system

Abstract

Provide a system. 【Solution means】 Means for accessing a past database to obtain historical data, Means for analyzing the obtained historical data to identify risk factors and potential problems, Means for generating and notifying a risk list, Means for inputting tasks and dependencies of a project, Means for scheduling based on the input information, Means for notifying the generated schedule to the user, Means for receiving questions using a chat interface, Means for analyzing the questions and generating appropriate answers, Means for notifying the generated answers via the chat interface, A system including the above.

Description

Technical Field

[0001] The technology of this disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Modern project management requires the management of complex tasks, the optimal allocation of resources, and the prediction and countermeasures of risks. As a result, project managers and team members will spend a great deal of man - hours, and there is a risk that the progress of the project will be delayed. To solve this problem, a system that automates risk prediction, schedule optimization, and information sharing based on past experience and data is needed.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing the following means: means for accessing a past database to obtain historical data; means for analyzing the obtained historical data to identify risk factors and potential problems; and means for generating and notifying a risk list. It also includes means for inputting project tasks and dependencies, means for scheduling based on the input information, and means for notifying the user of the generated schedule. Furthermore, the system provides means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, and means for notifying the user of the generated answers via the chat interface. This enables risk identification and countermeasures, schedule optimization, and efficient information sharing within the team, significantly reducing the man-hours required for project management.

[0006] A "database" is a system that organizes and stores data, allowing it to be retrieved as needed.

[0007] "Historical data" refers to data that includes information about the progress and performance of past projects.

[0008] A "machine learning model" is a program trained with mathematical and statistical algorithms to make predictions and classifications based on data.

[0009] "Risk factors" are elements or conditions that could negatively impact the progress of a project.

[0010] A "risk list" is a list of identified risk factors compiled in a table format.

[0011] A "task" is an individual work item that needs to be performed in order to achieve the objectives of a project.

[0012] A "dependency" is a relationship that describes a state in which the progress or completion of one task depends on another task.

[0013] "Scheduling" is the process of determining the order in which tasks are executed and how resources are allocated.

[0014] A "chat interface" is an interface that allows users to communicate with a system in real time using text.

[0015] Natural Language Processing (NLP) is a technology that uses computers to understand, analyze, and generate human language.

[0016] "Optimization" is the process of adjusting plans and arrangements to use resources and time in the most efficient way. [Brief explanation of the drawing]

[0017] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] As shown in Figure 1, the 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.

[0028] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0031] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0037] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0038] This invention is a system for efficient project management that accesses historical databases to retrieve historical data and analyzes that data to identify risk factors and potential problems. Furthermore, it allows users to input project tasks and dependencies, optimizes the schedule based on that information, and provides it to the user. In addition, it utilizes a chat interface to respond to team members' questions in real time.

[0039] Basic System Configuration

[0040] 1. Data acquisition function

[0041] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[0042] 2. Data Analysis Function

[0043] The server passes the acquired historical data to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[0044] 3. Task Input Function

[0045] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[0046] 4. Schedule Optimization Function

[0047] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[0048] 5. Chat Interface

[0049] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[0050] Specific example

[0051] For example, when a user starts a new software development project, they can use the system by following these steps:

[0052] 1. Risk prediction and analysis

[0053] The user logs into the system and requests a risk analysis based on past project data.

[0054] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[0055] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0056] 2. Adjusting the project schedule

[0057] The user enters the project's task list and its dependencies from the terminal.

[0058] The server optimizes the schedule using an AI model based on the input information.

[0059] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[0060] 3. Information sharing

[0061] A user uses the chat interface to ask, "When is the next meeting scheduled?"

[0062] The server receives the question and analyzes it using an NLP model.

[0063] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[0064] As described above, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[0065] The following describes the processing flow.

[0066] Risk prediction and analysis

[0067] Step 1:

[0068] The server accesses the past project database to retrieve historical data. Specifically, it uses SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors encountered.

[0069] Step 2:

[0070] The server preprocesses the historical data it acquires. This involves tasks such as data cleaning, imputation of missing values, and format conversion. This preprocessing allows machine learning models to accurately analyze the data.

[0071] Step 3:

[0072] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[0073] Step 4:

[0074] The server extracts risk factors from the analysis results and compiles them into a risk list. It then scores and ranks the risk factors and prioritizes the extraction of high-risk items.

[0075] Step 5:

[0076] The server notifies the user of the risk list. The risk list is converted to JSON format and displayed on the web application's dashboard.

[0077] Adjusting the project schedule

[0078] Step 1:

[0079] The user inputs the project's task list, its dependencies, and resource information from their terminal. This includes information such as the task name, start date, end date, dependent task IDs, and required resources.

[0080] Step 2:

[0081] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[0082] Step 3:

[0083] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[0084] Step 4:

[0085] The server sends the generated schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[0086] Step 5:

[0087] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[0088] Information sharing

[0089] Step 1:

[0090] Team members (users) post questions through the chat interface. These questions include information such as project progress and the schedule for the next meeting.

[0091] Step 2:

[0092] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[0093] Step 3:

[0094] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[0095] Step 4:

[0096] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[0097] Step 5:

[0098] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[0099] (Example 1)

[0100] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] Traditional project management systems have struggled to efficiently utilize historical data to identify risk factors and potential problems, and to use those results to optimize project schedules. Furthermore, they lacked sufficient real-time information sharing and question-and-answer functions, hindering smooth communication among team members.

[0102] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0103] In this invention, the server includes means for accessing a past database to acquire historical data, means for inputting the acquired historical data into a machine learning model to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for optimizing scheduling using an AI model based on the input information, means for notifying the user of the generated schedule and visualizing it on a dashboard, means for receiving questions using a chat interface, means for analyzing questions with a natural language processing model to generate appropriate answers, and means for notifying the user of the generated answers via the chat interface. This makes it possible to comprehensively perform risk identification and countermeasures, schedule optimization, and information sharing in project management.

[0104] A "database" is an information system that stores and allows access to past project data.

[0105] "Historical data" refers to a set of information related to past projects, including progress, completed tasks, resources used, and risk factors encountered.

[0106] A "machine learning model" refers to an algorithm or mathematical model used to analyze historical data to identify risk factors and potential problems.

[0107] A "risk list" is a compilation of risk factors and potential problems identified by a machine learning model.

[0108] A "task" refers to a specific task or activity within a project, carried out to achieve the project's objectives.

[0109] "Dependencies" refer to the relationships between tasks within a project, indicating that one task needs to be performed only after another task has been completed.

[0110] An "AI model" refers to a generative algorithm or mathematical model used to optimize a schedule based on input task and dependency information.

[0111] "Scheduling" is the process of efficiently determining the order and timing of project tasks.

[0112] A "dashboard" is an interface that allows users to centrally view project progress and various information.

[0113] A "chat interface" is an interface that allows users and systems to communicate in real time using text.

[0114] A "natural language processing model" refers to an algorithm or mathematical model used to analyze text-based questions from users and generate appropriate answers.

[0115] This invention is a system for efficiently managing projects. The main components of the system consist of a server, terminals, and users, enabling project risk identification, schedule optimization, and real-time information sharing.

[0116] Data acquisition function

[0117] The server accesses a database of past projects. For example, the database stores completed tasks, resources used, project progress, and risk factors encountered. A database management system (e.g., MySQL®, PostgreSQL) is used in this process.

[0118] Data analysis function

[0119] After acquiring the data, the server passes the acquired historical data to a machine learning model. Examples of machine learning models used include TENSORFLOW® and PyTorch. The analysis model learns patterns in the data and identifies risk factors and potential problems. A risk list is generated and notified to the user's dashboard.

[0120] Task input function

[0121] The user inputs the project's task list, its dependencies, and resource information from a terminal. The information entered on the terminal is sent to the server and becomes the basis for scheduling.

[0122] Schedule optimization function

[0123] The server optimizes the schedule using an AI model based on the input task, dependency, and resource information. A generative AI model is applied during this process. The model takes task dependencies and resource constraints into account to generate the optimal schedule. The generated schedule is sent to the user, who can view and edit it on the dashboard.

[0124] Chat interface

[0125] Users post questions using a chat interface. The server analyzes the questions using a generative AI model and generates appropriate answers. For example, natural language processing models (e.g., GPT-3®, BERT) are used at this stage. The generated answers are notified to the user in real time.

[0126] Specific example

[0127] For example, when a user starts a new software development project, they can use the system by following these steps:

[0128] 1. Risk prediction and analysis

[0129] The user logs into the system and requests a risk analysis based on past project data.

[0130] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[0131] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0132] Example of a prompt:

[0133] "Please analyze the data from the past 10 projects and tell me the risk factors."

[0134] 2. Adjusting the project schedule

[0135] The user enters the project's task list and its dependencies from the terminal.

[0136] The server optimizes the schedule using an AI model based on the input information.

[0137] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[0138] Example of a prompt:

[0139] "Please generate a project schedule based on the following task list and dependencies."

[0140] 3. Information sharing

[0141] Users use the chat interface to ask about the schedule for the next meeting.

[0142] The server analyzes the question using a natural language processing model and accesses the schedule database to retrieve information about the next meeting.

[0143] The server will notify you of the generated response via the chat interface.

[0144] Example of a prompt:

[0145] "Please let me know when the next meeting will be held."

[0146] Thus, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[0147] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0148] Step 1: The user logs into the system.

[0149] Input: The user enters their ID and password.

[0150] Specific operation: The terminal receives this and sends it to the server. The server accesses the database and verifies the entered ID and password against the authentication information in the database.

[0151] Output: If authentication is successful, the user is redirected to the dashboard. If authentication fails, an error message is displayed.

[0152] Step 2: Request a risk analysis of the user.

[0153] Input: The user clicks the "Start Risk Analysis" button on the dashboard.

[0154] Specific operation: The terminal receives the user's request and sends it to the server. The server accesses the project database and retrieves past project data.

[0155] Output: The acquired historical data is sent to the server.

[0156] Step 3: The server inputs data into the machine learning model.

[0157] Input: Acquired historical data.

[0158] Specific operation: The server inputs historical data into a machine learning model (e.g., TensorFlow or PyTorch). The model analyzes the data and identifies risk factors and potential problems.

[0159] Output: A risk list is generated as an analysis result.

[0160] Step 4: The server notifies the user of the risk list.

[0161] Input: Generated risk list.

[0162] Specific operation: The server sends the risk list to the user's dashboard. The user is then able to view the risk list.

[0163] Output: The risk list is displayed on the user's dashboard.

[0164] Step 5: The user enters the tasks and dependencies.

[0165] Input: The user enters the project task list and dependencies.

[0166] Specific operation: The terminal sends the entered data to the server. The server saves this data to the database.

[0167] Output: The task list and dependencies are saved to the database.

[0168] Step 6: The server optimizes the schedule.

[0169] Input: Saved task list and dependencies.

[0170] Specific operation: The server uses an AI model to optimize the schedule. The model generates the optimal schedule by considering task dependencies and resource constraints.

[0171] Output: Optimized schedule.

[0172] Step 7: The server notifies the user of the schedule.

[0173] Input: Generated schedule.

[0174] Specific operation: The server sends the schedule to the user, and it is displayed on the dashboard.

[0175] Output: The schedule displayed on the dashboard.

[0176] Step 8: The user posts a question in the chat interface.

[0177] Input: The user enters a question in text format via the chat interface.

[0178] Specific operation: The terminal sends a question to the server. The server has a natural language processing model (e.g., GPT-3 or BERT) analyze the question.

[0179] Output: The intent of the analyzed question.

[0180] Step 9: The server generates the answer to the question.

[0181] Input: The intent of the analyzed question.

[0182] Specific operation: The server accesses the schedule database and retrieves relevant information. Based on the retrieved information, the server generates a response and converts it to text format.

[0183] Output: Generated answer.

[0184] Step 10: The server notifies the user of the answer.

[0185] Input: Generated response.

[0186] Specific operation: The server notifies the user of the answer via the chat interface.

[0187] Output: The response displayed in the chat interface.

[0188] (Application Example 1)

[0189] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0190] In modern factories, risk management is a crucial issue alongside improving production efficiency. However, conventional factory management systems have been unable to fully utilize historical data, making it difficult to identify risks and optimize schedules. Furthermore, the lack of real-time risk management and smooth information sharing with factory staff has made it difficult to maximize the efficiency of production lines. This invention aims to solve these problems.

[0191] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0192] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, factory management means for acquiring data and identifying risk factors in real time, factory operation means for optimizing the schedule, means for inputting prompt sentences into a generation AI model based on questions to generate answers, and means for notifying factory staff of the generated answers. This enables real-time risk management, optimization of production schedules, and more efficient information sharing within the factory.

[0193] A "past database" refers to a database containing historical information about previous projects and work.

[0194] "Historical data" refers to data recorded in the past, such as the progress of a project, completed tasks, resources used, and risk factors encountered.

[0195] "Risk factors" refer to potential problems or obstacles that could hinder the progress of a project or work.

[0196] A "potential problem" refers to an element that is not currently apparent but could potentially become a problem in the future.

[0197] A "risk list" refers to a list that compiles identified risk factors and problems in a list format.

[0198] "Project tasks" refer to the specific tasks and activities necessary to move a project forward.

[0199] A "dependency" refers to a relationship in which one task depends on the completion of another task.

[0200] "Scheduling" refers to time management that involves efficiently allocating tasks and resources and proceeding in a planned manner.

[0201] A "chat interface" refers to an interface that allows users and systems to communicate in real time using text.

[0202] A "generative AI model" refers to a model that uses artificial intelligence technology to generate text and responses.

[0203] A "prompt" refers to the text input to an AI model in order to generate an appropriate response.

[0204] "Factory management methods" refer to techniques and systems for managing the operation and production processes of a factory.

[0205] "Factory operation methods" refer to the techniques and systems used to efficiently manage the overall operations of a factory.

[0206] This invention is a system aimed at efficient factory operation and risk management. This system has the ability to access historical databases to retrieve historical data, analyze it to identify risk factors and potential problems, and generate and notify users of risk lists. Furthermore, it allows users to input project tasks and dependencies, optimize scheduling based on this information, and notify users of the generated schedule. It also has a function to receive questions from factory staff in real time using a chat interface, generate appropriate answers accordingly, and notify users.

[0207] The following key hardware and software are required to implement this system.

