progress data and emotion data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[0296] Step 8: Generate countermeasures

[0297] The server generates risk countermeasures and notifies the project manager, for example, suggesting additional resources or rescheduling the schedule.

[0298] Step 9: Notifications and User Interface Updates

[0299] The device receives notifications and suggestions from the server and displays them in the user interface, which is designed to help users intuitively understand important information.

[0300] Step 10: Accepting User Input

[0301] The terminal accepts manual task assignments and schedule changes by the project manager, including input of emotional information, and transmits that information to the server.

[0302] Step 11: Visualize risk information

[0303] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0304] Step 12: Review progress and risk information

[0305] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[0306] Step 13: Task assignment and scheduling

[0307] The user can review the task assignments and schedules proposed by the server and manually correct them if necessary. They can also provide feedback on emotional data, which can be used for further optimization.

[0308] Step 14: Implement risk responses

[0309] Users receive risk prediction information and take countermeasures based on it, such as assigning lighter tasks to members experiencing high stress levels.

[0310] Step 15: Feedback Loop

[0311] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[0312] Example 2

[0313] 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."

[0314] Conventional project management systems do not adequately grasp progress and resource usage, optimally allocate tasks, or predict risks and present countermeasures. Furthermore, they are unable to optimize or manage risks taking into account the emotional state of users, resulting in insufficient project efficiency and risk management. This increases uncertainty in the progress of projects, making it difficult to achieve optimal results.

[0315] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0316] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks and proposing countermeasures based on past data and current progress data; means for presenting the proposals to the user through notifications and a user interface; means for collecting, analyzing, and integrating user emotion data using an emotion engine; and means for improving risk predictions and countermeasure proposals based on the emotion data. This enables real-time understanding of project progress and resource usage, optimal task allocation and schedule optimization including emotion data, and highly accurate risk predictions and proposals of countermeasures.

[0317] - "Generative AI" is a system that uses artificial intelligence technology to collect, integrate, analyze, and predict data.

[0318] "Project data" refers to a group of information that indicates the progress of a project, task information, resource usage status, emotional data, and the like.

[0319] "Real-time analysis" is the process of processing data instantly to understand the current situation.

[0320] "Progress" is information that indicates how much of a project's tasks have been completed.

[0321] "Resource usage status" refers to the current status of human and material resources used in a project.

[0322] "Optimal task allocation" is the process of assigning each task to the most suitable member based on the project members' skills and circumstances.

[0323] "Schedule optimization" is a method of optimizing the timeline of the entire project to ensure efficient progress.

[0324] "Risk prediction" is the process of predicting possible future problems or failures based on past and current data.

[0325] "Proposing countermeasures" means proposing specific solutions or actions to address predicted risks.

[0326] A "user interface" is a screen or operating means that allows a user to interact with a system.

[0327] "Presenting a proposal to the user" refers to the act of displaying the proposal content from the system to the user.

[0328] The "emotion engine" is a system that recognizes and analyzes the user's emotional state and collects that data.

[0329] "Emotion data" is data that indicates the user's stress level and emotional state.

[0330] "Analyze and synthesize" is the process of processing collected data and turning it into a unified, usable information.

[0331] "Improving risk prediction and countermeasure proposals" means providing more accurate risk predictions and specific, effective countermeasures based on emotion data.

[0332] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[0333] Server Processing

[0334] The server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process. A relational database such as MySQL is used as the database.

[0335] The server analyzes the collected data in real time to understand the progress of each task and the resource usage status. It also uses a generative AI model to predict progress and resource supply and demand, and immediately updates the results. For example, it provides a prediction such as, "Based on the current progress, Task A will be completed in three days."

[0336] Furthermore, the server uses generative AI to optimally assign tasks to project members, taking into account their skill sets, work history, and emotional data provided by the emotion engine. For example, it may suggest, "Since member C has high data analysis skills, he should be assigned to analysis tasks." It also uses techniques such as the critical path method (CPM) to optimize the overall project schedule and make suggestions for efficient progress.

[0337] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that tend to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[0338] Terminal handling

[0339] The device receives notifications and suggestions from the server and displays them in the user interface. An intuitive UI is designed to make it easy for users to understand important information. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[0340] The terminal also accepts manual task assignments and schedule changes by the project manager, as well as emotional information, and sends this information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[0341] Furthermore, the device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[0342] User interaction and feedback

[0343] The user (project manager) checks the project progress and risk information through the terminal interface. The dashboard displays information that is updated in real time. For example, the user can perform an operation such as "Check the progress rate and risk information for Task A on the dashboard."

[0344] The user can also check the task assignments and schedules proposed by the server and manually revise them as necessary. Emotional data is also fed back, and further optimization is performed based on that information. For example, the system may provide feedback such as "If you feel stressed, enter that emotional data into the device."

[0345] Furthermore, users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[0346] Emotion engine integration

[0347] The emotion engine recognizes emotions in real time based on the user's facial expressions, voice, and text data, and sends that data to the server. For example, it can detect "fatigue" from the user's facial expressions and record it as data.

[0348] The server integrates the data sent from the emotion engine with project data and uses it for analysis. If a user's stress level increases, it can take that into account and adjust task assignments. For example, task progress data can be linked to user emotion data and managed centrally.

[0349] The server uses the emotional data to make more accurate risk predictions and propose countermeasures. Specifically, it predicts the "stress level for the next week" based on the emotional data and generates specific countermeasures based on that.

[0350] Examples of concrete examples and prompts

[0351] Specific examples

[0352] 1. Example of task assignment:

[0353] A suggestion is made such as, "Member C has high skills in data analysis, so we will assign him to the analysis task."

[0354] 2. Examples of risk prediction and countermeasures:

[0355] "Detect rising stress levels from current team members' emotional data and suggest countermeasures to reduce the risk of resource shortages."

[0356] Prompt Sentence Examples

[0357] PROGRESS_TRACK='Check your progress.'

[0358] TASK_ASSIGN = 'Consider the skill sets and sentiment data of project members to assign optimal tasks.'

[0359] RISK_RESPONSE = 'Predict risks based on past and current data and provide countermeasures.'

[0360] In this way, this system will significantly improve the efficiency of project management operations and help increase the success rate of projects. In addition, the use of generative AI and an emotion engine will enable data-driven decision-making, improving the ability of even project novices to manage projects.

[0361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0362] Step 1:

[0363] The server collects progress data, task data, resource data, and emotion data from project management tools and emotion engines via APIs. Specifically, it collects project progress and task information from JIRA, Trello, etc., and obtains data on users' stress and emotional state from the emotion engine.

[0364] Input: Data from project management tools and sentiment engines

[0365] Output: Collected data (progress data, task data, resource data, emotion data)

[0366] Step 2:

[0367] The server formats and cleanses the collected data, for example, by removing unnecessary data and completing missing values, thereby improving the quality of the data.

[0368] Input: Various collected data

[0369] Output: Formatted and cleansed data

[0370] Step 3:

[0371] The server then consolidates the formatted and cleansed data and stores it in a database (e.g., MySQL), resulting in a unified data set.

[0372] Input: Formatted and cleansed data

[0373] Output: Consolidated data stored in a database

[0374] Step 4:

[0375] The server analyzes the integrated data in real time and visualizes progress and resource usage, for example, by outputting graphs showing the progress rate of each task and the workload of each member.

[0376] Input: Integrated data stored in a database

[0377] Output: Analysis results (progress, resource usage visualization graphs)

[0378] Step 5:

[0379] The server uses the generative AI model to predict progress and resource demand and supply, for example, generating a prediction such as "Task A is expected to be completed in three days, based on the current progress."

[0380] Inputs: Integrated data and real-time progress

[0381] Output: Progress forecast and resource demand forecast

[0382] Step 6:

[0383] The server uses a generative AI model to analyze the skill sets, work history, and emotional data of project members, and then optimally assigns tasks and optimizes the schedule. For example, it may suggest that "member C has high data analysis skills, so he should be assigned to analysis tasks."

[0384] Input: Integrated data, project member skill sets and work history, sentiment data

[0385] Output: Optimized task assignment and schedule

[0386] Step 7:

[0387] The server predicts risks based on past project data, current progress data, and emotion data. For example, it generates countermeasures to reduce the risk if the user has many tasks that are likely to cause stress.

[0388] Inputs: Integration data, past and current progress data, sentiment data

[0389] Output: Risk prediction and countermeasures

[0390] Step 8:

[0391] The device receives notifications and suggestions from the server and displays them in the user interface. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[0392] Input: Notifications and suggestions from the server

[0393] Output: Notifications and suggestions displayed in the user interface

[0394] Step 9:

[0395] The terminal accepts the project manager's manual task assignment and schedule change operations, as well as emotional information input, and sends that information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[0396] Input: Manual input from project manager (task assignments, schedule changes, sentiment information)

[0397] Output: Updates sent to the server

[0398] Step 10:

[0399] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions. For example, it displays information such as "There is a risk of resource shortage in the next phase" in a graph.

[0400] Input: Risk prediction and countermeasure information provided by the server

[0401] Output: Risk information and countermeasures displayed in the user interface

[0402] Step 11:

[0403] Users can check the project's progress and risk information through the device interface and manually modify tasks as needed. Emotional data is also provided as feedback. For example, users can "check the progress rate and risk information for Task A on the dashboard, and if they feel stressed, enter their emotional data into the device."

[0404] Inputs: Progress and risk information from the dashboard, manual user input (task corrections, sentiment data)

[0405] Output: Updated progress and risk information, feedback information to the server

[0406] Step 12:

[0407] The user receives risk prediction information and takes countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[0408] Input: Risk prediction information and countermeasure proposals

[0409] Output: Measures taken, risk mitigation

[0410] (Application example 2)

[0411] 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."

[0412] Modern manufacturing requires efficient project management, but conventional systems have difficulty taking into account the emotional state of human resources when allocating tasks and managing schedules. This increases worker stress, risking reduced productivity and quality. Furthermore, adequate information is often unavailable for risk prediction and countermeasures, resulting in measures being implemented only after a problem has occurred. To address these issues, it is necessary to develop a system that uses real-time emotional data to optimally allocate tasks and predict risks.

[0413] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting and integrating data for each project using a generation AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing the schedule using the generation AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting suggestions to the user through notifications and a user interface; means for collecting emotional data in real time using various sensors used in the work environment and integrating and analyzing this emotional data with project data; and means for allocating tasks and predicting risks based on the emotional data. This enables efficient task allocation and risk management while taking into account the emotional states of workers.

[0414] "Generative AI" is a technology that uses artificial intelligence techniques to generate data, make inferences, and make predictions.

[0415] "Project data" refers to information necessary for project management, such as progress, task details, and resource usage.

[0416] "Real-time" refers to data being collected, analyzed, and processed with minimal delay, and updated and reflected immediately.

[0417] "Emotion data" is data that represents the emotional state of a worker and is acquired using sensors and analytical algorithms.

[0418] "Optimal task allocation" means assigning tasks to the person best suited to each task, taking into account the worker's skill set and emotional data.

[0419] "Schedule optimization" refers to the readjustment and optimization of a schedule to most efficiently move a project forward.

[0420] "Risk prediction" means predicting problems or obstacles that may occur in the future based on past data and current progress data.

[0421] "Proposing countermeasures" means proposing appropriate measures and action plans for predicted risks.

[0422] "Notification" is a function that allows the server to convey information such as warnings and suggestions to the user.

[0423] "User interface" refers to the screen and input devices that allow a user to interact with a system.

[0424] "Various sensors used in the work environment" refers to devices such as cameras, microphones, and vital signs sensors that detect data within the environment and the status of workers.

[0425] This invention is a system that supports project management by combining generative AI and an emotion engine, with the aim of improving the efficiency of work within factories. This system consists of a server, terminals, users, and an emotion engine, each of which has a specific role.

[0426] Server Processing

[0427] The server is responsible for collecting and integrating data from each project using generative AI. Specifically, it uses the following hardware and software:

[0428] Hardware: General-purpose server equipment

[0429] Software: Generative AI models implemented in TensorFlow and PyTorch, and data collection APIs

[0430] First, the server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a data shaping and cleansing process. Next, the server analyzes the data in real time to understand the progress and resource usage of each task. It also uses generative AI models to forecast progress and resource supply and demand, and immediately updates the results.

[0431] The server also uses generative AI to optimally allocate tasks and optimize schedules. For example, it considers the skill sets, work history, and emotional data of project members to optimally allocate tasks. It also uses optimization algorithms such as the critical path method (CPM) to make suggestions for efficiently progressing the entire project schedule.

[0432] Terminal handling

[0433] The terminal functions as an interface for receiving notifications and suggestions from the server. The user interface (UI) is intuitively designed so that users can easily understand important information. Specifically, it provides the following functions:

[0434] Notifications and interface updates: Receives notifications and suggestions from the server and displays them in the user interface.

[0435] Accepting and sending user input: Accepting user actions such as manually assigning or rescheduling a task, and sending that information to the server.

[0436] User interaction and feedback

[0437] The project manager, who is the user, uses the system by performing the following operations.

[0438] Check progress and risk information: Check project progress and risk information through a user interface. The dashboard displays real-time updates.

[0439] Task Allocation and Schedule Management: You can check the task allocation and schedule proposed by the server and manually correct them if necessary. You can also provide emotional feedback.

[0440] Implement risk response measures: Receive risk prediction information and implement response measures based on it, such as reassigning stressful tasks to other members.

[0441] Emotion engine integration

[0442] The emotion engine collects emotion data in real time using various sensors used in the work environment and sends this data to the server. Based on this emotion data, the server can make more accurate risk predictions and propose countermeasures. Specifically, the process includes the following steps:

[0443] Emotion data collection: Recognize emotions in real time from the user's facial expressions, voice, text data, etc.

[0444] Emotional data integration and analysis: Emotional data can be integrated with project data and used for analysis, for example, to take into account increased user stress levels and adjust task assignments accordingly.

[0445] Risk prediction and improved response: Emotional data is used to generate suggestions to reduce task load for users showing signs of stress or fatigue.

[0446] Examples of concrete examples and prompts

[0447] Example of task allocation: Based on worker skill sets and emotional data, assign maintenance work for a particular machine to a worker who is familiar with operating that machine and does not feel stressed.

[0448] A concrete example of risk prediction and countermeasures: If emotional data indicates that a particular worker is prone to fatigue, the system can assign lighter work to reduce the worker's workload or send a notification recommending that they take a break.

[0449] An example of a prompt is, "Assign priority tasks to workers with high skill sets and low stress levels." By inputting this prompt into the generative AI model, optimal task assignments are made.

[0450] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0451] Step 1:

[0452] The server collects progress data, task data, and resource data for each project via API. At the same time, it also acquires emotional data from various sensors (cameras, microphones, vital signs sensors, etc.) installed in the work environment and stores it in a database. The input is data from various sensors and project management tools, and the output is formatted, cleansed, and integrated data.

[0453] Step 2:

[0454] The server analyzes the input data in real time to grasp the progress and resource usage of each task. At this time, it uses a generation AI to predict progress and resource supply and demand. The input is the integrated data from step 1, and the output is the analysis results and forecast data. For example, it calculates the progress rate and the planned resource usage.

[0455] Step 3:

[0456] The server uses generative AI to optimally allocate tasks and optimize the schedule, taking into account the skill sets, work history, and emotional data of project members. The input is the analysis results and prediction data from Step 2, and the output is the optimized task allocation and schedule.

[0457] Step 4:

[0458] The server analyzes the data to predict risks and propose countermeasures. Risk prediction is based on past data, current progress data, and emotion data. The input is the data from Steps 2 and 3, and the output is risk prediction and proposed countermeasures. For example, it generates a proposal to reduce tasks that are likely to cause stress to a specific worker.

[0459] Step 5:

[0460] The device receives notifications and suggestions from the server and displays them on the user interface. An intuitive UI is designed so that users can easily understand important information. The input is the notification and suggestion data from the server, and the output is the information displayed on the user interface.

[0461] Step 6:

[0462] The terminal accepts manual task assignments and schedule changes by the project manager and sends the information to the server. The input is the operation data from the user, and the output is the correction data sent to the server. For example, when a specific task is reassigned to a specific member.

[0463] Step 7:

[0464] The server assigns tasks and predicts risks based on the emotion data, and generates a further optimized plan based on the results. The inputs are emotion data and user feedback data, and the output is an updated task assignment and risk response plan.

[0465] Step 8:

[0466] Users input prompt statements into the generative AI model and obtain specific task assignments and risk response measures based on them. The input is the prompt statement, and the output is the assignment and response proposals from the generative AI model.

[0467] Through the above steps, the system of the present invention realizes project management that takes into account real-time emotional data, enabling efficient work and risk management.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] [Second embodiment]

[0472] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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).

[0478] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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.

[0483] 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."

[0484] The project management support system of this invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the system is implemented by a server, terminal, and user, each with their own role.

[0485] Server Processing

[0486] 1. Data Collection and Integration

[0487] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and integrated through a formatting and cleansing process.

