System

Abstract

A system is provided.SOLUTION: A system comprising: means for optimizing resource allocation of a project using generative artificial intelligence; means for tracking progress in real-time and generating alerts when problems occur; means for analyzing communication between project members and identifying areas prone to misunderstanding; and means for optimizing a schedule of the project.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] Traditional project management systems require a large number of resources and require manual management of complex tasks such as progress tracking, resource allocation, efficient communication, and scheduling. This places a heavy burden on project managers, resulting in lower project efficiency and success rates. In particular, when managing multiple projects simultaneously, it is difficult to optimize resources, track progress in real time, communicate effectively, and meet deadlines. [Means for solving the problem]

[0005] The present invention provides a system for automating and optimizing complex project management tasks by leveraging generative artificial intelligence, the system comprising:

[0006] 1. A means of optimizing resource allocation using generative artificial intelligence to learn from past project data.

[0007] 2. A means of collecting real-time progress data and generating early problem detection and alerts.

[0008] 3. A means of analyzing communication data between project members to identify information gaps and misunderstandings.

[0009] 4. A means of inputting the current schedule of the project and optimizing it.

[0010] This reduces the burden on project managers and significantly improves project efficiency and success rates.

[0011] "Generative AI" is an AI technology that automatically generates information through data analysis and pattern recognition to support problem-solving and decision-making.

[0012] "Resource allocation" refers to the efficient allocation and optimization of resources such as labor, time, funds, and equipment required for a project.

[0013] "Optimization" is the process of adjusting each element to achieve the most efficient and effective results given limited resources and conditions.

[0014] "Progress tracking" means monitoring the progress of each task and the overall progress of a project in real time and updating the information in a timely manner.

[0015] An "alert" is a warning message that notifies the user when the system detects an abnormality or problem.

[0016] "Communication data" refers to all communication records such as emails, chat logs, and meeting minutes exchanged between project members.

[0017] Schedule optimization is the process of optimizing the start and finish dates of project tasks, maximizing resource utilization, and adjusting the plan to complete the project on time. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention is a system that utilizes generative artificial intelligence to improve project management efficiency and quality. The specific operations of each component, server, terminal, and user, will be described below.

[0040] Optimizing resource allocation

[0041] The user inputs detailed project information into the terminal, including the project name, resource type, number of resources, project duration, etc. The terminal collects this information and sends it to the server.

[0042] The server uses generative artificial intelligence to calculate optimal resource allocation based on past project data. The calculation results are generated as optimized resource allocation. This optimized resource allocation is then sent back to the terminal from the server.

[0043] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[0044] Real-time progress tracking and alerts

[0045] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[0046] The server collects progress data in real time, analyzes it to check for problems, and if a problem is detected, generates an alert and sends it to the device.

[0047] The terminal notifies the user of the alert information received from the server, and the user can check the alert and take the necessary measures promptly.

[0048] Facilitating communication and preventing misunderstandings

[0049] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then collect and transmit this data to the server.

[0050] The server uses generative artificial intelligence to analyze communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The identified problems are then sent back to the terminal.

[0051] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[0052] Deadline Management and Scheduling

[0053] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[0054] The server optimizes the schedule using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal.

[0055] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[0056] Specific examples

[0057] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal, including the number of development team members, budget, required equipment, development time, etc. The terminal then sends this information to the server and receives an optimized resource allocation.

[0058] Once a project has begun, the server monitors its progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early.

[0059] To ensure smooth communication between development teams, the server analyzes chat logs and emails to identify potential misunderstandings and notify users on their devices. Users can use this information to resolve misunderstandings and improve communication.

[0060] Furthermore, when a user inputs their current schedule into the terminal while the project is in progress, the server optimizes the schedule and returns the optimized schedule to the terminal, allowing the user to efficiently progress the project according to the optimized schedule.

[0061] In this way, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[0062] The processing flow will be explained below.

[0063] Optimizing resource allocation

[0064] Step 1:

[0065] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[0066] Step 2:

[0067] The terminal transmits the input project information to the server.

[0068] Step 3:

[0069] The server uses generative AI to learn from past project data and calculate optimal resource allocation.

[0070] Step 4:

[0071] The server returns the calculated optimized resource allocation to the terminal.

[0072] Step 5:

[0073] The terminal displays the received optimized resource allocation to the user.

[0074] Real-time progress tracking and alerts

[0075] Step 1:

[0076] The user enters the ID of the project they want to track into the terminal.

[0077] Step 2:

[0078] The terminal transmits the project ID to the server.

[0079] Step 3:

[0080] The server collects project progress data in real time.

[0081] Step 4:

[0082] The server analyzes the progress data and generates alerts if it detects a problem.

[0083] Step 5:

[0084] The server transmits the generated alert to the terminal.

[0085] Step 6:

[0086] The terminal notifies the user of the alert information.

[0087] Facilitating communication and preventing misunderstandings

[0088] Step 1:

[0089] The user inputs communication data between project members into the terminal.

[0090] Step 2:

[0091] The terminal transmits the communication data to the server.

[0092] Step 3:

[0093] The server uses generative AI to analyze communication data and identify points where misunderstandings are likely to occur.

[0094] Step 4:

[0095] The server returns the identified problem to the terminal.

[0096] Step 5:

[0097] The terminal displays the received analysis results to the user.

[0098] Deadline Management and Scheduling

[0099] Step 1:

[0100] The user inputs the current schedule of the project into the terminal.

[0101] Step 2:

[0102] The terminal transmits the schedule information to the server.

[0103] Step 3:

[0104] The server uses a generative AI to optimize the input schedule.

[0105] Step 4:

[0106] The server transmits the optimized schedule to the terminal.

[0107] Step 5:

[0108] The terminal displays the received optimized schedule to the user.

[0109] The above is a specific flow of each process performed by the system of the present invention, which optimizes project management, reduces the burden on users, and improves the success rate of projects.

[0110] Example 1

[0111] 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."

[0112] In project management, efficient resource allocation, real-time progress tracking, preventing communication gaps, and optimizing scheduling are important. However, performing these tasks manually is extremely time-consuming and prone to errors. These challenges are particularly pronounced in large-scale, complex projects, and can have a significant impact on project success. Therefore, there is a need for a system that automates project management and operates it efficiently.

[0113] 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.

[0114] In this invention, the server includes: a means for a user to input detailed project information into a terminal and for the terminal to transmit the information to the server; a means for the server to calculate optimal resource allocation using a generative AI model and return the calculation result to the terminal for display to the user; a means for a user to input an ID of a project they want to track into the terminal and for the terminal to transmit the ID to the server, and for the server to collect progress data in real time and check for any problems; a means for the server to generate an alert and transmit it to the terminal if a problem is detected; a means for a user to input communication data between project members into the terminal and for the terminal to transmit the data to the server; a means for the server to analyze the communication data using the generative AI model and identify points where information is lacking or misunderstandings are likely to occur and return the identified points to the terminal; a means for a user to input a current project schedule into the terminal and for the terminal to transmit the schedule information to the server; and a means for the server to optimize the schedule using the generative AI model and transmit the optimized schedule to the terminal, which displays it to the user. This automates various project management tasks, enabling efficient and highly accurate project management.

[0115] "User" refers to the person who operates the system and inputs project details, progress, communication data, etc.

[0116] "Terminal" refers to a device or computer that collects information entered by a user and communicates with a server.

[0117] "Server" refers to a central processing unit that uses generative AI models to analyze data and perform calculations such as optimal resource allocation, progress tracking, and schedule optimization.

[0118] "Generative AI model" refers to artificial intelligence technology that learns from past data and uses input information to optimally allocate resources, optimize schedules, and identify communication gaps.

[0119] "Project detailed information" refers to various information necessary for executing a project, such as the project name, resource type, number of resources, and project period.

[0120] "Resource allocation" refers to the optimal allocation of resources (e.g., personnel and equipment) required to efficiently progress a project.

[0121] "Project ID" means a unique identifier used to identify a particular project.

[0122] "Progress data" refers to information that indicates the progress of a project or the degree of task completion.

[0123] "Alert" refers to a warning message that notifies the user when a problem occurs based on the results of progress data analysis.

[0124] "Communication data" refers to records of interactions between project members, such as emails, chat logs, and meeting minutes.

[0125] A "schedule" refers to a plan that shows the order and deadlines for each task in a project.

[0126] This invention is a system that utilizes generative artificial intelligence to improve the efficiency and quality of project management. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role to support the smooth progress of a project.

[0127] The system's programming begins with the user entering detailed project information. The user enters the project name, resource type, number of resources, project duration, and other information into the device through a dedicated UI. The device then collects this information and sends it to the server. The server then uses a generative AI model (e.g., OpenAI's GPT-4®) to calculate optimal resource allocation. The server then sends the results of this calculation back to the device, which then displays the optimized resource allocation to the user.

[0128] Users can also enter the ID of the project they want to track into their device, which then sends it to the server. The server collects real-time progress data and analyzes it using a generative AI model. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user, allowing them to quickly resolve the issue.

[0129] Furthermore, when a user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the device, the device sends this data to the server. The server analyzes this data using a generative AI model and identifies points where information is lacking or where misunderstandings are likely to occur. The server then sends the results back to the device, which displays them to the user, allowing the user to implement measures to improve communication.

[0130] This system is also effective in project scheduling. When a user inputs the current project schedule into a device, the device sends this schedule information to a server. The server then optimizes the schedule using a generative AI model and sends the results to the device. The device then displays the optimized schedule to the user, who can then efficiently progress the project according to this schedule.

[0131] Examples:

[0132] For example, in the case of a new software development project, the user (project manager) enters detailed project information (such as the number of people in the development team, the budget, the necessary equipment, and the development period) into a terminal. The endpoint API obtains the input information, such as the project name and number of resources, and sends it to the server. The server receives this information and generates a prompt for the generative AI model. An example of a prompt input to the generative AI model would be, "Project name: XYZ, resources: 5 developers, 2 designers, 3 testers, duration: 6 months. Please suggest the optimal resource allocation."

[0133] Once a project has begun, the server monitors progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early. The server also analyzes chat logs and emails to identify areas where misunderstandings are likely to occur and notifies the device. Users can use this information to improve communication. Furthermore, when the user enters their current schedule into their device while the project is in progress, the server optimizes the schedule using a generative AI model, and the optimized schedule is sent back to the device. Users can then efficiently progress with the project according to the optimized schedule.

[0134] As described above, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1:

[0137] The user inputs project details into the terminal, such as the project name, resource type (e.g., developer, designer, tester), number of resources, and project duration, through a dedicated user interface (UI). The input data is converted into a standard format, such as JSON.

[0138] Input: Project details (Project name, resource type, number of resources, project duration)

[0139] Output: Project details in JSON format as entered in the terminal

[0140] Step 2:

[0141] The device sends the project details to the server. The device then sends the entered JSON format data to the server via a protocol such as an HTTP request. This data is encrypted before being sent.

[0142] Input: Project details in JSON format entered into the terminal

[0143] Output: Project details in JSON format sent to the server

[0144] Step 3:

[0145] The server analyzes the received project details and generates a prompt for the generative AI model. The server compares the information with past project data stored in the database and sends the information to the generative AI model. Example prompt: "Project name: XYZ, Resources: 5 developers, 2 designers, 3 testers, Duration: 6 months. Please suggest the optimal resource allocation."

[0146] Input: Project details in JSON format sent to the server

[0147] Output: The prompt sent to the generative AI model

[0148] Step 4:

[0149] The server uses a generative AI model to calculate optimal resource allocation. The generative AI model receives the prompt and calculates the optimal resource allocation based on the results of learning from past data. The calculation results are returned to the server in JSON format.

[0150] Input: The prompt sent to the generative AI model

[0151] Output: Optimal resource allocation returned by the generative AI model (JSON format)

[0152] Step 5:

[0153] The server returns the calculation results to the device and displays them to the user. The server analyzes the response from the generative AI model, converts it into a format that is easy for the user to understand, and then sends it to the device. The device receives this information and displays it on its UI, allowing the user to see the optimized resource allocation.

[0154] Input: Optimal resource allocation returned by the generative AI model (JSON format)

[0155] Output: Optimized resource allocation displayed on the terminal

[0156] Step 6:

[0157] The user enters a project ID into the device to track the progress of the project. The user uses a dedicated UI to enter the ID of the project they want to track.

[0158] Input: The project ID entered by the user

[0159] Output: Project ID saved on the device

[0160] Step 7:

[0161] The device sends the project ID to the server. The device sends the project ID to the server via a protocol such as an HTTP request.

[0162] Input: Project ID saved on your device

[0163] Output: Project ID sent to the server

[0164] Step 8:

[0165] The server collects progress data in real time based on the project ID and analyzes the data using the generative AI model. The server calls the API of the project management tool to collect progress data. The collected data is then sent to the generative AI model to check for any problems.

[0166] Input: Project ID sent to the server

[0167] Output: Analysis results by generative AI model (progress)

[0168] Step 9:

[0169] If the server detects a problem, it generates an alert and sends it to the device. Based on the analysis results of the generative AI model, the server identifies the problem and generates an alert message. The alert message is then sent to the device.

[0170] Input: Analysis results by generative AI model (progress)

[0171] Output: The alert message sent to the terminal.

[0172] Step 10:

[0173] The device notifies the user of the alert information. The device notifies the user of the received alert message via a pop-up or email notification, helping the user to deal with the problem early.

[0174] Input: The alert message received from the server

[0175] Output: Alert message sent to the user

[0176] The above are the specific processing steps of the system program.

[0177] (Application example 1)

[0178] 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."

[0179] In modern factory operations and project management, optimal resource allocation, real-time progress tracking, smooth communication, and efficient scheduling are key challenges. In particular, when operating robots in factories, it is necessary to accurately understand the operating status of each robot and respond immediately when an abnormality occurs. However, current systems manage these elements individually, making it difficult to optimize the entire process. This often leads to resource waste and stalls, and calls for improvements in the overall efficiency and quality of projects.

[0180] 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.

[0181] In this invention, the server includes means for optimizing resource allocation for a project using generative artificial intelligence, means for tracking progress in real time and generating warnings when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project timetable, means for managing factory robot operations and understanding the work status of each robot, means for monitoring the work progress of the robots in real time and generating warnings when an abnormality is detected, and means for analyzing communication data within the factory to identify areas for improvement. This enables efficient resource management, real-time tracking of work progress, rapid response when an abnormality occurs, and smooth communication.

[0182] "Generative artificial intelligence" is a technology that learns from huge amounts of data and automatically performs complex tasks and makes decisions.

[0183] "Resource allocation" is the act of appropriately allocating the necessary resources for a specific project or task.

[0184] "Real-time" refers to processing data and providing information without delay in accordance with actual time.

[0185] An "alert" is a notification that notifies you when some kind of problem or abnormality occurs.

[0186] "Project Member" refers to an individual member working on a project.

[0187] "Communication Data" refers to information regarding interactions between members (emails, chat logs, meeting minutes, etc.).

[0188] A "timetable" refers to the schedule for the progress of work or a project.

[0189] A "factory robot" refers to a mechanical device that automatically performs specific tasks in a factory.

[0190] "Work status" refers to the state in which a particular work is progressing.

[0191] An "anomaly" refers to a problem that deviates from normal or expected behavior.

[0192] This invention is a specific system that utilizes generative artificial intelligence to optimize the operation of factory robots, thereby improving project management efficiency and quality. The specific operations of each component, including the server, terminal, and user, are described below.

[0193] Optimizing resource allocation

[0194] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, project duration, etc. The terminal collects this data and sends it to the server. The server uses generative artificial intelligence to calculate the optimal resource allocation based on past project data. This optimized resource allocation is sent back from the server to the terminal, which then displays it to the user, thereby achieving efficient resource allocation.

[0195] Real-time progress tracking and alerts

[0196] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time progress data from sensors attached to factory robots and analyzes the data to check for problems. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of the alert information, allowing them to take timely action.

[0197] Facilitating communication and preventing misunderstandings

[0198] Users input communication data between project members (emails, chat logs, meeting minutes, etc.) into their terminals. The terminals collect this data and send it to the server. The server then uses generative artificial intelligence to analyze the communication data. This analysis identifies points where information is lacking or misunderstandings are likely to occur, and the results are sent back from the server to the terminal. The terminal then displays the analysis results to the user, who can then implement measures to improve communication based on these results.

[0199] Deadline Management and Scheduling

[0200] The user inputs the current project schedule into the device. The device then sends this schedule information to the server and requests that the schedule be optimized. The server then uses generative artificial intelligence to optimize the schedule and sends the results back to the device. The optimized schedule is displayed on the device, allowing the user to proceed with the project accordingly and complete it within the deadline while maximizing resource utilization efficiency.

[0201] Hardware and software used

[0202] The main hardware used includes servers (equipped with high-performance CPUs and GPUs), terminals (smartphones, tablets, PCs), and factory robots (equipped with various sensors and communication modules).

[0203] The software used includes an AI model on the server (TENSORFLOW (registered trademark), PyTorch), a communication API (REST API that communicates via HTTP), and control software (Python) on the edge device side.

[0204] Specific examples

[0205] As a specific example, the user (factory manager) enters detailed information about the robot line (number of robots, work period, etc.) into a terminal. This information is then sent to a server, which uses past data and generative artificial intelligence to calculate the optimal robot allocation and sends it back to the terminal. As the project progresses, progress information collected in real time from sensors is analyzed by the server, and if an abnormality is detected, an alert is sent immediately to the user. In addition, a function to facilitate communication between users is used to prevent misunderstandings and optimize the schedule.

[0206] A specific example of a prompt is as follows:

[0207] Prompt for project details: "Please enter the current project details (number of robots, work period, etc.)."

[0208] Progress Tracking Prompt: "Enter the ID of the project you want to track."

[0209] Communication data input prompt: "Please enter the communication data (emails, chat logs, etc.) you want to analyze."

[0210] Current Schedule Input Prompt: "Please enter your current schedule information."

[0211] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0212] Step 1:

[0213] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, and project duration. The input information is sent from the terminal to the server. This allows the basic conditions of the project to be collected as data.

[0214] Step 2:

[0215] The server uses generative artificial intelligence to calculate optimal resource allocation based on the received project details. Data from past projects and similar projects is utilized here. The calculated optimal resource allocation is sent from the server to the terminal. This allows the user to receive an efficient resource allocation plan.

[0216] Step 3:

[0217] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to obtain specific instructions regarding resource allocation, and the user can start a project based on this information.

[0218] Step 4:

[0219] The user enters the ID of the project they want to track into their device and sends that information to the server, which then identifies the project to be tracked.

[0220] Step 5:

[0221] The server collects real-time progress data from sensors attached to factory robots. This data is processed by the server and analyzed for abnormalities. If an abnormality is detected, an alert is generated and sent to the terminal, allowing the user to immediately recognize the abnormality and take action.

[0222] Step 6:

[0223] The terminal notifies the user of the alert information received from the server, allowing the user to take immediate action and resolve the problem quickly.

[0224] Step 7:

[0225] The user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the terminal and sends the data to the server, which starts the analysis of communication within the project.

[0226] Step 8:

[0227] The server uses generative artificial intelligence to analyze the received communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The analysis results are then sent from the server to the device.

[0228] Step 9:

[0229] The device then displays the analysis results to the user, allowing the user to identify areas for improvement in communication between project members and take specific measures to improve them.

[0230] Step 10:

[0231] The user inputs the current schedule of the project into the terminal and sends the schedule information to the server, which starts the schedule optimization process.

[0232] Step 11:

[0233] The server optimizes the received schedule information using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal. As a result, the user receives the optimized schedule, which helps to streamline the progress of the project.

[0234] Step 12:

[0235] The terminal displays the received optimized schedule to the user, allowing the user to take specific steps to efficiently progress the project.

[0236] 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.

[0237] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[0238] Optimizing resource allocation

[0239] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal, which then transmits the input project information to the server.

[0240] The server uses live artificial intelligence to calculate optimal resource allocation based on past project data, and the results are generated as optimized resource allocation and sent back to the terminal.

[0241] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[0242] Real-time progress tracking and alerts

[0243] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[0244] The server collects project progress data in real time, analyzes it, and checks for any issues. If a problem is detected, the server generates an alert and sends it to the device.

[0245] The terminal notifies the user of the alert information received from the server, so that the user can check the alert and take the necessary measures promptly.

[0246] Facilitating communication and preventing misunderstandings

[0247] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then transmit this data to the server.

[0248] The server uses generative artificial intelligence to analyze the communication data and identify points where misunderstandings are likely to occur, and the results of this analysis are sent back to the terminal.

[0249] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[0250] Deadline Management and Scheduling

[0251] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[0252] The server uses generative artificial intelligence to optimize the input schedule, and the optimized schedule is sent from the server to the terminal.

[0253] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule, maximizing resource utilization and completing the project within the deadline.

[0254] Use of emotion engine

[0255] Users use the device to record their emotional state during the project, for example, inputting stress levels and mood changes, and the device transmits this emotional data to a server.