[0208] 1. Hardware:

[0209] Factory robots (including various sensors and database access functions)

[0210] Server (for data analysis and scheduling processing)

[0211] 2. Software:

[0212] SQLite: Database Management System

[0213] scikit-learn: Machine learning library (RandomForestClassifier)

[0214] OpenAI® API: AI model for generating chat interfaces

[0215] Python: A programming language

[0216] The server accesses the factory's historical database to retrieve historical data. This includes information such as project progress, completed tasks, resources used, and risk factors encountered. For analysis, machine learning models such as RandomForestClassifier from the scikit-learn library are used to identify risk factors and potential problems. The identified risk factors are generated as a risk list and notified to the user.

[0217] Next, the user inputs the project's task list, its dependencies, and resource information from their device. This input data is sent to the server, where an AI model is used to perform scheduling. After the schedule is generated, the user is notified and it is visualized on a dashboard.

[0218] The server also accepts questions from factory staff via a chat interface. For these questions, it uses a generative AI model (OpenAI API) to generate appropriate answers, prompting the user to input prompts. These answers are then notified to the factory staff in real time.

[0219] As a concrete example, the following process can be considered, which involves identifying the risk of a part of the manufacturing line failing and then developing countermeasures.

[0220] 1. Historical data acquisition: Acquire past manufacturing data.

[0221] 2. Risk Factor Analysis: Identify the risk factors.

[0222] 3. Schedule Optimization: Optimize the schedule.

[0223] 4. Chat Response: Generate responses to questions.

[0224] Examples of prompt messages include the following:

[0225] "What is the schedule for the next maintenance?"

[0226] "What is the progress on Line A?"

[0227] "What is the estimated completion date for manufacturing task B?"

[0228] These prompts enable the system to manage risks in real time, optimize production schedules, and streamline information sharing within the factory.

[0229] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0230] Step 1:

[0231] The server accesses the past database to retrieve historical data.

[0232] Specific operation: The server sends queries to the SQLite database to retrieve data such as project progress, completed tasks, resources used, and risk factors encountered.

[0233] Input: Database query request

[0234] Output: Historical data

[0235] Step 2:

[0236] The server analyzes the acquired historical data to identify risk factors and potential problems.

[0237] Specific operation: The server uses machine learning models such as RandomForestClassifier from the scikit-learn library to identify risk factors and potential problems based on historical data.

[0238] Input: Historical data

[0239] Output: Risk List

[0240] Step 3:

[0241] The server generates a risk list and notifies the user.

[0242] Specific action: The server compiles identified risk factors into a list format and updates the UI to notify the user.

[0243] Input: Risk list

[0244] Output: Updated UI

[0245] Step 4:

[0246] The user inputs the project's task list, its dependencies, and resource information from their terminal.

[0247] Specific operation: The user uses a terminal to input the necessary tasks, dependencies, and resource information through the screen interface.

[0248] Input: Task list, dependencies, resource information

[0249] Output: Input is sent to the server.

[0250] Step 5:

[0251] The server performs scheduling based on the entered task list and dependencies.

[0252] Specific operation: The server uses an AI model to consider task priorities and dependencies and generate an optimal schedule.

[0253] Input: Task list, dependencies, resource information

[0254] Output: Generated schedule

[0255] Step 6:

[0256] The server notifies the user of the generated schedule and visualizes it on the dashboard.

[0257] Specific operation: The server displays the generated schedule on the user's dashboard, making it easy for the user to check.

[0258] Input: Generated schedule

[0259] Output: Updated dashboard

[0260] Step 7:

[0261] Factory staff enter questions using a chat interface.

[0262] Specific action: Factory staff open the chat interface on their terminal and enter their question.

[0263] Input: Question from the chat interface

[0264] Output: The question is sent to the server.

[0265] Step 8:

[0266] The server uses a generative AI model to generate appropriate answers to questions.

[0267] Specific operation: The server inputs the question as a prompt into the AI ​​model (OpenAI API) and generates an appropriate answer.

[0268] Input: Questions and prompts from the chat interface.

[0269] Output: Generated answer

[0270] Step 9:

[0271] The server notifies factory staff of the generated response via a chat interface.

[0272] Specific operation: The server notifies factory staff in real time of the generated responses via a chat interface.

[0273] Input: Generated answer

[0274] Output: Chat interface updates and notifications

[0275] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0276] The present invention is a system for further optimizing project management and corresponding to the psychological state of users. It accesses a past database to obtain historical data, analyzes the data to identify risk factors and potential problems. Also, it inputs the tasks and dependencies of the project, optimizes the schedule based on them, and provides it to the user. Furthermore, by combining the use of a chat interface to respond to questions from team members in real time with an emotion engine that recognizes the emotions of users, it is possible to take responses into account the psychological state of users during project progress and decision-making.

[0277] Basic Configuration of the System

[0278] 1. Data Acquisition Function

[0279] The server accesses a past project database to obtain historical data. This data includes information such as the progress of the project, completed tasks, resources used, and risk factors encountered.

[0280] 2. Data Analysis Function

[0281] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[0282] 3. Task Input Function

[0283] The user inputs the task list of the project, their respective dependencies, and resource information from the terminal. This input data is sent to the server and becomes the basic data for scheduling.

[0284] 4. Schedule Optimization Function

[0285] Based on the input information, the server performs scheduling using an AI model. In this process, the dependencies of tasks and resource constraints are taken into account to generate an optimal schedule. The generated schedule is sent to the user and visualized on the dashboard.

[0286] 5. Chat Interface

[0287] The team members have the function of posting questions through the chat interface. The server analyzes the questions using generative AI, generates appropriate answers, and notifies them to the chat interface in real time.

[0288] 6. Emotion Engine

[0289] The server includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes the user's negotiations, comments, chat messages, etc. to grasp the user's current emotional state. Thereby, the accuracy of risk prediction and countermeasures can be improved.

[0290] Specific Example

[0291] For example, when a user starts a new software development project, the system can be used in the following steps.

[0292] 1. Risk Prediction and Analysis

[0293] The user logs in to the system and requests a risk analysis based on past project data.

[0294] The server accesses the database to obtain historical data and analyzes it with a machine learning model.

[0295] The server extracts risk factors as analysis results and provides them to the user as a risk list.

[0296] The emotion engine recognizes the user's current emotional state and adjusts the priority order of the risk list.

[0297] 2. Adjustment of project schedule

[0298] The user inputs the task list of the project and its respective dependencies from the terminal.

[0299] Based on the input information, the server uses the AI model to optimize the schedule.

[0300] The server sends the generated schedule to the user and visualizes it on the dashboard.

[0301] The emotion engine provides feedback on the schedule based on the user's emotion.

[0302] 3. Information sharing

[0303] The team member (user) uses the chat interface to ask "What is the schedule for the next meeting?".

[0304] The server receives the question and analyzes it with the NLP model.

[0305] The server accesses the schedule database to obtain the information on the next meeting and notifies the generated answer through the chat interface.

[0306] The emotion engine recognizes the user's emotion and provides an answer in an appropriate tone.

[0307] As described above, the present invention can comprehensively perform risk identification and countermeasures, schedule optimization, and information sharing in project management, and further improve the quality and efficiency of project management by considering the user's emotion.

[0308] The processing flow will be described below.

[0309] A process that combines risk prediction, analysis, and sentiment recognition.

[0310] Step 1:

[0311] The user logs into the system and requests a risk analysis based on past project data. Specifically, they enter the required authentication information on the login screen and click the risk analysis button.

[0312] Step 2:

[0313] The server accesses the database to retrieve historical data. Specifically, it executes SQL queries to extract information such as past project progress, completed tasks, resources used, and risk factors encountered.

[0314] Step 3:

[0315] The server preprocesses the historical data it acquires. Specifically, it performs data cleaning, imputation of missing values, and format conversion to prepare the data for analysis by machine learning models.

[0316] Step 4:

[0317] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[0318] Step 5:

[0319] The server extracts risk factors from the analysis results and compiles them into a risk list. Specifically, it scores and ranks the risk factors and prioritizes extracting high-risk items.

[0320] Step 6:

[0321] The server generates a risk list and uses an emotion engine to analyze the user's current emotional state. Specifically, it recognizes emotions from the user's past comments and current activity.

[0322] Step 7:

[0323] The server reflects the results of the emotion engine and adjusts the priority of the risk list and the notification method. For example, if the user is stressed, less urgent risk factors may be postponed.

[0324] Step 8:

[0325] The server notifies the user of the adjusted risk list. Specifically, the risk list is converted to JSON format and displayed on the web application's dashboard.

[0326] A process that combines project schedule adjustment and emotion recognition.

[0327] Step 1:

[0328] The user inputs the project's task list, its dependencies, and resource information from their device. Specifically, they enter information such as the task name, start date, end date, dependent task IDs, and required resources into an input form.

[0329] Step 2:

[0330] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[0331] Step 3:

[0332] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[0333] Step 4:

[0334] The server passes the generated schedule to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is overloaded, it might suggest distributing tasks.

[0335] Step 5:

[0336] The server sends the adjusted schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[0337] Step 6:

[0338] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[0339] A process that combines information sharing and emotion recognition.

[0340] Step 1:

[0341] Team members (users) post questions through the chat interface. For example, they might type, "When is the next meeting scheduled?"

[0342] Step 2:

[0343] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[0344] Step 3:

[0345] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[0346] Step 4:

[0347] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[0348] Step 5:

[0349] The server passes the generated response to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is anxious, the response will be provided in a calm tone.

[0350] Step 6:

[0351] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[0352] (Example 2)

[0353] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0354] In project management, identifying and managing risks, effective scheduling, and real-time information sharing are crucial elements. However, traditional systems struggled to manage these elements in an integrated manner, particularly failing to consider the emotional state of users. This led to problems such as project delays and difficulties in smooth communication among team members.

[0355] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0356] In this invention, the server includes means for accessing a database and acquiring historical data, means for analyzing the acquired data to identify risk factors and potential problems, means for inputting project tasks and dependencies, means for scheduling, means for notifying the user, means for receiving questions using a chat interface, means for generating appropriate answers, means for analyzing and recognizing the user's emotions, and means for dynamically adjusting the priority of the risk list and schedule based on the user's emotions. This enables not only risk management and schedule optimization, but also project management that takes into account the user's psychological state.

[0357] A "database" is a system for systematically storing and managing collections of data.

[0358] "Historical data" refers to data that includes information such as the progress of past projects, completed tasks, resources used, and risk factors.

[0359] "Risk factors" refer to elements or events that could potentially hinder the progress of a project.

[0360] A "potential problem" refers to an event or situation that is not currently apparent but has the potential to become a problem in the future.

[0361] A "risk list" is a compilation of analyzed risk factors in a list format.

[0362] A "task" refers to an individual task or job performed as part of a project.

[0363] A "dependency" refers to a relationship where one task depends on the start or completion of another task.

[0364] "Scheduling" refers to the act of creating a plan to efficiently allocate project tasks and resources over time.

[0365] A "chat interface" refers to a communication method that allows for the sending and receiving of messages in real time.

[0366] A "generative AI model" refers to an artificial intelligence algorithm that generates appropriate output based on user input and past data.

[0367] "Emotion recognition" is a technology that analyzes a user's emotional state and adjusts its response based on that information.

[0368] "Dynamic prioritization" refers to changing the importance of risk lists and schedules in real time based on the project status and the users' emotional state.

[0369] "Notification" refers to the act of communicating important information or results to a user.

[0370] "Terminal" refers to a computer or mobile device used by a user for operation.

[0371] This invention is a system for streamlining risk management, schedule optimization, and information sharing in project management. Furthermore, by considering the user's psychological state, it can make project progress smoother. This system consists of server, terminal, and user elements, all of which work together. The following describes each element and its specific operation.

[0372] Required hardware and software

[0373] Server: Use a server equipped with a high-performance processor and large-capacity storage.

[0374] Database management systems: Relational database management systems such as MySQL and PostgreSQL.

[0375] Machine learning libraries: TensorFlow, Scikit-learn, Pandas.

[0376] User interface: Web browser, chat interface (JavaScript® framework, WebSocket).

[0377] Communication method: HTTP or HTTPS protocol between the server and the terminal.

[0378] Specific examples of data acquisition and preprocessing

[0379] The server accesses a database of past projects to retrieve historical data. This data includes project progress, completed tasks, resources used, and risk factors encountered. After retrieving the data, the Pandas library is used to cleanse the data, removing unnecessary data and imputing missing values.

[0380] Specific examples of risk analysis

[0381] The server passes the preprocessed data to machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[0382] Example of a prompt

[0383] "Please conduct a risk analysis for the new project."

[0384] Specific examples of task input and schedule optimization

[0385] Users input project task lists, dependencies, and resource information from their devices. This input data is sent to a server, where an AI model is used to perform scheduling. An optimal schedule is generated, taking into account task dependencies and resource constraints, and visualized on a dashboard.

[0386] Examples of chat interfaces and emotion recognition

[0387] When a user posts a question through the chat interface, the server uses a generative AI model to analyze the question and generate an appropriate answer. This answer is then notified to the user in real time through the chat interface. Additionally, an emotion recognition engine is used to analyze the user's emotions and dynamically adjust the priority of risk lists and schedules.

[0388] Example of a prompt

[0389] "When is the next project meeting?"

[0390] Thus, the present invention is a system that comprehensively addresses risk identification and countermeasures, schedule optimization, and information sharing in project management. Furthermore, by considering user emotions, the quality and efficiency of project management are improved.

[0391] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0392] Step 1:

[0393] Data acquisition

[0394] The server connects to the database and retrieves historical data. Specifically, it executes SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors.

[0395] Input: Database connection information and queries

[0396] Data processing: Execute SQL queries and retrieve result sets.

[0397] Output: Historical data

[0398] Step 2:

[0399] Data preprocessing

[0400] The historical data acquired by the server is preprocessed using the Python Pandas library. Specifically, this involves imputing missing values ​​and removing unnecessary data.

[0401] Input: Historical data

[0402] Data processing: Data cleansing (imputing missing values, removing unnecessary data)

[0403] Output: Preprocessed data

[0404] Step 3:

[0405] Risk analysis

[0406] The server inputs pre-processed data into machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Specifically, it uses machine learning algorithms to analyze patterns in the data and identify risk factors.

[0407] Input: Preprocessed data

[0408] Data processing: Analysis using machine learning models

[0409] Output: List of risk factors

[0410] Step 4:

[0411] Task entry

[0412] The user inputs the project's task list, dependencies, and resource information from their device and sends it to the server. Specifically, they input task information using a web form and press the "Submit" button.