[0488] 2. Data analysis

[0489] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[0490] 3. Task allocation and schedule optimization

[0491] The server uses generative AI to assign optimal tasks based on the skill sets and work history of project members, and also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[0492] 4. Risk prediction and countermeasures

[0493] The server predicts risks based on past project data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific phase, it generates countermeasures to mitigate the risk and notifies the user.

[0494] Terminal handling

[0495] 1. Notification and interface updates

[0496] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0497] 2. Accepting and Sending User Input

[0498] The terminal accepts manual task assignments and schedule changes by the project manager and sends that information to the server, allowing the terminal to reassign new tasks to specific members, for example.

[0499] 3. Visualization of risk information

[0500] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0501] User interaction and feedback

[0502] 1. Review progress and risk information

[0503] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[0504] 2. Task assignment and schedule management

[0505] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of project progress.

[0506] 3. Implementation of risk countermeasures

[0507] Users receive risk prediction information and take countermeasures based on it. The server provides options for countermeasures and implements specific action plans to reduce project risks.

[0508] Specific examples

[0509] Task assignment

[0510] The server analyzes each member's skill set and work history and assigns new tasks to the most suitable member. For example, a member with strong design skills might be assigned the task of user interface design, while a member with strong development skills might be assigned the task of coding new features.

[0511] Risk prediction

[0512] The server analyzes past project data and detects when specific phases are prone to resource shortages. For example, based on the fact that past projects have experienced many delays in the database migration phase, the server will suggest adding resources or extending the time.

[0513] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[0514] The processing flow will be explained below.

[0515] Step 1: Data collection

[0516] The server collects progress data, task data, and resource data for each project through APIs. Specifically, it connects with project management tools and resource management systems to obtain the latest data.

[0517] Step 2: Data integration

[0518] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[0519] Step 3: Real-time analytics

[0520] The server analyzes the consolidated data in real time, instantly understanding the progress of each task and resource usage, and generates information to display on a dashboard.

[0521] Step 4: Progress forecast

[0522] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data and current progress, it calculates future progress and the possibility of resource shortages.

[0523] Step 5: Task assignment

[0524] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set and work history. Specifically, it assigns the most appropriate work to each member, improving the efficiency of the entire project.

[0525] Step 6: Schedule optimization

[0526] The server optimizes the schedule for the entire project, using techniques such as the critical path method (CPM) to reconstruct the schedule to prevent unnecessary delays.

[0527] Step 7: Risk prediction

[0528] The server predicts risks based on past and current progress data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[0529] Step 8: Generate countermeasures

[0530] The server generates countermeasures to address risks and notifies the project manager, suggesting additional resources or rescheduling the project.

[0531] Step 9: Notifications and User Interface Updates

[0532] The device receives notifications and suggestions from the server and displays them in a user interface designed to help users intuitively understand important information.

[0533] Step 10: Accepting User Input

[0534] The terminal accepts manual task assignments and schedule changes made by the project manager, and sends that information to the server, which then reanalyzes the data based on the new information.

[0535] Step 11: Visualize risk information

[0536] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly implement specific countermeasures.

[0537] Step 12: Review progress and risk information

[0538] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[0539] Step 13: Task assignment and scheduling

[0540] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary. This operation is done through the terminal, and the information is again processed by the server.

[0541] Step 14: Implement risk responses

[0542] The user receives risk prediction information and takes countermeasures based on it. The server implements the countermeasures suggested by the user to reduce the risk of the project.

[0543] Step 15: Feedback Loop

[0544] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[0545] Example 1

[0546] 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."

[0547] In conventional project management systems, data collection and integration, progress management, and resource management are all performed separately, limiting overall efficiency and effectiveness. Risk prediction and countermeasure proposals are often performed manually, creating problems that are prone to human error and delays. This increases the risk of project delays and raises concerns about a lower overall project success rate. Furthermore, the system requires sufficient management skills, making it technically challenging, especially for project novices.

[0548] 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.

[0549] In this invention, the server includes a means for collecting and integrating data for each project using a data collection device, a means for analyzing the collected data in real time to grasp the project's progress and resource usage, and a means for optimally allocating tasks and optimizing the schedule using generative AI. This enables centralized management and real-time analysis of project data, significantly improving the efficiency of project progress management and resource management, and automating risk prediction and countermeasure proposals, thereby increasing the project success rate. It also provides support for even project beginners to effectively manage projects.

[0550] A "data collection device" is a device that can automatically collect data for each project and integrate it as needed.

[0551] "Real-time analytics" is the process of processing and analyzing data immediately at the moment it is collected.

[0552] "Generative AI" is a technology that uses artificial intelligence to analyze and predict data, and then generates optimal suggestions and actions based on the results.

[0553] "Optimal task allocation" is the process of efficiently assigning each project task to the most suitable member.

[0554] "Schedule optimization" is the process of managing the time schedule of all tasks in a project in the most efficient and effective way.

[0555] "Risk prediction" is the process of predicting potential problems and risks in the progress of a project in advance based on past data and current progress data.

[0556] "Proposing countermeasures" refers to proposing optimal countermeasures for predicted risks.

[0557] A "notification system" is a mechanism for quickly communicating important information and offers to users.

[0558] The "user interface" is the visual and operational part through which a user directly interacts with a system.

[0559] A "project manager" is a person responsible for planning, managing progress, and allocating resources for a project.

[0560] The project management support system of the present invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures.

[0561] Server Processing

[0562] First, the server collects progress data, task data, and resource data from each project management tool via its API and stores it in a database. Specifically, data is collected from tools such as JIRA, Trello, and Asana. This data is then formatted and cleansed using the Python pandas library and stored in a MySQL database.

[0563] The server then analyzes the stored data in real time, using generative AI models (e.g., GPT-3 and BERT) to forecast progress and resource demand and supply, and immediately updates the results, allowing project managers to understand the progress of their projects in real time.

[0564] Furthermore, the server uses generative AI to assign tasks and optimize the schedule. It considers each member's skill set and work history to assign optimal tasks. It also utilizes the critical path method to efficiently optimize the schedule. At this time, the server queries the generative AI model using a prompt such as, "What tasks should be assigned to members with high design skills?"

[0565] Finally, the server predicts risks based on past project data and current progress data and suggests countermeasures. For example, it sends a prompt such as, "Please tell me the predicted risks in the database migration phase and the countermeasures," to the generative AI model, and displays the results on the user interface to notify the project manager.

[0566] Terminal handling

[0567] The device receives notifications and suggestions from the server and displays that information in a user interface. The UI is designed to be intuitive and easy to use, allowing users to easily understand important information. Specifically, a dashboard built using React.js and Vue.js is used.

[0568] The terminal also has a function that allows project managers to manually assign tasks and change schedules. This allows project managers to reassign tasks and adjust schedules. In this case, the input data is sent to the server using the JavaScript fetch API.

[0569] Furthermore, the device visualizes risk and countermeasure information provided by the server and presents details and recommended actions to the user. Risk information is drawn as a graph using D3.js, and details are displayed in tooltips, making it easy for users to understand the risks.

[0570] User interaction and feedback

[0571] Project managers can check project progress and risk information through a dashboard on their devices. Real-time updates are available to reassign tasks and change schedules. They can also take appropriate countermeasures based on risk information and send feedback to the server.

[0572] Specifically, users can check real-time charts and graphs displayed on the dashboard and flexibly manage the progress of the project as needed. Risk response options are presented, and users can select and implement the appropriate response to effectively reduce project risks.

[0573] As a result, the system of the present invention will significantly improve the efficiency of project management work and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[0574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0575] Step 1: Data collection and integration

[0576] The server sends API requests to each project management tool (e.g., JIRA, Trello, Asana) to collect progress data, task data, and resource data. The retrieved data is temporarily saved in JSON format, and then reformatted and cleansed using Python's pandas library. Specifically, unnecessary columns are removed, leaving only the necessary information. The reformatted data is imported into a MySQL database and consolidated in a unified format. This creates a dataset for each project.

[0577] Input: API request (project management tool)

[0578] Output: Consolidated dataset (MySQL database)

[0579] Step 2: Real-time analysis

[0580] The server retrieves the latest project data from the database using SQL queries. It then sends prompts to a generative AI model (e.g., GPT-3 or BERT) to predict progress and resource supply and demand. The analysis results are immediately sent via WebSocket to a front-end built with React.js and displayed in the UI in real time. Specifically, metrics such as progress rate and resource usage are visualized.

[0581] Input: Latest project data (SQL query)

[0582] Output: Progress forecast, resource supply and demand forecast (WebSocket)

[0583] Step 3: Task allocation and schedule optimization

[0584] The server retrieves each member's skill set and work history from the database and sends prompts to the generative AI model. The optimal task assignment and schedule is received from the generative AI model and updated in the database. For example, a prompt such as "What tasks should be assigned to members with high design skills?" is used. The critical path method (CPM) is also used to optimize the overall project schedule.

[0585] Input: Member skill set, work history (SQL query)

[0586] Output: Optimal task assignment, optimized schedule (database update)

[0587] Step 4: Risk prediction and countermeasure proposal

[0588] The server predicts risks based on past and current project data. It sends prompts such as "Please tell us the risks predicted for the database migration phase and their countermeasures" to the generative AI model, and receives the risk predictions and countermeasures. The information based on this is displayed on the device's user interface and notified to the project management personnel.

[0589] Input: Past and current project data (SQL query)

[0590] Output: Risk prediction, countermeasures (user interface)

[0591] Step 5: Update notifications and interface

[0592] The device receives WebSocket notifications from the server, analyzes the content, and updates the user interface. Specifically, the UI, built with React.js and Vue.js, displays risk predictions and task assignment information in real time, allowing project managers to instantly grasp the latest situation.

[0593] Input: WebSocket notification (from server)

[0594] Output: Updated user interface (real-time information display)

[0595] Step 6: Accepting and Sending User Input

[0596] The terminal accepts operations from project managers. Specifically, it provides an input form for manual task assignment and schedule changes, and sends the input data to the server using the JavaScript fetch API. This allows task and schedule adjustments to be reflected in real time.

[0597] Input: User operations (task assignment, schedule change)

[0598] Output: Send data to the server (fetch API)

[0599] Step 7: Visualize risk information

[0600] The device receives risk information and countermeasure information provided by the server and visualizes it using D3.js. Specifically, the risk information is drawn as graphs and charts, and detailed information is displayed in tooltips. This allows users to easily understand the details of the risks and recommended actions.

[0601] Input: Risk information, countermeasure information (notification from the server)

[0602] Output: Visualized risk information (graphs, charts)

[0603] Step 8: Review progress and risk information

[0604] Users can access the dashboard on their device to check project progress and risk information in real time. By clicking on a specific graph, further details will be displayed in a modal window, allowing users to gain a detailed understanding of the project's status.

[0605] Input: Dashboard access

[0606] Output: Display of real-time information (modal window)

[0607] Step 9: Task assignment and scheduling

[0608] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary by using the drag-and-drop functionality to reassign tasks and clicking the save button to submit the changes to the server.

[0609] Input: Task assignment, schedule proposal (from server)

[0610] Output: Send manual correction data (to server)

[0611] Step 10: Implement risk responses

[0612] The user selects an action to be taken from the list of risk countermeasures displayed on the dashboard and clicks the execute button. The selected action is recorded on the server, and the execution results are also fed back.

[0613] Input: Risk Response Selection (Dashboard)

[0614] Output: Execution and feedback (notification to the server)

[0615] As a result, this system can improve the efficiency of project management operations and increase the success rate of projects.

[0616] (Application example 1)

[0617] 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."

[0618] In current factory operations, production planning, task allocation, resource optimization, risk prediction, and countermeasure presentation are often not adequately handled. This can lead to reduced efficiency and delayed troubleshooting, raising concerns about a decline in overall factory productivity. It is also difficult to integrate data from different devices and systems and analyze it in real time. Solving these issues will significantly improve factory operational efficiency.

[0619] 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.

[0620] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time and understanding progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting proposals to users through notifications and a user interface; means for collecting data in real time from each device in the factory and integrating it into a central server; means for analyzing and reporting resource usage in the production process in real time; means for optimally allocating tasks based on the specialized skills and past work history of each device; and means for predicting risks in the production process and proposing countermeasures to mitigate the risks, thereby significantly improving the operational efficiency of the entire factory and maximizing productivity.

[0621] "Generative AI" is artificial intelligence that uses machine learning techniques to collect, analyze, predict, and make suggestions about data.

[0622] "Data collection and integration" refers to collecting data from different systems and devices, formatting and cleansing that data, and integrating it into a single database.

[0623] "Real-time analysis" means instantly analyzing collected data to understand current progress and resource usage, and immediately reflecting the results.

[0624] "Task allocation" is the act of automatically specifying the most suitable task, taking into consideration the skill sets and work history of project members and equipment.

[0625] "Schedule optimization" refers to adjusting the overall project plan to proceed efficiently and deriving the optimal schedule using methods such as the critical path method (CPM).

[0626] "Risk prediction" is the act of predicting future risks based on past data and current conditions.

[0627] "Countermeasures" refer to specific actions or measures that should be taken in response to predicted risks.

[0628] "Notification" is the act of conveying important information or suggestions from the system to the user.

[0629] "User interface" refers to the screens and operating methods that users use to exchange information with a system.

[0630] "Each piece of equipment in the factory" refers to all the equipment and facilities used to carry out production activities.

[0631] A "central server" is a server that is responsible for integrating and managing all collected data and performing analysis and optimization.

[0632] "Specialized skills" refers to the knowledge and techniques required to perform a specific task or work.

[0633] "Work history" refers to a record of tasks and work done in the past.

[0634] MODE FOR CARRYING OUT THE INVENTION

[0635] The factory management system of this invention aims to maximize productivity by streamlining factory operations through generative AI. This system provides a series of functions including data collection and integration, real-time analysis, task assignment, schedule optimization, risk prediction, and countermeasure proposals.

[0636] Server Processing

[0637] 1. Data Collection and Integration

[0638] The server collects data in real time from each device in the factory and consolidates it into a central server. It uses APIs for data collection and the pandas library for data formatting and cleansing. This process allows data from different systems and devices to be managed centrally.

[0639] 2. Real-time analysis

[0640] The server instantly analyzes the collected data to understand the current progress and resource usage. This process uses a generative AI model to analyze the data and predict progress and resource supply and demand. The generative AI model makes it possible to understand the situation in real time.

[0641] 3. Task allocation and schedule optimization

[0642] The server uses generative AI to optimally allocate tasks, taking into account the specialized skills and past work history of each device. It also optimizes the overall project schedule for efficient progress. It optimizes the schedule using techniques such as the critical path method (CPM).

[0643] 4. Risk prediction and countermeasures

[0644] The server predicts risks based on past data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific production process, it generates countermeasures to mitigate the risk and notifies the user.

[0645] Terminal handling

[0646] 1. Notification and interface updates

[0647] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0648] 2. Accepting and Sending User Input

[0649] The terminal accepts manual task assignments and schedule changes by factory managers and sends the information to the server, allowing them to, for example, reassign new tasks to specific equipment.

[0650] 3. Visualization of risk information

[0651] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0652] User interaction and feedback

[0653] 1. Review progress and risk information

[0654] The user (factory manager) can check real-time updates of progress and risk information through the terminal interface, and all necessary information is displayed on the dashboard.

[0655] 2. Task assignment and schedule management

[0656] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of factory operations.

[0657] 3. Implementation of risk countermeasures

[0658] The user receives risk prediction information and takes specific countermeasures based on it. Based on the countermeasures proposed by the server, the user takes action to reduce risks throughout the factory.

[0659] Specific examples

[0660] For example, let's consider data collection and management when Robot A is performing welding work in a factory in real time. Data on Robot A's work efficiency and the materials used is automatically collected via API. The collected data is formatted and stored in a database using the pandas library. When a generative AI model analyzes this data and finds that Robot A is consuming more materials than usual, that information is immediately sent to the terminal and the necessary countermeasures are presented.

[0661] Example prompt for a generative AI model:

[0662] "Based on progress and resource usage, predict the process where risks are most likely to occur next and propose countermeasures."

[0663] The above is an embodiment of the present invention, which makes it possible to improve the efficiency of factory operations and maximize productivity.

[0664] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0665] Step 1:

[0666] The server collects data in real time from each device in the factory. The input is data from each device via API, and the output is formatted and cleansed data. This data is then stored in a database through pipeline processing.

[0667] Step 2:

[0668] The server analyzes the collected data in real time using a generative AI model. The input is formatted and cleansed data, and the output is a visualization of each device's progress and resource usage. The AI ​​model analyzes the data and detects anomalies and patterns.

[0669] Step 3:

[0670] The server uses a generation AI to optimally allocate tasks. The input is data including the specialized skills and past work history of each device, and the output is the optimal task allocation for each device. The generation AI automatically generates the allocation by taking into account the relationship between skills and tasks.