[0256] The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, it monitors the user's stress level and changes in emotions, and generates suggestions for stress reduction as needed. These suggestions are sent from the server to the device.

[0257] The terminal displays the suggestions received from the server to the user, who can then implement the suggested stress reduction measures and complete the project in better condition.

[0258] Team Sentiment Analysis and Feedback

[0259] Users collect emotional data for the entire team by having each team member record their emotional state using a device, including inputting their mood and stress level, which is then sent to a server.

[0260] The server uses an emotion engine to analyze the emotional state of the entire team, integrates the results, and generates feedback to improve team morale and motivation. This feedback is sent from the server to the terminal.

[0261] The device receives feedback from the server and displays it to the team leader and team members, allowing the team to improve communication and work processes and increase the chances of project success.

[0262] Specific examples

[0263] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal and optimizes resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[0264] In this way, the system of the present invention not only automates various project management tasks, but also enables comprehensive management including the emotional state of the team, thereby significantly improving the efficiency and success rate of the project.

[0265] The processing flow will be explained below.

[0266] Optimizing resource allocation

[0267] Step 1:

[0268] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[0269] Step 2:

[0270] The terminal transmits the input project information to the server.

[0271] Step 3:

[0272] The server uses generative artificial intelligence based on past project data to calculate optimal resource allocation.

[0273] Step 4:

[0274] The server returns the calculated optimized resource allocation to the terminal.

[0275] Step 5:

[0276] The terminal displays the received optimized resource allocation to the user.

[0277] Real-time progress tracking and alerts

[0278] Step 1:

[0279] The user enters the ID of the project they want to track into the terminal.

[0280] Step 2:

[0281] The terminal transmits the project ID to the server.

[0282] Step 3:

[0283] The server collects project progress data in real time.

[0284] Step 4:

[0285] The server analyzes the progress data and generates alerts if it detects a problem.

[0286] Step 5:

[0287] The server transmits the generated alert to the terminal.

[0288] Step 6:

[0289] The terminal notifies the user of the alert information.

[0290] Facilitating communication and preventing misunderstandings

[0291] Step 1:

[0292] Users input communication data (emails, chat logs, meeting minutes, etc.) between project members into their terminals.

[0293] Step 2:

[0294] The terminal transmits the communication data to the server.

[0295] Step 3:

[0296] The server uses generative artificial intelligence to analyze communication data and identify points where misunderstandings are likely to occur.

[0297] Step 4:

[0298] The server returns the analysis results to the terminal.

[0299] Step 5:

[0300] The terminal displays the received analysis results to the user.

[0301] Deadline Management and Scheduling

[0302] Step 1:

[0303] The user inputs the current schedule of the project into the terminal.

[0304] Step 2:

[0305] The terminal transmits the schedule information to the server.

[0306] Step 3:

[0307] The server uses generative artificial intelligence to optimize the input schedule.

[0308] Step 4:

[0309] The server returns the optimized schedule to the terminal.

[0310] Step 5:

[0311] The terminal displays the received optimized schedule to the user.

[0312] Use of emotion engine

[0313] Step 1:

[0314] Users input their emotional state (stress level and mood changes) into the terminal while the project is underway.

[0315] Step 2:

[0316] The terminal transmits the input emotion data to the server.

[0317] Step 3:

[0318] The server uses an emotion engine to analyze the user's emotional state.

[0319] Step 4:

[0320] Based on the analysis results, the server generates suggestions for reducing stress and sends them to the device.

[0321] Step 5:

[0322] The terminal displays the received suggestions to the user.

[0323] Team Sentiment Analysis and Feedback

[0324] Step 1:

[0325] Users (team members) input their emotional state (mood and stress level) into the terminal.

[0326] Step 2:

[0327] The terminal transmits the collected emotion data to the server.

[0328] Step 3:

[0329] The server uses an emotion engine to analyze the emotional state of the entire team.

[0330] Step 4:

[0331] Based on the analysis results, the server generates feedback to improve team morale and sends it to the device.

[0332] Step 5:

[0333] The device displays the feedback received to the team leader and team members.

[0334] The above is the specific flow of each process in the system of the present invention, which can optimize project management and effectively manage the emotional state of the team, thereby greatly improving the efficiency and success rate of the project.

[0335] Example 2

[0336] 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."

[0337] Traditional project management systems have individual functions, such as optimal resource allocation, real-time progress tracking, and preventing miscommunication between team members, but lack a means to manage these functions in an integrated manner. Furthermore, it is necessary to further improve the success rate and efficiency of projects by taking into account the emotional state and stress levels of project members. Therefore, a method is needed to ensure efficient project progress and properly manage the psychological state of each team member.

[0338] 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.

[0339] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project schedule, means for recording the user's emotional state during the project and generating stress reduction suggestions using an emotion engine, and means for collecting the emotional states of team members and generating feedback to improve team morale and motivation using an emotion engine. This not only enables efficient project management, but also makes it possible to significantly improve the success rate and efficiency of projects by appropriately managing the emotional states of members.

[0340] "Generative AI" refers to AI that has the ability to learn from past data and generate optimal results for new data.

[0341] "Resource allocation" refers to the efficient allocation of personnel, time, equipment, etc. required for a project.

[0342] "Real-time progress tracking" refers to monitoring the progress of a project in real time and updating the data immediately.

[0343] An "alert" is a warning message that is sent to the user when a specific condition or abnormality is detected.

[0344] "Communication analysis" refers to analyzing interactions between project members and identifying points and problems where misunderstandings are likely to occur.

[0345] "Schedule optimization" refers to efficiently managing project schedules and making adjustments to complete tasks within deadlines.

[0346] "Emotion engine" refers to a software component for analyzing the emotional state of users and team members.

[0347] "Stress reduction suggestions" refers to providing specific advice or measures to reduce the user's stress level.

[0348] "Feedback" refers to providing insight or advice based on a subject's behavior or results.

[0349] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[0350] Optimizing resource allocation

[0351] The user inputs project details, such as the project name, resource type and quantity, and project duration, into the device. The device then sends the input project information to the server. The server then uses a generative AI model based on past project data to calculate the optimal resource allocation. This calculation uses specific software, such as TensorFlow or PyTorch. The calculation results are generated as an optimized resource allocation and sent back from the server to the device. The device then displays this optimized resource allocation to the user, allowing the user to efficiently allocate resources and start the project.

[0352] Real-time progress tracking and alerts

[0353] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time project progress data and analyzes it using a generative AI model. This analysis can be performed using progress management software (such as Jira). If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of this alert information, allowing them to take prompt action.

[0354] Facilitating communication and preventing misunderstandings

[0355] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their devices. The devices then send this data to the server. The server then analyzes this communication data using a generative AI model to identify points where misunderstandings are likely to occur. This analysis can be performed using, for example, natural language processing (NLP) technology. The server then returns the analysis results to the device, which then displays them to the user. Based on this information, the user can implement measures to improve communication.

[0356] Deadline Management and Scheduling

[0357] The user inputs the current schedule of the project into the device. The device sends this schedule information to the server and requests schedule optimization. The server optimizes the input schedule using a generative AI model. As a result of this process, the optimized schedule is sent from the server to the device. The device displays the optimized schedule to the user. The user can proceed with the project according to this schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[0358] Use of emotion engine

[0359] The user uses the device to record their emotional state during the project. For example, they input their stress level and mood changes. The device sends this emotional data to the server. The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, the server monitors the user's stress level and changes in emotions and generates suggestions for stress reduction as needed. The suggestions are sent from the server to the device. The device displays the suggestions to the user, who can then implement the suggested stress reduction measures.

[0360] Team Sentiment Analysis and Feedback

[0361] The user collects emotional data for the entire team by having each team member record their emotional state using their device. This includes input of mood and stress levels. The device then sends this data to the server. The server then uses an emotion engine to analyze the emotional state of the entire team and generates feedback based on the results. This feedback is used to improve team morale and motivation. The server then sends the feedback to the device, which displays it to the team leader and team members. The team can use this feedback to improve communication and work processes and increase the chances of project success.

[0362] Specific examples

[0363] For example, for a new software development project, the user (project manager) inputs detailed project information into the device to optimize resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if any problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[0364] Example prompt sentence:

[0365] Project name: New software development

[0366] Resources: 3 developers, 2 designers, 2 testers

[0367] Project duration: 6 months

[0368] Tracking ID: 12345

[0369] Emotional data: Stress level 5 / 10, mood normal

[0370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0371] Optimizing resource allocation

[0372] Step 1:

[0373] The user inputs detailed project information such as the project name, the type and quantity of resources, and the project period into the terminal.

[0374] Step 2:

[0375] The terminal converts the input project information into JSON format and sends it to the server, specifying " / optimize_resources" as the endpoint.

[0376] Input: Project details entered by the user

[0377] Output: JSON format data sent to the server

[0378] Step 3:

[0379] The server analyzes the received project information and calculates optimal resource allocation using a generative AI model based on past project data, using TensorFlow and PyTorch.

[0380] Input: Project information received by the server

[0381] Data processing / calculation: Generative AI models based on past data optimize resource allocation

[0382] Output: JSON data as optimized resource allocation

[0383] Step 4:

[0384] The server returns the optimized resource allocation data to the terminal as an HTTP response.

[0385] Input: Optimized resource allocation data

[0386] Output: HTTP response to the device

[0387] Step 5:

[0388] The terminal analyzes the received optimized resource allocation data and displays it on the screen in a user-friendly format, for example, in the form of a graph or table.

[0389] Input: Optimized resource allocation data

[0390] Output: Optimization data displayed to the user

[0391] Real-time progress tracking and alerts

[0392] Step 1:

[0393] The user enters the ID of the project they want to track into the terminal.

[0394] Step 2:

[0395] The device sends the project ID to the server, specifying " / track_progress" as the endpoint.

[0396] Input: Project ID entered by the user

[0397] Output: Project ID sent to the server

[0398] Step 3:

[0399] Once the server receives the project ID, it retrieves real-time progress data from the database and analyzes it for issues using a generative AI model that detects outliers and trends.

[0400] Input: Received project ID and progress data from database

[0401] Data processing / calculation: Generative AI models for outlier detection and progress analysis

[0402] Output: Analysis results and any required alert messages

[0403] Step 4:

[0404] If the server detects a problem, it generates an alert message and sends it to the terminal.

[0405] Input: Analysis results that detected anomalies

[0406] Output: The alert message sent to the terminal.

[0407] Step 5:

[0408] The device analyzes the received alert information and immediately notifies the user, who can then check the alert via a pop-up alert or email notification.

[0409] Input: The alert message received on the device

[0410] Output: Alert information to be sent to the user

[0411] Facilitating communication and preventing misunderstandings

[0412] Step 1:

[0413] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals using copy and paste and file upload functions.

[0414] Step 2:

[0415] The device encodes the input communication data and sends it to the server, specifying " / analyze_communication" as the endpoint.

[0416] Input: Communication data entered by the user

[0417] Output: The encoded data sent to the server

[0418] Step 3:

[0419] The server analyzes the received communication data using natural language processing technology to identify points where misunderstandings are likely to occur, using NLP models such as BERT and GPT.

[0420] Input: Received communication data

[0421] Data processing / calculation: Identifying points of misunderstanding using NLP models

[0422] Output: Identification of points where misunderstandings occur

[0423] Step 4:

[0424] The server generates the analysis results in JSON format and returns them to the terminal.

[0425] Input: Analysis results from NLP model

[0426] Output: Send analysis results to your device

[0427] Step 5:

[0428] The device analyzes the received analysis results and displays points of misunderstanding and suggestions for improvement to the user, for example, by providing a function to highlight or annotate the points.

[0429] Input: Received analysis results

[0430] Output: Analysis results that are displayed to the user

[0431] Deadline Management and Scheduling

[0432] Step 1:

[0433] The user inputs the project schedule into the terminal.

[0434] Step 2:

[0435] The device sends this schedule information to the server and requests schedule optimization, specifying " / optimize_schedule" as the endpoint.

[0436] Input: User-entered schedule information

[0437] Output: Schedule information sent to the server

[0438] Step 3:

[0439] The server uses a generative AI model to analyze and optimize the input schedule, using a scheduling algorithm.

[0440] Input: Received schedule information

[0441] Data processing / calculation: Schedule optimization using generative AI models

[0442] Output: Optimized schedule data

[0443] Step 4:

[0444] The server transmits the optimized schedule data to the terminal.

[0445] Input: Optimized schedule data

[0446] Output: Sending optimization data to the terminal

[0447] Step 5:

[0448] The terminal analyzes the received optimized schedule and displays it to the user.

[0449] Input: Optimized schedule data

[0450] Output: The schedule that is displayed to the user

[0451] Use of emotion engine

[0452] Step 1:

[0453] Users input their emotional state into the terminal during the project, for example, inputting stress levels and mood changes.

[0454] Step 2:

[0455] The device sends this emotion data to the server, specifying " / record_emotion" as the endpoint.

[0456] Input: Emotion data entered by the user

[0457] Output: Emotion data sent to the server

[0458] Step 3:

[0459] The server analyzes the user's emotional data using an emotion engine, and monitors the user's stress level and emotional changes as a result of the analysis.

[0460] Input: Received emotion data

[0461] Data processing / calculation: Emotional state analysis using emotion engine

[0462] Output: Stress levels and emotional changes as a result of the analysis

[0463] Step 4:

[0464] The server generates suggestions for stress reduction as needed and transmits them to the terminal.

[0465] Input: Analysis results from the emotion engine

[0466] Output: Send stress reduction suggestions to device

[0467] Step 5:

[0468] The device displays the received suggestions to the user, who can then implement the suggested stress reduction measures.

[0469] Input: Stress reduction suggestions received

[0470] Output: The suggestions that are displayed to the user

[0471] Team Sentiment Analysis and Feedback

[0472] Step 1:

[0473] The user instructs team members to use the devices to record their emotional state, which includes inputting mood and stress levels.

[0474] Step 2:

[0475] The device sends this emotion data to the server, specifying " / collect_team_emotions" as the endpoint.

[0476] Input: Emotion data entered by team members

[0477] Output: Team sentiment data sent to the server

[0478] Step 3:

[0479] The server uses an emotion engine to analyze the emotional state of the entire team and generate feedback.

[0480] Input: Received team sentiment data

[0481] Data processing / calculation: Team emotion analysis using emotion engine

[0482] Output: Analysis results as feedback

[0483] Step 4:

[0484] The server transmits the generated feedback to the terminal.

[0485] Input: Generated feedback

[0486] Output: Sending feedback to the device

[0487] Step 5:

[0488] The device displays the feedback it receives to the user, allowing the team to improve communication and work processes to increase the project's chances of success.

[0489] Input: Feedback result

[0490] Output: Feedback that is visible to the team

[0491] This allows you to clearly understand how each function in this system operates in detail.

[0492] (Application example 2)

[0493] 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."

[0494] Conventional project management systems make it difficult to optimally allocate resources and track progress in real time. They also lack support for quickly responding to abnormalities and preventing misunderstandings through communication between members. They also lack the ability to monitor the emotional state of individual project members or propose stress reduction measures. There is a need to address these issues and simultaneously improve project management efficiency and quality while managing member stress.

[0495] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0496] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for monitoring the user's emotional state using an emotion engine and generating suggestions for stress reduction, and means for visually providing project management data and alert information to the user in real time using a head-mounted display, thereby enabling efficient project management and improved success rates, as well as monitoring the user's emotional state and suggesting stress reduction measures.

[0497] - "Generative AI" refers to AI technology that generates new information and knowledge through programmed data processing means to solve specific problems.

[0498] "Resource allocation optimization" refers to the most appropriate distribution of available resources to improve project progress and efficiency.

[0499] "Real-time progress tracking" means continuously monitoring the progress of a project on the spot and updating the information immediately.

[0500] "Generating an alert" means that the system issues a warning to the user when it detects a problem or abnormality.

[0501] "Communication analysis" involves analyzing messages and conversations exchanged between project members to identify important information and areas where misunderstandings are likely to occur.

[0502] The "Emotion Engine" is a system that analyzes the user's emotional state, grasps their stress level and psychological state, and suggests appropriate countermeasures.

[0503] A "head-mounted display" is a display device worn on the head to provide visual information to the user.

[0504] "Project management data" refers to all information necessary for management, such as project progress and resource allocation.

[0505] "Suggestions for stress reduction" are specific advice and measures provided to ease the user's mental burden and improve work efficiency.

[0506] MODE FOR CARRYING OUT THE INVENTION

[0507] System Configuration Overview

[0508] The system utilizes generative artificial intelligence (AI) and an emotion engine to improve project management efficiency and quality. Specifically, it optimizes resource allocation, tracks real-time progress, generates alerts, analyzes communication, and analyzes emotions, and provides information to users via a head-mounted display.

[0509] Hardware and software used

[0510] Hardware

[0511] Head-mounted displays: worn by the user on their head to provide real-time visual project management data (e.g., HoloLens®).

[0512] Factory robots: Robots for carrying out manufacturing tasks (e.g. KUKA, Fanuc).

[0513] software

[0514] Server side: Building generative AI models and emotion engines using Python and TensorFlow.

[0515] Front-end: Created a head-mounted display interface using Unity.

[0516] Specific Embodiments of the System

[0517] Optimizing resource allocation

[0518] 1. The user inputs project details (processing steps, resource types and numbers, factory flow, etc.) through a head-mounted display.

[0519] 2. The device sends this information to the server.

[0520] 3. The server uses an AI model based on past data to calculate optimal resource allocation.

[0521] 4. The calculation results are displayed on the head-mounted display via the terminal.

[0522] Real-time progress tracking and alerts

[0523] 1. The user inputs the ID of the robot they want to track into the head-mounted display.

[0524] 2. The device sends the information to the server.

[0525] 3. The server monitors the robot's operation data in real time and immediately generates an alert if it detects an abnormality.

[0526] 4. Alert information is displayed on the head-mounted display and is notified to the user immediately.

[0527] Use of emotion engine

[0528] 1. The user periodically inputs their emotional state through a head-mounted display.

[0529] 2. The device sends this emotion data to the server.

[0530] 3. The emotion engine on the server analyzes the data, monitors the user's stress level, and suggests appropriate stress reduction measures.

[0531] 4. The suggestions are displayed on a head-mounted display and feedback is provided to the user.

[0532] Examples of concrete examples and prompts

[0533] Specific examples

[0534] When starting a project to manufacture a new high-precision part, the user first enters detailed project information and receives the optimal robot placement and work schedule. If the robot exhibits abnormal behavior during the project, an alert is generated in real time and displayed on the head-mounted display. Furthermore, if the user feels high stress, the emotion engine will suggest appropriate relaxation methods or breaks.

[0535] Prompt Sentence Examples

[0536] "We are starting a new machining process. Please optimize resource allocation."

[0537] "Please track the progress of project ID 1234 and let me know if there are any irregularities."

[0538] "Current mood: High stress. Use the emotion engine to provide stress reduction suggestions."

[0539] This system automates various project management tasks and comprehensively manages the emotional state of the team, thereby increasing the chances of project success.

[0540] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0541] Specific processing flow and explanation of the program

[0542] Optimizing resource allocation

[0543] Step 1:

[0544] The user inputs detailed project information through a head-mounted display, including the project name, processing steps, resource types and quantities, factory flow, and project duration.

[0545] Step 2:

[0546] The device sends the entered data to the server, which formats and converts the data and communicates with the server via the appropriate API.

[0547] Step 3:

[0548] Based on the received data, the server uses a generative AI model to calculate optimal resource allocation while referencing past project data, and retrieves relevant data through database queries and inputs it into the model.

[0549] Step 4:

[0550] The server generates the calculation results and returns the optimal resource allocation to the device. The calculation results are sent to the device in JSON format.

[0551] Step 5:

[0552] The device then displays the received optimized resource allocation information on the head-mounted display, allowing the user to start a project based on the visual information.

[0553] Real-time progress tracking and alerts

[0554] Step 1:

[0555] The user inputs the ID of the robot they want to track into the head-mounted display, which is used to identify the robot whose progress they want to track.

[0556] Step 2:

[0557] The device sends the robot ID to the server using the appropriate data format and transmission protocol (e.g. HTTP POST).

[0558] Step 3:

[0559] The server monitors the robot's operational data in real time, collecting and analyzing sensor data. If an abnormality is detected, the AI ​​immediately generates an alert. The anomaly detection logic uses threshold judgment and machine learning models.

[0560] Step 4:

[0561] The server then sends the generated alert information to the terminal. Because the alert information contains real-time data, low-latency communication is required.

[0562] Step 5:

[0563] The device displays the alert information on the head-mounted display and notifies the user immediately, allowing the user to visually identify the problem and take prompt action.

[0564] Use of emotion engine

[0565] Step 1:

[0566] Users periodically input their emotional state (stress level and mood) through a head-mounted display, which is an important element for emotion analysis.

[0567] Step 2:

[0568] The device sends the emotion data to the server, which then formats and structures the data before transferring it to the server.