[0413] Input: User's task list, dependencies, and resource information

[0414] Data processing: Send data to the server

[0415] Output: Task data

[0416] Step 5:

[0417] Schedule optimization

[0418] The server uses an AI model to schedule tasks based on the input task information. Specifically, it considers task dependencies and resource constraints to generate the optimal schedule.

[0419] Input: Task data

[0420] Data processing: Scheduling in AI models

[0421] Output: Optimized schedule

[0422] Step 6:

[0423] Notification and visualization of results

[0424] The server notifies the user of the generated schedule information and visualizes it on a dashboard. Specifically, it uses data visualization libraries such as D3.js.

[0425] Input: Optimized schedule

[0426] Data processing: Visualization of schedule information

[0427] Output: Gantt chart on the dashboard

[0428] Step 7:

[0429] Chat interface

[0430] The user enters a question into a chat box, and the server generates an appropriate answer using an AI model. Specifically, the user might type "When is the next meeting?" into the chat, and the server generates an answer and notifies the user in real time.

[0431] Input: User's question

[0432] Data processing: Analysis using NLP models, response generation.

[0433] Output: Answer on the chat interface

[0434] Step 8:

[0435] Recognition of emotions

[0436] The server runs an emotion recognition engine to understand the user's emotional state by analyzing their comments and messages. Specifically, it analyzes the user's input data and dynamically adjusts the priority of the risk list and schedule.

[0437] Input: User comments or messages

[0438] Data processing: Analysis using emotion recognition algorithms

[0439] Output: Prioritized risk list and schedule

[0440] The above outlines the specific processing steps of this system. Each step clearly indicates the input and output and provides a detailed explanation of the data processing and calculations performed.

[0441] (Application Example 2)

[0442] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0443] Traditional factory project management systems have struggled not only to streamline production processes but also to identify risk factors, optimize schedules, share information in real time, and even address the emotions of workers. Furthermore, early detection and intervention of problems are crucial, especially in production environments, and a lack of efficient project management can lead to decreased productivity and increased risks. Against this backdrop, there is a need for a system that improves the quality and efficiency of project management in factories.

[0444] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0445] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, means for recognizing the user's emotions and adjusting the tone of responses based on emotion analysis, and means for visualizing the optimal production schedule in real time and managing the factory's production process. This enables comprehensive risk identification and countermeasures, schedule optimization, and information sharing in factory project management, and further allows for responses that take user emotions into consideration.

[0446] "Historical data" refers to various types of information collected during past projects and work, including progress, completed tasks, resources used, and risk factors encountered.

[0447] A "risk list" refers to a list of risk factors extracted based on the analysis of historical data. This allows users to identify potential problems and risks in advance.

[0448] A "task" refers to an individual job or activity that needs to be performed in a project or production process. Each task is defined as a specific action or unit of work.

[0449] "Dependencies" refer to situations where multiple tasks in a project are related to each other, with one task influencing or being influenced by another. This helps manage the order and progress of tasks.

[0450] "Scheduling" refers to the process of optimally allocating and planning the timing of each task in a project or production process. This ensures the efficient use of resources and the smooth progress of the project.

[0451] A "chat interface" refers to an interactive interface that allows users to ask questions and exchange information in real time. This enables rapid communication.

[0452] "Emotional analysis" refers to the technology that recognizes and analyzes emotions and emotional states from a user's text and comments. This allows the system to respond in a way that is appropriate to the user's psychological state.

[0453] An "AI model" refers to a collection of algorithms that use artificial intelligence to solve problems and analyze data. This allows the model to learn patterns from data and provide optimal solutions.

[0454] "Visualization" refers to a technique that makes data and information easier for users to understand by displaying them graphically. This makes it easier to grasp complex information.

[0455] System Implementation Overview

[0456] This invention is a system designed to improve efficiency in factory project management and to address risk factors and the emotional state of workers. This system includes the following main functions:

[0457] Data acquisition function

[0458] The server accesses a database of past projects to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered. The software used is a database management system (DBMS) and the Python pandas library.

[0459] Data analysis function

[0460] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. This analysis uses a random forest model based on the scikit-learn library. The risk list generated based on the analysis results is then notified to the user.

[0461] Task input function

[0462] Users input project task lists, their dependencies, and resource information via their devices. This input data is sent to a server and forms the basis for scheduling. For this purpose, smartphones and tablets are expected to be used as the interface.

[0463] Schedule optimization function

[0464] The server uses an AI model to perform scheduling based on the input information. The AI ​​model used is SVR (Support Vector Regression) from the scikit-learn library. In this process, task dependencies and resource constraints are taken into consideration to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[0465] Chat interface

[0466] The system allows team members to post questions via a chat interface. The server uses a generative AI model (OpenAI's GPT-3) to analyze the questions, generate appropriate answers, and notifies users of these answers in real time via the chat interface.

[0467] Emotional Engine

[0468] The server includes an emotion engine (TextBlob library) that recognizes the user's emotions. This emotion engine analyzes the user's business negotiations, comments, chat messages, etc., to understand the user's current emotional state and adjust the priority of the risk list and the tone of responses accordingly.

[0469] Specific example

[0470] For example, when a user starts a new production project, they can use the system by following these steps:

[0471] 1. Risk prediction and analysis:

[0472] The user logs into the system and requests a risk analysis based on past project data.

[0473] The server accesses the database to retrieve historical data and analyzes it using a machine learning model.

[0474] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0475] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[0476] 2. Adjusting the project schedule:

[0477] The user enters the project's task list and its dependencies from the terminal.

[0478] The server uses an AI model to optimize the schedule based on the input information.

[0479] The server sends the generated schedule to the user and visualizes it on the dashboard.

[0480] The emotion engine provides feedback about the schedule based on the user's emotions.

[0481] 3. Information sharing:

[0482] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[0483] The server receives the question and analyzes it using a generative AI model (OpenAI's GPT-3).

[0484] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[0485] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[0486] Example of a prompt

[0487] When is the next maintenance task?

[0488] Hardware and software used

[0489] Hardware: Smartphones, tablets, dedicated devices

[0490] software:

[0491] Python

[0492] pandas

[0493] scikit-learn

[0494] TextBlob

[0495] OpenAI's GPT-3

[0496] Database Management System (DBMS)

[0497] Thus, the present invention can streamline factory project management and improve the quality and efficiency of project management by comprehensively facilitating risk identification and countermeasures, schedule optimization, and information sharing.

[0498] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0499] Step 1:

[0500] Retrieving past project data

[0501] The server accesses the database to retrieve historical data from past projects. The user then logs into the system and requests a risk analysis. The server uses the database management system to extract the historical project data. Inputs include past project IDs and time periods, while output is the historical data.

[0502] Step 2:

[0503] Analysis of risk factors

[0504] The server passes the acquired historical data to a machine learning model for analysis. Specifically, it preprocesses the historical data and analyzes risk factors and potential problems using a scikit-learn random forest model. The input is preprocessed historical data, and the output is a list of risk factors. The server generates a risk list and notifies the user of it.

[0505] Step 3:

[0506] Task and dependency input

[0507] The user enters the project's task list and its dependencies from their device. The user uses a smartphone or tablet interface to enter detailed task information (task name, duration, resources, etc.). Input consists of task information and dependencies, while output is data sent to the server.

[0508] Step 4:

[0509] Schedule optimization

[0510] The server optimizes the schedule using an AI model based on the input task information. This process utilizes scikit-learn's SVR (Support Vector Regression) to calculate the optimal start and end times, taking into account task dependencies and resource constraints. The input consists of task and resource information, and the output is the optimized schedule.

[0511] Step 5:

[0512] Schedule notifications and visualization

[0513] The server sends the generated schedule to the user and visualizes it on a dashboard. Users can check the schedule in real time through their device. The input is an optimized schedule, and the output is visualized schedule data.

[0514] Step 6:

[0515] Accepting questions via the chat interface

[0516] Users post questions to the system using a chat interface. Users use smartphones or tablets to input questions such as, "What is the schedule for the next meeting?" The input is the user's question, and the output is the question data sent to the chat interface.

[0517] Step 7:

[0518] Question analysis and answer generation

[0519] The server receives the user's question, analyzes it using a generative AI model (OpenAI's GPT-3), and generates an appropriate answer. The server uses NLP (Natural Language Processing) techniques to understand the user's question and generate an appropriate answer. The input is the user's question, and the output is the generated answer.

[0520] Step 8:

[0521] Emotion analysis

[0522] The server uses the TextBlob library to analyze the sentiment of user comments and questions. The sentiment engine recognizes the user's emotional state and adjusts the tone of the response accordingly. The input is the user's comments and questions, and the output is the result of the sentiment analysis.

[0523] Step 9:

[0524] Response notification and emotion-based adjustment

[0525] The server adjusts the generated response to an appropriate tone based on the user's sentiment analysis results and notifies the user via the chat interface. The user can receive the response in real time. The input is the generated response and the sentiment analysis results, and the output is the adjusted response.

[0526] In this way, a system that effectively supports factory project management can be realized through the specific actions performed at each step.

[0527] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0528] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0529] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0530] [Second Embodiment]

[0531] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0532] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0533] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0534] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0535] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0536] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0537] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0538] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0539] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0540] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0541] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0542] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0543] This invention is a system for efficient project management that accesses historical databases to retrieve historical data and analyzes that data to identify risk factors and potential problems. Furthermore, it allows users to input project tasks and dependencies, optimizes the schedule based on that information, and provides it to the user. In addition, it utilizes a chat interface to respond to team members' questions in real time.

[0544] Basic System Configuration

[0545] 1. Data acquisition function

[0546] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[0547] 2. Data Analysis Function

[0548] The server passes the acquired historical data to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[0549] 3. Task Input Function

[0550] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[0551] 4. Schedule Optimization Function

[0552] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[0553] 5. Chat Interface

[0554] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[0555] Specific example

[0556] For example, when a user starts a new software development project, they can use the system by following these steps:

[0557] 1. Risk prediction and analysis

[0558] The user logs into the system and requests a risk analysis based on past project data.

[0559] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[0560] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0561] 2. Adjusting the project schedule

[0562] The user enters the project's task list and its dependencies from the terminal.

[0563] The server optimizes the schedule using an AI model based on the input information.

[0564] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[0565] 3. Information sharing

[0566] A user uses the chat interface to ask, "When is the next meeting scheduled?"

[0567] The server receives the question and analyzes it using an NLP model.

[0568] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[0569] As described above, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[0570] The following describes the processing flow.

[0571] Risk prediction and analysis

[0572] Step 1:

[0573] The server accesses the past project database to retrieve historical data. Specifically, it uses SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors encountered.

[0574] Step 2:

[0575] The server preprocesses the historical data it acquires. This involves tasks such as data cleaning, imputation of missing values, and format conversion. This preprocessing allows machine learning models to accurately analyze the data.

[0576] Step 3:

[0577] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[0578] Step 4:

[0579] The server extracts risk factors from the analysis results and compiles them into a risk list. It then scores and ranks the risk factors and prioritizes the extraction of high-risk items.

[0580] Step 5:

[0581] The server notifies the user of the risk list. The risk list is converted to JSON format and displayed on the web application's dashboard.

[0582] Adjusting the project schedule

[0583] Step 1:

[0584] The user inputs the project's task list, its dependencies, and resource information from their terminal. This includes information such as the task name, start date, end date, dependent task IDs, and required resources.

[0585] Step 2:

[0586] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[0587] Step 3:

[0588] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[0589] Step 4:

[0590] The server sends the generated schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[0591] Step 5:

[0592] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[0593] Information sharing

[0594] Step 1:

[0595] Team members (users) post questions through the chat interface. These questions include information such as project progress and the schedule for the next meeting.

[0596] Step 2:

[0597] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[0598] Step 3:

[0599] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[0600] Step 4:

[0601] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[0602] Step 5:

[0603] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[0604] (Example 1)

[0605] Next, we will describe Example 1. 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".

[0606] Traditional project management systems have struggled to efficiently utilize historical data to identify risk factors and potential problems, and to use those results to optimize project schedules. Furthermore, they lacked sufficient real-time information sharing and question-and-answer functions, hindering smooth communication among team members.

[0607] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0608] In this invention, the server includes means for accessing a past database to acquire historical data, means for inputting the acquired historical data into a machine learning model to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for optimizing scheduling using an AI model based on the input information, means for notifying the user of the generated schedule and visualizing it on a dashboard, means for receiving questions using a chat interface, means for analyzing questions with a natural language processing model to generate appropriate answers, and means for notifying the user of the generated answers via the chat interface. This makes it possible to comprehensively perform risk identification and countermeasures, schedule optimization, and information sharing in project management.

[0609] A "database" is an information system that stores and allows access to past project data.

[0610] "Historical data" refers to a set of information related to past projects, including progress, completed tasks, resources used, and risk factors encountered.

[0611] A "machine learning model" refers to an algorithm or mathematical model used to analyze historical data to identify risk factors and potential problems.

[0612] A "risk list" is a compilation of risk factors and potential problems identified by a machine learning model.

[0613] A "task" refers to a specific task or activity within a project, carried out to achieve the project's objectives.

[0614] "Dependencies" refer to the relationships between tasks within a project, indicating that one task needs to be performed only after another task has been completed.

[0615] An "AI model" refers to a generative algorithm or mathematical model used to optimize a schedule based on input task and dependency information.

[0616] "Scheduling" is the process of efficiently determining the order and timing of project tasks.

[0617] A "dashboard" is an interface that allows users to centrally view project progress and various information.

[0618] A "chat interface" is an interface that allows users and systems to communicate in real time using text.

[0619] A "natural language processing model" refers to an algorithm or mathematical model used to analyze text-based questions from users and generate appropriate answers.

[0620] This invention is a system for efficiently managing projects. The main components of the system consist of a server, terminals, and users, enabling project risk identification, schedule optimization, and real-time information sharing.

[0621] Data acquisition function

[0622] The server accesses a database of past projects. For example, the database stores completed tasks, resources used, project progress, and risk factors encountered. A database management system (e.g., MySQL, PostgreSQL) is used in this process.

[0623] Data analysis function

[0624] After acquiring the data, the server passes the acquired historical data to a machine learning model. Examples of machine learning models used include TensorFlow and PyTorch. The analysis model learns patterns in the data and identifies risk factors and potential problems. A risk list is generated and notified to the user's dashboard.