[0671] Step 4:

[0672] The server optimizes the schedule for the entire project. The input is current progress and resource usage data, and the output is an optimized schedule. It uses the critical path method (CPM) to create an efficient production plan.

[0673] Step 5:

[0674] The server predicts risks based on past data and current progress data and proposes countermeasures. The input is past project data and current progress data, and the output is predicted risks and proposed countermeasures. The AI ​​model analyzes risks and generates countermeasures.

[0675] Step 6:

[0676] The terminal displays notifications and suggestions from the server on a user interface. The input is notification data and suggestion data from the server, and the output is an intuitive presentation of information on a UI. The interface displays important information visually and clearly.

[0677] Step 7:

[0678] The terminal accepts user input and sends that information to the server. The input is the user's task assignment or schedule change operation, and the output is updated data to the server. The user operates the interface and inputs information.

[0679] Step 8:

[0680] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents it to the user. The input is risk prediction data and countermeasure data, and the output is detailed risk information and recommended actions. The user checks the risk information and takes specific countermeasures.

[0681] Step 9:

[0682] Users can view progress and risk information through a device interface. The input is real-time data on the device, and the output is understanding the current situation and taking action. Users can view the information on the dashboard and select the necessary actions.

[0683] Step 10:

[0684] The user implements the risk countermeasures presented by the server. The input is the countermeasures proposed by the server, and the output is a specific action plan for risk reduction. Measures are then taken promptly based on the countermeasures.

[0685] Step 11:

[0686] Users can input prompt statements into the generative AI model to request additional analysis, such as "Based on progress and resource usage, please predict the next process where a risk is most likely to occur and propose countermeasures," to obtain more detailed analysis results.

[0687] 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.

[0688] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. This provides advanced support for improving project efficiency and risk management. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[0689] Server Processing

[0690] 1. Data Collection and Integration

[0691] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process.

[0692] 2. Data analysis

[0693] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[0694] 3. Task allocation and schedule optimization

[0695] The server uses generative AI to optimally assign tasks based on the skill sets and work history of project members, as well as emotional data provided by the emotion engine. It also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[0696] 4. Risk prediction and countermeasures

[0697] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that are likely to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[0698] Terminal handling

[0699] 1. Notification and interface updates

[0700] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0701] 2. Accepting and Sending User Input

[0702] The terminal accepts manual task assignments and schedule changes by the project manager, as well as emotional input, and sends that information to the server, allowing it to, for example, reassign new tasks to specific members.

[0703] 3. Visualization of risk information

[0704] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[0705] User interaction and feedback

[0706] 1. Review progress and risk information

[0707] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[0708] 2. Task assignment and schedule management

[0709] The user can review the task assignments and schedules proposed by the server, manually revise them as needed, and provide feedback on emotional data, which is then used for further optimization.

[0710] 3. Implementation of risk countermeasures

[0711] Users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[0712] Emotion engine integration

[0713] 1. Collecting Emotional Data

[0714] The emotion engine recognizes emotions in real time from the user's facial expressions, voice, text data, etc., and sends that data to the server.

[0715] 2. Emotional Data Integration and Analysis

[0716] The server combines the data sent by the emotion engine with project data and uses it for analysis, for example, adjusting task assignments to take into account a user's increased stress level.

[0717] 3. Improving risk prediction and countermeasures

[0718] The server uses the emotion data to more accurately predict risks and propose countermeasures, such as reducing the task load of users who show signs of stress or fatigue.

[0719] Specific examples

[0720] Task assignment

[0721] The server analyzes each member's skill set, work history, and emotional data and assigns tasks to the most suitable member. For example, if a member with strong design skills is confirmed to have not been feeling stressed recently, he or she will be assigned the task of user interface design.

[0722] Risk prediction and countermeasures

[0723] The server predicts project risks based on past project data, current progress data, and emotional data. For example, it can determine that a particular phase is prone to resource shortages, while also detecting rising stress levels from the emotional data of current team members and suggesting countermeasures.

[0724] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI and an emotion engine, even beginners can improve their project management skills.

[0725] The processing flow will be explained below.

[0726] Step 1: Data collection

[0727] The server collects progress data, task data, and resource data for each project through APIs. It connects with project management tools and resource management systems and obtains emotion data from the emotion engine.

[0728] Step 2: Data integration

[0729] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[0730] Step 3: Real-time analytics

[0731] The server analyzes the integrated data in real time, instantly understanding the progress of each task, resource usage, and user sentiment data.

[0732] Step 4: Progress forecast

[0733] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data, current progress, and emotion data, it calculates future progress and the possibility of resource shortages.

[0734] Step 5: Task assignment

[0735] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set, work history, and emotional data. For example, it assigns important tasks to members with low stress levels.

[0736] Step 6: Schedule optimization

[0737] The server optimizes the schedule for the entire project, using the critical path method (CPM) to prevent unnecessary delays.

[0738] Step 7: Risk prediction

[0739] The server predicts risks based on past and current progress data and emotion data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[0740] Step 8: Generate countermeasures

[0741] The server generates risk countermeasures and notifies the project manager, for example, suggesting additional resources or rescheduling the schedule.

[0742] Step 9: Notifications and User Interface Updates

[0743] The device receives notifications and suggestions from the server and displays them in the user interface, which is designed to help users intuitively understand important information.

[0744] Step 10: Accepting User Input

[0745] The terminal accepts manual task assignments and schedule changes by the project manager, including input of emotional information, and transmits that information to the server.

[0746] Step 11: Visualize risk information

[0747] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0748] Step 12: Review progress and risk information

[0749] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[0750] Step 13: Task assignment and scheduling

[0751] The user can review the task assignments and schedules proposed by the server and manually correct them if necessary. They can also provide feedback on emotional data, which can be used for further optimization.

[0752] Step 14: Implement risk responses

[0753] Users receive risk prediction information and take countermeasures based on it, such as assigning lighter tasks to members experiencing high stress levels.

[0754] Step 15: Feedback Loop

[0755] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[0756] Example 2

[0757] 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."

[0758] Conventional project management systems do not adequately grasp progress and resource usage, optimally allocate tasks, or predict risks and present countermeasures. Furthermore, they are unable to optimize or manage risks taking into account the emotional state of users, resulting in insufficient project efficiency and risk management. This increases uncertainty in the progress of projects, making it difficult to achieve optimal results.

[0759] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0760] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks and proposing countermeasures based on past data and current progress data; means for presenting the proposals to the user through notifications and a user interface; means for collecting, analyzing, and integrating user emotion data using an emotion engine; and means for improving risk predictions and countermeasure proposals based on the emotion data. This enables real-time understanding of project progress and resource usage, optimal task allocation and schedule optimization including emotion data, and highly accurate risk predictions and proposals of countermeasures.

[0761] - "Generative AI" is a system that uses artificial intelligence technology to collect, integrate, analyze, and predict data.

[0762] "Project data" refers to a group of information that indicates the progress of a project, task information, resource usage status, emotional data, and the like.

[0763] "Real-time analysis" is the process of processing data instantly to understand the current situation.

[0764] "Progress" is information that indicates how much of a project's tasks have been completed.

[0765] "Resource usage status" refers to the current status of human and material resources used in a project.

[0766] "Optimal task allocation" is the process of assigning each task to the most suitable member based on the project members' skills and circumstances.

[0767] "Schedule optimization" is a method of optimizing the timeline of the entire project to ensure efficient progress.

[0768] "Risk prediction" is the process of predicting possible future problems or failures based on past and current data.

[0769] "Proposing countermeasures" means proposing specific solutions or actions to address predicted risks.

[0770] A "user interface" is a screen or operating means that allows a user to interact with a system.

[0771] "Presenting a proposal to the user" refers to the act of displaying the proposal content from the system to the user.

[0772] The "emotion engine" is a system that recognizes and analyzes the user's emotional state and collects that data.

[0773] "Emotion data" is data that indicates the user's stress level and emotional state.

[0774] "Analyze and synthesize" is the process of processing collected data and turning it into a unified, usable information.

[0775] "Improving risk prediction and countermeasure proposals" means providing more accurate risk predictions and specific, effective countermeasures based on emotion data.

[0776] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[0777] Server Processing

[0778] The server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process. A relational database such as MySQL is used as the database.

[0779] The server analyzes the collected data in real time to understand the progress of each task and the resource usage status. It also uses a generative AI model to predict progress and resource supply and demand, and immediately updates the results. For example, it provides a prediction such as, "Based on the current progress, Task A will be completed in three days."

[0780] Furthermore, the server uses generative AI to optimally assign tasks to project members, taking into account their skill sets, work history, and emotional data provided by the emotion engine. For example, it may suggest, "Since member C has high data analysis skills, he should be assigned to analysis tasks." It also uses techniques such as the critical path method (CPM) to optimize the overall project schedule and make suggestions for efficient progress.

[0781] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that tend to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[0782] Terminal handling

[0783] The device receives notifications and suggestions from the server and displays them in the user interface. An intuitive UI is designed to make it easy for users to understand important information. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[0784] The terminal also accepts manual task assignments and schedule changes by the project manager, as well as emotional information, and sends this information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[0785] Furthermore, the device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[0786] User interaction and feedback

[0787] The user (project manager) checks the project progress and risk information through the terminal interface. The dashboard displays information that is updated in real time. For example, the user can perform an operation such as "Check the progress rate and risk information for Task A on the dashboard."

[0788] The user can also check the task assignments and schedules proposed by the server and manually revise them as necessary. Emotional data is also fed back, and further optimization is performed based on that information. For example, the system may provide feedback such as "If you feel stressed, enter that emotional data into the device."

[0789] Furthermore, users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[0790] Emotion engine integration

[0791] The emotion engine recognizes emotions in real time based on the user's facial expressions, voice, and text data, and sends that data to the server. For example, it can detect "fatigue" from the user's facial expressions and record it as data.

[0792] The server integrates the data sent from the emotion engine with project data and uses it for analysis. If a user's stress level increases, it can take that into account and adjust task assignments. For example, task progress data can be linked to user emotion data and managed centrally.

[0793] The server uses the emotional data to make more accurate risk predictions and propose countermeasures. Specifically, it predicts the "stress level for the next week" based on the emotional data and generates specific countermeasures based on that.

[0794] Examples of concrete examples and prompts

[0795] Specific examples

[0796] 1. Example of task assignment:

[0797] A suggestion is made such as, "Member C has high skills in data analysis, so we will assign him to the analysis task."

[0798] 2. Examples of risk prediction and countermeasures:

[0799] "Detect rising stress levels from current team members' emotional data and suggest countermeasures to reduce the risk of resource shortages."

[0800] Prompt Sentence Examples

[0801] PROGRESS_TRACK='Check your progress.'

[0802] TASK_ASSIGN = 'Consider the skill sets and sentiment data of project members to assign optimal tasks.'

[0803] RISK_RESPONSE = 'Predict risks based on past and current data and provide countermeasures.'

[0804] In this way, this system will significantly improve the efficiency of project management operations and help increase the success rate of projects. In addition, the use of generative AI and an emotion engine will enable data-driven decision-making, improving the ability of even project novices to manage projects.

[0805] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0806] Step 1:

[0807] The server collects progress data, task data, resource data, and emotion data from project management tools and emotion engines via APIs. Specifically, it collects project progress and task information from JIRA, Trello, etc., and obtains data on users' stress and emotional state from the emotion engine.

[0808] Input: Data from project management tools and sentiment engines

[0809] Output: Collected data (progress data, task data, resource data, emotion data)

[0810] Step 2:

[0811] The server formats and cleanses the collected data, for example, by removing unnecessary data and completing missing values, thereby improving the quality of the data.

[0812] Input: Various collected data

[0813] Output: Formatted and cleansed data

[0814] Step 3:

[0815] The server then consolidates the formatted and cleansed data and stores it in a database (e.g., MySQL), resulting in a unified data set.

[0816] Input: Formatted and cleansed data

[0817] Output: Consolidated data stored in a database

[0818] Step 4:

[0819] The server analyzes the integrated data in real time and visualizes progress and resource usage, for example, by outputting graphs showing the progress rate of each task and the workload of each member.

[0820] Input: Integrated data stored in a database

[0821] Output: Analysis results (progress, resource usage visualization graphs)

[0822] Step 5:

[0823] The server uses the generative AI model to predict progress and resource demand and supply, for example, generating a prediction such as "Task A is expected to be completed in three days, based on the current progress."

[0824] Inputs: Integrated data and real-time progress

[0825] Output: Progress forecast and resource demand forecast

[0826] Step 6:

[0827] The server uses a generative AI model to analyze the skill sets, work history, and emotional data of project members, and then optimally assigns tasks and optimizes the schedule. For example, it may suggest that "member C has high data analysis skills, so he should be assigned to analysis tasks."

[0828] Input: Integrated data, project member skill sets and work history, sentiment data

[0829] Output: Optimized task assignment and schedule

[0830] Step 7:

[0831] The server predicts risks based on past project data, current progress data, and emotion data. For example, it generates countermeasures to reduce the risk if the user has many tasks that are likely to cause stress.

[0832] Inputs: Integration data, past and current progress data, sentiment data

[0833] Output: Risk prediction and countermeasures

[0834] Step 8:

[0835] The device receives notifications and suggestions from the server and displays them in the user interface. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[0836] Input: Notifications and suggestions from the server

[0837] Output: Notifications and suggestions displayed in the user interface

[0838] Step 9:

[0839] The terminal accepts the project manager's manual task assignment and schedule change operations, as well as emotional information input, and sends that information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[0840] Input: Manual input from project manager (task assignments, schedule changes, sentiment information)

[0841] Output: Updates sent to the server

[0842] Step 10:

[0843] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions. For example, it displays information such as "There is a risk of resource shortage in the next phase" in a graph.

[0844] Input: Risk prediction and countermeasure information provided by the server

[0845] Output: Risk information and countermeasures displayed in the user interface

[0846] Step 11:

[0847] Users can check the project's progress and risk information through the device interface and manually modify tasks as needed. Emotional data is also provided as feedback. For example, users can "check the progress rate and risk information for Task A on the dashboard, and if they feel stressed, enter their emotional data into the device."

[0848] Inputs: Progress and risk information from the dashboard, manual user input (task corrections, sentiment data)

[0849] Output: Updated progress and risk information, feedback information to the server

[0850] Step 12:

[0851] The user receives risk prediction information and takes countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[0852] Input: Risk prediction information and countermeasure proposals

[0853] Output: Measures taken, risk mitigation

[0854] (Application example 2)

[0855] 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."

[0856] Modern manufacturing requires efficient project management, but conventional systems have difficulty taking into account the emotional state of human resources when allocating tasks and managing schedules. This increases worker stress, risking reduced productivity and quality. Furthermore, adequate information is often unavailable for risk prediction and countermeasures, resulting in measures being implemented only after a problem has occurred. To address these issues, it is necessary to develop a system that uses real-time emotional data to optimally allocate tasks and predict risks.

[0857] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting and integrating data for each project using a generation AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing the schedule using the generation AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting suggestions to the user through notifications and a user interface; means for collecting emotional data in real time using various sensors used in the work environment and integrating and analyzing this emotional data with project data; and means for allocating tasks and predicting risks based on the emotional data. This enables efficient task allocation and risk management while taking into account the emotional states of workers.

[0858] "Generative AI" is a technology that uses artificial intelligence techniques to generate data, make inferences, and make predictions.

[0859] "Project data" refers to information necessary for project management, such as progress, task details, and resource usage.

[0860] "Real-time" refers to data being collected, analyzed, and processed with minimal delay, and updated and reflected immediately.

[0861] "Emotion data" is data that represents the emotional state of a worker and is acquired using sensors and analytical algorithms.

[0862] "Optimal task allocation" means assigning tasks to the person best suited to each task, taking into account the worker's skill set and emotional data.

[0863] "Schedule optimization" refers to the readjustment and optimization of a schedule to most efficiently move a project forward.

[0864] "Risk prediction" means predicting problems or obstacles that may occur in the future based on past data and current progress data.

[0865] "Proposing countermeasures" means proposing appropriate measures and action plans for predicted risks.

[0866] "Notification" is a function that allows the server to convey information such as warnings and suggestions to the user.

[0867] "User interface" refers to the screen and input devices that allow a user to interact with a system.

[0868] "Various sensors used in the work environment" refers to devices such as cameras, microphones, and vital signs sensors that detect data within the environment and the status of workers.

[0869] This invention is a system that supports project management by combining generative AI and an emotion engine, with the aim of improving the efficiency of work within factories. This system consists of a server, terminals, users, and an emotion engine, each of which has a specific role.

[0870] Server Processing

[0871] The server is responsible for collecting and integrating data from each project using generative AI. Specifically, it uses the following hardware and software:

[0872] Hardware: General-purpose server equipment

[0873] Software: Generative AI models implemented in TensorFlow and PyTorch, and data collection APIs

[0874] First, the server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a data shaping and cleansing process. Next, the server analyzes the data in real time to understand the progress and resource usage of each task. It also uses generative AI models to forecast progress and resource supply and demand, and immediately updates the results.