[0569] Step 3:

[0570] The emotion engine in the server analyzes the emotion data, identifies emotional states, and monitors stress levels using emotion recognition algorithms and natural language processing techniques.

[0571] Step 4:

[0572] Based on the analysis results, the server generates and proposes stress reduction measures, which are individually customized by the AI ​​model.

[0573] Step 5:

[0574] The server sends the proposed measures to the device and displays them on the head-mounted display. The user confirms and implements the proposed measures (e.g., relaxation methods, setting break times).

[0575] This allows users to efficiently manage projects, understand progress in real time, resolve issues, and receive comprehensive support to minimize stress.

[0576] 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.

[0577] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0578] 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.

[0579] [Second embodiment]

[0580] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0581] 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.

[0582] 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).

[0583] 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.

[0584] 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.

[0585] 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).

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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."

[0592] The present invention is a system that utilizes generative artificial intelligence to improve project management efficiency and quality. The specific operations of each component, server, terminal, and user, will be described below.

[0593] Optimizing resource allocation

[0594] The user inputs detailed project information into the terminal, including the project name, resource type, number of resources, project duration, etc. The terminal collects this information and sends it to the server.

[0595] The server uses generative artificial intelligence to calculate optimal resource allocation based on past project data. The calculation results are generated as optimized resource allocation. This optimized resource allocation is then sent back to the terminal from the server.

[0596] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[0597] Real-time progress tracking and alerts

[0598] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[0599] The server collects progress data in real time, analyzes it to check for problems, and if a problem is detected, generates an alert and sends it to the device.

[0600] The terminal notifies the user of the alert information received from the server, and the user can check the alert and take the necessary measures promptly.

[0601] Facilitating communication and preventing misunderstandings

[0602] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then collect and transmit this data to the server.

[0603] The server uses generative artificial intelligence to analyze communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The identified problems are then sent back to the terminal.

[0604] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[0605] Deadline Management and Scheduling

[0606] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[0607] The server optimizes the schedule using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal.

[0608] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[0609] Specific examples

[0610] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal, including the number of development team members, budget, required equipment, development time, etc. The terminal then sends this information to the server and receives an optimized resource allocation.

[0611] Once a project has begun, the server monitors its progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early.

[0612] To ensure smooth communication between development teams, the server analyzes chat logs and emails to identify potential misunderstandings and notify users on their devices. Users can use this information to resolve misunderstandings and improve communication.

[0613] Furthermore, when a user inputs their current schedule into the terminal while the project is in progress, the server optimizes the schedule and returns the optimized schedule to the terminal, allowing the user to efficiently progress the project according to the optimized schedule.

[0614] In this way, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[0615] The processing flow will be explained below.

[0616] Optimizing resource allocation

[0617] Step 1:

[0618] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[0619] Step 2:

[0620] The terminal transmits the input project information to the server.

[0621] Step 3:

[0622] The server uses generative AI to learn from past project data and calculate optimal resource allocation.

[0623] Step 4:

[0624] The server returns the calculated optimized resource allocation to the terminal.

[0625] Step 5:

[0626] The terminal displays the received optimized resource allocation to the user.

[0627] Real-time progress tracking and alerts

[0628] Step 1:

[0629] The user enters the ID of the project they want to track into the terminal.

[0630] Step 2:

[0631] The terminal transmits the project ID to the server.

[0632] Step 3:

[0633] The server collects project progress data in real time.

[0634] Step 4:

[0635] The server analyzes the progress data and generates alerts if it detects a problem.

[0636] Step 5:

[0637] The server transmits the generated alert to the terminal.

[0638] Step 6:

[0639] The terminal notifies the user of the alert information.

[0640] Facilitating communication and preventing misunderstandings

[0641] Step 1:

[0642] The user inputs communication data between project members into the terminal.

[0643] Step 2:

[0644] The terminal transmits the communication data to the server.

[0645] Step 3:

[0646] The server uses generative AI to analyze communication data and identify points where misunderstandings are likely to occur.

[0647] Step 4:

[0648] The server returns the identified problem to the terminal.

[0649] Step 5:

[0650] The terminal displays the received analysis results to the user.

[0651] Deadline Management and Scheduling

[0652] Step 1:

[0653] The user inputs the current schedule of the project into the terminal.

[0654] Step 2:

[0655] The terminal transmits the schedule information to the server.

[0656] Step 3:

[0657] The server uses a generative AI to optimize the input schedule.

[0658] Step 4:

[0659] The server transmits the optimized schedule to the terminal.

[0660] Step 5:

[0661] The terminal displays the received optimized schedule to the user.

[0662] The above is a specific flow of each process performed by the system of the present invention, which optimizes project management, reduces the burden on users, and improves the success rate of projects.

[0663] Example 1

[0664] 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."

[0665] In project management, efficient resource allocation, real-time progress tracking, preventing communication gaps, and optimizing scheduling are important. However, performing these tasks manually is extremely time-consuming and prone to errors. These challenges are particularly pronounced in large-scale, complex projects, and can have a significant impact on project success. Therefore, there is a need for a system that automates project management and operates it efficiently.

[0666] 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.

[0667] In this invention, the server includes: a means for a user to input detailed project information into a terminal and for the terminal to transmit the information to the server; a means for the server to calculate optimal resource allocation using a generative AI model and return the calculation result to the terminal for display to the user; a means for a user to input an ID of a project they want to track into the terminal and for the terminal to transmit the ID to the server, and for the server to collect progress data in real time and check for any problems; a means for the server to generate an alert and transmit it to the terminal if a problem is detected; a means for a user to input communication data between project members into the terminal and for the terminal to transmit the data to the server; a means for the server to analyze the communication data using the generative AI model and identify points where information is lacking or misunderstandings are likely to occur and return the identified points to the terminal; a means for a user to input a current project schedule into the terminal and for the terminal to transmit the schedule information to the server; and a means for the server to optimize the schedule using the generative AI model and transmit the optimized schedule to the terminal, which displays it to the user. This automates various project management tasks, enabling efficient and highly accurate project management.

[0668] "User" refers to the person who operates the system and inputs project details, progress, communication data, etc.

[0669] "Terminal" refers to a device or computer that collects information entered by a user and communicates with a server.

[0670] "Server" refers to a central processing unit that uses generative AI models to analyze data and perform calculations such as optimal resource allocation, progress tracking, and schedule optimization.

[0671] "Generative AI model" refers to artificial intelligence technology that learns from past data and uses input information to optimally allocate resources, optimize schedules, and identify communication gaps.

[0672] "Project detailed information" refers to various information necessary for executing a project, such as the project name, resource type, number of resources, and project period.

[0673] "Resource allocation" refers to the optimal allocation of resources (e.g., personnel and equipment) required to efficiently progress a project.

[0674] "Project ID" means a unique identifier used to identify a particular project.

[0675] "Progress data" refers to information that indicates the progress of a project or the degree of task completion.

[0676] "Alert" refers to a warning message that notifies the user when a problem occurs based on the results of progress data analysis.

[0677] "Communication data" refers to records of interactions between project members, such as emails, chat logs, and meeting minutes.

[0678] A "schedule" refers to a plan that shows the order and deadlines for each task in a project.

[0679] This invention is a system that utilizes generative artificial intelligence to improve the efficiency and quality of project management. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role to support the smooth progress of a project.

[0680] The system's programming begins with the user entering detailed project information. The user enters the project name, resource type, number of resources, project duration, and other information into the device through a dedicated UI. The device then collects this information and sends it to the server. The server then uses a generative AI model (e.g., OpenAI's GPT-4) to calculate the optimal resource allocation. The server then sends the results of this calculation back to the device, which then displays the optimized resource allocation to the user.

[0681] Users can also enter the ID of the project they want to track into their device, which then sends it to the server. The server collects real-time progress data and analyzes it using a generative AI model. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user, allowing them to quickly resolve the issue.

[0682] Furthermore, when a user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the device, the device sends this data to the server. The server analyzes this data using a generative AI model and identifies points where information is lacking or where misunderstandings are likely to occur. The server then sends the results back to the device, which displays them to the user, allowing the user to implement measures to improve communication.

[0683] This system is also effective in project scheduling. When a user inputs the current project schedule into a device, the device sends this schedule information to a server. The server then optimizes the schedule using a generative AI model and sends the results to the device. The device then displays the optimized schedule to the user, who can then efficiently progress the project according to this schedule.

[0684] Examples:

[0685] For example, in the case of a new software development project, the user (project manager) enters detailed project information (such as the number of people in the development team, the budget, the necessary equipment, and the development period) into a terminal. The endpoint API obtains the input information, such as the project name and number of resources, and sends it to the server. The server receives this information and generates a prompt for the generative AI model. An example of a prompt input to the generative AI model would be, "Project name: XYZ, resources: 5 developers, 2 designers, 3 testers, duration: 6 months. Please suggest the optimal resource allocation."

[0686] Once a project has begun, the server monitors progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early. The server also analyzes chat logs and emails to identify areas where misunderstandings are likely to occur and notifies the device. Users can use this information to improve communication. Furthermore, when the user enters their current schedule into their device while the project is in progress, the server optimizes the schedule using a generative AI model, and the optimized schedule is sent back to the device. Users can then efficiently progress with the project according to the optimized schedule.

[0687] As described above, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[0688] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0689] Step 1:

[0690] The user inputs project details into the terminal, such as the project name, resource type (e.g., developer, designer, tester), number of resources, and project duration, through a dedicated user interface (UI). The input data is converted into a standard format, such as JSON.

[0691] Input: Project details (Project name, resource type, number of resources, project duration)

[0692] Output: Project details in JSON format as entered in the terminal

[0693] Step 2:

[0694] The device sends the project details to the server. The device then sends the entered JSON format data to the server via a protocol such as an HTTP request. This data is encrypted before being sent.

[0695] Input: Project details in JSON format entered into the terminal

[0696] Output: Project details in JSON format sent to the server

[0697] Step 3:

[0698] The server analyzes the received project details and generates a prompt for the generative AI model. The server compares the information with past project data stored in the database and sends the information to the generative AI model. Example prompt: "Project name: XYZ, Resources: 5 developers, 2 designers, 3 testers, Duration: 6 months. Please suggest the optimal resource allocation."

[0699] Input: Project details in JSON format sent to the server

[0700] Output: The prompt sent to the generative AI model

[0701] Step 4:

[0702] The server uses a generative AI model to calculate optimal resource allocation. The generative AI model receives the prompt and calculates the optimal resource allocation based on the results of learning from past data. The calculation results are returned to the server in JSON format.

[0703] Input: The prompt sent to the generative AI model

[0704] Output: Optimal resource allocation returned by the generative AI model (JSON format)

[0705] Step 5:

[0706] The server returns the calculation results to the device and displays them to the user. The server analyzes the response from the generative AI model, converts it into a format that is easy for the user to understand, and then sends it to the device. The device receives this information and displays it on its UI, allowing the user to see the optimized resource allocation.

[0707] Input: Optimal resource allocation returned by the generative AI model (JSON format)

[0708] Output: Optimized resource allocation displayed on the terminal

[0709] Step 6:

[0710] The user enters a project ID into the device to track the progress of the project. The user uses a dedicated UI to enter the ID of the project they want to track.

[0711] Input: The project ID entered by the user

[0712] Output: Project ID saved on the device

[0713] Step 7:

[0714] The device sends the project ID to the server. The device sends the project ID to the server via a protocol such as an HTTP request.

[0715] Input: Project ID saved on your device

[0716] Output: Project ID sent to the server

[0717] Step 8:

[0718] The server collects progress data in real time based on the project ID and analyzes the data using the generative AI model. The server calls the API of the project management tool to collect progress data. The collected data is then sent to the generative AI model to check for any problems.

[0719] Input: Project ID sent to the server

[0720] Output: Analysis results by generative AI model (progress)

[0721] Step 9:

[0722] If the server detects a problem, it generates an alert and sends it to the device. Based on the analysis results of the generative AI model, the server identifies the problem and generates an alert message. The alert message is then sent to the device.

[0723] Input: Analysis results by generative AI model (progress)

[0724] Output: The alert message sent to the terminal.

[0725] Step 10:

[0726] The device notifies the user of the alert information. The device notifies the user of the received alert message via a pop-up or email notification, helping the user to deal with the problem early.

[0727] Input: The alert message received from the server

[0728] Output: Alert message sent to the user

[0729] The above are the specific processing steps of the system program.

[0730] (Application example 1)

[0731] 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."

[0732] In modern factory operations and project management, optimal resource allocation, real-time progress tracking, smooth communication, and efficient scheduling are key challenges. In particular, when operating robots in factories, it is necessary to accurately understand the operating status of each robot and respond immediately when an abnormality occurs. However, current systems manage these elements individually, making it difficult to optimize the entire process. This often leads to resource waste and stalls, and calls for improvements in the overall efficiency and quality of projects.

[0733] 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.

[0734] In this invention, the server includes means for optimizing resource allocation for a project using generative artificial intelligence, means for tracking progress in real time and generating warnings when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project timetable, means for managing factory robot operations and understanding the work status of each robot, means for monitoring the work progress of the robots in real time and generating warnings when an abnormality is detected, and means for analyzing communication data within the factory to identify areas for improvement. This enables efficient resource management, real-time tracking of work progress, rapid response when an abnormality occurs, and smooth communication.

[0735] "Generative artificial intelligence" is a technology that learns from huge amounts of data and automatically performs complex tasks and makes decisions.

[0736] "Resource allocation" is the act of appropriately allocating the necessary resources for a specific project or task.

[0737] "Real-time" refers to processing data and providing information without delay in accordance with actual time.

[0738] An "alert" is a notification that notifies you when some kind of problem or abnormality occurs.

[0739] "Project Member" refers to an individual member working on a project.

[0740] "Communication Data" refers to information regarding interactions between members (emails, chat logs, meeting minutes, etc.).

[0741] A "timetable" refers to the schedule for the progress of work or a project.

[0742] A "factory robot" refers to a mechanical device that automatically performs specific tasks in a factory.

[0743] "Work status" refers to the state in which a particular work is progressing.

[0744] An "anomaly" refers to a problem that deviates from normal or expected behavior.

[0745] This invention is a specific system that utilizes generative artificial intelligence to optimize the operation of factory robots, thereby improving project management efficiency and quality. The specific operations of each component, including the server, terminal, and user, are described below.

[0746] Optimizing resource allocation

[0747] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, project duration, etc. The terminal collects this data and sends it to the server. The server uses generative artificial intelligence to calculate the optimal resource allocation based on past project data. This optimized resource allocation is sent back from the server to the terminal, which then displays it to the user, thereby achieving efficient resource allocation.

[0748] Real-time progress tracking and alerts

[0749] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time progress data from sensors attached to factory robots and analyzes the data to check for problems. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of the alert information, allowing them to take timely action.

[0750] Facilitating communication and preventing misunderstandings

[0751] Users input communication data between project members (emails, chat logs, meeting minutes, etc.) into their terminals. The terminals collect this data and send it to the server. The server then uses generative artificial intelligence to analyze the communication data. This analysis identifies points where information is lacking or misunderstandings are likely to occur, and the results are sent back from the server to the terminal. The terminal then displays the analysis results to the user, who can then implement measures to improve communication based on these results.

[0752] Deadline Management and Scheduling

[0753] The user inputs the current project schedule into the device. The device then sends this schedule information to the server and requests that the schedule be optimized. The server then uses generative artificial intelligence to optimize the schedule and sends the results back to the device. The optimized schedule is displayed on the device, allowing the user to proceed with the project accordingly and complete it within the deadline while maximizing resource utilization efficiency.

[0754] Hardware and software used

[0755] The main hardware used includes servers (equipped with high-performance CPUs and GPUs), terminals (smartphones, tablets, PCs), and factory robots (equipped with various sensors and communication modules).

[0756] The software used includes an AI model (TensorFlow, PyTorch) on the server, a communication API (REST API that communicates via HTTP), and control software (Python) on the edge device.

[0757] Specific examples

[0758] As a specific example, the user (factory manager) enters detailed information about the robot line (number of robots, work period, etc.) into a terminal. This information is then sent to a server, which uses past data and generative artificial intelligence to calculate the optimal robot allocation and sends it back to the terminal. As the project progresses, progress information collected in real time from sensors is analyzed by the server, and if an abnormality is detected, an alert is sent immediately to the user. In addition, a function to facilitate communication between users is used to prevent misunderstandings and optimize the schedule.

[0759] A specific example of a prompt is as follows:

[0760] Prompt for project details: "Please enter the current project details (number of robots, work period, etc.)."

[0761] Progress Tracking Prompt: "Enter the ID of the project you want to track."

[0762] Communication data input prompt: "Please enter the communication data (emails, chat logs, etc.) you want to analyze."

[0763] Current Schedule Input Prompt: "Please enter your current schedule information."

[0764] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0765] Step 1:

[0766] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, and project duration. The input information is sent from the terminal to the server. This allows the basic conditions of the project to be collected as data.

[0767] Step 2:

[0768] The server uses generative artificial intelligence to calculate optimal resource allocation based on the received project details. Data from past projects and similar projects is utilized here. The calculated optimal resource allocation is sent from the server to the terminal. This allows the user to receive an efficient resource allocation plan.

[0769] Step 3:

[0770] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to obtain specific instructions regarding resource allocation, and the user can start a project based on this information.

[0771] Step 4:

[0772] The user enters the ID of the project they want to track into their device and sends that information to the server, which then identifies the project to be tracked.

[0773] Step 5:

[0774] The server collects real-time progress data from sensors attached to factory robots. This data is processed by the server and analyzed for abnormalities. If an abnormality is detected, an alert is generated and sent to the terminal, allowing the user to immediately recognize the abnormality and take action.

[0775] Step 6:

[0776] The terminal notifies the user of the alert information received from the server, allowing the user to take immediate action and resolve the problem quickly.

[0777] Step 7:

[0778] The user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the terminal and sends the data to the server, which starts the analysis of communication within the project.

[0779] Step 8:

[0780] The server uses generative artificial intelligence to analyze the received communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The analysis results are then sent from the server to the device.

[0781] Step 9:

[0782] The device then displays the analysis results to the user, allowing the user to identify areas for improvement in communication between project members and take specific measures to improve them.

[0783] Step 10:

[0784] The user inputs the current schedule of the project into the terminal and sends the schedule information to the server, which starts the schedule optimization process.

[0785] Step 11:

[0786] The server optimizes the received schedule information using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal. As a result, the user receives the optimized schedule, which helps to streamline the progress of the project.

[0787] Step 12:

[0788] The terminal displays the received optimized schedule to the user, allowing the user to take specific steps to efficiently progress the project.

[0789] 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.

[0790] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[0791] Optimizing resource allocation

[0792] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal, which then transmits the input project information to the server.

[0793] The server uses live artificial intelligence to calculate optimal resource allocation based on past project data, and the results are generated as optimized resource allocation and sent back to the terminal.

[0794] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[0795] Real-time progress tracking and alerts

[0796] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[0797] The server collects project progress data in real time, analyzes it, and checks for any issues. If a problem is detected, the server generates an alert and sends it to the device.

[0798] The terminal notifies the user of the alert information received from the server, so that the user can check the alert and take the necessary measures promptly.

[0799] Facilitating communication and preventing misunderstandings

[0800] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then transmit this data to the server.

[0801] The server uses generative artificial intelligence to analyze the communication data and identify points where misunderstandings are likely to occur, and the results of this analysis are sent back to the terminal.

[0802] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[0803] Deadline Management and Scheduling

[0804] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[0805] The server uses generative artificial intelligence to optimize the input schedule, and the optimized schedule is sent from the server to the terminal.

[0806] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule, maximizing resource utilization and completing the project within the deadline.

[0807] Use of emotion engine

[0808] Users use the device to record their emotional state during the project, for example, inputting stress levels and mood changes, and the device transmits this emotional data to a server.

[0809] The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, it monitors the user's stress level and changes in emotions, and generates suggestions for stress reduction as needed. These suggestions are sent from the server to the device.

[0810] The terminal displays the suggestions received from the server to the user, who can then implement the suggested stress reduction measures and complete the project in better condition.

[0811] Team Sentiment Analysis and Feedback

[0812] Users collect emotional data for the entire team by having each team member record their emotional state using a device, including inputting their mood and stress level, which is then sent to a server.

[0813] The server uses an emotion engine to analyze the emotional state of the entire team, integrates the results, and generates feedback to improve team morale and motivation. This feedback is sent from the server to the terminal.

[0814] The device receives feedback from the server and displays it to the team leader and team members, allowing the team to improve communication and work processes and increase the chances of project success.

[0815] Specific examples

[0816] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal and optimizes resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[0817] In this way, the system of the present invention not only automates various project management tasks, but also enables comprehensive management including the emotional state of the team, thereby significantly improving the efficiency and success rate of the project.

[0818] The processing flow will be explained below.

[0819] Optimizing resource allocation

[0820] Step 1:

[0821] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[0822] Step 2:

[0823] The terminal transmits the input project information to the server.