[0625] Task input function

[0626] The user inputs the project's task list, its dependencies, and resource information from a terminal. The information entered on the terminal is sent to the server and becomes the basis for scheduling.

[0627] Schedule optimization function

[0628] The server optimizes the schedule using an AI model based on the input task, dependency, and resource information. A generative AI model is applied during this process. The model takes task dependencies and resource constraints into account to generate the optimal schedule. The generated schedule is sent to the user, who can view and edit it on the dashboard.

[0629] Chat interface

[0630] Users post questions using a chat interface. The server analyzes the questions using a generative AI model and generates appropriate answers. For example, natural language processing models (e.g., GPT-3, BERT) are used at this stage. The generated answers are notified to the user in real time.

[0631] Specific example

[0632] For example, when a user starts a new software development project, they can use the system by following these steps:

[0633] 1. Risk prediction and analysis

[0634] The user logs into the system and requests a risk analysis based on past project data.

[0635] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[0636] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0637] Example of a prompt:

[0638] "Please analyze the data from the past 10 projects and tell me the risk factors."

[0639] 2. Adjusting the project schedule

[0640] The user enters the project's task list and its dependencies from the terminal.

[0641] The server optimizes the schedule using an AI model based on the input information.

[0642] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[0643] Example of a prompt:

[0644] "Please generate a project schedule based on the following task list and dependencies."

[0645] 3. Information sharing

[0646] Users use the chat interface to ask about the schedule for the next meeting.

[0647] The server analyzes the question using a natural language processing model and accesses the schedule database to retrieve information about the next meeting.

[0648] The server will notify you of the generated response via the chat interface.

[0649] Example of a prompt:

[0650] "Please let me know when the next meeting will be held."

[0651] Thus, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[0652] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0653] Step 1: The user logs into the system.

[0654] Input: The user enters their ID and password.

[0655] Specific operation: The terminal receives this and sends it to the server. The server accesses the database and verifies the entered ID and password against the authentication information in the database.

[0656] Output: If authentication is successful, the user is redirected to the dashboard. If authentication fails, an error message is displayed.

[0657] Step 2: Request a risk analysis of the user.

[0658] Input: The user clicks the "Start Risk Analysis" button on the dashboard.

[0659] Specific operation: The terminal receives the user's request and sends it to the server. The server accesses the project database and retrieves past project data.

[0660] Output: The acquired historical data is sent to the server.

[0661] Step 3: The server inputs data into the machine learning model.

[0662] Input: Acquired historical data.

[0663] Specific operation: The server inputs historical data into a machine learning model (e.g., TensorFlow or PyTorch). The model analyzes the data and identifies risk factors and potential problems.

[0664] Output: A risk list is generated as an analysis result.

[0665] Step 4: The server notifies the user of the risk list.

[0666] Input: Generated risk list.

[0667] Specific operation: The server sends the risk list to the user's dashboard. The user is then able to view the risk list.

[0668] Output: The risk list is displayed on the user's dashboard.

[0669] Step 5: The user enters the tasks and dependencies.

[0670] Input: The user enters the project task list and dependencies.

[0671] Specific operation: The terminal sends the entered data to the server. The server saves this data to the database.

[0672] Output: The task list and dependencies are saved to the database.

[0673] Step 6: The server optimizes the schedule.

[0674] Input: Saved task list and dependencies.

[0675] Specific operation: The server uses an AI model to optimize the schedule. The model generates the optimal schedule by considering task dependencies and resource constraints.

[0676] Output: Optimized schedule.

[0677] Step 7: The server notifies the user of the schedule.

[0678] Input: Generated schedule.

[0679] Specific operation: The server sends the schedule to the user, and it is displayed on the dashboard.

[0680] Output: The schedule displayed on the dashboard.

[0681] Step 8: The user posts a question in the chat interface.

[0682] Input: The user enters a question in text format via the chat interface.

[0683] Specific operation: The terminal sends a question to the server. The server has a natural language processing model (e.g., GPT-3 or BERT) analyze the question.

[0684] Output: The intent of the analyzed question.

[0685] Step 9: The server generates the answer to the question.

[0686] Input: The intent of the analyzed question.

[0687] Specific operation: The server accesses the schedule database and retrieves relevant information. Based on the retrieved information, the server generates a response and converts it to text format.

[0688] Output: Generated answer.

[0689] Step 10: The server notifies the user of the answer.

[0690] Input: Generated response.

[0691] Specific operation: The server notifies the user of the answer via the chat interface.

[0692] Output: The response displayed in the chat interface.

[0693] (Application Example 1)

[0694] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0695] In modern factories, risk management is a crucial issue alongside improving production efficiency. However, conventional factory management systems have been unable to fully utilize historical data, making it difficult to identify risks and optimize schedules. Furthermore, the lack of real-time risk management and smooth information sharing with factory staff has made it difficult to maximize the efficiency of production lines. This invention aims to solve these problems.

[0696] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0697] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, factory management means for acquiring data and identifying risk factors in real time, factory operation means for optimizing the schedule, means for inputting prompt sentences into a generation AI model based on questions to generate answers, and means for notifying factory staff of the generated answers. This enables real-time risk management, optimization of production schedules, and more efficient information sharing within the factory.

[0698] A "past database" refers to a database containing historical information about previous projects and work.

[0699] "Historical data" refers to data recorded in the past, such as the progress of a project, completed tasks, resources used, and risk factors encountered.

[0700] "Risk factors" refer to potential problems or obstacles that could hinder the progress of a project or work.

[0701] A "potential problem" refers to an element that is not currently apparent but could potentially become a problem in the future.

[0702] A "risk list" refers to a list that compiles identified risk factors and problems in a list format.

[0703] "Project tasks" refer to the specific tasks and activities necessary to move a project forward.

[0704] A "dependency" refers to a relationship in which one task depends on the completion of another task.

[0705] "Scheduling" refers to time management that involves efficiently allocating tasks and resources and proceeding in a planned manner.

[0706] A "chat interface" refers to an interface that allows users and systems to communicate in real time using text.

[0707] A "generative AI model" refers to a model that uses artificial intelligence technology to generate text and responses.

[0708] A "prompt" refers to the text input to an AI model in order to generate an appropriate response.

[0709] "Factory management methods" refer to techniques and systems for managing the operation and production processes of a factory.

[0710] "Factory operation methods" refer to the techniques and systems used to efficiently manage the overall operations of a factory.

[0711] This invention is a system aimed at efficient factory operation and risk management. This system has the ability to access historical databases to retrieve historical data, analyze it to identify risk factors and potential problems, and generate and notify users of risk lists. Furthermore, it allows users to input project tasks and dependencies, optimize scheduling based on this information, and notify users of the generated schedule. It also has a function to receive questions from factory staff in real time using a chat interface, generate appropriate answers accordingly, and notify users.

[0712] The following key hardware and software are required to implement this system.

[0713] 1. Hardware:

[0714] Factory robots (including various sensors and database access functions)

[0715] Server (for data analysis and scheduling processing)

[0716] 2. Software:

[0717] SQLite: Database Management System

[0718] scikit-learn: Machine learning library (RandomForestClassifier)

[0719] OpenAI API: AI model for generating chat interfaces

[0720] Python: A programming language

[0721] The server accesses the factory's historical database to retrieve historical data. This includes information such as project progress, completed tasks, resources used, and risk factors encountered. For analysis, machine learning models such as RandomForestClassifier from the scikit-learn library are used to identify risk factors and potential problems. The identified risk factors are generated as a risk list and notified to the user.

[0722] Next, the user inputs the project's task list, its dependencies, and resource information from their device. This input data is sent to the server, where an AI model is used to perform scheduling. After the schedule is generated, the user is notified and it is visualized on a dashboard.

[0723] The server also accepts questions from factory staff via a chat interface. For these questions, it uses a generative AI model (OpenAI API) to generate appropriate answers, prompting the user to input prompts. These answers are then notified to the factory staff in real time.

[0724] As a concrete example, the following process can be considered, which involves identifying the risk of a part of the manufacturing line failing and then developing countermeasures.

[0725] 1. Historical data acquisition: Acquire past manufacturing data.

[0726] 2. Risk Factor Analysis: Identify the risk factors.

[0727] 3. Schedule Optimization: Optimize the schedule.

[0728] 4. Chat Response: Generate responses to questions.

[0729] Examples of prompt messages include the following:

[0730] "What is the schedule for the next maintenance?"

[0731] "What is the progress on Line A?"

[0732] "What is the estimated completion date for manufacturing task B?"

[0733] These prompts enable the system to manage risks in real time, optimize production schedules, and streamline information sharing within the factory.

[0734] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0735] Step 1:

[0736] The server accesses the past database to retrieve historical data.

[0737] Specific operation: The server sends queries to the SQLite database to retrieve data such as project progress, completed tasks, resources used, and risk factors encountered.

[0738] Input: Database query request

[0739] Output: Historical data

[0740] Step 2:

[0741] The server analyzes the acquired historical data to identify risk factors and potential problems.

[0742] Specific operation: The server uses machine learning models such as RandomForestClassifier from the scikit-learn library to identify risk factors and potential problems based on historical data.

[0743] Input: Historical data

[0744] Output: Risk List

[0745] Step 3:

[0746] The server generates a risk list and notifies the user.

[0747] Specific action: The server compiles identified risk factors into a list format and updates the UI to notify the user.

[0748] Input: Risk list

[0749] Output: Updated UI

[0750] Step 4:

[0751] The user inputs the project's task list, its dependencies, and resource information from their terminal.

[0752] Specific operation: The user uses a terminal to input the necessary tasks, dependencies, and resource information through the screen interface.

[0753] Input: Task list, dependencies, resource information

[0754] Output: Input is sent to the server.

[0755] Step 5:

[0756] The server performs scheduling based on the entered task list and dependencies.

[0757] Specific operation: The server uses an AI model to consider task priorities and dependencies and generate an optimal schedule.

[0758] Input: Task list, dependencies, resource information

[0759] Output: Generated schedule

[0760] Step 6:

[0761] The server notifies the user of the generated schedule and visualizes it on the dashboard.

[0762] Specific operation: The server displays the generated schedule on the user's dashboard, making it easy for the user to check.

[0763] Input: Generated schedule

[0764] Output: Updated dashboard

[0765] Step 7:

[0766] Factory staff enter questions using a chat interface.

[0767] Specific action: Factory staff open the chat interface on their terminal and enter their question.

[0768] Input: Question from the chat interface

[0769] Output: The question is sent to the server.

[0770] Step 8:

[0771] The server uses a generative AI model to generate appropriate answers to questions.

[0772] Specific operation: The server inputs the question as a prompt into the AI ​​model (OpenAI API) and generates an appropriate answer.

[0773] Input: Questions and prompts from the chat interface.

[0774] Output: Generated answer

[0775] Step 9:

[0776] The server notifies factory staff of the generated response via a chat interface.

[0777] Specific operation: The server notifies factory staff in real time of the generated responses via a chat interface.

[0778] Input: Generated answer

[0779] Output: Chat interface updates and notifications

[0780] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0781] This invention is a system for further streamlining project management and responding to the user's psychological state. It accesses a historical database to retrieve historical data, analyzes that data to identify risk factors and potential problems, and inputs project tasks and dependencies, optimizing the schedule based on that data and providing it to the user. Furthermore, by utilizing a chat interface to respond to team members' questions in real time and combining it with an emotion engine that recognizes the user's emotions, it is possible to respond in a way that takes into account the user's psychological state during project progress and decision-making.

[0782] Basic System Configuration

[0783] 1. Data acquisition function

[0784] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[0785] 2. Data Analysis Function

[0786] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[0787] 3. Task Input Function

[0788] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[0789] 4. Schedule Optimization Function

[0790] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[0791] 5. Chat Interface

[0792] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[0793] 6. Emotional Engine

[0794] The server includes an emotion engine that recognizes user emotions. This emotion engine analyzes user interactions, comments, chat messages, etc., to understand the user's current emotional state. This improves the accuracy of risk prediction and countermeasures.

[0795] Specific example

[0796] For example, when a user starts a new software development project, they can use the system by following these steps:

[0797] 1. Risk prediction and analysis

[0798] The user logs into the system and requests a risk analysis based on past project data.

[0799] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[0800] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0801] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[0802] 2. Adjusting the project schedule

[0803] The user enters the project's task list and its dependencies from the terminal.

[0804] The server optimizes the schedule using an AI model based on the input information.

[0805] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[0806] The emotion engine provides feedback about the schedule based on the user's emotions.

[0807] 3. Information sharing

[0808] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[0809] The server receives the question and analyzes it using an NLP model.

[0810] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[0811] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[0812] As described above, the present invention can comprehensively address risk identification and countermeasures, optimize schedules, and share information in project management, and further improve the quality and efficiency of project management by taking user emotions into consideration.

[0813] The following describes the processing flow.

[0814] A process that combines risk prediction, analysis, and sentiment recognition.

[0815] Step 1:

[0816] The user logs into the system and requests a risk analysis based on past project data. Specifically, they enter the required authentication information on the login screen and click the risk analysis button.

[0817] Step 2:

[0818] The server accesses the database to retrieve historical data. Specifically, it executes SQL queries to extract information such as past project progress, completed tasks, resources used, and risk factors encountered.

[0819] Step 3:

[0820] The server preprocesses the historical data it acquires. Specifically, it performs data cleaning, imputation of missing values, and format conversion to prepare the data for analysis by machine learning models.

[0821] Step 4:

[0822] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[0823] Step 5:

[0824] The server extracts risk factors from the analysis results and compiles them into a risk list. Specifically, it scores and ranks the risk factors and prioritizes extracting high-risk items.

[0825] Step 6:

[0826] The server generates a risk list and uses an emotion engine to analyze the user's current emotional state. Specifically, it recognizes emotions from the user's past comments and current activity.

[0827] Step 7:

[0828] The server reflects the results of the emotion engine and adjusts the priority of the risk list and the notification method. For example, if the user is stressed, less urgent risk factors may be postponed.

[0829] Step 8:

[0830] The server notifies the user of the adjusted risk list. Specifically, the risk list is converted to JSON format and displayed on the web application's dashboard.

[0831] A process that combines project schedule adjustment and emotion recognition.

[0832] Step 1:

[0833] The user inputs the project's task list, its dependencies, and resource information from their device. Specifically, they enter information such as the task name, start date, end date, dependent task IDs, and required resources into an input form.