[0875] The server also uses generative AI to optimally allocate tasks and optimize schedules. For example, it considers the skill sets, work history, and emotional data of project members to optimally allocate tasks. It also uses optimization algorithms such as the critical path method (CPM) to make suggestions for efficiently progressing the entire project schedule.

[0876] Terminal handling

[0877] The terminal functions as an interface for receiving notifications and suggestions from the server. The user interface (UI) is intuitively designed so that users can easily understand important information. Specifically, it provides the following functions:

[0878] Notifications and interface updates: Receives notifications and suggestions from the server and displays them in the user interface.

[0879] Accepting and sending user input: Accepting user actions such as manually assigning or rescheduling a task, and sending that information to the server.

[0880] User interaction and feedback

[0881] The project manager, who is the user, uses the system by performing the following operations.

[0882] Check progress and risk information: Check project progress and risk information through a user interface. The dashboard displays real-time updates.

[0883] Task Allocation and Schedule Management: You can check the task allocation and schedule proposed by the server and manually correct them if necessary. You can also provide emotional feedback.

[0884] Implement risk response measures: Receive risk prediction information and implement response measures based on it, such as reassigning stressful tasks to other members.

[0885] Emotion engine integration

[0886] The emotion engine collects emotion data in real time using various sensors used in the work environment and sends this data to the server. Based on this emotion data, the server can make more accurate risk predictions and propose countermeasures. Specifically, the process includes the following steps:

[0887] Emotion data collection: Recognize emotions in real time from the user's facial expressions, voice, text data, etc.

[0888] Emotional data integration and analysis: Emotional data can be integrated with project data and used for analysis, for example, to take into account increased user stress levels and adjust task assignments accordingly.

[0889] Risk prediction and improved response: Emotional data is used to generate suggestions to reduce task load for users showing signs of stress or fatigue.

[0890] Examples of concrete examples and prompts

[0891] Example of task allocation: Based on worker skill sets and emotional data, assign maintenance work for a particular machine to a worker who is familiar with operating that machine and does not feel stressed.

[0892] A concrete example of risk prediction and countermeasures: If emotional data indicates that a particular worker is prone to fatigue, the system can assign lighter work to reduce the worker's workload or send a notification recommending that they take a break.

[0893] An example of a prompt is, "Assign priority tasks to workers with high skill sets and low stress levels." By inputting this prompt into the generative AI model, optimal task assignments are made.

[0894] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0895] Step 1:

[0896] The server collects progress data, task data, and resource data for each project via API. At the same time, it also acquires emotional data from various sensors (cameras, microphones, vital signs sensors, etc.) installed in the work environment and stores it in a database. The input is data from various sensors and project management tools, and the output is formatted, cleansed, and integrated data.

[0897] Step 2:

[0898] The server analyzes the input data in real time to grasp the progress and resource usage of each task. At this time, it uses a generation AI to predict progress and resource supply and demand. The input is the integrated data from step 1, and the output is the analysis results and forecast data. For example, it calculates the progress rate and the planned resource usage.

[0899] Step 3:

[0900] The server uses generative AI to optimally allocate tasks and optimize the schedule, taking into account the skill sets, work history, and emotional data of project members. The input is the analysis results and prediction data from Step 2, and the output is the optimized task allocation and schedule.

[0901] Step 4:

[0902] The server analyzes the data to predict risks and propose countermeasures. Risk prediction is based on past data, current progress data, and emotion data. The input is the data from Steps 2 and 3, and the output is risk prediction and proposed countermeasures. For example, it generates a proposal to reduce tasks that are likely to cause stress to a specific worker.

[0903] Step 5:

[0904] The device receives notifications and suggestions from the server and displays them on the user interface. An intuitive UI is designed so that users can easily understand important information. The input is the notification and suggestion data from the server, and the output is the information displayed on the user interface.

[0905] Step 6:

[0906] The terminal accepts manual task assignments and schedule changes by the project manager and sends the information to the server. The input is the operation data from the user, and the output is the correction data sent to the server. For example, when a specific task is reassigned to a specific member.

[0907] Step 7:

[0908] The server assigns tasks and predicts risks based on the emotion data, and generates a further optimized plan based on the results. The inputs are emotion data and user feedback data, and the output is an updated task assignment and risk response plan.

[0909] Step 8:

[0910] Users input prompt statements into the generative AI model and obtain specific task assignments and risk response measures based on them. The input is the prompt statement, and the output is the assignment and response proposals from the generative AI model.

[0911] Through the above steps, the system of the present invention realizes project management that takes into account real-time emotional data, enabling efficient work and risk management.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] [Third embodiment]

[0916] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0917] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0918] 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).

[0919] 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.

[0920] 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.

[0921] 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).

[0922] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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."

[0928] The project management support system of this invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the system is implemented by a server, terminal, and user, each with their own role.

[0929] Server Processing

[0930] 1. Data Collection and Integration

[0931] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and integrated through a formatting and cleansing process.

[0932] 2. Data analysis

[0933] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[0934] 3. Task allocation and schedule optimization

[0935] The server uses generative AI to assign optimal tasks based on the skill sets and work history of project members, and also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[0936] 4. Risk prediction and countermeasures

[0937] The server predicts risks based on past project data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific phase, it generates countermeasures to mitigate the risk and notifies the user.

[0938] Terminal handling

[0939] 1. Notification and interface updates

[0940] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[0941] 2. Accepting and Sending User Input

[0942] The terminal accepts manual task assignments and schedule changes by the project manager and sends that information to the server, allowing the terminal to reassign new tasks to specific members, for example.

[0943] 3. Visualization of risk information

[0944] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[0945] User interaction and feedback

[0946] 1. Review progress and risk information

[0947] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[0948] 2. Task assignment and schedule management

[0949] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of project progress.

[0950] 3. Implementation of risk countermeasures

[0951] Users receive risk prediction information and take countermeasures based on it. The server provides options for countermeasures and implements specific action plans to reduce project risks.

[0952] Specific examples

[0953] Task assignment

[0954] The server analyzes each member's skill set and work history and assigns new tasks to the most suitable member. For example, a member with strong design skills might be assigned the task of user interface design, while a member with strong development skills might be assigned the task of coding new features.

[0955] Risk prediction

[0956] The server analyzes past project data and detects when specific phases are prone to resource shortages. For example, based on the fact that past projects have experienced many delays in the database migration phase, the server will suggest adding resources or extending the time.

[0957] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[0958] The processing flow will be explained below.

[0959] Step 1: Data collection

[0960] The server collects progress data, task data, and resource data for each project through APIs. Specifically, it connects with project management tools and resource management systems to obtain the latest data.

[0961] Step 2: Data integration

[0962] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[0963] Step 3: Real-time analytics

[0964] The server analyzes the consolidated data in real time, instantly understanding the progress of each task and resource usage, and generates information to display on a dashboard.

[0965] Step 4: Progress forecast

[0966] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data and current progress, it calculates future progress and the possibility of resource shortages.

[0967] Step 5: Task assignment

[0968] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set and work history. Specifically, it assigns the most appropriate work to each member, improving the efficiency of the entire project.

[0969] Step 6: Schedule optimization

[0970] The server optimizes the schedule for the entire project, using techniques such as the critical path method (CPM) to reconstruct the schedule to prevent unnecessary delays.

[0971] Step 7: Risk prediction

[0972] The server predicts risks based on past and current progress data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[0973] Step 8: Generate countermeasures

[0974] The server generates countermeasures to address risks and notifies the project manager, suggesting additional resources or rescheduling the project.

[0975] Step 9: Notifications and User Interface Updates

[0976] The device receives notifications and suggestions from the server and displays them in a user interface designed to help users intuitively understand important information.

[0977] Step 10: Accepting User Input

[0978] The terminal accepts manual task assignments and schedule changes made by the project manager, and sends that information to the server, which then reanalyzes the data based on the new information.

[0979] Step 11: Visualize risk information

[0980] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly implement specific countermeasures.

[0981] Step 12: Review progress and risk information

[0982] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[0983] Step 13: Task assignment and scheduling

[0984] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary. This operation is done through the terminal, and the information is again processed by the server.

[0985] Step 14: Implement risk responses

[0986] The user receives risk prediction information and takes countermeasures based on it. The server implements the countermeasures suggested by the user to reduce the risk of the project.

[0987] Step 15: Feedback Loop

[0988] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[0989] Example 1

[0990] 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."

[0991] In conventional project management systems, data collection and integration, progress management, and resource management are all performed separately, limiting overall efficiency and effectiveness. Risk prediction and countermeasure proposals are often performed manually, creating problems that are prone to human error and delays. This increases the risk of project delays and raises concerns about a lower overall project success rate. Furthermore, the system requires sufficient management skills, making it technically challenging, especially for project novices.

[0992] 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.

[0993] In this invention, the server includes a means for collecting and integrating data for each project using a data collection device, a means for analyzing the collected data in real time to grasp the project's progress and resource usage, and a means for optimally allocating tasks and optimizing the schedule using generative AI. This enables centralized management and real-time analysis of project data, significantly improving the efficiency of project progress management and resource management, and automating risk prediction and countermeasure proposals, thereby increasing the project success rate. It also provides support for even project beginners to effectively manage projects.

[0994] A "data collection device" is a device that can automatically collect data for each project and integrate it as needed.

[0995] "Real-time analytics" is the process of processing and analyzing data immediately at the moment it is collected.

[0996] "Generative AI" is a technology that uses artificial intelligence to analyze and predict data, and then generates optimal suggestions and actions based on the results.

[0997] "Optimal task allocation" is the process of efficiently assigning each project task to the most suitable member.

[0998] "Schedule optimization" is the process of managing the time schedule of all tasks in a project in the most efficient and effective way.

[0999] "Risk prediction" is the process of predicting potential problems and risks in the progress of a project in advance based on past data and current progress data.

[1000] "Proposing countermeasures" refers to proposing optimal countermeasures for predicted risks.

[1001] A "notification system" is a mechanism for quickly communicating important information and offers to users.

[1002] The "user interface" is the visual and operational part through which a user directly interacts with a system.

[1003] A "project manager" is a person responsible for planning, managing progress, and allocating resources for a project.

[1004] The project management support system of the present invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures.

[1005] Server Processing

[1006] First, the server collects progress data, task data, and resource data from each project management tool via its API and stores it in a database. Specifically, data is collected from tools such as JIRA, Trello, and Asana. This data is then formatted and cleansed using the Python pandas library and stored in a MySQL database.

[1007] The server then analyzes the stored data in real time, using generative AI models (e.g., GPT-3 and BERT) to forecast progress and resource demand and supply, and immediately updates the results, allowing project managers to understand the progress of their projects in real time.

[1008] Furthermore, the server uses generative AI to assign tasks and optimize the schedule. It considers each member's skill set and work history to assign optimal tasks. It also utilizes the critical path method to efficiently optimize the schedule. At this time, the server queries the generative AI model using a prompt such as, "What tasks should be assigned to members with high design skills?"

[1009] Finally, the server predicts risks based on past project data and current progress data and suggests countermeasures. For example, it sends a prompt such as, "Please tell me the predicted risks in the database migration phase and the countermeasures," to the generative AI model, and displays the results on the user interface to notify the project manager.

[1010] Terminal handling

[1011] The device receives notifications and suggestions from the server and displays that information in a user interface. The UI is designed to be intuitive and easy to use, allowing users to easily understand important information. Specifically, a dashboard built using React.js and Vue.js is used.

[1012] The terminal also has a function that allows project managers to manually assign tasks and change schedules. This allows project managers to reassign tasks and adjust schedules. In this case, the input data is sent to the server using the JavaScript fetch API.

[1013] Furthermore, the device visualizes risk and countermeasure information provided by the server and presents details and recommended actions to the user. Risk information is drawn as a graph using D3.js, and details are displayed in tooltips, making it easy for users to understand the risks.

[1014] User interaction and feedback

[1015] Project managers can check project progress and risk information through a dashboard on their devices. Real-time updates are available to reassign tasks and change schedules. They can also take appropriate countermeasures based on risk information and send feedback to the server.

[1016] Specifically, users can check real-time charts and graphs displayed on the dashboard and flexibly manage the progress of the project as needed. Risk response options are presented, and users can select and implement the appropriate response to effectively reduce project risks.

[1017] As a result, the system of the present invention will significantly improve the efficiency of project management work and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[1018] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1019] Step 1: Data collection and integration

[1020] The server sends API requests to each project management tool (e.g., JIRA, Trello, Asana) to collect progress data, task data, and resource data. The retrieved data is temporarily saved in JSON format, and then reformatted and cleansed using Python's pandas library. Specifically, unnecessary columns are removed, leaving only the necessary information. The reformatted data is imported into a MySQL database and consolidated in a unified format. This creates a dataset for each project.

[1021] Input: API request (project management tool)

[1022] Output: Consolidated dataset (MySQL database)

[1023] Step 2: Real-time analysis

[1024] The server retrieves the latest project data from the database using SQL queries. It then sends prompts to a generative AI model (e.g., GPT-3 or BERT) to predict progress and resource supply and demand. The analysis results are immediately sent via WebSocket to a front-end built with React.js and displayed in the UI in real time. Specifically, metrics such as progress rate and resource usage are visualized.

[1025] Input: Latest project data (SQL query)

[1026] Output: Progress forecast, resource supply and demand forecast (WebSocket)

[1027] Step 3: Task allocation and schedule optimization

[1028] The server retrieves each member's skill set and work history from the database and sends prompts to the generative AI model. The optimal task assignment and schedule is received from the generative AI model and updated in the database. For example, a prompt such as "What tasks should be assigned to members with high design skills?" is used. The critical path method (CPM) is also used to optimize the overall project schedule.

[1029] Input: Member skill set, work history (SQL query)

[1030] Output: Optimal task assignment, optimized schedule (database update)

[1031] Step 4: Risk prediction and countermeasure proposal

[1032] The server predicts risks based on past and current project data. It sends prompts such as "Please tell us the risks predicted for the database migration phase and their countermeasures" to the generative AI model, and receives the risk predictions and countermeasures. The information based on this is displayed on the device's user interface and notified to the project management personnel.

[1033] Input: Past and current project data (SQL query)

[1034] Output: Risk prediction, countermeasures (user interface)

[1035] Step 5: Update notifications and interface

[1036] The device receives WebSocket notifications from the server, analyzes the content, and updates the user interface. Specifically, the UI, built with React.js and Vue.js, displays risk predictions and task assignment information in real time, allowing project managers to instantly grasp the latest situation.

[1037] Input: WebSocket notification (from server)

[1038] Output: Updated user interface (real-time information display)

[1039] Step 6: Accepting and Sending User Input

[1040] The terminal accepts operations from project managers. Specifically, it provides an input form for manual task assignment and schedule changes, and sends the input data to the server using the JavaScript fetch API. This allows task and schedule adjustments to be reflected in real time.

[1041] Input: User operations (task assignment, schedule change)

[1042] Output: Send data to the server (fetch API)

[1043] Step 7: Visualize risk information

[1044] The device receives risk information and countermeasure information provided by the server and visualizes it using D3.js. Specifically, the risk information is drawn as graphs and charts, and detailed information is displayed in tooltips. This allows users to easily understand the details of the risks and recommended actions.

[1045] Input: Risk information, countermeasure information (notification from the server)

[1046] Output: Visualized risk information (graphs, charts)

[1047] Step 8: Review progress and risk information

[1048] Users can access the dashboard on their device to check project progress and risk information in real time. By clicking on a specific graph, further details will be displayed in a modal window, allowing users to gain a detailed understanding of the project's status.

[1049] Input: Dashboard access

[1050] Output: Display of real-time information (modal window)

[1051] Step 9: Task assignment and scheduling

[1052] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary by using the drag-and-drop functionality to reassign tasks and clicking the save button to submit the changes to the server.

[1053] Input: Task assignment, schedule proposal (from server)

[1054] Output: Send manual correction data (to server)

[1055] Step 10: Implement risk responses

[1056] The user selects an action to be taken from the list of risk countermeasures displayed on the dashboard and clicks the execute button. The selected action is recorded on the server, and the execution results are also fed back.

[1057] Input: Risk Response Selection (Dashboard)

[1058] Output: Execution and feedback (notification to the server)

[1059] As a result, this system can improve the efficiency of project management operations and increase the success rate of projects.

[1060] (Application example 1)

[1061] 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."

[1062] In current factory operations, production planning, task allocation, resource optimization, risk prediction, and countermeasure presentation are often not adequately handled. This can lead to reduced efficiency and delayed troubleshooting, raising concerns about a decline in overall factory productivity. It is also difficult to integrate data from different devices and systems and analyze it in real time. Solving these issues will significantly improve factory operational efficiency.

[1063] 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.

[1064] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time and understanding progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting proposals to users through notifications and a user interface; means for collecting data in real time from each device in the factory and integrating it into a central server; means for analyzing and reporting resource usage in the production process in real time; means for optimally allocating tasks based on the specialized skills and past work history of each device; and means for predicting risks in the production process and proposing countermeasures to mitigate the risks, thereby significantly improving the operational efficiency of the entire factory and maximizing productivity.