[0824] Step 3:

[0825] The server uses generative artificial intelligence based on past project data to calculate optimal resource allocation.

[0826] Step 4:

[0827] The server returns the calculated optimized resource allocation to the terminal.

[0828] Step 5:

[0829] The terminal displays the received optimized resource allocation to the user.

[0830] Real-time progress tracking and alerts

[0831] Step 1:

[0832] The user enters the ID of the project they want to track into the terminal.

[0833] Step 2:

[0834] The terminal transmits the project ID to the server.

[0835] Step 3:

[0836] The server collects project progress data in real time.

[0837] Step 4:

[0838] The server analyzes the progress data and generates alerts if it detects a problem.

[0839] Step 5:

[0840] The server transmits the generated alert to the terminal.

[0841] Step 6:

[0842] The terminal notifies the user of the alert information.

[0843] Facilitating communication and preventing misunderstandings

[0844] Step 1:

[0845] Users input communication data (emails, chat logs, meeting minutes, etc.) between project members into their terminals.

[0846] Step 2:

[0847] The terminal transmits the communication data to the server.

[0848] Step 3:

[0849] The server uses generative artificial intelligence to analyze communication data and identify points where misunderstandings are likely to occur.

[0850] Step 4:

[0851] The server returns the analysis results to the terminal.

[0852] Step 5:

[0853] The terminal displays the received analysis results to the user.

[0854] Deadline Management and Scheduling

[0855] Step 1:

[0856] The user inputs the current schedule of the project into the terminal.

[0857] Step 2:

[0858] The terminal transmits the schedule information to the server.

[0859] Step 3:

[0860] The server uses generative artificial intelligence to optimize the input schedule.

[0861] Step 4:

[0862] The server returns the optimized schedule to the terminal.

[0863] Step 5:

[0864] The terminal displays the received optimized schedule to the user.

[0865] Use of emotion engine

[0866] Step 1:

[0867] Users input their emotional state (stress level and mood changes) into the terminal while the project is underway.

[0868] Step 2:

[0869] The terminal transmits the input emotion data to the server.

[0870] Step 3:

[0871] The server uses an emotion engine to analyze the user's emotional state.

[0872] Step 4:

[0873] Based on the analysis results, the server generates suggestions for reducing stress and sends them to the device.

[0874] Step 5:

[0875] The terminal displays the received suggestions to the user.

[0876] Team Sentiment Analysis and Feedback

[0877] Step 1:

[0878] Users (team members) input their emotional state (mood and stress level) into the terminal.

[0879] Step 2:

[0880] The terminal transmits the collected emotion data to the server.

[0881] Step 3:

[0882] The server uses an emotion engine to analyze the emotional state of the entire team.

[0883] Step 4:

[0884] Based on the analysis results, the server generates feedback to improve team morale and sends it to the device.

[0885] Step 5:

[0886] The device displays the feedback received to the team leader and team members.

[0887] The above is the specific flow of each process in the system of the present invention, which can optimize project management and effectively manage the emotional state of the team, thereby greatly improving the efficiency and success rate of the project.

[0888] Example 2

[0889] 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."

[0890] Traditional project management systems have individual functions, such as optimal resource allocation, real-time progress tracking, and preventing miscommunication between team members, but lack a means to manage these functions in an integrated manner. Furthermore, it is necessary to further improve the success rate and efficiency of projects by taking into account the emotional state and stress levels of project members. Therefore, a method is needed to ensure efficient project progress and properly manage the psychological state of each team member.

[0891] 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.

[0892] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project schedule, means for recording the user's emotional state during the project and generating stress reduction suggestions using an emotion engine, and means for collecting the emotional states of team members and generating feedback to improve team morale and motivation using an emotion engine. This not only enables efficient project management, but also makes it possible to significantly improve the success rate and efficiency of projects by appropriately managing the emotional states of members.

[0893] "Generative AI" refers to AI that has the ability to learn from past data and generate optimal results for new data.

[0894] "Resource allocation" refers to the efficient allocation of personnel, time, equipment, etc. required for a project.

[0895] "Real-time progress tracking" refers to monitoring the progress of a project in real time and updating the data immediately.

[0896] An "alert" is a warning message that is sent to the user when a specific condition or abnormality is detected.

[0897] "Communication analysis" refers to analyzing interactions between project members and identifying points and problems where misunderstandings are likely to occur.

[0898] "Schedule optimization" refers to efficiently managing project schedules and making adjustments to complete tasks within deadlines.

[0899] "Emotion engine" refers to a software component for analyzing the emotional state of users and team members.

[0900] "Stress reduction suggestions" refers to providing specific advice or measures to reduce the user's stress level.

[0901] "Feedback" refers to providing insight or advice based on a subject's behavior or results.

[0902] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[0903] Optimizing resource allocation

[0904] The user inputs project details, such as the project name, resource type and quantity, and project duration, into the device. The device then sends the input project information to the server. The server then uses a generative AI model based on past project data to calculate the optimal resource allocation. This calculation uses specific software, such as TensorFlow or PyTorch. The calculation results are generated as an optimized resource allocation and sent back from the server to the device. The device then displays this optimized resource allocation to the user, allowing the user to efficiently allocate resources and start the project.

[0905] Real-time progress tracking and alerts

[0906] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time project progress data and analyzes it using a generative AI model. This analysis can be performed using progress management software (such as Jira). If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of this alert information, allowing them to take prompt action.

[0907] Facilitating communication and preventing misunderstandings

[0908] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their devices. The devices then send this data to the server. The server then analyzes this communication data using a generative AI model to identify points where misunderstandings are likely to occur. This analysis can be performed using, for example, natural language processing (NLP) technology. The server then returns the analysis results to the device, which then displays them to the user. Based on this information, the user can implement measures to improve communication.

[0909] Deadline Management and Scheduling

[0910] The user inputs the current schedule of the project into the device. The device sends this schedule information to the server and requests schedule optimization. The server optimizes the input schedule using a generative AI model. As a result of this process, the optimized schedule is sent from the server to the device. The device displays the optimized schedule to the user. The user can proceed with the project according to this schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[0911] Use of emotion engine

[0912] The user uses the device to record their emotional state during the project. For example, they input their stress level and mood changes. The device sends this emotional data to the server. The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, the server monitors the user's stress level and changes in emotions and generates suggestions for stress reduction as needed. The suggestions are sent from the server to the device. The device displays the suggestions to the user, who can then implement the suggested stress reduction measures.

[0913] Team Sentiment Analysis and Feedback

[0914] The user collects emotional data for the entire team by having each team member record their emotional state using their device. This includes input of mood and stress levels. The device then sends this data to the server. The server then uses an emotion engine to analyze the emotional state of the entire team and generates feedback based on the results. This feedback is used to improve team morale and motivation. The server then sends the feedback to the device, which displays it to the team leader and team members. The team can use this feedback to improve communication and work processes and increase the chances of project success.

[0915] Specific examples

[0916] For example, for a new software development project, the user (project manager) inputs detailed project information into the device to optimize resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if any problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[0917] Example prompt sentence:

[0918] Project name: New software development

[0919] Resources: 3 developers, 2 designers, 2 testers

[0920] Project duration: 6 months

[0921] Tracking ID: 12345

[0922] Emotional data: Stress level 5 / 10, mood normal

[0923] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0924] Optimizing resource allocation

[0925] Step 1:

[0926] The user inputs detailed project information such as the project name, the type and quantity of resources, and the project period into the terminal.

[0927] Step 2:

[0928] The terminal converts the input project information into JSON format and sends it to the server, specifying " / optimize_resources" as the endpoint.

[0929] Input: Project details entered by the user

[0930] Output: JSON format data sent to the server

[0931] Step 3:

[0932] The server analyzes the received project information and calculates optimal resource allocation using a generative AI model based on past project data, using TensorFlow and PyTorch.

[0933] Input: Project information received by the server

[0934] Data processing / calculation: Generative AI models based on past data optimize resource allocation

[0935] Output: JSON data as optimized resource allocation

[0936] Step 4:

[0937] The server returns the optimized resource allocation data to the terminal as an HTTP response.

[0938] Input: Optimized resource allocation data

[0939] Output: HTTP response to the device

[0940] Step 5:

[0941] The terminal analyzes the received optimized resource allocation data and displays it on the screen in a user-friendly format, for example, in the form of a graph or table.

[0942] Input: Optimized resource allocation data

[0943] Output: Optimization data displayed to the user

[0944] Real-time progress tracking and alerts

[0945] Step 1:

[0946] The user enters the ID of the project they want to track into the terminal.

[0947] Step 2:

[0948] The device sends the project ID to the server, specifying " / track_progress" as the endpoint.

[0949] Input: Project ID entered by the user

[0950] Output: Project ID sent to the server

[0951] Step 3:

[0952] Once the server receives the project ID, it retrieves real-time progress data from the database and analyzes it for issues using a generative AI model that detects outliers and trends.

[0953] Input: Received project ID and progress data from database

[0954] Data processing / calculation: Generative AI models for outlier detection and progress analysis

[0955] Output: Analysis results and any required alert messages

[0956] Step 4:

[0957] If the server detects a problem, it generates an alert message and sends it to the terminal.

[0958] Input: Analysis results that detected anomalies

[0959] Output: The alert message sent to the terminal.

[0960] Step 5:

[0961] The device analyzes the received alert information and immediately notifies the user, who can then check the alert via a pop-up alert or email notification.

[0962] Input: The alert message received on the device

[0963] Output: Alert information to be sent to the user

[0964] Facilitating communication and preventing misunderstandings

[0965] Step 1:

[0966] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals using copy and paste and file upload functions.

[0967] Step 2:

[0968] The device encodes the input communication data and sends it to the server, specifying " / analyze_communication" as the endpoint.

[0969] Input: Communication data entered by the user

[0970] Output: The encoded data sent to the server

[0971] Step 3:

[0972] The server analyzes the received communication data using natural language processing technology to identify points where misunderstandings are likely to occur, using NLP models such as BERT and GPT.

[0973] Input: Received communication data

[0974] Data processing / calculation: Identifying points of misunderstanding using NLP models

[0975] Output: Identification of points where misunderstandings occur

[0976] Step 4:

[0977] The server generates the analysis results in JSON format and returns them to the terminal.

[0978] Input: Analysis results from NLP model

[0979] Output: Send analysis results to your device

[0980] Step 5:

[0981] The device analyzes the received analysis results and displays points of misunderstanding and suggestions for improvement to the user, for example, by providing a function to highlight or annotate the points.

[0982] Input: Received analysis results

[0983] Output: Analysis results that are displayed to the user

[0984] Deadline Management and Scheduling

[0985] Step 1:

[0986] The user inputs the project schedule into the terminal.

[0987] Step 2:

[0988] The device sends this schedule information to the server and requests schedule optimization, specifying " / optimize_schedule" as the endpoint.

[0989] Input: User-entered schedule information

[0990] Output: Schedule information sent to the server

[0991] Step 3:

[0992] The server uses a generative AI model to analyze and optimize the input schedule, using a scheduling algorithm.

[0993] Input: Received schedule information

[0994] Data processing / calculation: Schedule optimization using generative AI models

[0995] Output: Optimized schedule data

[0996] Step 4:

[0997] The server transmits the optimized schedule data to the terminal.

[0998] Input: Optimized schedule data

[0999] Output: Sending optimization data to the terminal

[1000] Step 5:

[1001] The terminal analyzes the received optimized schedule and displays it to the user.

[1002] Input: Optimized schedule data

[1003] Output: The schedule that is displayed to the user

[1004] Use of emotion engine

[1005] Step 1:

[1006] Users input their emotional state into the terminal during the project, for example, inputting stress levels and mood changes.

[1007] Step 2:

[1008] The device sends this emotion data to the server, specifying " / record_emotion" as the endpoint.

[1009] Input: Emotion data entered by the user

[1010] Output: Emotion data sent to the server

[1011] Step 3:

[1012] The server analyzes the user's emotional data using an emotion engine, and monitors the user's stress level and emotional changes as a result of the analysis.

[1013] Input: Received emotion data

[1014] Data processing / calculation: Emotional state analysis using emotion engine

[1015] Output: Stress levels and emotional changes as a result of the analysis

[1016] Step 4:

[1017] The server generates suggestions for stress reduction as needed and transmits them to the terminal.

[1018] Input: Analysis results from the emotion engine

[1019] Output: Send stress reduction suggestions to device

[1020] Step 5:

[1021] The device displays the received suggestions to the user, who can then implement the suggested stress reduction measures.

[1022] Input: Stress reduction suggestions received

[1023] Output: The suggestions that are displayed to the user

[1024] Team Sentiment Analysis and Feedback

[1025] Step 1:

[1026] The user instructs team members to use the devices to record their emotional state, which includes inputting mood and stress levels.

[1027] Step 2:

[1028] The device sends this emotion data to the server, specifying " / collect_team_emotions" as the endpoint.

[1029] Input: Emotion data entered by team members

[1030] Output: Team sentiment data sent to the server

[1031] Step 3:

[1032] The server uses an emotion engine to analyze the emotional state of the entire team and generate feedback.

[1033] Input: Received team sentiment data

[1034] Data processing / calculation: Team emotion analysis using emotion engine

[1035] Output: Analysis results as feedback

[1036] Step 4:

[1037] The server transmits the generated feedback to the terminal.

[1038] Input: Generated feedback

[1039] Output: Sending feedback to the device

[1040] Step 5:

[1041] The device displays the feedback it receives to the user, allowing the team to improve communication and work processes to increase the project's chances of success.

[1042] Input: Feedback result

[1043] Output: Feedback that is visible to the team

[1044] This allows you to clearly understand how each function in this system operates in detail.

[1045] (Application example 2)

[1046] 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."

[1047] Conventional project management systems make it difficult to optimally allocate resources and track progress in real time. They also lack support for quickly responding to abnormalities and preventing misunderstandings through communication between members. They also lack the ability to monitor the emotional state of individual project members or propose stress reduction measures. There is a need to address these issues and simultaneously improve project management efficiency and quality while managing member stress.

[1048] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1049] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for monitoring the user's emotional state using an emotion engine and generating suggestions for stress reduction, and means for visually providing project management data and alert information to the user in real time using a head-mounted display, thereby enabling efficient project management and improved success rates, as well as monitoring the user's emotional state and suggesting stress reduction measures.

[1050] - "Generative AI" refers to AI technology that generates new information and knowledge through programmed data processing means to solve specific problems.

[1051] "Resource allocation optimization" refers to the most appropriate distribution of available resources to improve project progress and efficiency.

[1052] "Real-time progress tracking" means continuously monitoring the progress of a project on the spot and updating the information immediately.

[1053] "Generating an alert" means that the system issues a warning to the user when it detects a problem or abnormality.

[1054] "Communication analysis" involves analyzing messages and conversations exchanged between project members to identify important information and areas where misunderstandings are likely to occur.

[1055] The "Emotion Engine" is a system that analyzes the user's emotional state, grasps their stress level and psychological state, and suggests appropriate countermeasures.

[1056] A "head-mounted display" is a display device worn on the head to provide visual information to the user.

[1057] "Project management data" refers to all information necessary for management, such as project progress and resource allocation.

[1058] "Suggestions for stress reduction" are specific advice and measures provided to ease the user's mental burden and improve work efficiency.

[1059] MODE FOR CARRYING OUT THE INVENTION

[1060] System Configuration Overview

[1061] The system utilizes generative artificial intelligence (AI) and an emotion engine to improve project management efficiency and quality. Specifically, it optimizes resource allocation, tracks real-time progress, generates alerts, analyzes communication, and analyzes emotions, and provides information to users via a head-mounted display.

[1062] Hardware and software used

[1063] Hardware

[1064] Head-mounted displays: These are worn by the user on their head and provide real-time visuals of project management data (e.g., HoloLens).

[1065] Factory robots: Robots for carrying out manufacturing tasks (e.g. KUKA, Fanuc).

[1066] software

[1067] Server side: Building generative AI models and emotion engines using Python and TensorFlow.

[1068] Front-end: Created a head-mounted display interface using Unity.

[1069] Specific Embodiments of the System

[1070] Optimizing resource allocation

[1071] 1. The user inputs project details (processing steps, resource types and numbers, factory flow, etc.) through a head-mounted display.

[1072] 2. The device sends this information to the server.

[1073] 3. The server uses an AI model based on past data to calculate optimal resource allocation.

[1074] 4. The calculation results are displayed on the head-mounted display via the terminal.

[1075] Real-time progress tracking and alerts

[1076] 1. The user inputs the ID of the robot they want to track into the head-mounted display.

[1077] 2. The device sends the information to the server.

[1078] 3. The server monitors the robot's operation data in real time and immediately generates an alert if it detects an abnormality.

[1079] 4. Alert information is displayed on the head-mounted display and is notified to the user immediately.

[1080] Use of emotion engine

[1081] 1. The user periodically inputs their emotional state through a head-mounted display.

[1082] 2. The device sends this emotion data to the server.

[1083] 3. The emotion engine on the server analyzes the data, monitors the user's stress level, and suggests appropriate stress reduction measures.

[1084] 4. The suggestions are displayed on a head-mounted display and feedback is provided to the user.

[1085] Examples of concrete examples and prompts

[1086] Specific examples

[1087] When starting a project to manufacture a new high-precision part, the user first enters detailed project information and receives the optimal robot placement and work schedule. If the robot exhibits abnormal behavior during the project, an alert is generated in real time and displayed on the head-mounted display. Furthermore, if the user feels high stress, the emotion engine will suggest appropriate relaxation methods or breaks.

[1088] Prompt Sentence Examples

[1089] "We are starting a new machining process. Please optimize resource allocation."

[1090] "Please track the progress of project ID 1234 and let me know if there are any irregularities."

[1091] "Current mood: High stress. Use the emotion engine to provide stress reduction suggestions."

[1092] This system automates various project management tasks and comprehensively manages the emotional state of the team, thereby increasing the chances of project success.

[1093] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1094] Specific processing flow and explanation of the program

[1095] Optimizing resource allocation

[1096] Step 1:

[1097] The user inputs detailed project information through a head-mounted display, including the project name, processing steps, resource types and quantities, factory flow, and project duration.

[1098] Step 2:

[1099] The device sends the entered data to the server, which formats and converts the data and communicates with the server via the appropriate API.

[1100] Step 3:

[1101] Based on the received data, the server uses a generative AI model to calculate optimal resource allocation while referencing past project data, and retrieves relevant data through database queries and inputs it into the model.

[1102] Step 4:

[1103] The server generates the calculation results and returns the optimal resource allocation to the device. The calculation results are sent to the device in JSON format.

[1104] Step 5:

[1105] The device then displays the received optimized resource allocation information on the head-mounted display, allowing the user to start a project based on the visual information.

[1106] Real-time progress tracking and alerts

[1107] Step 1:

[1108] The user inputs the ID of the robot they want to track into the head-mounted display, which is used to identify the robot whose progress they want to track.

[1109] Step 2:

[1110] The device sends the robot ID to the server using the appropriate data format and transmission protocol (e.g. HTTP POST).

[1111] Step 3:

[1112] The server monitors the robot's operational data in real time, collecting and analyzing sensor data. If an abnormality is detected, the AI ​​immediately generates an alert. The anomaly detection logic uses threshold judgment and machine learning models.

[1113] Step 4:

[1114] The server then sends the generated alert information to the terminal. Because the alert information contains real-time data, low-latency communication is required.

[1115] Step 5:

[1116] The device displays the alert information on the head-mounted display and notifies the user immediately, allowing the user to visually identify the problem and take prompt action.

[1117] Use of emotion engine

[1118] Step 1:

[1119] Users periodically input their emotional state (stress level and mood) through a head-mounted display, which is an important element for emotion analysis.

[1120] Step 2:

[1121] The device sends the emotion data to the server, which then formats and structures the data before transferring it to the server.

[1122] Step 3:

[1123] The emotion engine in the server analyzes the emotion data, identifies emotional states, and monitors stress levels using emotion recognition algorithms and natural language processing techniques.

[1124] Step 4:

[1125] Based on the analysis results, the server generates and proposes stress reduction measures, which are individually customized by the AI ​​model.

[1126] Step 5:

[1127] The server sends the proposed measures to the device and displays them on the head-mounted display. The user confirms and implements the proposed measures (e.g., relaxation methods, setting break times).

[1128] This allows users to efficiently manage projects, understand progress in real time, resolve issues, and receive comprehensive support to minimize stress.

[1129] 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.

[1130] 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.

[1131] 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.

[1132] [Third embodiment]

[1133] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1134] 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.

[1135] 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).

[1136] 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.

[1137] 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.

[1138] 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).

[1139] 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.

[1140] 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.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] 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."

[1145] The present invention is a system that utilizes generative artificial intelligence to improve project management efficiency and quality. The specific operations of each component, server, terminal, and user, will be described below.

[1146] Optimizing resource allocation

[1147] The user inputs detailed project information into the terminal, including the project name, resource type, number of resources, project duration, etc. The terminal collects this information and sends it to the server.