[0834] Step 2:

[0835] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[0836] Step 3:

[0837] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[0838] Step 4:

[0839] The server passes the generated schedule to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is overloaded, it might suggest distributing tasks.

[0840] Step 5:

[0841] The server sends the adjusted schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[0842] Step 6:

[0843] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[0844] A process that combines information sharing and emotion recognition.

[0845] Step 1:

[0846] Team members (users) post questions through the chat interface. For example, they might type, "When is the next meeting scheduled?"

[0847] Step 2:

[0848] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[0849] Step 3:

[0850] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[0851] Step 4:

[0852] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[0853] Step 5:

[0854] The server passes the generated response to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is anxious, the response will be provided in a calm tone.

[0855] Step 6:

[0856] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[0857] (Example 2)

[0858] Next, we will describe Example 2. 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".

[0859] In project management, identifying and managing risks, effective scheduling, and real-time information sharing are crucial elements. However, traditional systems struggled to manage these elements in an integrated manner, particularly failing to consider the emotional state of users. This led to problems such as project delays and difficulties in smooth communication among team members.

[0860] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0861] In this invention, the server includes means for accessing a database and acquiring historical data, means for analyzing the acquired data to identify risk factors and potential problems, means for inputting project tasks and dependencies, means for scheduling, means for notifying the user, means for receiving questions using a chat interface, means for generating appropriate answers, means for analyzing and recognizing the user's emotions, and means for dynamically adjusting the priority of the risk list and schedule based on the user's emotions. This enables not only risk management and schedule optimization, but also project management that takes into account the user's psychological state.

[0862] A "database" is a system for systematically storing and managing collections of data.

[0863] "Historical data" refers to data that includes information such as the progress of past projects, completed tasks, resources used, and risk factors.

[0864] "Risk factors" refer to elements or events that could potentially hinder the progress of a project.

[0865] A "potential problem" refers to an event or situation that is not currently apparent but has the potential to become a problem in the future.

[0866] A "risk list" is a compilation of analyzed risk factors in a list format.

[0867] A "task" refers to an individual task or job performed as part of a project.

[0868] A "dependency" refers to a relationship where one task depends on the start or completion of another task.

[0869] "Scheduling" refers to the act of creating a plan to efficiently allocate project tasks and resources over time.

[0870] A "chat interface" refers to a communication method that allows for the sending and receiving of messages in real time.

[0871] A "generative AI model" refers to an artificial intelligence algorithm that generates appropriate output based on user input and past data.

[0872] "Emotion recognition" is a technology that analyzes a user's emotional state and adjusts its response based on that information.

[0873] "Dynamic prioritization" refers to changing the importance of risk lists and schedules in real time based on the project status and the users' emotional state.

[0874] "Notification" refers to the act of communicating important information or results to a user.

[0875] "Terminal" refers to a computer or mobile device used by a user for operation.

[0876] This invention is a system for streamlining risk management, schedule optimization, and information sharing in project management. Furthermore, by considering the user's psychological state, it can make project progress smoother. This system consists of server, terminal, and user elements, all of which work together. The following describes each element and its specific operation.

[0877] Required hardware and software

[0878] Server: Use a server equipped with a high-performance processor and large-capacity storage.

[0879] Database management systems: Relational database management systems such as MySQL and PostgreSQL.

[0880] Machine learning libraries: TensorFlow, Scikit-learn, Pandas.

[0881] User interface: Web browser, chat interface (JavaScript framework, WebSocket).

[0882] Communication method: HTTP or HTTPS protocol between the server and the terminal.

[0883] Specific examples of data acquisition and preprocessing

[0884] The server accesses a database of past projects to retrieve historical data. This data includes project progress, completed tasks, resources used, and risk factors encountered. After retrieving the data, the Pandas library is used to cleanse the data, removing unnecessary data and imputing missing values.

[0885] Specific examples of risk analysis

[0886] The server passes the preprocessed data to machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[0887] Example of a prompt

[0888] "Please conduct a risk analysis for the new project."

[0889] Specific examples of task input and schedule optimization

[0890] Users input project task lists, dependencies, and resource information from their devices. This input data is sent to a server, where an AI model is used to perform scheduling. An optimal schedule is generated, taking into account task dependencies and resource constraints, and visualized on a dashboard.

[0891] Examples of chat interfaces and emotion recognition

[0892] When a user posts a question through the chat interface, the server uses a generative AI model to analyze the question and generate an appropriate answer. This answer is then notified to the user in real time through the chat interface. Additionally, an emotion recognition engine is used to analyze the user's emotions and dynamically adjust the priority of risk lists and schedules.

[0893] Example of a prompt

[0894] "When is the next project meeting?"

[0895] Thus, the present invention is a system that comprehensively addresses risk identification and countermeasures, schedule optimization, and information sharing in project management. Furthermore, by considering user emotions, the quality and efficiency of project management are improved.

[0896] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0897] Step 1:

[0898] Data acquisition

[0899] The server connects to the database and retrieves historical data. Specifically, it executes SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors.

[0900] Input: Database connection information and queries

[0901] Data processing: Execute SQL queries and retrieve result sets.

[0902] Output: Historical data

[0903] Step 2:

[0904] Data preprocessing

[0905] The historical data acquired by the server is preprocessed using the Python Pandas library. Specifically, this involves imputing missing values ​​and removing unnecessary data.

[0906] Input: Historical data

[0907] Data processing: Data cleansing (imputing missing values, removing unnecessary data)

[0908] Output: Preprocessed data

[0909] Step 3:

[0910] Risk analysis

[0911] The server inputs pre-processed data into machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Specifically, it uses machine learning algorithms to analyze patterns in the data and identify risk factors.

[0912] Input: Preprocessed data

[0913] Data processing: Analysis using machine learning models

[0914] Output: List of risk factors

[0915] Step 4:

[0916] Task entry

[0917] The user inputs the project's task list, dependencies, and resource information from their device and sends it to the server. Specifically, they input task information using a web form and press the "Submit" button.

[0918] Input: User's task list, dependencies, and resource information

[0919] Data processing: Send data to the server

[0920] Output: Task data

[0921] Step 5:

[0922] Schedule optimization

[0923] The server uses an AI model to schedule tasks based on the input task information. Specifically, it considers task dependencies and resource constraints to generate the optimal schedule.

[0924] Input: Task data

[0925] Data processing: Scheduling in AI models

[0926] Output: Optimized schedule

[0927] Step 6:

[0928] Notification and visualization of results

[0929] The server notifies the user of the generated schedule information and visualizes it on a dashboard. Specifically, it uses data visualization libraries such as D3.js.

[0930] Input: Optimized schedule

[0931] Data processing: Visualization of schedule information

[0932] Output: Gantt chart on the dashboard

[0933] Step 7:

[0934] Chat interface

[0935] The user enters a question into a chat box, and the server generates an appropriate answer using an AI model. Specifically, the user might type "When is the next meeting?" into the chat, and the server generates an answer and notifies the user in real time.

[0936] Input: User's question

[0937] Data processing: Analysis using NLP models, response generation.

[0938] Output: Answer on the chat interface

[0939] Step 8:

[0940] Recognition of emotions

[0941] The server runs an emotion recognition engine to understand the user's emotional state by analyzing their comments and messages. Specifically, it analyzes the user's input data and dynamically adjusts the priority of the risk list and schedule.

[0942] Input: User comments or messages

[0943] Data processing: Analysis using emotion recognition algorithms

[0944] Output: Prioritized risk list and schedule

[0945] The above outlines the specific processing steps of this system. Each step clearly indicates the input and output and provides a detailed explanation of the data processing and calculations performed.

[0946] (Application Example 2)

[0947] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0948] Traditional factory project management systems have struggled not only to streamline production processes but also to identify risk factors, optimize schedules, share information in real time, and even address the emotions of workers. Furthermore, early detection and intervention of problems are crucial, especially in production environments, and a lack of efficient project management can lead to decreased productivity and increased risks. Against this backdrop, there is a need for a system that improves the quality and efficiency of project management in factories.

[0949] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0950] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, means for recognizing the user's emotions and adjusting the tone of responses based on emotion analysis, and means for visualizing the optimal production schedule in real time and managing the factory's production process. This enables comprehensive risk identification and countermeasures, schedule optimization, and information sharing in factory project management, and further allows for responses that take user emotions into consideration.

[0951] "Historical data" refers to various types of information collected during past projects and work, including progress, completed tasks, resources used, and risk factors encountered.

[0952] A "risk list" refers to a list of risk factors extracted based on the analysis of historical data. This allows users to identify potential problems and risks in advance.

[0953] A "task" refers to an individual job or activity that needs to be performed in a project or production process. Each task is defined as a specific action or unit of work.

[0954] "Dependencies" refer to situations where multiple tasks in a project are related to each other, with one task influencing or being influenced by another. This helps manage the order and progress of tasks.

[0955] "Scheduling" refers to the process of optimally allocating and planning the timing of each task in a project or production process. This ensures the efficient use of resources and the smooth progress of the project.

[0956] A "chat interface" refers to an interactive interface that allows users to ask questions and exchange information in real time. This enables rapid communication.

[0957] "Emotional analysis" refers to the technology that recognizes and analyzes emotions and emotional states from a user's text and comments. This allows the system to respond in a way that is appropriate to the user's psychological state.

[0958] An "AI model" refers to a collection of algorithms that use artificial intelligence to solve problems and analyze data. This allows the model to learn patterns from data and provide optimal solutions.

[0959] "Visualization" refers to a technique that makes data and information easier for users to understand by displaying them graphically. This makes it easier to grasp complex information.

[0960] System Implementation Overview

[0961] This invention is a system designed to improve efficiency in factory project management and to address risk factors and the emotional state of workers. This system includes the following main functions:

[0962] Data acquisition function

[0963] The server accesses a database of past projects to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered. The software used is a database management system (DBMS) and the Python pandas library.

[0964] Data analysis function

[0965] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. This analysis uses a random forest model based on the scikit-learn library. The risk list generated based on the analysis results is then notified to the user.

[0966] Task input function

[0967] Users input project task lists, their dependencies, and resource information via their devices. This input data is sent to a server and forms the basis for scheduling. For this purpose, smartphones and tablets are expected to be used as the interface.

[0968] Schedule optimization function

[0969] The server uses an AI model to perform scheduling based on the input information. The AI ​​model used is SVR (Support Vector Regression) from the scikit-learn library. In this process, task dependencies and resource constraints are taken into consideration to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[0970] Chat interface

[0971] The system allows team members to post questions via a chat interface. The server uses a generative AI model (OpenAI's GPT-3) to analyze the questions, generate appropriate answers, and notifies users of these answers in real time via the chat interface.

[0972] Emotional Engine

[0973] The server includes an emotion engine (TextBlob library) that recognizes the user's emotions. This emotion engine analyzes the user's business negotiations, comments, chat messages, etc., to understand the user's current emotional state and adjust the priority of the risk list and the tone of responses accordingly.

[0974] Specific example

[0975] For example, when a user starts a new production project, they can use the system by following these steps:

[0976] 1. Risk prediction and analysis:

[0977] The user logs into the system and requests a risk analysis based on past project data.

[0978] The server accesses the database to retrieve historical data and analyzes it using a machine learning model.

[0979] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[0980] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[0981] 2. Adjusting the project schedule:

[0982] The user enters the project's task list and its dependencies from the terminal.

[0983] The server uses an AI model to optimize the schedule based on the input information.

[0984] The server sends the generated schedule to the user and visualizes it on the dashboard.

[0985] The emotion engine provides feedback about the schedule based on the user's emotions.

[0986] 3. Information sharing:

[0987] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[0988] The server receives the question and analyzes it using a generative AI model (OpenAI's GPT-3).

[0989] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[0990] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[0991] Example of a prompt

[0992] When is the next maintenance task?

[0993] Hardware and software used

[0994] Hardware: Smartphones, tablets, dedicated devices

[0995] software:

[0996] Python

[0997] pandas

[0998] scikit-learn

[0999] TextBlob

[1000] OpenAI's GPT-3

[1001] Database Management System (DBMS)

[1002] Thus, the present invention can streamline factory project management and improve the quality and efficiency of project management by comprehensively facilitating risk identification and countermeasures, schedule optimization, and information sharing.

[1003] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1004] Step 1:

[1005] Retrieving past project data

[1006] The server accesses the database to retrieve historical data from past projects. The user then logs into the system and requests a risk analysis. The server uses the database management system to extract the historical project data. Inputs include past project IDs and time periods, while output is the historical data.

[1007] Step 2:

[1008] Analysis of risk factors

[1009] The server passes the acquired historical data to a machine learning model for analysis. Specifically, it preprocesses the historical data and analyzes risk factors and potential problems using a scikit-learn random forest model. The input is preprocessed historical data, and the output is a list of risk factors. The server generates a risk list and notifies the user of it.

[1010] Step 3:

[1011] Task and dependency input

[1012] The user enters the project's task list and its dependencies from their device. The user uses a smartphone or tablet interface to enter detailed task information (task name, duration, resources, etc.). Input consists of task information and dependencies, while output is data sent to the server.

[1013] Step 4:

[1014] Schedule optimization

[1015] The server optimizes the schedule using an AI model based on the input task information. This process utilizes scikit-learn's SVR (Support Vector Regression) to calculate the optimal start and end times, taking into account task dependencies and resource constraints. The input consists of task and resource information, and the output is the optimized schedule.

[1016] Step 5:

[1017] Schedule notifications and visualization

[1018] The server sends the generated schedule to the user and visualizes it on a dashboard. Users can check the schedule in real time through their device. The input is an optimized schedule, and the output is visualized schedule data.

[1019] Step 6:

[1020] Accepting questions via the chat interface

[1021] Users post questions to the system using a chat interface. Users use smartphones or tablets to input questions such as, "What is the schedule for the next meeting?" The input is the user's question, and the output is the question data sent to the chat interface.

[1022] Step 7:

[1023] Question analysis and answer generation

[1024] The server receives the user's question, analyzes it using a generative AI model (OpenAI's GPT-3), and generates an appropriate answer. The server uses NLP (Natural Language Processing) techniques to understand the user's question and generate an appropriate answer. The input is the user's question, and the output is the generated answer.

[1025] Step 8:

[1026] Emotion analysis

[1027] The server uses the TextBlob library to analyze the sentiment of user comments and questions. The sentiment engine recognizes the user's emotional state and adjusts the tone of the response accordingly. The input is the user's comments and questions, and the output is the result of the sentiment analysis.