[1065] "Generative AI" is artificial intelligence that uses machine learning techniques to collect, analyze, predict, and make suggestions about data.

[1066] "Data collection and integration" refers to collecting data from different systems and devices, formatting and cleansing that data, and integrating it into a single database.

[1067] "Real-time analysis" means instantly analyzing collected data to understand current progress and resource usage, and immediately reflecting the results.

[1068] "Task allocation" is the act of automatically specifying the most suitable task, taking into consideration the skill sets and work history of project members and equipment.

[1069] "Schedule optimization" refers to adjusting the overall project plan to proceed efficiently and deriving the optimal schedule using methods such as the critical path method (CPM).

[1070] "Risk prediction" is the act of predicting future risks based on past data and current conditions.

[1071] "Countermeasures" refer to specific actions or measures that should be taken in response to predicted risks.

[1072] "Notification" is the act of conveying important information or suggestions from the system to the user.

[1073] "User interface" refers to the screens and operating methods that users use to exchange information with a system.

[1074] "Each piece of equipment in the factory" refers to all the equipment and facilities used to carry out production activities.

[1075] A "central server" is a server that is responsible for integrating and managing all collected data and performing analysis and optimization.

[1076] "Specialized skills" refers to the knowledge and techniques required to perform a specific task or work.

[1077] "Work history" refers to a record of tasks and work done in the past.

[1078] MODE FOR CARRYING OUT THE INVENTION

[1079] The factory management system of this invention aims to maximize productivity by streamlining factory operations through generative AI. This system provides a series of functions including data collection and integration, real-time analysis, task assignment, schedule optimization, risk prediction, and countermeasure proposals.

[1080] Server Processing

[1081] 1. Data Collection and Integration

[1082] The server collects data in real time from each device in the factory and consolidates it into a central server. It uses APIs for data collection and the pandas library for data formatting and cleansing. This process allows data from different systems and devices to be managed centrally.

[1083] 2. Real-time analysis

[1084] The server instantly analyzes the collected data to understand the current progress and resource usage. This process uses a generative AI model to analyze the data and predict progress and resource supply and demand. The generative AI model makes it possible to understand the situation in real time.

[1085] 3. Task allocation and schedule optimization

[1086] The server uses generative AI to optimally allocate tasks, taking into account the specialized skills and past work history of each device. It also optimizes the overall project schedule for efficient progress. It optimizes the schedule using techniques such as the critical path method (CPM).

[1087] 4. Risk prediction and countermeasures

[1088] The server predicts risks based on past data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific production process, it generates countermeasures to mitigate the risk and notifies the user.

[1089] Terminal handling

[1090] 1. Notification and interface updates

[1091] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[1092] 2. Accepting and Sending User Input

[1093] The terminal accepts manual task assignments and schedule changes by factory managers and sends the information to the server, allowing them to, for example, reassign new tasks to specific equipment.

[1094] 3. Visualization of risk information

[1095] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[1096] User interaction and feedback

[1097] 1. Review progress and risk information

[1098] The user (factory manager) can check real-time updates of progress and risk information through the terminal interface, and all necessary information is displayed on the dashboard.

[1099] 2. Task assignment and schedule management

[1100] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of factory operations.

[1101] 3. Implementation of risk countermeasures

[1102] The user receives risk prediction information and takes specific countermeasures based on it. Based on the countermeasures proposed by the server, the user takes action to reduce risks throughout the factory.

[1103] Specific examples

[1104] For example, let's consider data collection and management when Robot A is performing welding work in a factory in real time. Data on Robot A's work efficiency and the materials used is automatically collected via API. The collected data is formatted and stored in a database using the pandas library. When a generative AI model analyzes this data and finds that Robot A is consuming more materials than usual, that information is immediately sent to the terminal and the necessary countermeasures are presented.

[1105] Example prompt for a generative AI model:

[1106] "Based on progress and resource usage, predict the process where risks are most likely to occur next and propose countermeasures."

[1107] The above is an embodiment of the present invention, which makes it possible to improve the efficiency of factory operations and maximize productivity.

[1108] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1109] Step 1:

[1110] The server collects data in real time from each device in the factory. The input is data from each device via API, and the output is formatted and cleansed data. This data is then stored in a database through pipeline processing.

[1111] Step 2:

[1112] The server analyzes the collected data in real time using a generative AI model. The input is formatted and cleansed data, and the output is a visualization of each device's progress and resource usage. The AI ​​model analyzes the data and detects anomalies and patterns.

[1113] Step 3:

[1114] The server uses a generation AI to optimally allocate tasks. The input is data including the specialized skills and past work history of each device, and the output is the optimal task allocation for each device. The generation AI automatically generates the allocation by taking into account the relationship between skills and tasks.

[1115] Step 4:

[1116] The server optimizes the schedule for the entire project. The input is current progress and resource usage data, and the output is an optimized schedule. It uses the critical path method (CPM) to create an efficient production plan.

[1117] Step 5:

[1118] The server predicts risks based on past data and current progress data and proposes countermeasures. The input is past project data and current progress data, and the output is predicted risks and proposed countermeasures. The AI ​​model analyzes risks and generates countermeasures.

[1119] Step 6:

[1120] The terminal displays notifications and suggestions from the server on a user interface. The input is notification data and suggestion data from the server, and the output is an intuitive presentation of information on a UI. The interface displays important information visually and clearly.

[1121] Step 7:

[1122] The terminal accepts user input and sends that information to the server. The input is the user's task assignment or schedule change operation, and the output is updated data to the server. The user operates the interface and inputs information.

[1123] Step 8:

[1124] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents it to the user. The input is risk prediction data and countermeasure data, and the output is detailed risk information and recommended actions. The user checks the risk information and takes specific countermeasures.

[1125] Step 9:

[1126] Users can view progress and risk information through a device interface. The input is real-time data on the device, and the output is understanding the current situation and taking action. Users can view the information on the dashboard and select the necessary actions.

[1127] Step 10:

[1128] The user implements the risk countermeasures presented by the server. The input is the countermeasures proposed by the server, and the output is a specific action plan for risk reduction. Measures are then taken promptly based on the countermeasures.

[1129] Step 11:

[1130] Users can input prompt statements into the generative AI model to request additional analysis, such as "Based on progress and resource usage, please predict the next process where a risk is most likely to occur and propose countermeasures," to obtain more detailed analysis results.

[1131] 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.

[1132] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. This provides advanced support for improving project efficiency and risk management. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[1133] Server Processing

[1134] 1. Data Collection and Integration

[1135] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process.

[1136] 2. Data analysis

[1137] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[1138] 3. Task allocation and schedule optimization

[1139] The server uses generative AI to optimally assign tasks based on the skill sets and work history of project members, as well as emotional data provided by the emotion engine. It also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[1140] 4. Risk prediction and countermeasures

[1141] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that are likely to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[1142] Terminal handling

[1143] 1. Notification and interface updates

[1144] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[1145] 2. Accepting and Sending User Input

[1146] The terminal accepts manual task assignments and schedule changes by the project manager, as well as emotional input, and sends that information to the server, allowing it to, for example, reassign new tasks to specific members.

[1147] 3. Visualization of risk information

[1148] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[1149] User interaction and feedback

[1150] 1. Review progress and risk information

[1151] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[1152] 2. Task assignment and schedule management

[1153] The user can review the task assignments and schedules proposed by the server, manually revise them as needed, and provide feedback on emotional data, which is then used for further optimization.

[1154] 3. Implementation of risk countermeasures

[1155] Users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[1156] Emotion engine integration

[1157] 1. Collecting Emotional Data

[1158] The emotion engine recognizes emotions in real time from the user's facial expressions, voice, text data, etc., and sends that data to the server.

[1159] 2. Emotional Data Integration and Analysis

[1160] The server combines the data sent by the emotion engine with project data and uses it for analysis, for example, adjusting task assignments to take into account a user's increased stress level.

[1161] 3. Improving risk prediction and countermeasures

[1162] The server uses the emotion data to more accurately predict risks and propose countermeasures, such as reducing the task load of users who show signs of stress or fatigue.

[1163] Specific examples

[1164] Task assignment

[1165] The server analyzes each member's skill set, work history, and emotional data and assigns tasks to the most suitable member. For example, if a member with strong design skills is confirmed to have not been feeling stressed recently, he or she will be assigned the task of user interface design.

[1166] Risk prediction and countermeasures

[1167] The server predicts project risks based on past project data, current progress data, and emotional data. For example, it can determine that a particular phase is prone to resource shortages, while also detecting rising stress levels from the emotional data of current team members and suggesting countermeasures.

[1168] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI and an emotion engine, even beginners can improve their project management skills.

[1169] The processing flow will be explained below.

[1170] Step 1: Data collection

[1171] The server collects progress data, task data, and resource data for each project through APIs. It connects with project management tools and resource management systems and obtains emotion data from the emotion engine.

[1172] Step 2: Data integration

[1173] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[1174] Step 3: Real-time analytics

[1175] The server analyzes the integrated data in real time, instantly understanding the progress of each task, resource usage, and user sentiment data.

[1176] Step 4: Progress forecast

[1177] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data, current progress, and emotion data, it calculates future progress and the possibility of resource shortages.

[1178] Step 5: Task assignment

[1179] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set, work history, and emotional data. For example, it assigns important tasks to members with low stress levels.

[1180] Step 6: Schedule optimization

[1181] The server optimizes the schedule for the entire project, using the critical path method (CPM) to prevent unnecessary delays.

[1182] Step 7: Risk prediction

[1183] The server predicts risks based on past and current progress data and emotion data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[1184] Step 8: Generate countermeasures

[1185] The server generates risk countermeasures and notifies the project manager, for example, suggesting additional resources or rescheduling the schedule.

[1186] Step 9: Notifications and User Interface Updates

[1187] The device receives notifications and suggestions from the server and displays them in the user interface, which is designed to help users intuitively understand important information.

[1188] Step 10: Accepting User Input

[1189] The terminal accepts manual task assignments and schedule changes by the project manager, including input of emotional information, and transmits that information to the server.

[1190] Step 11: Visualize risk information

[1191] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[1192] Step 12: Review progress and risk information

[1193] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[1194] Step 13: Task assignment and scheduling

[1195] The user can review the task assignments and schedules proposed by the server and manually correct them if necessary. They can also provide feedback on emotional data, which can be used for further optimization.

[1196] Step 14: Implement risk responses

[1197] Users receive risk prediction information and take countermeasures based on it, such as assigning lighter tasks to members experiencing high stress levels.

[1198] Step 15: Feedback Loop

[1199] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[1200] Example 2

[1201] 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."

[1202] Conventional project management systems do not adequately grasp progress and resource usage, optimally allocate tasks, or predict risks and present countermeasures. Furthermore, they are unable to optimize or manage risks taking into account the emotional state of users, resulting in insufficient project efficiency and risk management. This increases uncertainty in the progress of projects, making it difficult to achieve optimal results.

[1203] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1204] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks and proposing countermeasures based on past data and current progress data; means for presenting the proposals to the user through notifications and a user interface; means for collecting, analyzing, and integrating user emotion data using an emotion engine; and means for improving risk predictions and countermeasure proposals based on the emotion data. This enables real-time understanding of project progress and resource usage, optimal task allocation and schedule optimization including emotion data, and highly accurate risk predictions and proposals of countermeasures.

[1205] - "Generative AI" is a system that uses artificial intelligence technology to collect, integrate, analyze, and predict data.

[1206] "Project data" refers to a group of information that indicates the progress of a project, task information, resource usage status, emotional data, and the like.

[1207] "Real-time analysis" is the process of processing data instantly to understand the current situation.

[1208] "Progress" is information that indicates how much of a project's tasks have been completed.

[1209] "Resource usage status" refers to the current status of human and material resources used in a project.

[1210] "Optimal task allocation" is the process of assigning each task to the most suitable member based on the project members' skills and circumstances.

[1211] "Schedule optimization" is a method of optimizing the timeline of the entire project to ensure efficient progress.

[1212] "Risk prediction" is the process of predicting possible future problems or failures based on past and current data.

[1213] "Proposing countermeasures" means proposing specific solutions or actions to address predicted risks.

[1214] A "user interface" is a screen or operating means that allows a user to interact with a system.

[1215] "Presenting a proposal to the user" refers to the act of displaying the proposal content from the system to the user.

[1216] The "emotion engine" is a system that recognizes and analyzes the user's emotional state and collects that data.

[1217] "Emotion data" is data that indicates the user's stress level and emotional state.

[1218] "Analyze and synthesize" is the process of processing collected data and turning it into a unified, usable information.

[1219] "Improving risk prediction and countermeasure proposals" means providing more accurate risk predictions and specific, effective countermeasures based on emotion data.

[1220] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[1221] Server Processing

[1222] The server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process. A relational database such as MySQL is used as the database.

[1223] The server analyzes the collected data in real time to understand the progress of each task and the resource usage status. It also uses a generative AI model to predict progress and resource supply and demand, and immediately updates the results. For example, it provides a prediction such as, "Based on the current progress, Task A will be completed in three days."

[1224] Furthermore, the server uses generative AI to optimally assign tasks to project members, taking into account their skill sets, work history, and emotional data provided by the emotion engine. For example, it may suggest, "Since member C has high data analysis skills, he should be assigned to analysis tasks." It also uses techniques such as the critical path method (CPM) to optimize the overall project schedule and make suggestions for efficient progress.

[1225] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that tend to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[1226] Terminal handling

[1227] The device receives notifications and suggestions from the server and displays them in the user interface. An intuitive UI is designed to make it easy for users to understand important information. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[1228] The terminal also accepts manual task assignments and schedule changes by the project manager, as well as emotional information, and sends this information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[1229] Furthermore, the device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[1230] User interaction and feedback

[1231] The user (project manager) checks the project progress and risk information through the terminal interface. The dashboard displays information that is updated in real time. For example, the user can perform an operation such as "Check the progress rate and risk information for Task A on the dashboard."

[1232] The user can also check the task assignments and schedules proposed by the server and manually revise them as necessary. Emotional data is also fed back, and further optimization is performed based on that information. For example, the system may provide feedback such as "If you feel stressed, enter that emotional data into the device."

[1233] Furthermore, users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[1234] Emotion engine integration

[1235] The emotion engine recognizes emotions in real time based on the user's facial expressions, voice, and text data, and sends that data to the server. For example, it can detect "fatigue" from the user's facial expressions and record it as data.

[1236] The server integrates the data sent from the emotion engine with project data and uses it for analysis. If a user's stress level increases, it can take that into account and adjust task assignments. For example, task progress data can be linked to user emotion data and managed centrally.

[1237] The server uses the emotional data to make more accurate risk predictions and propose countermeasures. Specifically, it predicts the "stress level for the next week" based on the emotional data and generates specific countermeasures based on that.

[1238] Examples of concrete examples and prompts

[1239] Specific examples

[1240] 1. Example of task assignment:

[1241] A suggestion is made such as, "Member C has high skills in data analysis, so we will assign him to the analysis task."

[1242] 2. Examples of risk prediction and countermeasures:

[1243] "Detect rising stress levels from current team members' emotional data and suggest countermeasures to reduce the risk of resource shortages."

[1244] Prompt Sentence Examples

[1245] PROGRESS_TRACK='Check your progress.'

[1246] TASK_ASSIGN = 'Consider the skill sets and sentiment data of project members to assign optimal tasks.'

[1247] RISK_RESPONSE = 'Predict risks based on past and current data and provide countermeasures.'

[1248] In this way, this system will significantly improve the efficiency of project management operations and help increase the success rate of projects. In addition, the use of generative AI and an emotion engine will enable data-driven decision-making, improving the ability of even project novices to manage projects.

[1249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1250] Step 1:

[1251] The server collects progress data, task data, resource data, and emotion data from project management tools and emotion engines via APIs. Specifically, it collects project progress and task information from JIRA, Trello, etc., and obtains data on users' stress and emotional state from the emotion engine.

[1252] Input: Data from project management tools and sentiment engines

[1253] Output: Collected data (progress data, task data, resource data, emotion data)

[1254] Step 2:

[1255] The server formats and cleanses the collected data, for example, by removing unnecessary data and completing missing values, thereby improving the quality of the data.

[1256] Input: Various collected data

[1257] Output: Formatted and cleansed data

[1258] Step 3:

[1259] The server then consolidates the formatted and cleansed data and stores it in a database (e.g., MySQL), resulting in a unified data set.

[1260] Input: Formatted and cleansed data

[1261] Output: Consolidated data stored in a database

[1262] Step 4:

[1263] The server analyzes the integrated data in real time and visualizes progress and resource usage, for example, by outputting graphs showing the progress rate of each task and the workload of each member.

[1264] Input: Integrated data stored in a database

[1265] Output: Analysis results (progress, resource usage visualization graphs)

[1266] Step 5:

[1267] The server uses the generative AI model to predict progress and resource demand and supply, for example, generating a prediction such as "Task A is expected to be completed in three days, based on the current progress."