[1148] The server uses generative artificial intelligence to calculate optimal resource allocation based on past project data. The calculation results are generated as optimized resource allocation. This optimized resource allocation is then sent back to the terminal from the server.

[1149] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[1150] Real-time progress tracking and alerts

[1151] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[1152] The server collects progress data in real time, analyzes it to check for problems, and if a problem is detected, generates an alert and sends it to the device.

[1153] The terminal notifies the user of the alert information received from the server, and the user can check the alert and take the necessary measures promptly.

[1154] Facilitating communication and preventing misunderstandings

[1155] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then collect and transmit this data to the server.

[1156] The server uses generative artificial intelligence to analyze communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The identified problems are then sent back to the terminal.

[1157] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[1158] Deadline Management and Scheduling

[1159] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[1160] The server optimizes the schedule using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal.

[1161] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[1162] Specific examples

[1163] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal, including the number of development team members, budget, required equipment, development time, etc. The terminal then sends this information to the server and receives an optimized resource allocation.

[1164] Once a project has begun, the server monitors its progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early.

[1165] To ensure smooth communication between development teams, the server analyzes chat logs and emails to identify potential misunderstandings and notify users on their devices. Users can use this information to resolve misunderstandings and improve communication.

[1166] Furthermore, when a user inputs their current schedule into the terminal while the project is in progress, the server optimizes the schedule and returns the optimized schedule to the terminal, allowing the user to efficiently progress the project according to the optimized schedule.

[1167] In this way, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[1168] The processing flow will be explained below.

[1169] Optimizing resource allocation

[1170] Step 1:

[1171] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[1172] Step 2:

[1173] The terminal transmits the input project information to the server.

[1174] Step 3:

[1175] The server uses generative AI to learn from past project data and calculate optimal resource allocation.

[1176] Step 4:

[1177] The server returns the calculated optimized resource allocation to the terminal.

[1178] Step 5:

[1179] The terminal displays the received optimized resource allocation to the user.

[1180] Real-time progress tracking and alerts

[1181] Step 1:

[1182] The user enters the ID of the project they want to track into the terminal.

[1183] Step 2:

[1184] The terminal transmits the project ID to the server.

[1185] Step 3:

[1186] The server collects project progress data in real time.

[1187] Step 4:

[1188] The server analyzes the progress data and generates alerts if it detects a problem.

[1189] Step 5:

[1190] The server transmits the generated alert to the terminal.

[1191] Step 6:

[1192] The terminal notifies the user of the alert information.

[1193] Facilitating communication and preventing misunderstandings

[1194] Step 1:

[1195] The user inputs communication data between project members into the terminal.

[1196] Step 2:

[1197] The terminal transmits the communication data to the server.

[1198] Step 3:

[1199] The server uses generative AI to analyze communication data and identify points where misunderstandings are likely to occur.

[1200] Step 4:

[1201] The server returns the identified problem to the terminal.

[1202] Step 5:

[1203] The terminal displays the received analysis results to the user.

[1204] Deadline Management and Scheduling

[1205] Step 1:

[1206] The user inputs the current schedule of the project into the terminal.

[1207] Step 2:

[1208] The terminal transmits the schedule information to the server.

[1209] Step 3:

[1210] The server uses a generative AI to optimize the input schedule.

[1211] Step 4:

[1212] The server transmits the optimized schedule to the terminal.

[1213] Step 5:

[1214] The terminal displays the received optimized schedule to the user.

[1215] The above is a specific flow of each process performed by the system of the present invention, which optimizes project management, reduces the burden on users, and improves the success rate of projects.

[1216] Example 1

[1217] 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."

[1218] In project management, efficient resource allocation, real-time progress tracking, preventing communication gaps, and optimizing scheduling are important. However, performing these tasks manually is extremely time-consuming and prone to errors. These challenges are particularly pronounced in large-scale, complex projects, and can have a significant impact on project success. Therefore, there is a need for a system that automates project management and operates it efficiently.

[1219] 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.

[1220] In this invention, the server includes: a means for a user to input detailed project information into a terminal and for the terminal to transmit the information to the server; a means for the server to calculate optimal resource allocation using a generative AI model and return the calculation result to the terminal for display to the user; a means for a user to input an ID of a project they want to track into the terminal and for the terminal to transmit the ID to the server, and for the server to collect progress data in real time and check for any problems; a means for the server to generate an alert and transmit it to the terminal if a problem is detected; a means for a user to input communication data between project members into the terminal and for the terminal to transmit the data to the server; a means for the server to analyze the communication data using the generative AI model and identify points where information is lacking or misunderstandings are likely to occur and return the identified points to the terminal; a means for a user to input a current project schedule into the terminal and for the terminal to transmit the schedule information to the server; and a means for the server to optimize the schedule using the generative AI model and transmit the optimized schedule to the terminal, which displays it to the user. This automates various project management tasks, enabling efficient and highly accurate project management.

[1221] "User" refers to the person who operates the system and inputs project details, progress, communication data, etc.

[1222] "Terminal" refers to a device or computer that collects information entered by a user and communicates with a server.

[1223] "Server" refers to a central processing unit that uses generative AI models to analyze data and perform calculations such as optimal resource allocation, progress tracking, and schedule optimization.

[1224] "Generative AI model" refers to artificial intelligence technology that learns from past data and uses input information to optimally allocate resources, optimize schedules, and identify communication gaps.

[1225] "Project detailed information" refers to various information necessary for executing a project, such as the project name, resource type, number of resources, and project period.

[1226] "Resource allocation" refers to the optimal allocation of resources (e.g., personnel and equipment) required to efficiently progress a project.

[1227] "Project ID" means a unique identifier used to identify a particular project.

[1228] "Progress data" refers to information that indicates the progress of a project or the degree of task completion.

[1229] "Alert" refers to a warning message that notifies the user when a problem occurs based on the results of progress data analysis.

[1230] "Communication data" refers to records of interactions between project members, such as emails, chat logs, and meeting minutes.

[1231] A "schedule" refers to a plan that shows the order and deadlines for each task in a project.

[1232] This invention is a system that utilizes generative artificial intelligence to improve the efficiency and quality of project management. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role to support the smooth progress of a project.

[1233] The system's programming begins with the user entering detailed project information. The user enters the project name, resource type, number of resources, project duration, and other information into the device through a dedicated UI. The device then collects this information and sends it to the server. The server then uses a generative AI model (e.g., OpenAI's GPT-4) to calculate the optimal resource allocation. The server then sends the results of this calculation back to the device, which then displays the optimized resource allocation to the user.

[1234] Users can also enter the ID of the project they want to track into their device, which then sends it to the server. The server collects real-time progress data and analyzes it using a generative AI model. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user, allowing them to quickly resolve the issue.

[1235] Furthermore, when a user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the device, the device sends this data to the server. The server analyzes this data using a generative AI model and identifies points where information is lacking or where misunderstandings are likely to occur. The server then sends the results back to the device, which displays them to the user, allowing the user to implement measures to improve communication.

[1236] This system is also effective in project scheduling. When a user inputs the current project schedule into a device, the device sends this schedule information to a server. The server then optimizes the schedule using a generative AI model and sends the results to the device. The device then displays the optimized schedule to the user, who can then efficiently progress the project according to this schedule.

[1237] Examples:

[1238] For example, in the case of a new software development project, the user (project manager) enters detailed project information (such as the number of people in the development team, the budget, the necessary equipment, and the development period) into a terminal. The endpoint API obtains the input information, such as the project name and number of resources, and sends it to the server. The server receives this information and generates a prompt for the generative AI model. An example of a prompt input to the generative AI model would be, "Project name: XYZ, resources: 5 developers, 2 designers, 3 testers, duration: 6 months. Please suggest the optimal resource allocation."

[1239] Once a project has begun, the server monitors progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early. The server also analyzes chat logs and emails to identify areas where misunderstandings are likely to occur and notifies the device. Users can use this information to improve communication. Furthermore, when the user enters their current schedule into their device while the project is in progress, the server optimizes the schedule using a generative AI model, and the optimized schedule is sent back to the device. Users can then efficiently progress with the project according to the optimized schedule.

[1240] As described above, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] The user inputs project details into the terminal, such as the project name, resource type (e.g., developer, designer, tester), number of resources, and project duration, through a dedicated user interface (UI). The input data is converted into a standard format, such as JSON.

[1244] Input: Project details (Project name, resource type, number of resources, project duration)

[1245] Output: Project details in JSON format as entered in the terminal

[1246] Step 2:

[1247] The device sends the project details to the server. The device then sends the entered JSON format data to the server via a protocol such as an HTTP request. This data is encrypted before being sent.

[1248] Input: Project details in JSON format entered into the terminal

[1249] Output: Project details in JSON format sent to the server

[1250] Step 3:

[1251] The server analyzes the received project details and generates a prompt for the generative AI model. The server compares the information with past project data stored in the database and sends the information to the generative AI model. Example prompt: "Project name: XYZ, Resources: 5 developers, 2 designers, 3 testers, Duration: 6 months. Please suggest the optimal resource allocation."

[1252] Input: Project details in JSON format sent to the server

[1253] Output: The prompt sent to the generative AI model

[1254] Step 4:

[1255] The server uses a generative AI model to calculate optimal resource allocation. The generative AI model receives the prompt and calculates the optimal resource allocation based on the results of learning from past data. The calculation results are returned to the server in JSON format.

[1256] Input: The prompt sent to the generative AI model

[1257] Output: Optimal resource allocation returned by the generative AI model (JSON format)

[1258] Step 5:

[1259] The server returns the calculation results to the device and displays them to the user. The server analyzes the response from the generative AI model, converts it into a format that is easy for the user to understand, and then sends it to the device. The device receives this information and displays it on its UI, allowing the user to see the optimized resource allocation.

[1260] Input: Optimal resource allocation returned by the generative AI model (JSON format)

[1261] Output: Optimized resource allocation displayed on the terminal

[1262] Step 6:

[1263] The user enters a project ID into the device to track the progress of the project. The user uses a dedicated UI to enter the ID of the project they want to track.

[1264] Input: The project ID entered by the user

[1265] Output: Project ID saved on the device

[1266] Step 7:

[1267] The device sends the project ID to the server. The device sends the project ID to the server via a protocol such as an HTTP request.

[1268] Input: Project ID saved on your device

[1269] Output: Project ID sent to the server

[1270] Step 8:

[1271] The server collects progress data in real time based on the project ID and analyzes the data using the generative AI model. The server calls the API of the project management tool to collect progress data. The collected data is then sent to the generative AI model to check for any problems.

[1272] Input: Project ID sent to the server

[1273] Output: Analysis results by generative AI model (progress)

[1274] Step 9:

[1275] If the server detects a problem, it generates an alert and sends it to the device. Based on the analysis results of the generative AI model, the server identifies the problem and generates an alert message. The alert message is then sent to the device.

[1276] Input: Analysis results by generative AI model (progress)

[1277] Output: The alert message sent to the terminal.

[1278] Step 10:

[1279] The device notifies the user of the alert information. The device notifies the user of the received alert message via a pop-up or email notification, helping the user to deal with the problem early.

[1280] Input: The alert message received from the server

[1281] Output: Alert message sent to the user

[1282] The above are the specific processing steps of the system program.

[1283] (Application example 1)

[1284] 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."

[1285] In modern factory operations and project management, optimal resource allocation, real-time progress tracking, smooth communication, and efficient scheduling are key challenges. In particular, when operating robots in factories, it is necessary to accurately understand the operating status of each robot and respond immediately when an abnormality occurs. However, current systems manage these elements individually, making it difficult to optimize the entire process. This often leads to resource waste and stalls, and calls for improvements in the overall efficiency and quality of projects.

[1286] 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.

[1287] In this invention, the server includes means for optimizing resource allocation for a project using generative artificial intelligence, means for tracking progress in real time and generating warnings when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project timetable, means for managing factory robot operations and understanding the work status of each robot, means for monitoring the work progress of the robots in real time and generating warnings when an abnormality is detected, and means for analyzing communication data within the factory to identify areas for improvement. This enables efficient resource management, real-time tracking of work progress, rapid response when an abnormality occurs, and smooth communication.

[1288] "Generative artificial intelligence" is a technology that learns from huge amounts of data and automatically performs complex tasks and makes decisions.

[1289] "Resource allocation" is the act of appropriately allocating the necessary resources for a specific project or task.

[1290] "Real-time" refers to processing data and providing information without delay in accordance with actual time.

[1291] An "alert" is a notification that notifies you when some kind of problem or abnormality occurs.

[1292] "Project Member" refers to an individual member working on a project.

[1293] "Communication Data" refers to information regarding interactions between members (emails, chat logs, meeting minutes, etc.).

[1294] A "timetable" refers to the schedule for the progress of work or a project.

[1295] A "factory robot" refers to a mechanical device that automatically performs specific tasks in a factory.

[1296] "Work status" refers to the state in which a particular work is progressing.

[1297] An "anomaly" refers to a problem that deviates from normal or expected behavior.

[1298] This invention is a specific system that utilizes generative artificial intelligence to optimize the operation of factory robots, thereby improving project management efficiency and quality. The specific operations of each component, including the server, terminal, and user, are described below.

[1299] Optimizing resource allocation

[1300] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, project duration, etc. The terminal collects this data and sends it to the server. The server uses generative artificial intelligence to calculate the optimal resource allocation based on past project data. This optimized resource allocation is sent back from the server to the terminal, which then displays it to the user, thereby achieving efficient resource allocation.

[1301] Real-time progress tracking and alerts

[1302] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time progress data from sensors attached to factory robots and analyzes the data to check for problems. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of the alert information, allowing them to take timely action.

[1303] Facilitating communication and preventing misunderstandings

[1304] Users input communication data between project members (emails, chat logs, meeting minutes, etc.) into their terminals. The terminals collect this data and send it to the server. The server then uses generative artificial intelligence to analyze the communication data. This analysis identifies points where information is lacking or misunderstandings are likely to occur, and the results are sent back from the server to the terminal. The terminal then displays the analysis results to the user, who can then implement measures to improve communication based on these results.

[1305] Deadline Management and Scheduling

[1306] The user inputs the current project schedule into the device. The device then sends this schedule information to the server and requests that the schedule be optimized. The server then uses generative artificial intelligence to optimize the schedule and sends the results back to the device. The optimized schedule is displayed on the device, allowing the user to proceed with the project accordingly and complete it within the deadline while maximizing resource utilization efficiency.

[1307] Hardware and software used

[1308] The main hardware used includes servers (equipped with high-performance CPUs and GPUs), terminals (smartphones, tablets, PCs), and factory robots (equipped with various sensors and communication modules).

[1309] The software used includes an AI model (TensorFlow, PyTorch) on the server, a communication API (REST API that communicates via HTTP), and control software (Python) on the edge device.

[1310] Specific examples

[1311] As a specific example, the user (factory manager) enters detailed information about the robot line (number of robots, work period, etc.) into a terminal. This information is then sent to a server, which uses past data and generative artificial intelligence to calculate the optimal robot allocation and sends it back to the terminal. As the project progresses, progress information collected in real time from sensors is analyzed by the server, and if an abnormality is detected, an alert is sent immediately to the user. In addition, a function to facilitate communication between users is used to prevent misunderstandings and optimize the schedule.

[1312] A specific example of a prompt is as follows:

[1313] Prompt for project details: "Please enter the current project details (number of robots, work period, etc.)."

[1314] Progress Tracking Prompt: "Enter the ID of the project you want to track."

[1315] Communication data input prompt: "Please enter the communication data (emails, chat logs, etc.) you want to analyze."

[1316] Current Schedule Input Prompt: "Please enter your current schedule information."

[1317] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1318] Step 1:

[1319] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, and project duration. The input information is sent from the terminal to the server. This allows the basic conditions of the project to be collected as data.

[1320] Step 2:

[1321] The server uses generative artificial intelligence to calculate optimal resource allocation based on the received project details. Data from past projects and similar projects is utilized here. The calculated optimal resource allocation is sent from the server to the terminal. This allows the user to receive an efficient resource allocation plan.

[1322] Step 3:

[1323] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to obtain specific instructions regarding resource allocation, and the user can start a project based on this information.

[1324] Step 4:

[1325] The user enters the ID of the project they want to track into their device and sends that information to the server, which then identifies the project to be tracked.

[1326] Step 5:

[1327] The server collects real-time progress data from sensors attached to factory robots. This data is processed by the server and analyzed for abnormalities. If an abnormality is detected, an alert is generated and sent to the terminal, allowing the user to immediately recognize the abnormality and take action.

[1328] Step 6:

[1329] The terminal notifies the user of the alert information received from the server, allowing the user to take immediate action and resolve the problem quickly.

[1330] Step 7:

[1331] The user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the terminal and sends the data to the server, which starts the analysis of communication within the project.

[1332] Step 8:

[1333] The server uses generative artificial intelligence to analyze the received communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The analysis results are then sent from the server to the device.

[1334] Step 9:

[1335] The device then displays the analysis results to the user, allowing the user to identify areas for improvement in communication between project members and take specific measures to improve them.

[1336] Step 10:

[1337] The user inputs the current schedule of the project into the terminal and sends the schedule information to the server, which starts the schedule optimization process.

[1338] Step 11:

[1339] The server optimizes the received schedule information using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal. As a result, the user receives the optimized schedule, which helps to streamline the progress of the project.

[1340] Step 12:

[1341] The terminal displays the received optimized schedule to the user, allowing the user to take specific steps to efficiently progress the project.

[1342] 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.

[1343] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[1344] Optimizing resource allocation

[1345] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal, which then transmits the input project information to the server.

[1346] The server uses live artificial intelligence to calculate optimal resource allocation based on past project data, and the results are generated as optimized resource allocation and sent back to the terminal.

[1347] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[1348] Real-time progress tracking and alerts

[1349] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[1350] The server collects project progress data in real time, analyzes it, and checks for any issues. If a problem is detected, the server generates an alert and sends it to the device.

[1351] The terminal notifies the user of the alert information received from the server, so that the user can check the alert and take the necessary measures promptly.

[1352] Facilitating communication and preventing misunderstandings

[1353] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then transmit this data to the server.

[1354] The server uses generative artificial intelligence to analyze the communication data and identify points where misunderstandings are likely to occur, and the results of this analysis are sent back to the terminal.

[1355] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[1356] Deadline Management and Scheduling

[1357] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[1358] The server uses generative artificial intelligence to optimize the input schedule, and the optimized schedule is sent from the server to the terminal.

[1359] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule, maximizing resource utilization and completing the project within the deadline.

[1360] Use of emotion engine

[1361] Users use the device to record their emotional state during the project, for example, inputting stress levels and mood changes, and the device transmits this emotional data to a server.

[1362] The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, it monitors the user's stress level and changes in emotions, and generates suggestions for stress reduction as needed. These suggestions are sent from the server to the device.

[1363] The terminal displays the suggestions received from the server to the user, who can then implement the suggested stress reduction measures and complete the project in better condition.

[1364] Team Sentiment Analysis and Feedback

[1365] Users collect emotional data for the entire team by having each team member record their emotional state using a device, including inputting their mood and stress level, which is then sent to a server.

[1366] The server uses an emotion engine to analyze the emotional state of the entire team, integrates the results, and generates feedback to improve team morale and motivation. This feedback is sent from the server to the terminal.

[1367] The device receives feedback from the server and displays it to the team leader and team members, allowing the team to improve communication and work processes and increase the chances of project success.

[1368] Specific examples

[1369] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal and optimizes resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[1370] In this way, the system of the present invention not only automates various project management tasks, but also enables comprehensive management including the emotional state of the team, thereby significantly improving the efficiency and success rate of the project.

[1371] The processing flow will be explained below.

[1372] Optimizing resource allocation

[1373] Step 1:

[1374] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[1375] Step 2:

[1376] The terminal transmits the input project information to the server.

[1377] Step 3:

[1378] The server uses generative artificial intelligence based on past project data to calculate optimal resource allocation.

[1379] Step 4:

[1380] The server returns the calculated optimized resource allocation to the terminal.

[1381] Step 5:

[1382] The terminal displays the received optimized resource allocation to the user.

[1383] Real-time progress tracking and alerts

[1384] Step 1:

[1385] The user enters the ID of the project they want to track into the terminal.

[1386] Step 2:

[1387] The terminal transmits the project ID to the server.

[1388] Step 3:

[1389] The server collects project progress data in real time.

[1390] Step 4:

[1391] The server analyzes the progress data and generates alerts if it detects a problem.

[1392] Step 5:

[1393] The server transmits the generated alert to the terminal.

[1394] Step 6:

[1395] The terminal notifies the user of the alert information.

[1396] Facilitating communication and preventing misunderstandings

[1397] Step 1:

[1398] Users input communication data (emails, chat logs, meeting minutes, etc.) between project members into their terminals.

[1399] Step 2:

[1400] The terminal transmits the communication data to the server.