[1028] Step 9:

[1029] Response notification and emotion-based adjustment

[1030] The server adjusts the generated response to an appropriate tone based on the user's sentiment analysis results and notifies the user via the chat interface. The user can receive the response in real time. The input is the generated response and the sentiment analysis results, and the output is the adjusted response.

[1031] In this way, a system that effectively supports factory project management can be realized through the specific actions performed at each step.

[1032] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1033] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1034] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1035] [Third Embodiment]

[1036] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1037] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1038] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1039] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1040] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1041] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1042] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1043] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1044] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1045] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1046] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1047] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1048] This invention is a system for efficient project management that accesses historical databases to retrieve historical data and analyzes that data to identify risk factors and potential problems. Furthermore, it allows users to input project tasks and dependencies, optimizes the schedule based on that information, and provides it to the user. In addition, it utilizes a chat interface to respond to team members' questions in real time.

[1049] Basic System Configuration

[1050] 1. Data acquisition function

[1051] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[1052] 2. Data Analysis Function

[1053] The server passes the acquired historical data to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[1054] 3. Task Input Function

[1055] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[1056] 4. Schedule Optimization Function

[1057] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[1058] 5. Chat Interface

[1059] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[1060] Specific example

[1061] For example, when a user starts a new software development project, they can use the system by following these steps:

[1062] 1. Risk prediction and analysis

[1063] The user logs into the system and requests a risk analysis based on past project data.

[1064] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[1065] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1066] 2. Adjusting the project schedule

[1067] The user enters the project's task list and its dependencies from the terminal.

[1068] The server optimizes the schedule using an AI model based on the input information.

[1069] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[1070] 3. Information sharing

[1071] A user uses the chat interface to ask, "When is the next meeting scheduled?"

[1072] The server receives the question and analyzes it using an NLP model.

[1073] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[1074] As described above, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[1075] The following describes the processing flow.

[1076] Risk prediction and analysis

[1077] Step 1:

[1078] The server accesses the past project database to retrieve historical data. Specifically, it uses SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors encountered.

[1079] Step 2:

[1080] The server preprocesses the historical data it acquires. This involves tasks such as data cleaning, imputation of missing values, and format conversion. This preprocessing allows machine learning models to accurately analyze the data.

[1081] Step 3:

[1082] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[1083] Step 4:

[1084] The server extracts risk factors from the analysis results and compiles them into a risk list. It then scores and ranks the risk factors and prioritizes the extraction of high-risk items.

[1085] Step 5:

[1086] The server notifies the user of the risk list. The risk list is converted to JSON format and displayed on the web application's dashboard.

[1087] Adjusting the project schedule

[1088] Step 1:

[1089] The user inputs the project's task list, its dependencies, and resource information from their terminal. This includes information such as the task name, start date, end date, dependent task IDs, and required resources.

[1090] Step 2:

[1091] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[1092] Step 3:

[1093] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[1094] Step 4:

[1095] The server sends the generated schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[1096] Step 5:

[1097] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[1098] Information sharing

[1099] Step 1:

[1100] Team members (users) post questions through the chat interface. These questions include information such as project progress and the schedule for the next meeting.

[1101] Step 2:

[1102] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[1103] Step 3:

[1104] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[1105] Step 4:

[1106] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[1107] Step 5:

[1108] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[1109] (Example 1)

[1110] Next, we will describe Example 1. 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."

[1111] Traditional project management systems have struggled to efficiently utilize historical data to identify risk factors and potential problems, and to use those results to optimize project schedules. Furthermore, they lacked sufficient real-time information sharing and question-and-answer functions, hindering smooth communication among team members.

[1112] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1113] In this invention, the server includes means for accessing a past database to acquire historical data, means for inputting the acquired historical data into a machine learning model to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for optimizing scheduling using an AI model based on the input information, means for notifying the user of the generated schedule and visualizing it on a dashboard, means for receiving questions using a chat interface, means for analyzing questions with a natural language processing model to generate appropriate answers, and means for notifying the user of the generated answers via the chat interface. This makes it possible to comprehensively perform risk identification and countermeasures, schedule optimization, and information sharing in project management.

[1114] A "database" is an information system that stores and allows access to past project data.

[1115] "Historical data" refers to a set of information related to past projects, including progress, completed tasks, resources used, and risk factors encountered.

[1116] A "machine learning model" refers to an algorithm or mathematical model used to analyze historical data to identify risk factors and potential problems.

[1117] A "risk list" is a compilation of risk factors and potential problems identified by a machine learning model.

[1118] A "task" refers to a specific task or activity within a project, carried out to achieve the project's objectives.

[1119] "Dependencies" refer to the relationships between tasks within a project, indicating that one task needs to be performed only after another task has been completed.

[1120] An "AI model" refers to a generative algorithm or mathematical model used to optimize a schedule based on input task and dependency information.

[1121] "Scheduling" is the process of efficiently determining the order and timing of project tasks.

[1122] A "dashboard" is an interface that allows users to centrally view project progress and various information.

[1123] A "chat interface" is an interface that allows users and systems to communicate in real time using text.

[1124] A "natural language processing model" refers to an algorithm or mathematical model used to analyze text-based questions from users and generate appropriate answers.

[1125] This invention is a system for efficiently managing projects. The main components of the system consist of a server, terminals, and users, enabling project risk identification, schedule optimization, and real-time information sharing.

[1126] Data acquisition function

[1127] The server accesses a database of past projects. For example, the database stores completed tasks, resources used, project progress, and risk factors encountered. A database management system (e.g., MySQL, PostgreSQL) is used in this process.

[1128] Data analysis function

[1129] After acquiring the data, the server passes the acquired historical data to a machine learning model. Examples of machine learning models used include TensorFlow and PyTorch. The analysis model learns patterns in the data and identifies risk factors and potential problems. A risk list is generated and notified to the user's dashboard.

[1130] Task input function

[1131] The user inputs the project's task list, its dependencies, and resource information from a terminal. The information entered on the terminal is sent to the server and becomes the basis for scheduling.

[1132] Schedule optimization function

[1133] The server optimizes the schedule using an AI model based on the input task, dependency, and resource information. A generative AI model is applied during this process. The model takes task dependencies and resource constraints into account to generate the optimal schedule. The generated schedule is sent to the user, who can view and edit it on the dashboard.

[1134] Chat interface

[1135] Users post questions using a chat interface. The server analyzes the questions using a generative AI model and generates appropriate answers. For example, natural language processing models (e.g., GPT-3, BERT) are used at this stage. The generated answers are notified to the user in real time.

[1136] Specific example

[1137] For example, when a user starts a new software development project, they can use the system by following these steps:

[1138] 1. Risk prediction and analysis

[1139] The user logs into the system and requests a risk analysis based on past project data.

[1140] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[1141] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1142] Example of a prompt:

[1143] "Please analyze the data from the past 10 projects and tell me the risk factors."

[1144] 2. Adjusting the project schedule

[1145] The user enters the project's task list and its dependencies from the terminal.

[1146] The server optimizes the schedule using an AI model based on the input information.

[1147] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[1148] Example of a prompt:

[1149] "Please generate a project schedule based on the following task list and dependencies."

[1150] 3. Information sharing

[1151] Users use the chat interface to ask about the schedule for the next meeting.

[1152] The server analyzes the question using a natural language processing model and accesses the schedule database to retrieve information about the next meeting.

[1153] The server will notify you of the generated response via the chat interface.

[1154] Example of a prompt:

[1155] "Please let me know when the next meeting will be held."

[1156] Thus, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[1157] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1158] Step 1: The user logs into the system.

[1159] Input: The user enters their ID and password.

[1160] Specific operation: The terminal receives this and sends it to the server. The server accesses the database and verifies the entered ID and password against the authentication information in the database.

[1161] Output: If authentication is successful, the user is redirected to the dashboard. If authentication fails, an error message is displayed.

[1162] Step 2: Request a risk analysis of the user.

[1163] Input: The user clicks the "Start Risk Analysis" button on the dashboard.

[1164] Specific operation: The terminal receives the user's request and sends it to the server. The server accesses the project database and retrieves past project data.

[1165] Output: The acquired historical data is sent to the server.

[1166] Step 3: The server inputs data into the machine learning model.

[1167] Input: Acquired historical data.

[1168] Specific operation: The server inputs historical data into a machine learning model (e.g., TensorFlow or PyTorch). The model analyzes the data and identifies risk factors and potential problems.

[1169] Output: A risk list is generated as an analysis result.

[1170] Step 4: The server notifies the user of the risk list.

[1171] Input: Generated risk list.

[1172] Specific operation: The server sends the risk list to the user's dashboard. The user is then able to view the risk list.

[1173] Output: The risk list is displayed on the user's dashboard.

[1174] Step 5: The user enters the tasks and dependencies.

[1175] Input: The user enters the project task list and dependencies.

[1176] Specific operation: The terminal sends the entered data to the server. The server saves this data to the database.

[1177] Output: The task list and dependencies are saved to the database.

[1178] Step 6: The server optimizes the schedule.

[1179] Input: Saved task list and dependencies.

[1180] Specific operation: The server uses an AI model to optimize the schedule. The model generates the optimal schedule by considering task dependencies and resource constraints.

[1181] Output: Optimized schedule.

[1182] Step 7: The server notifies the user of the schedule.

[1183] Input: Generated schedule.

[1184] Specific operation: The server sends the schedule to the user, and it is displayed on the dashboard.

[1185] Output: The schedule displayed on the dashboard.

[1186] Step 8: The user posts a question in the chat interface.

[1187] Input: The user enters a question in text format via the chat interface.

[1188] Specific operation: The terminal sends a question to the server. The server has a natural language processing model (e.g., GPT-3 or BERT) analyze the question.

[1189] Output: The intent of the analyzed question.

[1190] Step 9: The server generates the answer to the question.

[1191] Input: The intent of the analyzed question.

[1192] Specific operation: The server accesses the schedule database and retrieves relevant information. Based on the retrieved information, the server generates a response and converts it to text format.

[1193] Output: Generated answer.

[1194] Step 10: The server notifies the user of the answer.

[1195] Input: Generated response.

[1196] Specific operation: The server notifies the user of the answer via the chat interface.

[1197] Output: The response displayed in the chat interface.

[1198] (Application Example 1)

[1199] Next, we will explain Application Example 1. In the following explanation, 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."

[1200] In modern factories, risk management is a crucial issue alongside improving production efficiency. However, conventional factory management systems have been unable to fully utilize historical data, making it difficult to identify risks and optimize schedules. Furthermore, the lack of real-time risk management and smooth information sharing with factory staff has made it difficult to maximize the efficiency of production lines. This invention aims to solve these problems.

[1201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1202] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, factory management means for acquiring data and identifying risk factors in real time, factory operation means for optimizing the schedule, means for inputting prompt sentences into a generation AI model based on questions to generate answers, and means for notifying factory staff of the generated answers. This enables real-time risk management, optimization of production schedules, and more efficient information sharing within the factory.

[1203] A "past database" refers to a database containing historical information about previous projects and work.

[1204] "Historical data" refers to data recorded in the past, such as the progress of a project, completed tasks, resources used, and risk factors encountered.

[1205] "Risk factors" refer to potential problems or obstacles that could hinder the progress of a project or work.

[1206] A "potential problem" refers to an element that is not currently apparent but could potentially become a problem in the future.

[1207] A "risk list" refers to a list that compiles identified risk factors and problems in a list format.

[1208] "Project tasks" refer to the specific tasks and activities necessary to move a project forward.

[1209] A "dependency" refers to a relationship in which one task depends on the completion of another task.

[1210] "Scheduling" refers to time management that involves efficiently allocating tasks and resources and proceeding in a planned manner.

[1211] A "chat interface" refers to an interface that allows users and systems to communicate in real time using text.

[1212] A "generative AI model" refers to a model that uses artificial intelligence technology to generate text and responses.

[1213] A "prompt" refers to the text input to an AI model in order to generate an appropriate response.

[1214] "Factory management methods" refer to techniques and systems for managing the operation and production processes of a factory.

[1215] "Factory operation methods" refer to the techniques and systems used to efficiently manage the overall operations of a factory.

[1216] This invention is a system aimed at efficient factory operation and risk management. This system has the ability to access historical databases to retrieve historical data, analyze it to identify risk factors and potential problems, and generate and notify users of risk lists. Furthermore, it allows users to input project tasks and dependencies, optimize scheduling based on this information, and notify users of the generated schedule. It also has a function to receive questions from factory staff in real time using a chat interface, generate appropriate answers accordingly, and notify users.

[1217] The following key hardware and software are required to implement this system.

[1218] 1. Hardware:

[1219] Factory robots (including various sensors and database access functions)

[1220] Server (for data analysis and scheduling processing)

[1221] 2. Software:

[1222] SQLite: Database Management System

[1223] scikit-learn: Machine learning library (RandomForestClassifier)

[1224] OpenAI API: AI model for generating chat interfaces

[1225] Python: A programming language

[1226] The server accesses the factory's historical database to retrieve historical data. This includes information such as project progress, completed tasks, resources used, and risk factors encountered. For analysis, machine learning models such as RandomForestClassifier from the scikit-learn library are used to identify risk factors and potential problems. The identified risk factors are generated as a risk list and notified to the user.

[1227] Next, the user inputs the project's task list, its dependencies, and resource information from their device. This input data is sent to the server, where an AI model is used to perform scheduling. After the schedule is generated, the user is notified and it is visualized on a dashboard.

[1228] The server also accepts questions from factory staff via a chat interface. For these questions, it uses a generative AI model (OpenAI API) to generate appropriate answers, prompting the user to input prompts. These answers are then notified to the factory staff in real time.

[1229] As a concrete example, the following process can be considered, which involves identifying the risk of a part of the manufacturing line failing and then developing countermeasures.

[1230] 1. Historical data acquisition: Acquire past manufacturing data.

[1231] 2. Risk Factor Analysis: Identify the risk factors.

[1232] 3. Schedule Optimization: Optimize the schedule.

[1233] 4. Chat Response: Generate responses to questions.

[1234] Examples of prompt messages include the following:

[1235] "What is the schedule for the next maintenance?"

[1236] "What is the progress on Line A?"

[1237] "What is the estimated completion date for manufacturing task B?"

[1238] These prompts enable the system to manage risks in real time, optimize production schedules, and streamline information sharing within the factory.