[1268] Inputs: Integrated data and real-time progress

[1269] Output: Progress forecast and resource demand forecast

[1270] Step 6:

[1271] The server uses a generative AI model to analyze the skill sets, work history, and emotional data of project members, and then optimally assigns tasks and optimizes the schedule. For example, it may suggest that "member C has high data analysis skills, so he should be assigned to analysis tasks."

[1272] Input: Integrated data, project member skill sets and work history, sentiment data

[1273] Output: Optimized task assignment and schedule

[1274] Step 7:

[1275] The server predicts risks based on past project data, current progress data, and emotion data. For example, it generates countermeasures to reduce the risk if the user has many tasks that are likely to cause stress.

[1276] Inputs: Integration data, past and current progress data, sentiment data

[1277] Output: Risk prediction and countermeasures

[1278] Step 8:

[1279] The device receives notifications and suggestions from the server and displays them in the user interface. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[1280] Input: Notifications and suggestions from the server

[1281] Output: Notifications and suggestions displayed in the user interface

[1282] Step 9:

[1283] The terminal accepts the project manager's manual task assignment and schedule change operations, as well as emotional information input, and sends that information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[1284] Input: Manual input from project manager (task assignments, schedule changes, sentiment information)

[1285] Output: Updates sent to the server

[1286] Step 10:

[1287] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions. For example, it displays information such as "There is a risk of resource shortage in the next phase" in a graph.

[1288] Input: Risk prediction and countermeasure information provided by the server

[1289] Output: Risk information and countermeasures displayed in the user interface

[1290] Step 11:

[1291] Users can check the project's progress and risk information through the device interface and manually modify tasks as needed. Emotional data is also provided as feedback. For example, users can "check the progress rate and risk information for Task A on the dashboard, and if they feel stressed, enter their emotional data into the device."

[1292] Inputs: Progress and risk information from the dashboard, manual user input (task corrections, sentiment data)

[1293] Output: Updated progress and risk information, feedback information to the server

[1294] Step 12:

[1295] The user receives risk prediction information and takes countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[1296] Input: Risk prediction information and countermeasure proposals

[1297] Output: Measures taken, risk mitigation

[1298] (Application example 2)

[1299] 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."

[1300] Modern manufacturing requires efficient project management, but conventional systems have difficulty taking into account the emotional state of human resources when allocating tasks and managing schedules. This increases worker stress, risking reduced productivity and quality. Furthermore, adequate information is often unavailable for risk prediction and countermeasures, resulting in measures being implemented only after a problem has occurred. To address these issues, it is necessary to develop a system that uses real-time emotional data to optimally allocate tasks and predict risks.

[1301] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting and integrating data for each project using a generation AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing the schedule using the generation AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting suggestions to the user through notifications and a user interface; means for collecting emotional data in real time using various sensors used in the work environment and integrating and analyzing this emotional data with project data; and means for allocating tasks and predicting risks based on the emotional data. This enables efficient task allocation and risk management while taking into account the emotional states of workers.

[1302] "Generative AI" is a technology that uses artificial intelligence techniques to generate data, make inferences, and make predictions.

[1303] "Project data" refers to information necessary for project management, such as progress, task details, and resource usage.

[1304] "Real-time" refers to data being collected, analyzed, and processed with minimal delay, and updated and reflected immediately.

[1305] "Emotion data" is data that represents the emotional state of a worker and is acquired using sensors and analytical algorithms.

[1306] "Optimal task allocation" means assigning tasks to the person best suited to each task, taking into account the worker's skill set and emotional data.

[1307] "Schedule optimization" refers to the readjustment and optimization of a schedule to most efficiently move a project forward.

[1308] "Risk prediction" means predicting problems or obstacles that may occur in the future based on past data and current progress data.

[1309] "Proposing countermeasures" means proposing appropriate measures and action plans for predicted risks.

[1310] "Notification" is a function that allows the server to convey information such as warnings and suggestions to the user.

[1311] "User interface" refers to the screen and input devices that allow a user to interact with a system.

[1312] "Various sensors used in the work environment" refers to devices such as cameras, microphones, and vital signs sensors that detect data within the environment and the status of workers.

[1313] This invention is a system that supports project management by combining generative AI and an emotion engine, with the aim of improving the efficiency of work within factories. This system consists of a server, terminals, users, and an emotion engine, each of which has a specific role.

[1314] Server Processing

[1315] The server is responsible for collecting and integrating data from each project using generative AI. Specifically, it uses the following hardware and software:

[1316] Hardware: General-purpose server equipment

[1317] Software: Generative AI models implemented in TensorFlow and PyTorch, and data collection APIs

[1318] First, the server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a data shaping and cleansing process. Next, the server analyzes the data in real time to understand the progress and resource usage of each task. It also uses generative AI models to forecast progress and resource supply and demand, and immediately updates the results.

[1319] The server also uses generative AI to optimally allocate tasks and optimize schedules. For example, it considers the skill sets, work history, and emotional data of project members to optimally allocate tasks. It also uses optimization algorithms such as the critical path method (CPM) to make suggestions for efficiently progressing the entire project schedule.

[1320] Terminal handling

[1321] The terminal functions as an interface for receiving notifications and suggestions from the server. The user interface (UI) is intuitively designed so that users can easily understand important information. Specifically, it provides the following functions:

[1322] Notifications and interface updates: Receives notifications and suggestions from the server and displays them in the user interface.

[1323] Accepting and sending user input: Accepting user actions such as manually assigning or rescheduling a task, and sending that information to the server.

[1324] User interaction and feedback

[1325] The project manager, who is the user, uses the system by performing the following operations.

[1326] Check progress and risk information: Check project progress and risk information through a user interface. The dashboard displays real-time updates.

[1327] Task Allocation and Schedule Management: You can check the task allocation and schedule proposed by the server and manually correct them if necessary. You can also provide emotional feedback.

[1328] Implement risk response measures: Receive risk prediction information and implement response measures based on it, such as reassigning stressful tasks to other members.

[1329] Emotion engine integration

[1330] The emotion engine collects emotion data in real time using various sensors used in the work environment and sends this data to the server. Based on this emotion data, the server can make more accurate risk predictions and propose countermeasures. Specifically, the process includes the following steps:

[1331] Emotion data collection: Recognize emotions in real time from the user's facial expressions, voice, text data, etc.

[1332] Emotional data integration and analysis: Emotional data can be integrated with project data and used for analysis, for example, to take into account increased user stress levels and adjust task assignments accordingly.

[1333] Risk prediction and improved response: Emotional data is used to generate suggestions to reduce task load for users showing signs of stress or fatigue.

[1334] Examples of concrete examples and prompts

[1335] Example of task allocation: Based on worker skill sets and emotional data, assign maintenance work for a particular machine to a worker who is familiar with operating that machine and does not feel stressed.

[1336] A concrete example of risk prediction and countermeasures: If emotional data indicates that a particular worker is prone to fatigue, the system can assign lighter work to reduce the worker's workload or send a notification recommending that they take a break.

[1337] An example of a prompt is, "Assign priority tasks to workers with high skill sets and low stress levels." By inputting this prompt into the generative AI model, optimal task assignments are made.

[1338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1339] Step 1:

[1340] The server collects progress data, task data, and resource data for each project via API. At the same time, it also acquires emotional data from various sensors (cameras, microphones, vital signs sensors, etc.) installed in the work environment and stores it in a database. The input is data from various sensors and project management tools, and the output is formatted, cleansed, and integrated data.

[1341] Step 2:

[1342] The server analyzes the input data in real time to grasp the progress and resource usage of each task. At this time, it uses a generation AI to predict progress and resource supply and demand. The input is the integrated data from step 1, and the output is the analysis results and forecast data. For example, it calculates the progress rate and the planned resource usage.

[1343] Step 3:

[1344] The server uses generative AI to optimally allocate tasks and optimize the schedule, taking into account the skill sets, work history, and emotional data of project members. The input is the analysis results and prediction data from Step 2, and the output is the optimized task allocation and schedule.

[1345] Step 4:

[1346] The server analyzes the data to predict risks and propose countermeasures. Risk prediction is based on past data, current progress data, and emotion data. The input is the data from Steps 2 and 3, and the output is risk prediction and proposed countermeasures. For example, it generates a proposal to reduce tasks that are likely to cause stress to a specific worker.

[1347] Step 5:

[1348] The device receives notifications and suggestions from the server and displays them on the user interface. An intuitive UI is designed so that users can easily understand important information. The input is the notification and suggestion data from the server, and the output is the information displayed on the user interface.

[1349] Step 6:

[1350] The terminal accepts manual task assignments and schedule changes by the project manager and sends the information to the server. The input is the operation data from the user, and the output is the correction data sent to the server. For example, when a specific task is reassigned to a specific member.

[1351] Step 7:

[1352] The server assigns tasks and predicts risks based on the emotion data, and generates a further optimized plan based on the results. The inputs are emotion data and user feedback data, and the output is an updated task assignment and risk response plan.

[1353] Step 8:

[1354] Users input prompt statements into the generative AI model and obtain specific task assignments and risk response measures based on them. The input is the prompt statement, and the output is the assignment and response proposals from the generative AI model.

[1355] Through the above steps, the system of the present invention realizes project management that takes into account real-time emotional data, enabling efficient work and risk management.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] [Fourth embodiment]

[1360] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1361] 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.

[1362] 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).

[1363] 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.

[1364] 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.

[1365] 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).

[1366] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] 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.

[1371] 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.

[1372] 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."

[1373] The project management support system of this invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the system is implemented by a server, terminal, and user, each with their own role.

[1374] Server Processing

[1375] 1. Data Collection and Integration

[1376] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and integrated through a formatting and cleansing process.

[1377] 2. Data analysis

[1378] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[1379] 3. Task allocation and schedule optimization

[1380] The server uses generative AI to assign optimal tasks based on the skill sets and work history of project members, and also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[1381] 4. Risk prediction and countermeasures

[1382] The server predicts risks based on past project data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific phase, it generates countermeasures to mitigate the risk and notifies the user.

[1383] Terminal handling

[1384] 1. Notification and interface updates

[1385] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[1386] 2. Accepting and Sending User Input

[1387] The terminal accepts manual task assignments and schedule changes by the project manager and sends that information to the server, allowing the terminal to reassign new tasks to specific members, for example.

[1388] 3. Visualization of risk information

[1389] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[1390] User interaction and feedback

[1391] 1. Review progress and risk information

[1392] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[1393] 2. Task assignment and schedule management

[1394] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of project progress.

[1395] 3. Implementation of risk countermeasures

[1396] Users receive risk prediction information and take countermeasures based on it. The server provides options for countermeasures and implements specific action plans to reduce project risks.

[1397] Specific examples

[1398] Task assignment

[1399] The server analyzes each member's skill set and work history and assigns new tasks to the most suitable member. For example, a member with strong design skills might be assigned the task of user interface design, while a member with strong development skills might be assigned the task of coding new features.

[1400] Risk prediction

[1401] The server analyzes past project data and detects when specific phases are prone to resource shortages. For example, based on the fact that past projects have experienced many delays in the database migration phase, the server will suggest adding resources or extending the time.

[1402] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[1403] The processing flow will be explained below.

[1404] Step 1: Data collection

[1405] The server collects progress data, task data, and resource data for each project through APIs. Specifically, it connects with project management tools and resource management systems to obtain the latest data.

[1406] Step 2: Data integration

[1407] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[1408] Step 3: Real-time analytics

[1409] The server analyzes the consolidated data in real time, instantly understanding the progress of each task and resource usage, and generates information to display on a dashboard.

[1410] Step 4: Progress forecast

[1411] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data and current progress, it calculates future progress and the possibility of resource shortages.

[1412] Step 5: Task assignment

[1413] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set and work history. Specifically, it assigns the most appropriate work to each member, improving the efficiency of the entire project.

[1414] Step 6: Schedule optimization

[1415] The server optimizes the schedule for the entire project, using techniques such as the critical path method (CPM) to reconstruct the schedule to prevent unnecessary delays.

[1416] Step 7: Risk prediction

[1417] The server predicts risks based on past and current progress data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[1418] Step 8: Generate countermeasures

[1419] The server generates countermeasures to address risks and notifies the project manager, suggesting additional resources or rescheduling the project.

[1420] Step 9: Notifications and User Interface Updates

[1421] The device receives notifications and suggestions from the server and displays them in a user interface designed to help users intuitively understand important information.

[1422] Step 10: Accepting User Input

[1423] The terminal accepts manual task assignments and schedule changes made by the project manager, and sends that information to the server, which then reanalyzes the data based on the new information.

[1424] Step 11: Visualize risk information

[1425] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly implement specific countermeasures.

[1426] Step 12: Review progress and risk information

[1427] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[1428] Step 13: Task assignment and scheduling

[1429] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary. This operation is done through the terminal, and the information is again processed by the server.

[1430] Step 14: Implement risk responses

[1431] The user receives risk prediction information and takes countermeasures based on it. The server implements the countermeasures suggested by the user to reduce the risk of the project.

[1432] Step 15: Feedback Loop

[1433] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[1434] Example 1

[1435] 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."

[1436] In conventional project management systems, data collection and integration, progress management, and resource management are all performed separately, limiting overall efficiency and effectiveness. Risk prediction and countermeasure proposals are often performed manually, creating problems that are prone to human error and delays. This increases the risk of project delays and raises concerns about a lower overall project success rate. Furthermore, the system requires sufficient management skills, making it technically challenging, especially for project novices.

[1437] 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.

[1438] In this invention, the server includes a means for collecting and integrating data for each project using a data collection device, a means for analyzing the collected data in real time to grasp the project's progress and resource usage, and a means for optimally allocating tasks and optimizing the schedule using generative AI. This enables centralized management and real-time analysis of project data, significantly improving the efficiency of project progress management and resource management, and automating risk prediction and countermeasure proposals, thereby increasing the project success rate. It also provides support for even project beginners to effectively manage projects.

[1439] A "data collection device" is a device that can automatically collect data for each project and integrate it as needed.

[1440] "Real-time analytics" is the process of processing and analyzing data immediately at the moment it is collected.

[1441] "Generative AI" is a technology that uses artificial intelligence to analyze and predict data, and then generates optimal suggestions and actions based on the results.

[1442] "Optimal task allocation" is the process of efficiently assigning each project task to the most suitable member.

[1443] "Schedule optimization" is the process of managing the time schedule of all tasks in a project in the most efficient and effective way.

[1444] "Risk prediction" is the process of predicting potential problems and risks in the progress of a project in advance based on past data and current progress data.

[1445] "Proposing countermeasures" refers to proposing optimal countermeasures for predicted risks.

[1446] A "notification system" is a mechanism for quickly communicating important information and offers to users.

[1447] The "user interface" is the visual and operational part through which a user directly interacts with a system.

[1448] A "project manager" is a person responsible for planning, managing progress, and allocating resources for a project.

[1449] The project management support system of the present invention utilizes generative AI to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures.

[1450] Server Processing

[1451] First, the server collects progress data, task data, and resource data from each project management tool via its API and stores it in a database. Specifically, data is collected from tools such as JIRA, Trello, and Asana. This data is then formatted and cleansed using the Python pandas library and stored in a MySQL database.

[1452] The server then analyzes the stored data in real time, using generative AI models (e.g., GPT-3 and BERT) to forecast progress and resource demand and supply, and immediately updates the results, allowing project managers to understand the progress of their projects in real time.

[1453] Furthermore, the server uses generative AI to assign tasks and optimize the schedule. It considers each member's skill set and work history to assign optimal tasks. It also utilizes the critical path method to efficiently optimize the schedule. At this time, the server queries the generative AI model using a prompt such as, "What tasks should be assigned to members with high design skills?"

[1454] Finally, the server predicts risks based on past project data and current progress data and suggests countermeasures. For example, it sends a prompt such as, "Please tell me the predicted risks in the database migration phase and the countermeasures," to the generative AI model, and displays the results on the user interface to notify the project manager.

[1455] Terminal handling

[1456] The device receives notifications and suggestions from the server and displays that information in a user interface. The UI is designed to be intuitive and easy to use, allowing users to easily understand important information. Specifically, a dashboard built using React.js and Vue.js is used.

[1457] The terminal also has a function that allows project managers to manually assign tasks and change schedules. This allows project managers to reassign tasks and adjust schedules. In this case, the input data is sent to the server using the JavaScript fetch API.

[1458] Furthermore, the device visualizes risk and countermeasure information provided by the server and presents details and recommended actions to the user. Risk information is drawn as a graph using D3.js, and details are displayed in tooltips, making it easy for users to understand the risks.

[1459] User interaction and feedback

[1460] Project managers can check project progress and risk information through a dashboard on their devices. Real-time updates are available to reassign tasks and change schedules. They can also take appropriate countermeasures based on risk information and send feedback to the server.