[1401] Step 3:

[1402] The server uses generative artificial intelligence to analyze communication data and identify points where misunderstandings are likely to occur.

[1403] Step 4:

[1404] The server returns the analysis results to the terminal.

[1405] Step 5:

[1406] The terminal displays the received analysis results to the user.

[1407] Deadline Management and Scheduling

[1408] Step 1:

[1409] The user inputs the current schedule of the project into the terminal.

[1410] Step 2:

[1411] The terminal transmits the schedule information to the server.

[1412] Step 3:

[1413] The server uses generative artificial intelligence to optimize the input schedule.

[1414] Step 4:

[1415] The server returns the optimized schedule to the terminal.

[1416] Step 5:

[1417] The terminal displays the received optimized schedule to the user.

[1418] Use of emotion engine

[1419] Step 1:

[1420] Users input their emotional state (stress level and mood changes) into the terminal while the project is underway.

[1421] Step 2:

[1422] The terminal transmits the input emotion data to the server.

[1423] Step 3:

[1424] The server uses an emotion engine to analyze the user's emotional state.

[1425] Step 4:

[1426] Based on the analysis results, the server generates suggestions for reducing stress and sends them to the device.

[1427] Step 5:

[1428] The terminal displays the received suggestions to the user.

[1429] Team Sentiment Analysis and Feedback

[1430] Step 1:

[1431] Users (team members) input their emotional state (mood and stress level) into the terminal.

[1432] Step 2:

[1433] The terminal transmits the collected emotion data to the server.

[1434] Step 3:

[1435] The server uses an emotion engine to analyze the emotional state of the entire team.

[1436] Step 4:

[1437] Based on the analysis results, the server generates feedback to improve team morale and sends it to the device.

[1438] Step 5:

[1439] The device displays the feedback received to the team leader and team members.

[1440] The above is the specific flow of each process in the system of the present invention, which can optimize project management and effectively manage the emotional state of the team, thereby greatly improving the efficiency and success rate of the project.

[1441] Example 2

[1442] 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."

[1443] Traditional project management systems have individual functions, such as optimal resource allocation, real-time progress tracking, and preventing miscommunication between team members, but lack a means to manage these functions in an integrated manner. Furthermore, it is necessary to further improve the success rate and efficiency of projects by taking into account the emotional state and stress levels of project members. Therefore, a method is needed to ensure efficient project progress and properly manage the psychological state of each team member.

[1444] 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.

[1445] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project schedule, means for recording the user's emotional state during the project and generating stress reduction suggestions using an emotion engine, and means for collecting the emotional states of team members and generating feedback to improve team morale and motivation using an emotion engine. This not only enables efficient project management, but also makes it possible to significantly improve the success rate and efficiency of projects by appropriately managing the emotional states of members.

[1446] "Generative AI" refers to AI that has the ability to learn from past data and generate optimal results for new data.

[1447] "Resource allocation" refers to the efficient allocation of personnel, time, equipment, etc. required for a project.

[1448] "Real-time progress tracking" refers to monitoring the progress of a project in real time and updating the data immediately.

[1449] An "alert" is a warning message that is sent to the user when a specific condition or abnormality is detected.

[1450] "Communication analysis" refers to analyzing interactions between project members and identifying points and problems where misunderstandings are likely to occur.

[1451] "Schedule optimization" refers to efficiently managing project schedules and making adjustments to complete tasks within deadlines.

[1452] "Emotion engine" refers to a software component for analyzing the emotional state of users and team members.

[1453] "Stress reduction suggestions" refers to providing specific advice or measures to reduce the user's stress level.

[1454] "Feedback" refers to providing insight or advice based on a subject's behavior or results.

[1455] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[1456] Optimizing resource allocation

[1457] The user inputs project details, such as the project name, resource type and quantity, and project duration, into the device. The device then sends the input project information to the server. The server then uses a generative AI model based on past project data to calculate the optimal resource allocation. This calculation uses specific software, such as TensorFlow or PyTorch. The calculation results are generated as an optimized resource allocation and sent back from the server to the device. The device then displays this optimized resource allocation to the user, allowing the user to efficiently allocate resources and start the project.

[1458] Real-time progress tracking and alerts

[1459] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time project progress data and analyzes it using a generative AI model. This analysis can be performed using progress management software (such as Jira). If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of this alert information, allowing them to take prompt action.

[1460] Facilitating communication and preventing misunderstandings

[1461] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their devices. The devices then send this data to the server. The server then analyzes this communication data using a generative AI model to identify points where misunderstandings are likely to occur. This analysis can be performed using, for example, natural language processing (NLP) technology. The server then returns the analysis results to the device, which then displays them to the user. Based on this information, the user can implement measures to improve communication.

[1462] Deadline Management and Scheduling

[1463] The user inputs the current schedule of the project into the device. The device sends this schedule information to the server and requests schedule optimization. The server optimizes the input schedule using a generative AI model. As a result of this process, the optimized schedule is sent from the server to the device. The device displays the optimized schedule to the user. The user can proceed with the project according to this schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[1464] Use of emotion engine

[1465] The user uses the device to record their emotional state during the project. For example, they input their stress level and mood changes. The device sends this emotional data to the server. The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, the server monitors the user's stress level and changes in emotions and generates suggestions for stress reduction as needed. The suggestions are sent from the server to the device. The device displays the suggestions to the user, who can then implement the suggested stress reduction measures.

[1466] Team Sentiment Analysis and Feedback

[1467] The user collects emotional data for the entire team by having each team member record their emotional state using their device. This includes input of mood and stress levels. The device then sends this data to the server. The server then uses an emotion engine to analyze the emotional state of the entire team and generates feedback based on the results. This feedback is used to improve team morale and motivation. The server then sends the feedback to the device, which displays it to the team leader and team members. The team can use this feedback to improve communication and work processes and increase the chances of project success.

[1468] Specific examples

[1469] For example, for a new software development project, the user (project manager) inputs detailed project information into the device to optimize resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if any problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[1470] Example prompt sentence:

[1471] Project name: New software development

[1472] Resources: 3 developers, 2 designers, 2 testers

[1473] Project duration: 6 months

[1474] Tracking ID: 12345

[1475] Emotional data: Stress level 5 / 10, mood normal

[1476] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1477] Optimizing resource allocation

[1478] Step 1:

[1479] The user inputs detailed project information such as the project name, the type and quantity of resources, and the project period into the terminal.

[1480] Step 2:

[1481] The terminal converts the input project information into JSON format and sends it to the server, specifying " / optimize_resources" as the endpoint.

[1482] Input: Project details entered by the user

[1483] Output: JSON format data sent to the server

[1484] Step 3:

[1485] The server analyzes the received project information and calculates optimal resource allocation using a generative AI model based on past project data, using TensorFlow and PyTorch.

[1486] Input: Project information received by the server

[1487] Data processing / calculation: Generative AI models based on past data optimize resource allocation

[1488] Output: JSON data as optimized resource allocation

[1489] Step 4:

[1490] The server returns the optimized resource allocation data to the terminal as an HTTP response.

[1491] Input: Optimized resource allocation data

[1492] Output: HTTP response to the device

[1493] Step 5:

[1494] The terminal analyzes the received optimized resource allocation data and displays it on the screen in a user-friendly format, for example, in the form of a graph or table.

[1495] Input: Optimized resource allocation data

[1496] Output: Optimization data displayed to the user

[1497] Real-time progress tracking and alerts

[1498] Step 1:

[1499] The user enters the ID of the project they want to track into the terminal.

[1500] Step 2:

[1501] The device sends the project ID to the server, specifying " / track_progress" as the endpoint.

[1502] Input: Project ID entered by the user

[1503] Output: Project ID sent to the server

[1504] Step 3:

[1505] Once the server receives the project ID, it retrieves real-time progress data from the database and analyzes it for issues using a generative AI model that detects outliers and trends.

[1506] Input: Received project ID and progress data from database

[1507] Data processing / calculation: Generative AI models for outlier detection and progress analysis

[1508] Output: Analysis results and any required alert messages

[1509] Step 4:

[1510] If the server detects a problem, it generates an alert message and sends it to the terminal.

[1511] Input: Analysis results that detected anomalies

[1512] Output: The alert message sent to the terminal.

[1513] Step 5:

[1514] The device analyzes the received alert information and immediately notifies the user, who can then check the alert via a pop-up alert or email notification.

[1515] Input: The alert message received on the device

[1516] Output: Alert information to be sent to the user

[1517] Facilitating communication and preventing misunderstandings

[1518] Step 1:

[1519] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals using copy and paste and file upload functions.

[1520] Step 2:

[1521] The device encodes the input communication data and sends it to the server, specifying " / analyze_communication" as the endpoint.

[1522] Input: Communication data entered by the user

[1523] Output: The encoded data sent to the server

[1524] Step 3:

[1525] The server analyzes the received communication data using natural language processing technology to identify points where misunderstandings are likely to occur, using NLP models such as BERT and GPT.

[1526] Input: Received communication data

[1527] Data processing / calculation: Identifying points of misunderstanding using NLP models

[1528] Output: Identification of points where misunderstandings occur

[1529] Step 4:

[1530] The server generates the analysis results in JSON format and returns them to the terminal.

[1531] Input: Analysis results from NLP model

[1532] Output: Send analysis results to your device

[1533] Step 5:

[1534] The device analyzes the received analysis results and displays points of misunderstanding and suggestions for improvement to the user, for example, by providing a function to highlight or annotate the points.

[1535] Input: Received analysis results

[1536] Output: Analysis results that are displayed to the user

[1537] Deadline Management and Scheduling

[1538] Step 1:

[1539] The user inputs the project schedule into the terminal.

[1540] Step 2:

[1541] The device sends this schedule information to the server and requests schedule optimization, specifying " / optimize_schedule" as the endpoint.

[1542] Input: User-entered schedule information

[1543] Output: Schedule information sent to the server

[1544] Step 3:

[1545] The server uses a generative AI model to analyze and optimize the input schedule, using a scheduling algorithm.

[1546] Input: Received schedule information

[1547] Data processing / calculation: Schedule optimization using generative AI models

[1548] Output: Optimized schedule data

[1549] Step 4:

[1550] The server transmits the optimized schedule data to the terminal.

[1551] Input: Optimized schedule data

[1552] Output: Sending optimization data to the terminal

[1553] Step 5:

[1554] The terminal analyzes the received optimized schedule and displays it to the user.

[1555] Input: Optimized schedule data

[1556] Output: The schedule that is displayed to the user

[1557] Use of emotion engine

[1558] Step 1:

[1559] Users input their emotional state into the terminal during the project, for example, inputting stress levels and mood changes.

[1560] Step 2:

[1561] The device sends this emotion data to the server, specifying " / record_emotion" as the endpoint.

[1562] Input: Emotion data entered by the user

[1563] Output: Emotion data sent to the server

[1564] Step 3:

[1565] The server analyzes the user's emotional data using an emotion engine, and monitors the user's stress level and emotional changes as a result of the analysis.

[1566] Input: Received emotion data

[1567] Data processing / calculation: Emotional state analysis using emotion engine

[1568] Output: Stress levels and emotional changes as a result of the analysis

[1569] Step 4:

[1570] The server generates suggestions for stress reduction as needed and transmits them to the terminal.

[1571] Input: Analysis results from the emotion engine

[1572] Output: Send stress reduction suggestions to device

[1573] Step 5:

[1574] The device displays the received suggestions to the user, who can then implement the suggested stress reduction measures.

[1575] Input: Stress reduction suggestions received

[1576] Output: The suggestions that are displayed to the user

[1577] Team Sentiment Analysis and Feedback

[1578] Step 1:

[1579] The user instructs team members to use the devices to record their emotional state, which includes inputting mood and stress levels.

[1580] Step 2:

[1581] The device sends this emotion data to the server, specifying " / collect_team_emotions" as the endpoint.

[1582] Input: Emotion data entered by team members

[1583] Output: Team sentiment data sent to the server

[1584] Step 3:

[1585] The server uses an emotion engine to analyze the emotional state of the entire team and generate feedback.

[1586] Input: Received team sentiment data

[1587] Data processing / calculation: Team emotion analysis using emotion engine

[1588] Output: Analysis results as feedback

[1589] Step 4:

[1590] The server transmits the generated feedback to the terminal.

[1591] Input: Generated feedback

[1592] Output: Sending feedback to the device

[1593] Step 5:

[1594] The device displays the feedback it receives to the user, allowing the team to improve communication and work processes to increase the project's chances of success.

[1595] Input: Feedback result

[1596] Output: Feedback that is visible to the team

[1597] This allows you to clearly understand how each function in this system operates in detail.

[1598] (Application example 2)

[1599] 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."

[1600] Conventional project management systems make it difficult to optimally allocate resources and track progress in real time. They also lack support for quickly responding to abnormalities and preventing misunderstandings through communication between members. They also lack the ability to monitor the emotional state of individual project members or propose stress reduction measures. There is a need to address these issues and simultaneously improve project management efficiency and quality while managing member stress.

[1601] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1602] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for monitoring the user's emotional state using an emotion engine and generating suggestions for stress reduction, and means for visually providing project management data and alert information to the user in real time using a head-mounted display, thereby enabling efficient project management and improved success rates, as well as monitoring the user's emotional state and suggesting stress reduction measures.

[1603] - "Generative AI" refers to AI technology that generates new information and knowledge through programmed data processing means to solve specific problems.

[1604] "Resource allocation optimization" refers to the most appropriate distribution of available resources to improve project progress and efficiency.

[1605] "Real-time progress tracking" means continuously monitoring the progress of a project on the spot and updating the information immediately.

[1606] "Generating an alert" means that the system issues a warning to the user when it detects a problem or abnormality.

[1607] "Communication analysis" involves analyzing messages and conversations exchanged between project members to identify important information and areas where misunderstandings are likely to occur.

[1608] The "Emotion Engine" is a system that analyzes the user's emotional state, grasps their stress level and psychological state, and suggests appropriate countermeasures.

[1609] A "head-mounted display" is a display device worn on the head to provide visual information to the user.

[1610] "Project management data" refers to all information necessary for management, such as project progress and resource allocation.

[1611] "Suggestions for stress reduction" are specific advice and measures provided to ease the user's mental burden and improve work efficiency.

[1612] MODE FOR CARRYING OUT THE INVENTION

[1613] System Configuration Overview

[1614] The system utilizes generative artificial intelligence (AI) and an emotion engine to improve project management efficiency and quality. Specifically, it optimizes resource allocation, tracks real-time progress, generates alerts, analyzes communication, and analyzes emotions, and provides information to users via a head-mounted display.

[1615] Hardware and software used

[1616] Hardware

[1617] Head-mounted displays: These are worn by the user on their head and provide real-time visuals of project management data (e.g., HoloLens).

[1618] Factory robots: Robots for carrying out manufacturing tasks (e.g. KUKA, Fanuc).

[1619] software

[1620] Server side: Building generative AI models and emotion engines using Python and TensorFlow.

[1621] Front-end: Created a head-mounted display interface using Unity.

[1622] Specific Embodiments of the System

[1623] Optimizing resource allocation

[1624] 1. The user inputs project details (processing steps, resource types and numbers, factory flow, etc.) through a head-mounted display.

[1625] 2. The device sends this information to the server.

[1626] 3. The server uses an AI model based on past data to calculate optimal resource allocation.

[1627] 4. The calculation results are displayed on the head-mounted display via the terminal.

[1628] Real-time progress tracking and alerts

[1629] 1. The user inputs the ID of the robot they want to track into the head-mounted display.

[1630] 2. The device sends the information to the server.

[1631] 3. The server monitors the robot's operation data in real time and immediately generates an alert if it detects an abnormality.

[1632] 4. Alert information is displayed on the head-mounted display and is notified to the user immediately.

[1633] Use of emotion engine

[1634] 1. The user periodically inputs their emotional state through a head-mounted display.

[1635] 2. The device sends this emotion data to the server.

[1636] 3. The emotion engine on the server analyzes the data, monitors the user's stress level, and suggests appropriate stress reduction measures.

[1637] 4. The suggestions are displayed on a head-mounted display and feedback is provided to the user.

[1638] Examples of concrete examples and prompts

[1639] Specific examples

[1640] When starting a project to manufacture a new high-precision part, the user first enters detailed project information and receives the optimal robot placement and work schedule. If the robot exhibits abnormal behavior during the project, an alert is generated in real time and displayed on the head-mounted display. Furthermore, if the user feels high stress, the emotion engine will suggest appropriate relaxation methods or breaks.

[1641] Prompt Sentence Examples

[1642] "We are starting a new machining process. Please optimize resource allocation."

[1643] "Please track the progress of project ID 1234 and let me know if there are any irregularities."

[1644] "Current mood: High stress. Use the emotion engine to provide stress reduction suggestions."

[1645] This system automates various project management tasks and comprehensively manages the emotional state of the team, thereby increasing the chances of project success.

[1646] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1647] Specific processing flow and explanation of the program

[1648] Optimizing resource allocation

[1649] Step 1:

[1650] The user inputs detailed project information through a head-mounted display, including the project name, processing steps, resource types and quantities, factory flow, and project duration.

[1651] Step 2:

[1652] The device sends the entered data to the server, which formats and converts the data and communicates with the server via the appropriate API.

[1653] Step 3:

[1654] Based on the received data, the server uses a generative AI model to calculate optimal resource allocation while referencing past project data, and retrieves relevant data through database queries and inputs it into the model.

[1655] Step 4:

[1656] The server generates the calculation results and returns the optimal resource allocation to the device. The calculation results are sent to the device in JSON format.

[1657] Step 5:

[1658] The device then displays the received optimized resource allocation information on the head-mounted display, allowing the user to start a project based on the visual information.

[1659] Real-time progress tracking and alerts

[1660] Step 1:

[1661] The user inputs the ID of the robot they want to track into the head-mounted display, which is used to identify the robot whose progress they want to track.

[1662] Step 2:

[1663] The device sends the robot ID to the server using the appropriate data format and transmission protocol (e.g. HTTP POST).

[1664] Step 3:

[1665] The server monitors the robot's operational data in real time, collecting and analyzing sensor data. If an abnormality is detected, the AI ​​immediately generates an alert. The anomaly detection logic uses threshold judgment and machine learning models.

[1666] Step 4:

[1667] The server then sends the generated alert information to the terminal. Because the alert information contains real-time data, low-latency communication is required.

[1668] Step 5:

[1669] The device displays the alert information on the head-mounted display and notifies the user immediately, allowing the user to visually identify the problem and take prompt action.

[1670] Use of emotion engine

[1671] Step 1:

[1672] Users periodically input their emotional state (stress level and mood) through a head-mounted display, which is an important element for emotion analysis.

[1673] Step 2:

[1674] The device sends the emotion data to the server, which then formats and structures the data before transferring it to the server.

[1675] Step 3:

[1676] The emotion engine in the server analyzes the emotion data, identifies emotional states, and monitors stress levels using emotion recognition algorithms and natural language processing techniques.

[1677] Step 4:

[1678] Based on the analysis results, the server generates and proposes stress reduction measures, which are individually customized by the AI ​​model.

[1679] Step 5:

[1680] The server sends the proposed measures to the device and displays them on the head-mounted display. The user confirms and implements the proposed measures (e.g., relaxation methods, setting break times).

[1681] This allows users to efficiently manage projects, understand progress in real time, resolve issues, and receive comprehensive support to minimize stress.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] [Fourth embodiment]

[1686] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1687] 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.

[1688] 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).

[1689] 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.

[1690] 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.

[1691] 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).

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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."

[1699] The present invention is a system that utilizes generative artificial intelligence to improve project management efficiency and quality. The specific operations of each component, server, terminal, and user, will be described below.

[1700] Optimizing resource allocation

[1701] The user inputs detailed project information into the terminal, including the project name, resource type, number of resources, project duration, etc. The terminal collects this information and sends it to the server.

[1702] The server uses generative artificial intelligence to calculate optimal resource allocation based on past project data. The calculation results are generated as optimized resource allocation. This optimized resource allocation is then sent back to the terminal from the server.

[1703] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[1704] Real-time progress tracking and alerts

[1705] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[1706] The server collects progress data in real time, analyzes it to check for problems, and if a problem is detected, generates an alert and sends it to the device.

[1707] The terminal notifies the user of the alert information received from the server, and the user can check the alert and take the necessary measures promptly.

[1708] Facilitating communication and preventing misunderstandings

[1709] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then collect and transmit this data to the server.

[1710] The server uses generative artificial intelligence to analyze communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The identified problems are then sent back to the terminal.

[1711] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[1712] Deadline Management and Scheduling

[1713] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[1714] The server optimizes the schedule using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal.

[1715] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[1716] Specific examples

[1717] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal, including the number of development team members, budget, required equipment, development time, etc. The terminal then sends this information to the server and receives an optimized resource allocation.

[1718] Once a project has begun, the server monitors its progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early.

[1719] To ensure smooth communication between development teams, the server analyzes chat logs and emails to identify potential misunderstandings and notify users on their devices. Users can use this information to resolve misunderstandings and improve communication.