[1239] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1240] Step 1:

[1241] The server accesses the past database to retrieve historical data.

[1242] Specific operation: The server sends queries to the SQLite database to retrieve data such as project progress, completed tasks, resources used, and risk factors encountered.

[1243] Input: Database query request

[1244] Output: Historical data

[1245] Step 2:

[1246] The server analyzes the acquired historical data to identify risk factors and potential problems.

[1247] Specific operation: The server uses machine learning models such as RandomForestClassifier from the scikit-learn library to identify risk factors and potential problems based on historical data.

[1248] Input: Historical data

[1249] Output: Risk List

[1250] Step 3:

[1251] The server generates a risk list and notifies the user.

[1252] Specific action: The server compiles identified risk factors into a list format and updates the UI to notify the user.

[1253] Input: Risk list

[1254] Output: Updated UI

[1255] Step 4:

[1256] The user inputs the project's task list, its dependencies, and resource information from their terminal.

[1257] Specific operation: The user uses a terminal to input the necessary tasks, dependencies, and resource information through the screen interface.

[1258] Input: Task list, dependencies, resource information

[1259] Output: Input is sent to the server.

[1260] Step 5:

[1261] The server performs scheduling based on the entered task list and dependencies.

[1262] Specific operation: The server uses an AI model to consider task priorities and dependencies and generate an optimal schedule.

[1263] Input: Task list, dependencies, resource information

[1264] Output: Generated schedule

[1265] Step 6:

[1266] The server notifies the user of the generated schedule and visualizes it on the dashboard.

[1267] Specific operation: The server displays the generated schedule on the user's dashboard, making it easy for the user to check.

[1268] Input: Generated schedule

[1269] Output: Updated dashboard

[1270] Step 7:

[1271] Factory staff enter questions using a chat interface.

[1272] Specific action: Factory staff open the chat interface on their terminal and enter their question.

[1273] Input: Question from the chat interface

[1274] Output: The question is sent to the server.

[1275] Step 8:

[1276] The server uses a generative AI model to generate appropriate answers to questions.

[1277] Specific operation: The server inputs the question as a prompt into the AI ​​model (OpenAI API) and generates an appropriate answer.

[1278] Input: Questions and prompts from the chat interface.

[1279] Output: Generated answer

[1280] Step 9:

[1281] The server notifies factory staff of the generated response via a chat interface.

[1282] Specific operation: The server notifies factory staff in real time of the generated responses via a chat interface.

[1283] Input: Generated answer

[1284] Output: Chat interface updates and notifications

[1285] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1286] This invention is a system for further streamlining project management and responding to the user's psychological state. It accesses a historical database to retrieve historical data, analyzes that data to identify risk factors and potential problems, and inputs project tasks and dependencies, optimizing the schedule based on that data and providing it to the user. Furthermore, by utilizing a chat interface to respond to team members' questions in real time and combining it with an emotion engine that recognizes the user's emotions, it is possible to respond in a way that takes into account the user's psychological state during project progress and decision-making.

[1287] Basic System Configuration

[1288] 1. Data acquisition function

[1289] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[1290] 2. Data Analysis Function

[1291] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[1292] 3. Task Input Function

[1293] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[1294] 4. Schedule Optimization Function

[1295] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[1296] 5. Chat Interface

[1297] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[1298] 6. Emotional Engine

[1299] The server includes an emotion engine that recognizes user emotions. This emotion engine analyzes user interactions, comments, chat messages, etc., to understand the user's current emotional state. This improves the accuracy of risk prediction and countermeasures.

[1300] Specific example

[1301] For example, when a user starts a new software development project, they can use the system by following these steps:

[1302] 1. Risk prediction and analysis

[1303] The user logs into the system and requests a risk analysis based on past project data.

[1304] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[1305] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1306] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[1307] 2. Adjusting the project schedule

[1308] The user enters the project's task list and its dependencies from the terminal.

[1309] The server optimizes the schedule using an AI model based on the input information.

[1310] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[1311] The emotion engine provides feedback about the schedule based on the user's emotions.

[1312] 3. Information sharing

[1313] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[1314] The server receives the question and analyzes it using an NLP model.

[1315] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[1316] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[1317] As described above, the present invention can comprehensively address risk identification and countermeasures, optimize schedules, and share information in project management, and further improve the quality and efficiency of project management by taking user emotions into consideration.

[1318] The following describes the processing flow.

[1319] A process that combines risk prediction, analysis, and sentiment recognition.

[1320] Step 1:

[1321] The user logs into the system and requests a risk analysis based on past project data. Specifically, they enter the required authentication information on the login screen and click the risk analysis button.

[1322] Step 2:

[1323] The server accesses the database to retrieve historical data. Specifically, it executes SQL queries to extract information such as past project progress, completed tasks, resources used, and risk factors encountered.

[1324] Step 3:

[1325] The server preprocesses the historical data it acquires. Specifically, it performs data cleaning, imputation of missing values, and format conversion to prepare the data for analysis by machine learning models.

[1326] Step 4:

[1327] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[1328] Step 5:

[1329] The server extracts risk factors from the analysis results and compiles them into a risk list. Specifically, it scores and ranks the risk factors and prioritizes extracting high-risk items.

[1330] Step 6:

[1331] The server generates a risk list and uses an emotion engine to analyze the user's current emotional state. Specifically, it recognizes emotions from the user's past comments and current activity.

[1332] Step 7:

[1333] The server reflects the results of the emotion engine and adjusts the priority of the risk list and the notification method. For example, if the user is stressed, less urgent risk factors may be postponed.

[1334] Step 8:

[1335] The server notifies the user of the adjusted risk list. Specifically, the risk list is converted to JSON format and displayed on the web application's dashboard.

[1336] A process that combines project schedule adjustment and emotion recognition.

[1337] Step 1:

[1338] The user inputs the project's task list, its dependencies, and resource information from their device. Specifically, they enter information such as the task name, start date, end date, dependent task IDs, and required resources into an input form.

[1339] Step 2:

[1340] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[1341] Step 3:

[1342] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[1343] Step 4:

[1344] The server passes the generated schedule to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is overloaded, it might suggest distributing tasks.

[1345] Step 5:

[1346] The server sends the adjusted schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[1347] Step 6:

[1348] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[1349] A process that combines information sharing and emotion recognition.

[1350] Step 1:

[1351] Team members (users) post questions through the chat interface. For example, they might type, "When is the next meeting scheduled?"

[1352] Step 2:

[1353] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[1354] Step 3:

[1355] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[1356] Step 4:

[1357] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[1358] Step 5:

[1359] The server passes the generated response to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is anxious, the response will be provided in a calm tone.

[1360] Step 6:

[1361] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[1362] (Example 2)

[1363] Next, we will describe Example 2. 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."

[1364] In project management, identifying and managing risks, effective scheduling, and real-time information sharing are crucial elements. However, traditional systems struggled to manage these elements in an integrated manner, particularly failing to consider the emotional state of users. This led to problems such as project delays and difficulties in smooth communication among team members.

[1365] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1366] In this invention, the server includes means for accessing a database and acquiring historical data, means for analyzing the acquired data to identify risk factors and potential problems, means for inputting project tasks and dependencies, means for scheduling, means for notifying the user, means for receiving questions using a chat interface, means for generating appropriate answers, means for analyzing and recognizing the user's emotions, and means for dynamically adjusting the priority of the risk list and schedule based on the user's emotions. This enables not only risk management and schedule optimization, but also project management that takes into account the user's psychological state.

[1367] A "database" is a system for systematically storing and managing collections of data.

[1368] "Historical data" refers to data that includes information such as the progress of past projects, completed tasks, resources used, and risk factors.

[1369] "Risk factors" refer to elements or events that could potentially hinder the progress of a project.

[1370] A "potential problem" refers to an event or situation that is not currently apparent but has the potential to become a problem in the future.

[1371] A "risk list" is a compilation of analyzed risk factors in a list format.

[1372] A "task" refers to an individual task or job performed as part of a project.

[1373] A "dependency" refers to a relationship where one task depends on the start or completion of another task.

[1374] "Scheduling" refers to the act of creating a plan to efficiently allocate project tasks and resources over time.

[1375] A "chat interface" refers to a communication method that allows for the sending and receiving of messages in real time.

[1376] A "generative AI model" refers to an artificial intelligence algorithm that generates appropriate output based on user input and past data.

[1377] "Emotion recognition" is a technology that analyzes a user's emotional state and adjusts its response based on that information.

[1378] "Dynamic prioritization" refers to changing the importance of risk lists and schedules in real time based on the project status and the users' emotional state.

[1379] "Notification" refers to the act of communicating important information or results to a user.

[1380] "Terminal" refers to a computer or mobile device used by a user for operation.

[1381] This invention is a system for streamlining risk management, schedule optimization, and information sharing in project management. Furthermore, by considering the user's psychological state, it can make project progress smoother. This system consists of server, terminal, and user elements, all of which work together. The following describes each element and its specific operation.

[1382] Required hardware and software

[1383] Server: Use a server equipped with a high-performance processor and large-capacity storage.

[1384] Database management systems: Relational database management systems such as MySQL and PostgreSQL.

[1385] Machine learning libraries: TensorFlow, Scikit-learn, Pandas.

[1386] User interface: Web browser, chat interface (JavaScript framework, WebSocket).

[1387] Communication method: HTTP or HTTPS protocol between the server and the terminal.

[1388] Specific examples of data acquisition and preprocessing

[1389] The server accesses a database of past projects to retrieve historical data. This data includes project progress, completed tasks, resources used, and risk factors encountered. After retrieving the data, the Pandas library is used to cleanse the data, removing unnecessary data and imputing missing values.

[1390] Specific examples of risk analysis

[1391] The server passes the preprocessed data to machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[1392] Example of a prompt

[1393] "Please conduct a risk analysis for the new project."

[1394] Specific examples of task input and schedule optimization

[1395] Users input project task lists, dependencies, and resource information from their devices. This input data is sent to a server, where an AI model is used to perform scheduling. An optimal schedule is generated, taking into account task dependencies and resource constraints, and visualized on a dashboard.

[1396] Examples of chat interfaces and emotion recognition

[1397] When a user posts a question through the chat interface, the server uses a generative AI model to analyze the question and generate an appropriate answer. This answer is then notified to the user in real time through the chat interface. Additionally, an emotion recognition engine is used to analyze the user's emotions and dynamically adjust the priority of risk lists and schedules.

[1398] Example of a prompt

[1399] "When is the next project meeting?"

[1400] Thus, the present invention is a system that comprehensively addresses risk identification and countermeasures, schedule optimization, and information sharing in project management. Furthermore, by considering user emotions, the quality and efficiency of project management are improved.

[1401] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1402] Step 1:

[1403] Data acquisition

[1404] The server connects to the database and retrieves historical data. Specifically, it executes SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors.

[1405] Input: Database connection information and queries

[1406] Data processing: Execute SQL queries and retrieve result sets.

[1407] Output: Historical data

[1408] Step 2:

[1409] Data preprocessing

[1410] The historical data acquired by the server is preprocessed using the Python Pandas library. Specifically, this involves imputing missing values ​​and removing unnecessary data.

[1411] Input: Historical data

[1412] Data processing: Data cleansing (imputing missing values, removing unnecessary data)

[1413] Output: Preprocessed data

[1414] Step 3:

[1415] Risk analysis

[1416] The server inputs pre-processed data into machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Specifically, it uses machine learning algorithms to analyze patterns in the data and identify risk factors.

[1417] Input: Preprocessed data

[1418] Data processing: Analysis using machine learning models

[1419] Output: List of risk factors

[1420] Step 4:

[1421] Task entry

[1422] The user inputs the project's task list, dependencies, and resource information from their device and sends it to the server. Specifically, they input task information using a web form and press the "Submit" button.

[1423] Input: User's task list, dependencies, and resource information

[1424] Data processing: Send data to the server

[1425] Output: Task data

[1426] Step 5:

[1427] Schedule optimization

[1428] The server uses an AI model to schedule tasks based on the input task information. Specifically, it considers task dependencies and resource constraints to generate the optimal schedule.

[1429] Input: Task data

[1430] Data processing: Scheduling in AI models

[1431] Output: Optimized schedule

[1432] Step 6:

[1433] Notification and visualization of results

[1434] The server notifies the user of the generated schedule information and visualizes it on a dashboard. Specifically, it uses data visualization libraries such as D3.js.

[1435] Input: Optimized schedule

[1436] Data processing: Visualization of schedule information

[1437] Output: Gantt chart on the dashboard

[1438] Step 7:

[1439] Chat interface

[1440] The user enters a question into a chat box, and the server generates an appropriate answer using an AI model. Specifically, the user might type "When is the next meeting?" into the chat, and the server generates an answer and notifies the user in real time.

[1441] Input: User's question

[1442] Data processing: Analysis using NLP models, response generation.

[1443] Output: Answer on the chat interface

[1444] Step 8:

[1445] Recognition of emotions

[1446] The server runs an emotion recognition engine to understand the user's emotional state by analyzing their comments and messages. Specifically, it analyzes the user's input data and dynamically adjusts the priority of the risk list and schedule.

[1447] Input: User comments or messages

[1448] Data processing: Analysis using emotion recognition algorithms

[1449] Output: Prioritized risk list and schedule

[1450] The above outlines the specific processing steps of this system. Each step clearly indicates the input and output and provides a detailed explanation of the data processing and calculations performed.

[1451] (Application Example 2)

[1452] Next, we will explain application example 2. In the following explanation, 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."

[1453] Traditional factory project management systems have struggled not only to streamline production processes but also to identify risk factors, optimize schedules, share information in real time, and even address the emotions of workers. Furthermore, early detection and intervention of problems are crucial, especially in production environments, and a lack of efficient project management can lead to decreased productivity and increased risks. Against this backdrop, there is a need for a system that improves the quality and efficiency of project management in factories.

[1454] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1455] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, means for recognizing the user's emotions and adjusting the tone of responses based on emotion analysis, and means for visualizing the optimal production schedule in real time and managing the factory's production process. This enables comprehensive risk identification and countermeasures, schedule optimization, and information sharing in factory project management, and further allows for responses that take user emotions into consideration.

[1456] "Historical data" refers to various types of information collected during past projects and work, including progress, completed tasks, resources used, and risk factors encountered.

[1457] A "risk list" refers to a list of risk factors extracted based on the analysis of historical data. This allows users to identify potential problems and risks in advance.