[1461] Specifically, users can check real-time charts and graphs displayed on the dashboard and flexibly manage the progress of the project as needed. Risk response options are presented, and users can select and implement the appropriate response to effectively reduce project risks.

[1462] As a result, the system of the present invention will significantly improve the efficiency of project management work and help increase the success rate of projects. In addition, by utilizing generative AI, even beginners can fully improve their project management skills.

[1463] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1464] Step 1: Data collection and integration

[1465] The server sends API requests to each project management tool (e.g., JIRA, Trello, Asana) to collect progress data, task data, and resource data. The retrieved data is temporarily saved in JSON format, and then reformatted and cleansed using Python's pandas library. Specifically, unnecessary columns are removed, leaving only the necessary information. The reformatted data is imported into a MySQL database and consolidated in a unified format. This creates a dataset for each project.

[1466] Input: API request (project management tool)

[1467] Output: Consolidated dataset (MySQL database)

[1468] Step 2: Real-time analysis

[1469] The server retrieves the latest project data from the database using SQL queries. It then sends prompts to a generative AI model (e.g., GPT-3 or BERT) to predict progress and resource supply and demand. The analysis results are immediately sent via WebSocket to a front-end built with React.js and displayed in the UI in real time. Specifically, metrics such as progress rate and resource usage are visualized.

[1470] Input: Latest project data (SQL query)

[1471] Output: Progress forecast, resource supply and demand forecast (WebSocket)

[1472] Step 3: Task allocation and schedule optimization

[1473] The server retrieves each member's skill set and work history from the database and sends prompts to the generative AI model. The optimal task assignment and schedule is received from the generative AI model and updated in the database. For example, a prompt such as "What tasks should be assigned to members with high design skills?" is used. The critical path method (CPM) is also used to optimize the overall project schedule.

[1474] Input: Member skill set, work history (SQL query)

[1475] Output: Optimal task assignment, optimized schedule (database update)

[1476] Step 4: Risk prediction and countermeasure proposal

[1477] The server predicts risks based on past and current project data. It sends prompts such as "Please tell us the risks predicted for the database migration phase and their countermeasures" to the generative AI model, and receives the risk predictions and countermeasures. The information based on this is displayed on the device's user interface and notified to the project management personnel.

[1478] Input: Past and current project data (SQL query)

[1479] Output: Risk prediction, countermeasures (user interface)

[1480] Step 5: Update notifications and interface

[1481] The device receives WebSocket notifications from the server, analyzes the content, and updates the user interface. Specifically, the UI, built with React.js and Vue.js, displays risk predictions and task assignment information in real time, allowing project managers to instantly grasp the latest situation.

[1482] Input: WebSocket notification (from server)

[1483] Output: Updated user interface (real-time information display)

[1484] Step 6: Accepting and Sending User Input

[1485] The terminal accepts operations from project managers. Specifically, it provides an input form for manual task assignment and schedule changes, and sends the input data to the server using the JavaScript fetch API. This allows task and schedule adjustments to be reflected in real time.

[1486] Input: User operations (task assignment, schedule change)

[1487] Output: Send data to the server (fetch API)

[1488] Step 7: Visualize risk information

[1489] The device receives risk information and countermeasure information provided by the server and visualizes it using D3.js. Specifically, the risk information is drawn as graphs and charts, and detailed information is displayed in tooltips. This allows users to easily understand the details of the risks and recommended actions.

[1490] Input: Risk information, countermeasure information (notification from the server)

[1491] Output: Visualized risk information (graphs, charts)

[1492] Step 8: Review progress and risk information

[1493] Users can access the dashboard on their device to check project progress and risk information in real time. By clicking on a specific graph, further details will be displayed in a modal window, allowing users to gain a detailed understanding of the project's status.

[1494] Input: Dashboard access

[1495] Output: Display of real-time information (modal window)

[1496] Step 9: Task assignment and scheduling

[1497] The user reviews the task assignments and schedules proposed by the server and manually corrects them if necessary by using the drag-and-drop functionality to reassign tasks and clicking the save button to submit the changes to the server.

[1498] Input: Task assignment, schedule proposal (from server)

[1499] Output: Send manual correction data (to server)

[1500] Step 10: Implement risk responses

[1501] The user selects an action to be taken from the list of risk countermeasures displayed on the dashboard and clicks the execute button. The selected action is recorded on the server, and the execution results are also fed back.

[1502] Input: Risk Response Selection (Dashboard)

[1503] Output: Execution and feedback (notification to the server)

[1504] As a result, this system can improve the efficiency of project management operations and increase the success rate of projects.

[1505] (Application example 1)

[1506] 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."

[1507] In current factory operations, production planning, task allocation, resource optimization, risk prediction, and countermeasure presentation are often not adequately handled. This can lead to reduced efficiency and delayed troubleshooting, raising concerns about a decline in overall factory productivity. It is also difficult to integrate data from different devices and systems and analyze it in real time. Solving these issues will significantly improve factory operational efficiency.

[1508] 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.

[1509] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time and understanding progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting proposals to users through notifications and a user interface; means for collecting data in real time from each device in the factory and integrating it into a central server; means for analyzing and reporting resource usage in the production process in real time; means for optimally allocating tasks based on the specialized skills and past work history of each device; and means for predicting risks in the production process and proposing countermeasures to mitigate the risks, thereby significantly improving the operational efficiency of the entire factory and maximizing productivity.

[1510] "Generative AI" is artificial intelligence that uses machine learning techniques to collect, analyze, predict, and make suggestions about data.

[1511] "Data collection and integration" refers to collecting data from different systems and devices, formatting and cleansing that data, and integrating it into a single database.

[1512] "Real-time analysis" means instantly analyzing collected data to understand current progress and resource usage, and immediately reflecting the results.

[1513] "Task allocation" is the act of automatically specifying the most suitable task, taking into consideration the skill sets and work history of project members and equipment.

[1514] "Schedule optimization" refers to adjusting the overall project plan to proceed efficiently and deriving the optimal schedule using methods such as the critical path method (CPM).

[1515] "Risk prediction" is the act of predicting future risks based on past data and current conditions.

[1516] "Countermeasures" refer to specific actions or measures that should be taken in response to predicted risks.

[1517] "Notification" is the act of conveying important information or suggestions from the system to the user.

[1518] "User interface" refers to the screens and operating methods that users use to exchange information with a system.

[1519] "Each piece of equipment in the factory" refers to all the equipment and facilities used to carry out production activities.

[1520] A "central server" is a server that is responsible for integrating and managing all collected data and performing analysis and optimization.

[1521] "Specialized skills" refers to the knowledge and techniques required to perform a specific task or work.

[1522] "Work history" refers to a record of tasks and work done in the past.

[1523] MODE FOR CARRYING OUT THE INVENTION

[1524] The factory management system of this invention aims to maximize productivity by streamlining factory operations through generative AI. This system provides a series of functions including data collection and integration, real-time analysis, task assignment, schedule optimization, risk prediction, and countermeasure proposals.

[1525] Server Processing

[1526] 1. Data Collection and Integration

[1527] The server collects data in real time from each device in the factory and consolidates it into a central server. It uses APIs for data collection and the pandas library for data formatting and cleansing. This process allows data from different systems and devices to be managed centrally.

[1528] 2. Real-time analysis

[1529] The server instantly analyzes the collected data to understand the current progress and resource usage. This process uses a generative AI model to analyze the data and predict progress and resource supply and demand. The generative AI model makes it possible to understand the situation in real time.

[1530] 3. Task allocation and schedule optimization

[1531] The server uses generative AI to optimally allocate tasks, taking into account the specialized skills and past work history of each device. It also optimizes the overall project schedule for efficient progress. It optimizes the schedule using techniques such as the critical path method (CPM).

[1532] 4. Risk prediction and countermeasures

[1533] The server predicts risks based on past data and current progress data. For example, if it predicts a risk of resource shortages or delays in a specific production process, it generates countermeasures to mitigate the risk and notifies the user.

[1534] Terminal handling

[1535] 1. Notification and interface updates

[1536] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[1537] 2. Accepting and Sending User Input

[1538] The terminal accepts manual task assignments and schedule changes by factory managers and sends the information to the server, allowing them to, for example, reassign new tasks to specific equipment.

[1539] 3. Visualization of risk information

[1540] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[1541] User interaction and feedback

[1542] 1. Review progress and risk information

[1543] The user (factory manager) can check real-time updates of progress and risk information through the terminal interface, and all necessary information is displayed on the dashboard.

[1544] 2. Task assignment and schedule management

[1545] Users can check the task assignments and schedules proposed by the server and manually modify them as necessary, allowing for flexible management of factory operations.

[1546] 3. Implementation of risk countermeasures

[1547] The user receives risk prediction information and takes specific countermeasures based on it. Based on the countermeasures proposed by the server, the user takes action to reduce risks throughout the factory.

[1548] Specific examples

[1549] For example, let's consider data collection and management when Robot A is performing welding work in a factory in real time. Data on Robot A's work efficiency and the materials used is automatically collected via API. The collected data is formatted and stored in a database using the pandas library. When a generative AI model analyzes this data and finds that Robot A is consuming more materials than usual, that information is immediately sent to the terminal and the necessary countermeasures are presented.

[1550] Example prompt for a generative AI model:

[1551] "Based on progress and resource usage, predict the process where risks are most likely to occur next and propose countermeasures."

[1552] The above is an embodiment of the present invention, which makes it possible to improve the efficiency of factory operations and maximize productivity.

[1553] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1554] Step 1:

[1555] The server collects data in real time from each device in the factory. The input is data from each device via API, and the output is formatted and cleansed data. This data is then stored in a database through pipeline processing.

[1556] Step 2:

[1557] The server analyzes the collected data in real time using a generative AI model. The input is formatted and cleansed data, and the output is a visualization of each device's progress and resource usage. The AI ​​model analyzes the data and detects anomalies and patterns.

[1558] Step 3:

[1559] The server uses a generation AI to optimally allocate tasks. The input is data including the specialized skills and past work history of each device, and the output is the optimal task allocation for each device. The generation AI automatically generates the allocation by taking into account the relationship between skills and tasks.

[1560] Step 4:

[1561] The server optimizes the schedule for the entire project. The input is current progress and resource usage data, and the output is an optimized schedule. It uses the critical path method (CPM) to create an efficient production plan.

[1562] Step 5:

[1563] The server predicts risks based on past data and current progress data and proposes countermeasures. The input is past project data and current progress data, and the output is predicted risks and proposed countermeasures. The AI ​​model analyzes risks and generates countermeasures.

[1564] Step 6:

[1565] The terminal displays notifications and suggestions from the server on a user interface. The input is notification data and suggestion data from the server, and the output is an intuitive presentation of information on a UI. The interface displays important information visually and clearly.

[1566] Step 7:

[1567] The terminal accepts user input and sends that information to the server. The input is the user's task assignment or schedule change operation, and the output is updated data to the server. The user operates the interface and inputs information.

[1568] Step 8:

[1569] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents it to the user. The input is risk prediction data and countermeasure data, and the output is detailed risk information and recommended actions. The user checks the risk information and takes specific countermeasures.

[1570] Step 9:

[1571] Users can view progress and risk information through a device interface. The input is real-time data on the device, and the output is understanding the current situation and taking action. Users can view the information on the dashboard and select the necessary actions.

[1572] Step 10:

[1573] The user implements the risk countermeasures presented by the server. The input is the countermeasures proposed by the server, and the output is a specific action plan for risk reduction. Measures are then taken promptly based on the countermeasures.

[1574] Step 11:

[1575] Users can input prompt statements into the generative AI model to request additional analysis, such as "Based on progress and resource usage, please predict the next process where a risk is most likely to occur and propose countermeasures," to obtain more detailed analysis results.

[1576] 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.

[1577] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. This provides advanced support for improving project efficiency and risk management. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[1578] Server Processing

[1579] 1. Data Collection and Integration

[1580] The server collects progress data, task data, and resource data for each project through APIs and stores them in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process.

[1581] 2. Data analysis

[1582] The server analyzes the stored data in real time to understand the progress of each task and resource usage, and uses generative AI models to predict progress and resource supply and demand, and immediately updates the results.

[1583] 3. Task allocation and schedule optimization

[1584] The server uses generative AI to optimally assign tasks based on the skill sets and work history of project members, as well as emotional data provided by the emotion engine. It also optimizes the overall project schedule and makes suggestions for efficient progress using techniques such as the critical path method (CPM).

[1585] 4. Risk prediction and countermeasures

[1586] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that are likely to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[1587] Terminal handling

[1588] 1. Notification and interface updates

[1589] The device receives notifications and suggestions from the server and displays them in the user interface. We designed an intuitive UI to help users easily understand important information.

[1590] 2. Accepting and Sending User Input

[1591] The terminal accepts manual task assignments and schedule changes by the project manager, as well as emotional input, and sends that information to the server, allowing it to, for example, reassign new tasks to specific members.

[1592] 3. Visualization of risk information

[1593] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[1594] User interaction and feedback

[1595] 1. Review progress and risk information

[1596] The user (project manager) checks the project progress and risk information through the terminal interface, and the dashboard displays information updated in real time.

[1597] 2. Task assignment and schedule management

[1598] The user can review the task assignments and schedules proposed by the server, manually revise them as needed, and provide feedback on emotional data, which is then used for further optimization.

[1599] 3. Implementation of risk countermeasures

[1600] Users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[1601] Emotion engine integration

[1602] 1. Collecting Emotional Data

[1603] The emotion engine recognizes emotions in real time from the user's facial expressions, voice, text data, etc., and sends that data to the server.

[1604] 2. Emotional Data Integration and Analysis

[1605] The server combines the data sent by the emotion engine with project data and uses it for analysis, for example, adjusting task assignments to take into account a user's increased stress level.

[1606] 3. Improving risk prediction and countermeasures

[1607] The server uses the emotion data to more accurately predict risks and propose countermeasures, such as reducing the task load of users who show signs of stress or fatigue.

[1608] Specific examples

[1609] Task assignment

[1610] The server analyzes each member's skill set, work history, and emotional data and assigns tasks to the most suitable member. For example, if a member with strong design skills is confirmed to have not been feeling stressed recently, he or she will be assigned the task of user interface design.

[1611] Risk prediction and countermeasures

[1612] The server predicts project risks based on past project data, current progress data, and emotional data. For example, it can determine that a particular phase is prone to resource shortages, while also detecting rising stress levels from the emotional data of current team members and suggesting countermeasures.

[1613] In this way, this system will significantly improve the efficiency of project management and help increase the success rate of projects. In addition, by utilizing generative AI and an emotion engine, even beginners can improve their project management skills.

[1614] The processing flow will be explained below.

[1615] Step 1: Data collection

[1616] The server collects progress data, task data, and resource data for each project through APIs. It connects with project management tools and resource management systems and obtains emotion data from the emotion engine.

[1617] Step 2: Data integration

[1618] The data collected by the server is integrated into a database for centralized management. This is the process of cleaning the data and unifying data in different formats.

[1619] Step 3: Real-time analytics

[1620] The server analyzes the integrated data in real time, instantly understanding the progress of each task, resource usage, and user sentiment data.

[1621] Step 4: Progress forecast

[1622] The server uses the generated AI to predict task progress and resource supply and demand. Based on past data, current progress, and emotion data, it calculates future progress and the possibility of resource shortages.

[1623] Step 5: Task assignment

[1624] The server uses generative AI to optimally assign tasks to each member, taking into account their skill set, work history, and emotional data. For example, it assigns important tasks to members with low stress levels.

[1625] Step 6: Schedule optimization

[1626] The server optimizes the schedule for the entire project, using the critical path method (CPM) to prevent unnecessary delays.

[1627] Step 7: Risk prediction

[1628] The server predicts risks based on past and current progress data and emotion data, providing early detection of the risk of resource shortages or delays in progress in specific phases or tasks.

[1629] Step 8: Generate countermeasures

[1630] The server generates risk countermeasures and notifies the project manager, for example, suggesting additional resources or rescheduling the schedule.

[1631] Step 9: Notifications and User Interface Updates

[1632] The device receives notifications and suggestions from the server and displays them in the user interface, which is designed to help users intuitively understand important information.

[1633] Step 10: Accepting User Input

[1634] The terminal accepts manual task assignments and schedule changes by the project manager, including input of emotional information, and transmits that information to the server.

[1635] Step 11: Visualize risk information

[1636] The device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions.

[1637] Step 12: Review progress and risk information

[1638] Users can check project progress and risk information through the interface, and with information updated in real time, users can manage projects efficiently.

[1639] Step 13: Task assignment and scheduling

[1640] The user can review the task assignments and schedules proposed by the server and manually correct them if necessary. They can also provide feedback on emotional data, which can be used for further optimization.

[1641] Step 14: Implement risk responses

[1642] Users receive risk prediction information and take countermeasures based on it, such as assigning lighter tasks to members experiencing high stress levels.

[1643] Step 15: Feedback Loop

[1644] The server again collects data on the results of user actions and the countermeasures taken, and feeds it back into the AI ​​model, thereby improving the accuracy of predictions and the quality of suggestions.