[1720] Furthermore, when a user inputs their current schedule into the terminal while the project is in progress, the server optimizes the schedule and returns the optimized schedule to the terminal, allowing the user to efficiently progress the project according to the optimized schedule.

[1721] In this way, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[1722] The processing flow will be explained below.

[1723] Optimizing resource allocation

[1724] Step 1:

[1725] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[1726] Step 2:

[1727] The terminal transmits the input project information to the server.

[1728] Step 3:

[1729] The server uses generative AI to learn from past project data and calculate optimal resource allocation.

[1730] Step 4:

[1731] The server returns the calculated optimized resource allocation to the terminal.

[1732] Step 5:

[1733] The terminal displays the received optimized resource allocation to the user.

[1734] Real-time progress tracking and alerts

[1735] Step 1:

[1736] The user enters the ID of the project they want to track into the terminal.

[1737] Step 2:

[1738] The terminal transmits the project ID to the server.

[1739] Step 3:

[1740] The server collects project progress data in real time.

[1741] Step 4:

[1742] The server analyzes the progress data and generates alerts if it detects a problem.

[1743] Step 5:

[1744] The server transmits the generated alert to the terminal.

[1745] Step 6:

[1746] The terminal notifies the user of the alert information.

[1747] Facilitating communication and preventing misunderstandings

[1748] Step 1:

[1749] The user inputs communication data between project members into the terminal.

[1750] Step 2:

[1751] The terminal transmits the communication data to the server.

[1752] Step 3:

[1753] The server uses generative AI to analyze communication data and identify points where misunderstandings are likely to occur.

[1754] Step 4:

[1755] The server returns the identified problem to the terminal.

[1756] Step 5:

[1757] The terminal displays the received analysis results to the user.

[1758] Deadline Management and Scheduling

[1759] Step 1:

[1760] The user inputs the current schedule of the project into the terminal.

[1761] Step 2:

[1762] The terminal transmits the schedule information to the server.

[1763] Step 3:

[1764] The server uses a generative AI to optimize the input schedule.

[1765] Step 4:

[1766] The server transmits the optimized schedule to the terminal.

[1767] Step 5:

[1768] The terminal displays the received optimized schedule to the user.

[1769] The above is a specific flow of each process performed by the system of the present invention, which optimizes project management, reduces the burden on users, and improves the success rate of projects.

[1770] Example 1

[1771] 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."

[1772] In project management, efficient resource allocation, real-time progress tracking, preventing communication gaps, and optimizing scheduling are important. However, performing these tasks manually is extremely time-consuming and prone to errors. These challenges are particularly pronounced in large-scale, complex projects, and can have a significant impact on project success. Therefore, there is a need for a system that automates project management and operates it efficiently.

[1773] 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.

[1774] In this invention, the server includes: a means for a user to input detailed project information into a terminal and for the terminal to transmit the information to the server; a means for the server to calculate optimal resource allocation using a generative AI model and return the calculation result to the terminal for display to the user; a means for a user to input an ID of a project they want to track into the terminal and for the terminal to transmit the ID to the server, and for the server to collect progress data in real time and check for any problems; a means for the server to generate an alert and transmit it to the terminal if a problem is detected; a means for a user to input communication data between project members into the terminal and for the terminal to transmit the data to the server; a means for the server to analyze the communication data using the generative AI model and identify points where information is lacking or misunderstandings are likely to occur and return the identified points to the terminal; a means for a user to input a current project schedule into the terminal and for the terminal to transmit the schedule information to the server; and a means for the server to optimize the schedule using the generative AI model and transmit the optimized schedule to the terminal, which displays it to the user. This automates various project management tasks, enabling efficient and highly accurate project management.

[1775] "User" refers to the person who operates the system and inputs project details, progress, communication data, etc.

[1776] "Terminal" refers to a device or computer that collects information entered by a user and communicates with a server.

[1777] "Server" refers to a central processing unit that uses generative AI models to analyze data and perform calculations such as optimal resource allocation, progress tracking, and schedule optimization.

[1778] "Generative AI model" refers to artificial intelligence technology that learns from past data and uses input information to optimally allocate resources, optimize schedules, and identify communication gaps.

[1779] "Project detailed information" refers to various information necessary for executing a project, such as the project name, resource type, number of resources, and project period.

[1780] "Resource allocation" refers to the optimal allocation of resources (e.g., personnel and equipment) required to efficiently progress a project.

[1781] "Project ID" means a unique identifier used to identify a particular project.

[1782] "Progress data" refers to information that indicates the progress of a project or the degree of task completion.

[1783] "Alert" refers to a warning message that notifies the user when a problem occurs based on the results of progress data analysis.

[1784] "Communication data" refers to records of interactions between project members, such as emails, chat logs, and meeting minutes.

[1785] A "schedule" refers to a plan that shows the order and deadlines for each task in a project.

[1786] This invention is a system that utilizes generative artificial intelligence to improve the efficiency and quality of project management. This system consists of three main components: a server, a terminal, and a user, each of which plays a specific role to support the smooth progress of a project.

[1787] The system's programming begins with the user entering detailed project information. The user enters the project name, resource type, number of resources, project duration, and other information into the device through a dedicated UI. The device then collects this information and sends it to the server. The server then uses a generative AI model (e.g., OpenAI's GPT-4) to calculate the optimal resource allocation. The server then sends the results of this calculation back to the device, which then displays the optimized resource allocation to the user.

[1788] Users can also enter the ID of the project they want to track into their device, which then sends it to the server. The server collects real-time progress data and analyzes it using a generative AI model. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user, allowing them to quickly resolve the issue.

[1789] Furthermore, when a user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the device, the device sends this data to the server. The server analyzes this data using a generative AI model and identifies points where information is lacking or where misunderstandings are likely to occur. The server then sends the results back to the device, which displays them to the user, allowing the user to implement measures to improve communication.

[1790] This system is also effective in project scheduling. When a user inputs the current project schedule into a device, the device sends this schedule information to a server. The server then optimizes the schedule using a generative AI model and sends the results to the device. The device then displays the optimized schedule to the user, who can then efficiently progress the project according to this schedule.

[1791] Examples:

[1792] For example, in the case of a new software development project, the user (project manager) enters detailed project information (such as the number of people in the development team, the budget, the necessary equipment, and the development period) into a terminal. The endpoint API obtains the input information, such as the project name and number of resources, and sends it to the server. The server receives this information and generates a prompt for the generative AI model. An example of a prompt input to the generative AI model would be, "Project name: XYZ, resources: 5 developers, 2 designers, 3 testers, duration: 6 months. Please suggest the optimal resource allocation."

[1793] Once a project has begun, the server monitors progress in real time and sends an alert to the user via their device if an abnormality is detected, allowing the user to resolve the issue early. The server also analyzes chat logs and emails to identify areas where misunderstandings are likely to occur and notifies the device. Users can use this information to improve communication. Furthermore, when the user enters their current schedule into their device while the project is in progress, the server optimizes the schedule using a generative AI model, and the optimized schedule is sent back to the device. Users can then efficiently progress with the project according to the optimized schedule.

[1794] As described above, the present invention automates various project management tasks, significantly reducing the burden on project managers and enabling efficient project management with a high probability of success.

[1795] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1796] Step 1:

[1797] The user inputs project details into the terminal, such as the project name, resource type (e.g., developer, designer, tester), number of resources, and project duration, through a dedicated user interface (UI). The input data is converted into a standard format, such as JSON.

[1798] Input: Project details (Project name, resource type, number of resources, project duration)

[1799] Output: Project details in JSON format as entered in the terminal

[1800] Step 2:

[1801] The device sends the project details to the server. The device then sends the entered JSON format data to the server via a protocol such as an HTTP request. This data is encrypted before being sent.

[1802] Input: Project details in JSON format entered into the terminal

[1803] Output: Project details in JSON format sent to the server

[1804] Step 3:

[1805] The server analyzes the received project details and generates a prompt for the generative AI model. The server compares the information with past project data stored in the database and sends the information to the generative AI model. Example prompt: "Project name: XYZ, Resources: 5 developers, 2 designers, 3 testers, Duration: 6 months. Please suggest the optimal resource allocation."

[1806] Input: Project details in JSON format sent to the server

[1807] Output: The prompt sent to the generative AI model

[1808] Step 4:

[1809] The server uses a generative AI model to calculate optimal resource allocation. The generative AI model receives the prompt and calculates the optimal resource allocation based on the results of learning from past data. The calculation results are returned to the server in JSON format.

[1810] Input: The prompt sent to the generative AI model

[1811] Output: Optimal resource allocation returned by the generative AI model (JSON format)

[1812] Step 5:

[1813] The server returns the calculation results to the device and displays them to the user. The server analyzes the response from the generative AI model, converts it into a format that is easy for the user to understand, and then sends it to the device. The device receives this information and displays it on its UI, allowing the user to see the optimized resource allocation.

[1814] Input: Optimal resource allocation returned by the generative AI model (JSON format)

[1815] Output: Optimized resource allocation displayed on the terminal

[1816] Step 6:

[1817] The user enters a project ID into the device to track the progress of the project. The user uses a dedicated UI to enter the ID of the project they want to track.

[1818] Input: The project ID entered by the user

[1819] Output: Project ID saved on the device

[1820] Step 7:

[1821] The device sends the project ID to the server. The device sends the project ID to the server via a protocol such as an HTTP request.

[1822] Input: Project ID saved on your device

[1823] Output: Project ID sent to the server

[1824] Step 8:

[1825] The server collects progress data in real time based on the project ID and analyzes the data using the generative AI model. The server calls the API of the project management tool to collect progress data. The collected data is then sent to the generative AI model to check for any problems.

[1826] Input: Project ID sent to the server

[1827] Output: Analysis results by generative AI model (progress)

[1828] Step 9:

[1829] If the server detects a problem, it generates an alert and sends it to the device. Based on the analysis results of the generative AI model, the server identifies the problem and generates an alert message. The alert message is then sent to the device.

[1830] Input: Analysis results by generative AI model (progress)

[1831] Output: The alert message sent to the terminal.

[1832] Step 10:

[1833] The device notifies the user of the alert information. The device notifies the user of the received alert message via a pop-up or email notification, helping the user to deal with the problem early.

[1834] Input: The alert message received from the server

[1835] Output: Alert message sent to the user

[1836] The above are the specific processing steps of the system program.

[1837] (Application example 1)

[1838] 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."

[1839] In modern factory operations and project management, optimal resource allocation, real-time progress tracking, smooth communication, and efficient scheduling are key challenges. In particular, when operating robots in factories, it is necessary to accurately understand the operating status of each robot and respond immediately when an abnormality occurs. However, current systems manage these elements individually, making it difficult to optimize the entire process. This often leads to resource waste and stalls, and calls for improvements in the overall efficiency and quality of projects.

[1840] 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.

[1841] In this invention, the server includes means for optimizing resource allocation for a project using generative artificial intelligence, means for tracking progress in real time and generating warnings when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project timetable, means for managing factory robot operations and understanding the work status of each robot, means for monitoring the work progress of the robots in real time and generating warnings when an abnormality is detected, and means for analyzing communication data within the factory to identify areas for improvement. This enables efficient resource management, real-time tracking of work progress, rapid response when an abnormality occurs, and smooth communication.

[1842] "Generative artificial intelligence" is a technology that learns from huge amounts of data and automatically performs complex tasks and makes decisions.

[1843] "Resource allocation" is the act of appropriately allocating the necessary resources for a specific project or task.

[1844] "Real-time" refers to processing data and providing information without delay in accordance with actual time.

[1845] An "alert" is a notification that notifies you when some kind of problem or abnormality occurs.

[1846] "Project Member" refers to an individual member working on a project.

[1847] "Communication Data" refers to information regarding interactions between members (emails, chat logs, meeting minutes, etc.).

[1848] A "timetable" refers to the schedule for the progress of work or a project.

[1849] A "factory robot" refers to a mechanical device that automatically performs specific tasks in a factory.

[1850] "Work status" refers to the state in which a particular work is progressing.

[1851] An "anomaly" refers to a problem that deviates from normal or expected behavior.

[1852] This invention is a specific system that utilizes generative artificial intelligence to optimize the operation of factory robots, thereby improving project management efficiency and quality. The specific operations of each component, including the server, terminal, and user, are described below.

[1853] Optimizing resource allocation

[1854] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, project duration, etc. The terminal collects this data and sends it to the server. The server uses generative artificial intelligence to calculate the optimal resource allocation based on past project data. This optimized resource allocation is sent back from the server to the terminal, which then displays it to the user, thereby achieving efficient resource allocation.

[1855] Real-time progress tracking and alerts

[1856] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time progress data from sensors attached to factory robots and analyzes the data to check for problems. If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of the alert information, allowing them to take timely action.

[1857] Facilitating communication and preventing misunderstandings

[1858] Users input communication data between project members (emails, chat logs, meeting minutes, etc.) into their terminals. The terminals collect this data and send it to the server. The server then uses generative artificial intelligence to analyze the communication data. This analysis identifies points where information is lacking or misunderstandings are likely to occur, and the results are sent back from the server to the terminal. The terminal then displays the analysis results to the user, who can then implement measures to improve communication based on these results.

[1859] Deadline Management and Scheduling

[1860] The user inputs the current project schedule into the device. The device then sends this schedule information to the server and requests that the schedule be optimized. The server then uses generative artificial intelligence to optimize the schedule and sends the results back to the device. The optimized schedule is displayed on the device, allowing the user to proceed with the project accordingly and complete it within the deadline while maximizing resource utilization efficiency.

[1861] Hardware and software used

[1862] The main hardware used includes servers (equipped with high-performance CPUs and GPUs), terminals (smartphones, tablets, PCs), and factory robots (equipped with various sensors and communication modules).

[1863] The software used includes an AI model (TensorFlow, PyTorch) on the server, a communication API (REST API that communicates via HTTP), and control software (Python) on the edge device.

[1864] Specific examples

[1865] As a specific example, the user (factory manager) enters detailed information about the robot line (number of robots, work period, etc.) into a terminal. This information is then sent to a server, which uses past data and generative artificial intelligence to calculate the optimal robot allocation and sends it back to the terminal. As the project progresses, progress information collected in real time from sensors is analyzed by the server, and if an abnormality is detected, an alert is sent immediately to the user. In addition, a function to facilitate communication between users is used to prevent misunderstandings and optimize the schedule.

[1866] A specific example of a prompt is as follows:

[1867] Prompt for project details: "Please enter the current project details (number of robots, work period, etc.)."

[1868] Progress Tracking Prompt: "Enter the ID of the project you want to track."

[1869] Communication data input prompt: "Please enter the communication data (emails, chat logs, etc.) you want to analyze."

[1870] Current Schedule Input Prompt: "Please enter your current schedule information."

[1871] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1872] Step 1:

[1873] The user inputs detailed project information into the terminal. This information includes the project name, resource type, number of resources, and project duration. The input information is sent from the terminal to the server. This allows the basic conditions of the project to be collected as data.

[1874] Step 2:

[1875] The server uses generative artificial intelligence to calculate optimal resource allocation based on the received project details. Data from past projects and similar projects is utilized here. The calculated optimal resource allocation is sent from the server to the terminal. This allows the user to receive an efficient resource allocation plan.

[1876] Step 3:

[1877] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to obtain specific instructions regarding resource allocation, and the user can start a project based on this information.

[1878] Step 4:

[1879] The user enters the ID of the project they want to track into their device and sends that information to the server, which then identifies the project to be tracked.

[1880] Step 5:

[1881] The server collects real-time progress data from sensors attached to factory robots. This data is processed by the server and analyzed for abnormalities. If an abnormality is detected, an alert is generated and sent to the terminal, allowing the user to immediately recognize the abnormality and take action.

[1882] Step 6:

[1883] The terminal notifies the user of the alert information received from the server, allowing the user to take immediate action and resolve the problem quickly.

[1884] Step 7:

[1885] The user inputs communication data between project members (e.g., emails, chat logs, and meeting minutes) into the terminal and sends the data to the server, which starts the analysis of communication within the project.

[1886] Step 8:

[1887] The server uses generative artificial intelligence to analyze the received communication data. This analysis identifies points where information is lacking or where misunderstandings are likely to occur. The analysis results are then sent from the server to the device.

[1888] Step 9:

[1889] The device then displays the analysis results to the user, allowing the user to identify areas for improvement in communication between project members and take specific measures to improve them.

[1890] Step 10:

[1891] The user inputs the current schedule of the project into the terminal and sends the schedule information to the server, which starts the schedule optimization process.

[1892] Step 11:

[1893] The server optimizes the received schedule information using generative artificial intelligence, and the optimized schedule is sent from the server to the terminal. As a result, the user receives the optimized schedule, which helps to streamline the progress of the project.

[1894] Step 12:

[1895] The terminal displays the received optimized schedule to the user, allowing the user to take specific steps to efficiently progress the project.

[1896] 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.

[1897] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[1898] Optimizing resource allocation

[1899] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal, which then transmits the input project information to the server.

[1900] The server uses live artificial intelligence to calculate optimal resource allocation based on past project data, and the results are generated as optimized resource allocation and sent back to the terminal.

[1901] The terminal displays the optimized resource allocation received from the server to the user, allowing the user to efficiently allocate resources and start projects.

[1902] Real-time progress tracking and alerts

[1903] The user enters the ID of the project they want to track into their device, which then sends the project ID to the server.

[1904] The server collects project progress data in real time, analyzes it, and checks for any issues. If a problem is detected, the server generates an alert and sends it to the device.

[1905] The terminal notifies the user of the alert information received from the server, so that the user can check the alert and take the necessary measures promptly.

[1906] Facilitating communication and preventing misunderstandings

[1907] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals, which then transmit this data to the server.

[1908] The server uses generative artificial intelligence to analyze the communication data and identify points where misunderstandings are likely to occur, and the results of this analysis are sent back to the terminal.

[1909] The terminal displays the analysis results received from the server to the user, who can then implement measures to improve communication based on this information.

[1910] Deadline Management and Scheduling

[1911] A user inputs the current schedule of a project into a terminal, which then sends this schedule information to a server and requests that the schedule be optimized.

[1912] The server uses generative artificial intelligence to optimize the input schedule, and the optimized schedule is sent from the server to the terminal.

[1913] The terminal displays the optimized schedule to the user, who can then proceed with the project according to the schedule, maximizing resource utilization and completing the project within the deadline.

[1914] Use of emotion engine

[1915] Users use the device to record their emotional state during the project, for example, inputting stress levels and mood changes, and the device transmits this emotional data to a server.

[1916] The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, it monitors the user's stress level and changes in emotions, and generates suggestions for stress reduction as needed. These suggestions are sent from the server to the device.

[1917] The terminal displays the suggestions received from the server to the user, who can then implement the suggested stress reduction measures and complete the project in better condition.

[1918] Team Sentiment Analysis and Feedback

[1919] Users collect emotional data for the entire team by having each team member record their emotional state using a device, including inputting their mood and stress level, which is then sent to a server.

[1920] The server uses an emotion engine to analyze the emotional state of the entire team, integrates the results, and generates feedback to improve team morale and motivation. This feedback is sent from the server to the terminal.

[1921] The device receives feedback from the server and displays it to the team leader and team members, allowing the team to improve communication and work processes and increase the chances of project success.

[1922] Specific examples

[1923] For example, for a new software development project, the user (project manager) inputs detailed project information into the terminal and optimizes resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[1924] In this way, the system of the present invention not only automates various project management tasks, but also enables comprehensive management including the emotional state of the team, thereby significantly improving the efficiency and success rate of the project.

[1925] The processing flow will be explained below.

[1926] Optimizing resource allocation

[1927] Step 1:

[1928] The user inputs detailed project information (project name, type and quantity of resources, project period, etc.) into the terminal.

[1929] Step 2:

[1930] The terminal transmits the input project information to the server.

[1931] Step 3:

[1932] The server uses generative artificial intelligence based on past project data to calculate optimal resource allocation.

[1933] Step 4:

[1934] The server returns the calculated optimized resource allocation to the terminal.

[1935] Step 5:

[1936] The terminal displays the received optimized resource allocation to the user.

[1937] Real-time progress tracking and alerts

[1938] Step 1:

[1939] The user enters the ID of the project they want to track into the terminal.

[1940] Step 2:

[1941] The terminal transmits the project ID to the server.

[1942] Step 3:

[1943] The server collects project progress data in real time.

[1944] Step 4:

[1945] The server analyzes the progress data and generates alerts if it detects a problem.

[1946] Step 5:

[1947] The server transmits the generated alert to the terminal.

[1948] Step 6:

[1949] The terminal notifies the user of the alert information.

[1950] Facilitating communication and preventing misunderstandings

[1951] Step 1:

[1952] Users input communication data (emails, chat logs, meeting minutes, etc.) between project members into their terminals.

[1953] Step 2:

[1954] The terminal transmits the communication data to the server.

[1955] Step 3:

[1956] The server uses generative artificial intelligence to analyze communication data and identify points where misunderstandings are likely to occur.

[1957] Step 4:

[1958] The server returns the analysis results to the terminal.

[1959] Step 5:

[1960] The terminal displays the received analysis results to the user.

[1961] Deadline Management and Scheduling

[1962] Step 1:

[1963] The user inputs the current schedule of the project into the terminal.

[1964] Step 2:

[1965] The terminal transmits the schedule information to the server.

[1966] Step 3:

[1967] The server uses generative artificial intelligence to optimize the input schedule.

[1968] Step 4:

[1969] The server returns the optimized schedule to the terminal.

[1970] Step 5:

[1971] The terminal displays the received optimized schedule to the user.

[1972] Use of emotion engine

[1973] Step 1:

[1974] Users input their emotional state (stress level and mood changes) into the terminal while the project is underway.

[1975] Step 2:

[1976] The terminal transmits the input emotion data to the server.

[1977] Step 3:

[1978] The server uses an emotion engine to analyze the user's emotional state.

[1979] Step 4:

[1980] Based on the analysis results, the server generates suggestions for reducing stress and sends them to the device.

[1981] Step 5:

[1982] The terminal displays the received suggestions to the user.

[1983] Team Sentiment Analysis and Feedback

[1984] Step 1:

[1985] Users (team members) input their emotional state (mood and stress level) into the terminal.

[1986] Step 2:

[1987] The terminal transmits the collected emotion data to the server.

[1988] Step 3:

[1989] The server uses an emotion engine to analyze the emotional state of the entire team.

[1990] Step 4:

[1991] Based on the analysis results, the server generates feedback to improve team morale and sends it to the device.

[1992] Step 5:

[1993] The device displays the feedback received to the team leader and team members.

[1994] The above is the specific flow of each process in the system of the present invention, which can optimize project management and effectively manage the emotional state of the team, thereby greatly improving the efficiency and success rate of the project.

[1995] Example 2

[1996] 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."

[1997] Traditional project management systems have individual functions, such as optimal resource allocation, real-time progress tracking, and preventing miscommunication between team members, but lack a means to manage these functions in an integrated manner. Furthermore, it is necessary to further improve the success rate and efficiency of projects by taking into account the emotional state and stress levels of project members. Therefore, a method is needed to ensure efficient project progress and properly manage the psychological state of each team member.

[1998] 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.

[1999] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for optimizing the project schedule, means for recording the user's emotional state during the project and generating stress reduction suggestions using an emotion engine, and means for collecting the emotional states of team members and generating feedback to improve team morale and motivation using an emotion engine. This not only enables efficient project management, but also makes it possible to significantly improve the success rate and efficiency of projects by appropriately managing the emotional states of members.

[2000] "Generative AI" refers to AI that has the ability to learn from past data and generate optimal results for new data.

[2001] "Resource allocation" refers to the efficient allocation of personnel, time, equipment, etc. required for a project.

[2002] "Real-time progress tracking" refers to monitoring the progress of a project in real time and updating the data immediately.

[2003] An "alert" is a warning message that is sent to the user when a specific condition or abnormality is detected.

[2004] "Communication analysis" refers to analyzing interactions between project members and identifying points and problems where misunderstandings are likely to occur.

[2005] "Schedule optimization" refers to efficiently managing project schedules and making adjustments to complete tasks within deadlines.

[2006] "Emotion engine" refers to a software component for analyzing the emotional state of users and team members.

[2007] "Stress reduction suggestions" refers to providing specific advice or measures to reduce the user's stress level.

[2008] "Feedback" refers to providing insight or advice based on a subject's behavior or results.

[2009] This invention is a system that utilizes generative artificial intelligence and an emotion engine to improve the efficiency and quality of project management. The specific operations of each component, server, terminal, and user, are explained below.

[2010] Optimizing resource allocation

[2011] The user inputs project details, such as the project name, resource type and quantity, and project duration, into the device. The device then sends the input project information to the server. The server then uses a generative AI model based on past project data to calculate the optimal resource allocation. This calculation uses specific software, such as TensorFlow or PyTorch. The calculation results are generated as an optimized resource allocation and sent back from the server to the device. The device then displays this optimized resource allocation to the user, allowing the user to efficiently allocate resources and start the project.

[2012] Real-time progress tracking and alerts

[2013] The user enters the ID of the project they want to track into the device. The device then sends the project ID to the server. The server collects real-time project progress data and analyzes it using a generative AI model. This analysis can be performed using progress management software (such as Jira). If a problem is detected, the server generates an alert and sends it to the device. The device then notifies the user of this alert information, allowing them to take prompt action.

[2014] Facilitating communication and preventing misunderstandings

[2015] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their devices. The devices then send this data to the server. The server then analyzes this communication data using a generative AI model to identify points where misunderstandings are likely to occur. This analysis can be performed using, for example, natural language processing (NLP) technology. The server then returns the analysis results to the device, which then displays them to the user. Based on this information, the user can implement measures to improve communication.

[2016] Deadline Management and Scheduling

[2017] The user inputs the current schedule of the project into the device. The device sends this schedule information to the server and requests schedule optimization. The server optimizes the input schedule using a generative AI model. As a result of this process, the optimized schedule is sent from the server to the device. The device displays the optimized schedule to the user. The user can proceed with the project according to this schedule and complete the project within the deadline while maximizing resource utilization efficiency.

[2018] Use of emotion engine

[2019] The user uses the device to record their emotional state during the project. For example, they input their stress level and mood changes. The device sends this emotional data to the server. The server uses an emotion engine to recognize and analyze the user's emotions. As a result of the analysis, the server monitors the user's stress level and changes in emotions and generates suggestions for stress reduction as needed. The suggestions are sent from the server to the device. The device displays the suggestions to the user, who can then implement the suggested stress reduction measures.

[2020] Team Sentiment Analysis and Feedback

[2021] The user collects emotional data for the entire team by having each team member record their emotional state using their device. This includes input of mood and stress levels. The device then sends this data to the server. The server then uses an emotion engine to analyze the emotional state of the entire team and generates feedback based on the results. This feedback is used to improve team morale and motivation. The server then sends the feedback to the device, which displays it to the team leader and team members. The team can use this feedback to improve communication and work processes and increase the chances of project success.

[2022] Specific examples

[2023] For example, for a new software development project, the user (project manager) inputs detailed project information into the device to optimize resource allocation. While the project is underway, the server tracks progress in real time and generates alerts if any problems arise. At the same time, the server monitors the emotional state of team members and provides feedback on stress reduction and communication. The user can use this information to optimally manage the project and ensure smooth progress.

[2024] Example prompt sentence:

[2025] Project name: New software development

[2026] Resources: 3 developers, 2 designers, 2 testers

[2027] Project duration: 6 months

[2028] Tracking ID: 12345

[2029] Emotional data: Stress level 5 / 10, mood normal

[2030] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2031] Optimizing resource allocation

[2032] Step 1:

[2033] The user inputs detailed project information such as the project name, the type and quantity of resources, and the project period into the terminal.

[2034] Step 2:

[2035] The terminal converts the input project information into JSON format and sends it to the server, specifying " / optimize_resources" as the endpoint.

[2036] Input: Project details entered by the user

[2037] Output: JSON format data sent to the server

[2038] Step 3:

[2039] The server analyzes the received project information and calculates optimal resource allocation using a generative AI model based on past project data, using TensorFlow and PyTorch.

[2040] Input: Project information received by the server

[2041] Data processing / calculation: Generative AI models based on past data optimize resource allocation

[2042] Output: JSON data as optimized resource allocation

[2043] Step 4:

[2044] The server returns the optimized resource allocation data to the terminal as an HTTP response.

[2045] Input: Optimized resource allocation data

[2046] Output: HTTP response to the device

[2047] Step 5:

[2048] The terminal analyzes the received optimized resource allocation data and displays it on the screen in a user-friendly format, for example, in the form of a graph or table.

[2049] Input: Optimized resource allocation data

[2050] Output: Optimization data displayed to the user

[2051] Real-time progress tracking and alerts

[2052] Step 1:

[2053] The user enters the ID of the project they want to track into the terminal.

[2054] Step 2:

[2055] The device sends the project ID to the server, specifying " / track_progress" as the endpoint.

[2056] Input: Project ID entered by the user

[2057] Output: Project ID sent to the server

[2058] Step 3:

[2059] Once the server receives the project ID, it retrieves real-time progress data from the database and analyzes it for issues using a generative AI model that detects outliers and trends.

[2060] Input: Received project ID and progress data from database

[2061] Data processing / calculation: Generative AI models for outlier detection and progress analysis

[2062] Output: Analysis results and any required alert messages

[2063] Step 4:

[2064] If the server detects a problem, it generates an alert message and sends it to the terminal.

[2065] Input: Analysis results that detected anomalies

[2066] Output: The alert message sent to the terminal.

[2067] Step 5:

[2068] The device analyzes the received alert information and immediately notifies the user, who can then check the alert via a pop-up alert or email notification.

[2069] Input: The alert message received on the device

[2070] Output: Alert information to be sent to the user

[2071] Facilitating communication and preventing misunderstandings

[2072] Step 1:

[2073] Users input communication data between project members (e.g., emails, chat logs, and meeting minutes) into their terminals using copy and paste and file upload functions.

[2074] Step 2:

[2075] The device encodes the input communication data and sends it to the server, specifying " / analyze_communication" as the endpoint.

[2076] Input: Communication data entered by the user

[2077] Output: The encoded data sent to the server

[2078] Step 3:

[2079] The server analyzes the received communication data using natural language processing technology to identify points where misunderstandings are likely to occur, using NLP models such as BERT and GPT.

[2080] Input: Received communication data

[2081] Data processing / calculation: Identifying points of misunderstanding using NLP models

[2082] Output: Identification of points where misunderstandings occur

[2083] Step 4:

[2084] The server generates the analysis results in JSON format and returns them to the terminal.

[2085] Input: Analysis results from NLP model

[2086] Output: Send analysis results to your device

[2087] Step 5:

[2088] The device analyzes the received analysis results and displays points of misunderstanding and suggestions for improvement to the user, for example, by providing a function to highlight or annotate the points.

[2089] Input: Received analysis results

[2090] Output: Analysis results that are displayed to the user

[2091] Deadline Management and Scheduling

[2092] Step 1:

[2093] The user inputs the project schedule into the terminal.

[2094] Step 2:

[2095] The device sends this schedule information to the server and requests schedule optimization, specifying " / optimize_schedule" as the endpoint.

[2096] Input: User-entered schedule information

[2097] Output: Schedule information sent to the server

[2098] Step 3:

[2099] The server uses a generative AI model to analyze and optimize the input schedule, using a scheduling algorithm.

[2100] Input: Received schedule information

[2101] Data processing / calculation: Schedule optimization using generative AI models

[2102] Output: Optimized schedule data

[2103] Step 4:

[2104] The server transmits the optimized schedule data to the terminal.

[2105] Input: Optimized schedule data

[2106] Output: Sending optimization data to the terminal

[2107] Step 5:

[2108] The terminal analyzes the received optimized schedule and displays it to the user.

[2109] Input: Optimized schedule data

[2110] Output: The schedule that is displayed to the user

[2111] Use of emotion engine

[2112] Step 1:

[2113] Users input their emotional state into the terminal during the project, for example, inputting stress levels and mood changes.

[2114] Step 2:

[2115] The device sends this emotion data to the server, specifying " / record_emotion" as the endpoint.

[2116] Input: Emotion data entered by the user

[2117] Output: Emotion data sent to the server

[2118] Step 3:

[2119] The server analyzes the user's emotional data using an emotion engine, and monitors the user's stress level and emotional changes as a result of the analysis.

[2120] Input: Received emotion data

[2121] Data processing / calculation: Emotional state analysis using emotion engine

[2122] Output: Stress levels and emotional changes as a result of the analysis

[2123] Step 4:

[2124] The server generates suggestions for stress reduction as needed and transmits them to the terminal.

[2125] Input: Analysis results from the emotion engine

[2126] Output: Send stress reduction suggestions to device

[2127] Step 5:

[2128] The device displays the received suggestions to the user, who can then implement the suggested stress reduction measures.

[2129] Input: Stress reduction suggestions received

[2130] Output: The suggestions that are displayed to the user

[2131] Team Sentiment Analysis and Feedback

[2132] Step 1:

[2133] The user instructs team members to use the devices to record their emotional state, which includes inputting mood and stress levels.

[2134] Step 2:

[2135] The device sends this emotion data to the server, specifying " / collect_team_emotions" as the endpoint.

[2136] Input: Emotion data entered by team members

[2137] Output: Team sentiment data sent to the server

[2138] Step 3:

[2139] The server uses an emotion engine to analyze the emotional state of the entire team and generate feedback.

[2140] Input: Received team sentiment data

[2141] Data processing / calculation: Team emotion analysis using emotion engine

[2142] Output: Analysis results as feedback

[2143] Step 4:

[2144] The server transmits the generated feedback to the terminal.

[2145] Input: Generated feedback

[2146] Output: Sending feedback to the device

[2147] Step 5:

[2148] The device displays the feedback it receives to the user, allowing the team to improve communication and work processes to increase the project's chances of success.

[2149] Input: Feedback result

[2150] Output: Feedback that is visible to the team

[2151] This allows you to clearly understand how each function in this system operates in detail.

[2152] (Application example 2)

[2153] 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."

[2154] Conventional project management systems make it difficult to optimally allocate resources and track progress in real time. They also lack support for quickly responding to abnormalities and preventing misunderstandings through communication between members. They also lack the ability to monitor the emotional state of individual project members or propose stress reduction measures. There is a need to address these issues and simultaneously improve project management efficiency and quality while managing member stress.

[2155] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2156] In this invention, the server includes means for optimizing project resource allocation using generative artificial intelligence, means for tracking progress in real time and generating alerts when problems occur, means for analyzing communication between project members and identifying areas where misunderstandings are likely to occur, means for monitoring the user's emotional state using an emotion engine and generating suggestions for stress reduction, and means for visually providing project management data and alert information to the user in real time using a head-mounted display, thereby enabling efficient project management and improved success rates, as well as monitoring the user's emotional state and suggesting stress reduction measures.

[2157] - "Generative AI" refers to AI technology that generates new information and knowledge through programmed data processing means to solve specific problems.

[2158] "Resource allocation optimization" refers to the most appropriate distribution of available resources to improve project progress and efficiency.

[2159] "Real-time progress tracking" means continuously monitoring the progress of a project on the spot and updating the information immediately.

[2160] "Generating an alert" means that the system issues a warning to the user when it detects a problem or abnormality.

[2161] "Communication analysis" involves analyzing messages and conversations exchanged between project members to identify important information and areas where misunderstandings are likely to occur.

[2162] The "Emotion Engine" is a system that analyzes the user's emotional state, grasps their stress level and psychological state, and suggests appropriate countermeasures.

[2163] A "head-mounted display" is a display device worn on the head to provide visual information to the user.

[2164] "Project management data" refers to all information necessary for management, such as project progress and resource allocation.

[2165] "Suggestions for stress reduction" are specific advice and measures provided to ease the user's mental burden and improve work efficiency.

[2166] MODE FOR CARRYING OUT THE INVENTION

[2167] System Configuration Overview

[2168] The system utilizes generative artificial intelligence (AI) and an emotion engine to improve project management efficiency and quality. Specifically, it optimizes resource allocation, tracks real-time progress, generates alerts, analyzes communication, and analyzes emotions, and provides information to users via a head-mounted display.

[2169] Hardware and software used

[2170] Hardware

[2171] Head-mounted displays: These are worn by the user on their head and provide real-time visuals of project management data (e.g., HoloLens).

[2172] Factory robots: Robots for carrying out manufacturing tasks (e.g. KUKA, Fanuc).

[2173] software

[2174] Server side: Building generative AI models and emotion engines using Python and TensorFlow.

[2175] Front-end: Created a head-mounted display interface using Unity.

[2176] Specific Embodiments of the System

[2177] Optimizing resource allocation

[2178] 1. The user inputs project details (processing steps, resource types and numbers, factory flow, etc.) through a head-mounted display.

[2179] 2. The device sends this information to the server.

[2180] 3. The server uses an AI model based on past data to calculate optimal resource allocation.

[2181] 4. The calculation results are displayed on the head-mounted display via the terminal.

[2182] Real-time progress tracking and alerts

[2183] 1. The user inputs the ID of the robot they want to track into the head-mounted display.

[2184] 2. The device sends the information to the server.

[2185] 3. The server monitors the robot's operation data in real time and immediately generates an alert if it detects an abnormality.

[2186] 4. Alert information is displayed on the head-mounted display and is notified to the user immediately.

[2187] Use of emotion engine

[2188] 1. The user periodically inputs their emotional state through a head-mounted display.

[2189] 2. The device sends this emotion data to the server.

[2190] 3. The emotion engine on the server analyzes the data, monitors the user's stress level, and suggests appropriate stress reduction measures.

[2191] 4. The suggestions are displayed on a head-mounted display and feedback is provided to the user.

[2192] Examples of concrete examples and prompts

[2193] Specific examples

[2194] When starting a project to manufacture a new high-precision part, the user first enters detailed project information and receives the optimal robot placement and work schedule. If the robot exhibits abnormal behavior during the project, an alert is generated in real time and displayed on the head-mounted display. Furthermore, if the user feels high stress, the emotion engine will suggest appropriate relaxation methods or breaks.

[2195] Prompt Sentence Examples

[2196] "We are starting a new machining process. Please optimize resource allocation."

[2197] "Please track the progress of project ID 1234 and let me know if there are any irregularities."

[2198] "Current mood: High stress. Use the emotion engine to provide stress reduction suggestions."

[2199] This system automates various project management tasks and comprehensively manages the emotional state of the team, thereby increasing the chances of project success.

[2200] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2201] Specific processing flow and explanation of the program

[2202] Optimizing resource allocation

[2203] Step 1:

[2204] The user inputs detailed project information through a head-mounted display, including the project name, processing steps, resource types and quantities, factory flow, and project duration.

[2205] Step 2:

[2206] The device sends the entered data to the server, which formats and converts the data and communicates with the server via the appropriate API.

[2207] Step 3:

[2208] Based on the received data, the server uses a generative AI model to calculate optimal resource allocation while referencing past project data, and retrieves relevant data through database queries and inputs it into the model.

[2209] Step 4:

[2210] The server generates the calculation results and returns the optimal resource allocation to the device. The calculation results are sent to the device in JSON format.

[2211] Step 5:

[2212] The device then displays the received optimized resource allocation information on the head-mounted display, allowing the user to start a project based on the visual information.

[2213] Real-time progress tracking and alerts

[2214] Step 1:

[2215] The user inputs the ID of the robot they want to track into the head-mounted display, which is used to identify the robot whose progress they want to track.

[2216] Step 2:

[2217] The device sends the robot ID to the server using the appropriate data format and transmission protocol (e.g. HTTP POST).

[2218] Step 3:

[2219] The server monitors the robot's operational data in real time, collecting and analyzing sensor data. If an abnormality is detected, the AI ​​immediately generates an alert. The anomaly detection logic uses threshold judgment and machine learning models.

[2220] Step 4:

[2221] The server then sends the generated alert information to the terminal. Because the alert information contains real-time data, low-latency communication is required.

[2222] Step 5:

[2223] The device displays the alert information on the head-mounted display and notifies the user immediately, allowing the user to visually identify the problem and take prompt action.

[2224] Use of emotion engine

[2225] Step 1:

[2226] Users periodically input their emotional state (stress level and mood) through a head-mounted display, which is an important element for emotion analysis.

[2227] Step 2:

[2228] The device sends the emotion data to the server, which then formats and structures the data before transferring it to the server.

[2229] Step 3:

[2230] The emotion engine in the server analyzes the emotion data, identifies emotional states, and monitors stress levels using emotion recognition algorithms and natural language processing techniques.

[2231] Step 4:

[2232] Based on the analysis results, the server generates and proposes stress reduction measures, which are individually customized by the AI ​​model.

[2233] Step 5:

[2234] The server sends the proposed measures to the device and displays them on the head-mounted display. The user confirms and implements the proposed measures (e.g., relaxation methods, setting break times).

[2235] This allows users to efficiently manage projects, understand progress in real time, resolve issues, and receive comprehensive support to minimize stress.

[2236] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2237] 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 5...

Claims

1. a means for optimizing resource allocation for a project using generative artificial intelligence; A means to track progress in real time and generate alerts when issues arise; A method to analyze communication between project members and identify areas where misunderstandings are likely to occur. A means of optimizing project schedules; A system including:

2. The system of claim 1 , which uses generative artificial intelligence to learn from past project data and optimize resource allocation.

3. The system of claim 1 , wherein the system collects real-time progress data and generates alerts for early problem detection.

4. The system of claim 1 , wherein the system analyzes communication data to identify information gaps and misunderstandings.

5. 10. The system of claim 1, wherein the system inputs a current schedule for a project and optimizes it.

Images