[1645] Example 2

[1646] 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."

[1647] Conventional project management systems do not adequately grasp progress and resource usage, optimally allocate tasks, or predict risks and present countermeasures. Furthermore, they are unable to optimize or manage risks taking into account the emotional state of users, resulting in insufficient project efficiency and risk management. This increases uncertainty in the progress of projects, making it difficult to achieve optimal results.

[1648] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1649] In this invention, the server includes: means for collecting and integrating data for each project using a generative AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing schedules using the generative AI; means for predicting risks and proposing countermeasures based on past data and current progress data; means for presenting the proposals to the user through notifications and a user interface; means for collecting, analyzing, and integrating user emotion data using an emotion engine; and means for improving risk predictions and countermeasure proposals based on the emotion data. This enables real-time understanding of project progress and resource usage, optimal task allocation and schedule optimization including emotion data, and highly accurate risk predictions and proposals of countermeasures.

[1650] - "Generative AI" is a system that uses artificial intelligence technology to collect, integrate, analyze, and predict data.

[1651] "Project data" refers to a group of information that indicates the progress of a project, task information, resource usage status, emotional data, and the like.

[1652] "Real-time analysis" is the process of processing data instantly to understand the current situation.

[1653] "Progress" is information that indicates how much of a project's tasks have been completed.

[1654] "Resource usage status" refers to the current status of human and material resources used in a project.

[1655] "Optimal task allocation" is the process of assigning each task to the most suitable member based on the project members' skills and circumstances.

[1656] "Schedule optimization" is a method of optimizing the timeline of the entire project to ensure efficient progress.

[1657] "Risk prediction" is the process of predicting possible future problems or failures based on past and current data.

[1658] "Proposing countermeasures" means proposing specific solutions or actions to address predicted risks.

[1659] A "user interface" is a screen or operating means that allows a user to interact with a system.

[1660] "Presenting a proposal to the user" refers to the act of displaying the proposal content from the system to the user.

[1661] The "emotion engine" is a system that recognizes and analyzes the user's emotional state and collects that data.

[1662] "Emotion data" is data that indicates the user's stress level and emotional state.

[1663] "Analyze and synthesize" is the process of processing collected data and turning it into a unified, usable information.

[1664] "Improving risk prediction and countermeasure proposals" means providing more accurate risk predictions and specific, effective countermeasures based on emotion data.

[1665] The project management support system of this invention combines generative AI and an emotion engine to provide a series of systems that collect and integrate project data, analyze progress and resource usage in real time, optimally allocate tasks, optimize schedules, predict risks, and present countermeasures. Specifically, the server, terminal, user, and emotion engine each have their own roles and implement the system.

[1666] Server Processing

[1667] The server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a formatting and cleansing process. A relational database such as MySQL is used as the database.

[1668] The server analyzes the collected data in real time to understand the progress of each task and the resource usage status. It also uses a generative AI model to predict progress and resource supply and demand, and immediately updates the results. For example, it provides a prediction such as, "Based on the current progress, Task A will be completed in three days."

[1669] Furthermore, the server uses generative AI to optimally assign tasks to project members, taking into account their skill sets, work history, and emotional data provided by the emotion engine. For example, it may suggest, "Since member C has high data analysis skills, he should be assigned to analysis tasks." It also uses techniques such as the critical path method (CPM) to optimize the overall project schedule and make suggestions for efficient progress.

[1670] The server predicts risks based on past project data, current progress data, and emotion data. For example, if a user has many tasks that tend to cause stress, the server generates countermeasures to reduce the risk and notifies the user.

[1671] Terminal handling

[1672] The device receives notifications and suggestions from the server and displays them in the user interface. An intuitive UI is designed to make it easy for users to understand important information. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[1673] The terminal also accepts manual task assignments and schedule changes by the project manager, as well as emotional information, and sends this information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[1674] Furthermore, the device visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions, allowing the user to quickly take specific countermeasures.

[1675] User interaction and feedback

[1676] The user (project manager) checks the project progress and risk information through the terminal interface. The dashboard displays information that is updated in real time. For example, the user can perform an operation such as "Check the progress rate and risk information for Task A on the dashboard."

[1677] The user can also check the task assignments and schedules proposed by the server and manually revise them as necessary. Emotional data is also fed back, and further optimization is performed based on that information. For example, the system may provide feedback such as "If you feel stressed, enter that emotional data into the device."

[1678] Furthermore, users receive risk prediction information and take countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[1679] Emotion engine integration

[1680] The emotion engine recognizes emotions in real time based on the user's facial expressions, voice, and text data, and sends that data to the server. For example, it can detect "fatigue" from the user's facial expressions and record it as data.

[1681] The server integrates the data sent from the emotion engine with project data and uses it for analysis. If a user's stress level increases, it can take that into account and adjust task assignments. For example, task progress data can be linked to user emotion data and managed centrally.

[1682] The server uses the emotional data to make more accurate risk predictions and propose countermeasures. Specifically, it predicts the "stress level for the next week" based on the emotional data and generates specific countermeasures based on that.

[1683] Examples of concrete examples and prompts

[1684] Specific examples

[1685] 1. Example of task assignment:

[1686] A suggestion is made such as, "Member C has high skills in data analysis, so we will assign him to the analysis task."

[1687] 2. Examples of risk prediction and countermeasures:

[1688] "Detect rising stress levels from current team members' emotional data and suggest countermeasures to reduce the risk of resource shortages."

[1689] Prompt Sentence Examples

[1690] PROGRESS_TRACK='Check your progress.'

[1691] TASK_ASSIGN = 'Consider the skill sets and sentiment data of project members to assign optimal tasks.'

[1692] RISK_RESPONSE = 'Predict risks based on past and current data and provide countermeasures.'

[1693] In this way, this system will significantly improve the efficiency of project management operations and help increase the success rate of projects. In addition, the use of generative AI and an emotion engine will enable data-driven decision-making, improving the ability of even project novices to manage projects.

[1694] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1695] Step 1:

[1696] The server collects progress data, task data, resource data, and emotion data from project management tools and emotion engines via APIs. Specifically, it collects project progress and task information from JIRA, Trello, etc., and obtains data on users' stress and emotional state from the emotion engine.

[1697] Input: Data from project management tools and sentiment engines

[1698] Output: Collected data (progress data, task data, resource data, emotion data)

[1699] Step 2:

[1700] The server formats and cleanses the collected data, for example, by removing unnecessary data and completing missing values, thereby improving the quality of the data.

[1701] Input: Various collected data

[1702] Output: Formatted and cleansed data

[1703] Step 3:

[1704] The server then consolidates the formatted and cleansed data and stores it in a database (e.g., MySQL), resulting in a unified data set.

[1705] Input: Formatted and cleansed data

[1706] Output: Consolidated data stored in a database

[1707] Step 4:

[1708] The server analyzes the integrated data in real time and visualizes progress and resource usage, for example, by outputting graphs showing the progress rate of each task and the workload of each member.

[1709] Input: Integrated data stored in a database

[1710] Output: Analysis results (progress, resource usage visualization graphs)

[1711] Step 5:

[1712] The server uses the generative AI model to predict progress and resource demand and supply, for example, generating a prediction such as "Task A is expected to be completed in three days, based on the current progress."

[1713] Inputs: Integrated data and real-time progress

[1714] Output: Progress forecast and resource demand forecast

[1715] Step 6:

[1716] The server uses a generative AI model to analyze the skill sets, work history, and emotional data of project members, and then optimally assigns tasks and optimizes the schedule. For example, it may suggest that "member C has high data analysis skills, so he should be assigned to analysis tasks."

[1717] Input: Integrated data, project member skill sets and work history, sentiment data

[1718] Output: Optimized task assignment and schedule

[1719] Step 7:

[1720] The server predicts risks based on past project data, current progress data, and emotion data. For example, it generates countermeasures to reduce the risk if the user has many tasks that are likely to cause stress.

[1721] Inputs: Integration data, past and current progress data, sentiment data

[1722] Output: Risk prediction and countermeasures

[1723] Step 8:

[1724] The device receives notifications and suggestions from the server and displays them in the user interface. For example, a pop-up notification such as "Task A's progress rate has exceeded 80%" is displayed.

[1725] Input: Notifications and suggestions from the server

[1726] Output: Notifications and suggestions displayed in the user interface

[1727] Step 9:

[1728] The terminal accepts the project manager's manual task assignment and schedule change operations, as well as emotional information input, and sends that information to the server. For example, it accepts an operation to reassign Task A to a specific member.

[1729] Input: Manual input from project manager (task assignments, schedule changes, sentiment information)

[1730] Output: Updates sent to the server

[1731] Step 10:

[1732] The terminal visualizes the risk prediction and countermeasure information provided by the server and presents the user with details of the risk and recommended actions. For example, it displays information such as "There is a risk of resource shortage in the next phase" in a graph.

[1733] Input: Risk prediction and countermeasure information provided by the server

[1734] Output: Risk information and countermeasures displayed in the user interface

[1735] Step 11:

[1736] Users can check the project's progress and risk information through the device interface and manually modify tasks as needed. Emotional data is also provided as feedback. For example, users can "check the progress rate and risk information for Task A on the dashboard, and if they feel stressed, enter their emotional data into the device."

[1737] Inputs: Progress and risk information from the dashboard, manual user input (task corrections, sentiment data)

[1738] Output: Updated progress and risk information, feedback information to the server

[1739] Step 12:

[1740] The user receives risk prediction information and takes countermeasures based on it. For example, they can reassign stressful tasks to other members. By implementing the countermeasures suggested by the server, the project risk is reduced.

[1741] Input: Risk prediction information and countermeasure proposals

[1742] Output: Measures taken, risk mitigation

[1743] (Application example 2)

[1744] 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."

[1745] Modern manufacturing requires efficient project management, but conventional systems have difficulty taking into account the emotional state of human resources when allocating tasks and managing schedules. This increases worker stress, risking reduced productivity and quality. Furthermore, adequate information is often unavailable for risk prediction and countermeasures, resulting in measures being implemented only after a problem has occurred. To address these issues, it is necessary to develop a system that uses real-time emotional data to optimally allocate tasks and predict risks.

[1746] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting and integrating data for each project using a generation AI; means for analyzing the collected data in real time to grasp progress and resource usage; means for optimally allocating tasks and optimizing the schedule using the generation AI; means for predicting risks based on past data and current progress data and proposing countermeasures; means for presenting suggestions to the user through notifications and a user interface; means for collecting emotional data in real time using various sensors used in the work environment and integrating and analyzing this emotional data with project data; and means for allocating tasks and predicting risks based on the emotional data. This enables efficient task allocation and risk management while taking into account the emotional states of workers.

[1747] "Generative AI" is a technology that uses artificial intelligence techniques to generate data, make inferences, and make predictions.

[1748] "Project data" refers to information necessary for project management, such as progress, task details, and resource usage.

[1749] "Real-time" refers to data being collected, analyzed, and processed with minimal delay, and updated and reflected immediately.

[1750] "Emotion data" is data that represents the emotional state of a worker and is acquired using sensors and analytical algorithms.

[1751] "Optimal task allocation" means assigning tasks to the person best suited to each task, taking into account the worker's skill set and emotional data.

[1752] "Schedule optimization" refers to the readjustment and optimization of a schedule to most efficiently move a project forward.

[1753] "Risk prediction" means predicting problems or obstacles that may occur in the future based on past data and current progress data.

[1754] "Proposing countermeasures" means proposing appropriate measures and action plans for predicted risks.

[1755] "Notification" is a function that allows the server to convey information such as warnings and suggestions to the user.

[1756] "User interface" refers to the screen and input devices that allow a user to interact with a system.

[1757] "Various sensors used in the work environment" refers to devices such as cameras, microphones, and vital signs sensors that detect data within the environment and the status of workers.

[1758] This invention is a system that supports project management by combining generative AI and an emotion engine, with the aim of improving the efficiency of work within factories. This system consists of a server, terminals, users, and an emotion engine, each of which has a specific role.

[1759] Server Processing

[1760] The server is responsible for collecting and integrating data from each project using generative AI. Specifically, it uses the following hardware and software:

[1761] Hardware: General-purpose server equipment

[1762] Software: Generative AI models implemented in TensorFlow and PyTorch, and data collection APIs

[1763] First, the server collects progress data, task data, and resource data for each project via API and stores it in a database. This data is collected from various project management tools and emotion engines and integrated through a data shaping and cleansing process. Next, the server analyzes the data in real time to understand the progress and resource usage of each task. It also uses generative AI models to forecast progress and resource supply and demand, and immediately updates the results.

[1764] The server also uses generative AI to optimally allocate tasks and optimize schedules. For example, it considers the skill sets, work history, and emotional data of project members to optimally allocate tasks. It also uses optimization algorithms such as the critical path method (CPM) to make suggestions for efficiently progressing the entire project schedule.

[1765] Terminal handling

[1766] The terminal functions as an interface for receiving notifications and suggestions from the server. The user interface (UI) is intuitively designed so that users can easily understand important information. Specifically, it provides the following functions:

[1767] Notifications and interface updates: Receives notifications and suggestions from the server and displays them in the user interface.

[1768] Accepting and sending user input: Accepting user actions such as manually assigning or rescheduling a task, and sending that information to the server.

[1769] User interaction and feedback

[1770] The project manager, who is the user, uses the system by performing the following operations.

[1771] Check progress and risk information: Check project progress and risk information through a user interface. The dashboard displays real-time updates.

[1772] Task Allocation and Schedule Management: You can check the task allocation and schedule proposed by the server and manually correct them if necessary. You can also provide emotional feedback.

[1773] Implement risk response measures: Receive risk prediction information and implement response measures based on it, such as reassigning stressful tasks to other members.

[1774] Emotion engine integration

[1775] The emotion engine collects emotion data in real time using various sensors used in the work environment and sends this data to the server. Based on this emotion data, the server can make more accurate risk predictions and propose countermeasures. Specifically, the process includes the following steps:

[1776] Emotion data collection: Recognize emotions in real time from the user's facial expressions, voice, text data, etc.

[1777] Emotional data integration and analysis: Emotional data can be integrated with project data and used for analysis, for example, to take into account increased user stress levels and adjust task assignments accordingly.

[1778] Risk prediction and improved response: Emotional data is used to generate suggestions to reduce task load for users showing signs of stress or fatigue.

[1779] Examples of concrete examples and prompts

[1780] Example of task allocation: Based on worker skill sets and emotional data, assign maintenance work for a particular machine to a worker who is familiar with operating that machine and does not feel stressed.

[1781] A concrete example of risk prediction and countermeasures: If emotional data indicates that a particular worker is prone to fatigue, the system can assign lighter work to reduce the worker's workload or send a notification recommending that they take a break.

[1782] An example of a prompt is, "Assign priority tasks to workers with high skill sets and low stress levels." By inputting this prompt into the generative AI model, optimal task assignments are made.

[1783] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1784] Step 1:

[1785] The server collects progress data, task data, and resource data for each project via API. At the same time, it also acquires emotional data from various sensors (cameras, microphones, vital signs sensors, etc.) installed in the work environment and stores it in a database. The input is data from various sensors and project management tools, and the output is formatted, cleansed, and integrated data.

[1786] Step 2:

[1787] The server analyzes the input data in real time to grasp the progress and resource usage of each task. At this time, it uses a generation AI to predict progress and resource supply and demand. The input is the integrated data from step 1, and the output is the analysis results and forecast data. For example, it calculates the progress rate and the planned resource usage.

[1788] Step 3:

[1789] The server uses generative AI to optimally allocate tasks and optimize the schedule, taking into account the skill sets, work history, and emotional data of project members. The input is the analysis results and prediction data from Step 2, and the output is the optimized task allocation and schedule.

[1790] Step 4:

[1791] The server analyzes the data to predict risks and propose countermeasures. Risk prediction is based on past data, current progress data, and emotion data. The input is the data from Steps 2 and 3, and the output is risk prediction and proposed countermeasures. For example, it generates a proposal to reduce tasks that are likely to cause stress to a specific worker.

[1792] Step 5:

[1793] The device receives notifications and suggestions from the server and displays them on the user interface. An intuitive UI is designed so that users can easily understand important information. The input is the notification and suggestion data from the server, and the output is the information displayed on the user interface.

[1794] Step 6:

[1795] The terminal accepts manual task assignments and schedule changes by the project manager and sends the information to the server. The input is the operation data from the user, and the output is the correction data sent to the server. For example, when a specif...

Claims

1. A means of collecting and integrating data for each project using generative AI, A means to analyze collected data in real time to understand progress and resource usage; A means of optimally allocating and scheduling tasks using generative AI; and A means of predicting risks and proposing countermeasures based on past data and current progress data; means for presenting the suggestions to the user through notifications and a user interface; A system including:

2. The system of claim 1, wherein the generation AI predicts task progress and resource supply and demand based on the data collected.

3. 10. The system of claim 1, wherein the user interface accepts manual task assignments and schedule changes by the project manager and transmits the information to the server.

Images