[1458] A "task" refers to an individual job or activity that needs to be performed in a project or production process. Each task is defined as a specific action or unit of work.

[1459] "Dependencies" refer to situations where multiple tasks in a project are related to each other, with one task influencing or being influenced by another. This helps manage the order and progress of tasks.

[1460] "Scheduling" refers to the process of optimally allocating and planning the timing of each task in a project or production process. This ensures the efficient use of resources and the smooth progress of the project.

[1461] A "chat interface" refers to an interactive interface that allows users to ask questions and exchange information in real time. This enables rapid communication.

[1462] "Emotional analysis" refers to the technology that recognizes and analyzes emotions and emotional states from a user's text and comments. This allows the system to respond in a way that is appropriate to the user's psychological state.

[1463] An "AI model" refers to a collection of algorithms that use artificial intelligence to solve problems and analyze data. This allows the model to learn patterns from data and provide optimal solutions.

[1464] "Visualization" refers to a technique that makes data and information easier for users to understand by displaying them graphically. This makes it easier to grasp complex information.

[1465] System Implementation Overview

[1466] This invention is a system designed to improve efficiency in factory project management and to address risk factors and the emotional state of workers. This system includes the following main functions:

[1467] Data acquisition function

[1468] The server accesses a database of past projects to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered. The software used is a database management system (DBMS) and the Python pandas library.

[1469] Data analysis function

[1470] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. This analysis uses a random forest model based on the scikit-learn library. The risk list generated based on the analysis results is then notified to the user.

[1471] Task input function

[1472] Users input project task lists, their dependencies, and resource information via their devices. This input data is sent to a server and forms the basis for scheduling. For this purpose, smartphones and tablets are expected to be used as the interface.

[1473] Schedule optimization function

[1474] The server uses an AI model to perform scheduling based on the input information. The AI ​​model used is SVR (Support Vector Regression) from the scikit-learn library. In this process, task dependencies and resource constraints are taken into consideration to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[1475] Chat interface

[1476] The system allows team members to post questions via a chat interface. The server uses a generative AI model (OpenAI's GPT-3) to analyze the questions, generate appropriate answers, and notifies users of these answers in real time via the chat interface.

[1477] Emotional Engine

[1478] The server includes an emotion engine (TextBlob library) that recognizes the user's emotions. This emotion engine analyzes the user's business negotiations, comments, chat messages, etc., to understand the user's current emotional state and adjust the priority of the risk list and the tone of responses accordingly.

[1479] Specific example

[1480] For example, when a user starts a new production project, they can use the system by following these steps:

[1481] 1. Risk prediction and analysis:

[1482] The user logs into the system and requests a risk analysis based on past project data.

[1483] The server accesses the database to retrieve historical data and analyzes it using a machine learning model.

[1484] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1485] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[1486] 2. Adjusting the project schedule:

[1487] The user enters the project's task list and its dependencies from the terminal.

[1488] The server uses an AI model to optimize the schedule based on the input information.

[1489] The server sends the generated schedule to the user and visualizes it on the dashboard.

[1490] The emotion engine provides feedback about the schedule based on the user's emotions.

[1491] 3. Information sharing:

[1492] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[1493] The server receives the question and analyzes it using a generative AI model (OpenAI's GPT-3).

[1494] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[1495] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[1496] Example of a prompt

[1497] When is the next maintenance task?

[1498] Hardware and software used

[1499] Hardware: Smartphones, tablets, dedicated devices

[1500] software:

[1501] Python

[1502] pandas

[1503] scikit-learn

[1504] TextBlob

[1505] OpenAI's GPT-3

[1506] Database Management System (DBMS)

[1507] Thus, the present invention can streamline factory project management and improve the quality and efficiency of project management by comprehensively facilitating risk identification and countermeasures, schedule optimization, and information sharing.

[1508] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1509] Step 1:

[1510] Retrieving past project data

[1511] The server accesses the database to retrieve historical data from past projects. The user then logs into the system and requests a risk analysis. The server uses the database management system to extract the historical project data. Inputs include past project IDs and time periods, while output is the historical data.

[1512] Step 2:

[1513] Analysis of risk factors

[1514] The server passes the acquired historical data to a machine learning model for analysis. Specifically, it preprocesses the historical data and analyzes risk factors and potential problems using a scikit-learn random forest model. The input is preprocessed historical data, and the output is a list of risk factors. The server generates a risk list and notifies the user of it.

[1515] Step 3:

[1516] Task and dependency input

[1517] The user enters the project's task list and its dependencies from their device. The user uses a smartphone or tablet interface to enter detailed task information (task name, duration, resources, etc.). Input consists of task information and dependencies, while output is data sent to the server.

[1518] Step 4:

[1519] Schedule optimization

[1520] The server optimizes the schedule using an AI model based on the input task information. This process utilizes scikit-learn's SVR (Support Vector Regression) to calculate the optimal start and end times, taking into account task dependencies and resource constraints. The input consists of task and resource information, and the output is the optimized schedule.

[1521] Step 5:

[1522] Schedule notifications and visualization

[1523] The server sends the generated schedule to the user and visualizes it on a dashboard. Users can check the schedule in real time through their device. The input is an optimized schedule, and the output is visualized schedule data.

[1524] Step 6:

[1525] Accepting questions via the chat interface

[1526] Users post questions to the system using a chat interface. Users use smartphones or tablets to input questions such as, "What is the schedule for the next meeting?" The input is the user's question, and the output is the question data sent to the chat interface.

[1527] Step 7:

[1528] Question analysis and answer generation

[1529] The server receives the user's question, analyzes it using a generative AI model (OpenAI's GPT-3), and generates an appropriate answer. The server uses NLP (Natural Language Processing) techniques to understand the user's question and generate an appropriate answer. The input is the user's question, and the output is the generated answer.

[1530] Step 8:

[1531] Emotion analysis

[1532] The server uses the TextBlob library to analyze the sentiment of user comments and questions. The sentiment engine recognizes the user's emotional state and adjusts the tone of the response accordingly. The input is the user's comments and questions, and the output is the result of the sentiment analysis.

[1533] Step 9:

[1534] Response notification and emotion-based adjustment

[1535] The server adjusts the generated response to an appropriate tone based on the user's sentiment analysis results and notifies the user via the chat interface. The user can receive the response in real time. The input is the generated response and the sentiment analysis results, and the output is the adjusted response.

[1536] In this way, a system that effectively supports factory project management can be realized through the specific actions performed at each step.

[1537] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1538] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1539] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1540] [Fourth Embodiment]

[1541] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1542] As shown in Figure 7, the 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.

[1543] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1544] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1545] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1546] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1547] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1548] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1549] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1550] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1551] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1552] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1553] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1554] This invention is a system for efficient project management that accesses historical databases to retrieve historical data and analyzes that data to identify risk factors and potential problems. Furthermore, it allows users to input project tasks and dependencies, optimizes the schedule based on that information, and provides it to the user. In addition, it utilizes a chat interface to respond to team members' questions in real time.

[1555] Basic System Configuration

[1556] 1. Data acquisition function

[1557] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[1558] 2. Data Analysis Function

[1559] The server passes the acquired historical data to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[1560] 3. Task Input Function

[1561] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[1562] 4. Schedule Optimization Function

[1563] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[1564] 5. Chat Interface

[1565] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[1566] Specific example

[1567] For example, when a user starts a new software development project, they can use the system by following these steps:

[1568] 1. Risk prediction and analysis

[1569] The user logs into the system and requests a risk analysis based on past project data.

[1570] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[1571] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1572] 2. Adjusting the project schedule

[1573] The user enters the project's task list and its dependencies from the terminal.

[1574] The server optimizes the schedule using an AI model based on the input information.

[1575] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[1576] 3. Information sharing

[1577] A user uses the chat interface to ask, "When is the next meeting scheduled?"

[1578] The server receives the question and analyzes it using an NLP model.

[1579] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[1580] As described above, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[1581] The following describes the processing flow.

[1582] Risk prediction and analysis

[1583] Step 1:

[1584] The server accesses the past project database to retrieve historical data. Specifically, it uses SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors encountered.

[1585] Step 2:

[1586] The server preprocesses the historical data it acquires. This involves tasks such as data cleaning, imputation of missing values, and format conversion. This preprocessing allows machine learning models to accurately analyze the data.

[1587] Step 3:

[1588] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[1589] Step 4:

[1590] The server extracts risk factors from the analysis results and compiles them into a risk list. It then scores and ranks the risk factors and prioritizes the extraction of high-risk items.

[1591] Step 5:

[1592] The server notifies the user of the risk list. The risk list is converted to JSON format and displayed on the web application's dashboard.

[1593] Adjusting the project schedule

[1594] Step 1:

[1595] The user inputs the project's task list, its dependencies, and resource information from their terminal. This includes information such as the task name, start date, end date, dependent task IDs, and required resources.

[1596] Step 2:

[1597] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[1598] Step 3:

[1599] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[1600] Step 4:

[1601] The server sends the generated schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[1602] Step 5:

[1603] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[1604] Information sharing

[1605] Step 1:

[1606] Team members (users) post questions through the chat interface. These questions include information such as project progress and the schedule for the next meeting.

[1607] Step 2:

[1608] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[1609] Step 3:

[1610] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[1611] Step 4:

[1612] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[1613] Step 5:

[1614] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[1615] (Example 1)

[1616] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1617] Traditional project management systems have struggled to efficiently utilize historical data to identify risk factors and potential problems, and to use those results to optimize project schedules. Furthermore, they lacked sufficient real-time information sharing and question-and-answer functions, hindering smooth communication among team members.

[1618] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1619] In this invention, the server includes means for accessing a past database to acquire historical data, means for inputting the acquired historical data into a machine learning model to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for optimizing scheduling using an AI model based on the input information, means for notifying the user of the generated schedule and visualizing it on a dashboard, means for receiving questions using a chat interface, means for analyzing questions with a natural language processing model to generate appropriate answers, and means for notifying the user of the generated answers via the chat interface. This makes it possible to comprehensively perform risk identification and countermeasures, schedule optimization, and information sharing in project management.

[1620] A "database" is an information system that stores and allows access to past project data.

[1621] "Historical data" refers to a set of information related to past projects, including progress, completed tasks, resources used, and risk factors encountered.

[1622] A "machine learning model" refers to an algorithm or mathematical model used to analyze historical data to identify risk factors and potential problems.

[1623] A "risk list" is a compilation of risk factors and potential problems identified by a machine learning model.

[1624] A "task" refers to a specific task or activity within a project, carried out to achieve the project's objectives.

[1625] "Dependencies" refer to the relationships between tasks within a project, indicating that one task needs to be performed only after another task has been completed.

[1626] An "AI model" refers to a generative algorithm or mathematical model used to optimize a schedule based on input task and dependency information.

[1627] "Scheduling" is the process of efficiently determining the order and timing of project tasks.

[1628] A "dashboard" is an interface that allows users to centrally view project progress and various information.

[1629] A "chat interface" is an interface that allows users and systems to communicate in real time using text.

[1630] A "natural language processing model" refers to an algorithm or mathematical model used to analyze text-based questions from users and generate appropriate answers.

[1631] This invention is a system for efficiently managing projects. The main components of the system consist of a server, terminals, and users, enabling project risk identification, schedule optimization, and real-time information sharing.

[1632] Data acquisition function

[1633] The server accesses a database of past projects. For example, the database stores completed tasks, resources used, project progress, and risk factors encountered. A database management system (e.g., MySQL, PostgreSQL) is used in this process.

[1634] Data analysis function

[1635] After acquiring the data, the server passes the acquired historical data to a machine learning model. Examples of machine learning models used include TensorFlow and PyTorch. The analysis model learns patterns in the data and identifies risk factors and potential problems. A risk list is generated and notified to the user's dashboard.

[1636] Task input function

[1637] The user inputs the project's task list, its dependencies, and resource information from a terminal. The information entered on the terminal is sent to the server and becomes the basis for scheduling.

[1638] Schedule optimization function

[1639] The server optimizes the schedule using an AI model based on the input task, dependency, and resource information. A generative AI model is applied during this process. The model takes task dependencies and resource constraints into account to generate the optimal schedule. The generated schedule is sent to the user, who can view and edit it on the dashboard.

[1640] Chat interface

[1641] Users post questions using a chat interface. The server analyzes the questions using a generative AI model and generates appropriate answers. For example, natural language processing models (e.g., GPT-3, BERT) are used at this stage. The generated answers are notified to the user in real time.

[1642] Specific example

[1643] For example, when a user starts a new software development project, they can use the system by following these steps:

[1644] 1. Risk prediction and analysis

[1645] The user logs into the system and requests a risk analysis based on past project data.

[1646] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[1647] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1648] Example of a prompt:

[1649] "Please analyze the data from the past 10 projects and tell me the risk factors."

[1650] 2. Adjusting the project schedule

[1651] The user enters the project's task list and its dependencies from the terminal.

[1652] The server optimizes the schedule using an AI model based on the input information.

[1653] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[1654] Example of a prompt:

[1655] "Please generate a project schedule based on the following task list and dependencies."

[1656] 3. Information sharing

[1657] Users use the chat interface to ask about the schedule for the next meeting.

[1658] The server analyzes the question using a natural language processing model and accesses the schedule database to retrieve information about the next meeting.

[1659] The server will notify you of the generated response via the chat interface.

[1660] Example of a prompt:

[1661] "Please let me know when the next meeting will be held."

[1662] Thus, the present invention comprehensively enables the identification and mitigation of risks in project management, the optimization of schedules, and information sharing, contributing to a significant reduction in the workload of project managers and team members.

[1663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1664] Step 1: The user logs into the system.

[1665] Input: The user enters their ID and password.

[1666] Specific operation: The terminal receives this and sends it to the server. The server accesses the database and verifies the entered ID and password against the authentication information in the database.

[1667] Output: If authentication is successful, the user is redirected to the dashboard. If authentication fails, an error message is displayed.

[1668] Step 2: Request a risk analysis of the user.

[1669] Input: The user clicks the "Start Risk Analysis" button on the dashboard.

[1670] Specific operation: The terminal receives the user's request and sends it to the server. The server accesses the project database and retrieves past project data.

[1671] Output: The acquired historical data is sent to the server.

[1672] Step 3: The server inputs data into the machine learning model.

[1673] Input: Acquired historical data.

[1674] Specific operation: The server inputs historical data into a machine learning model (e.g., TensorFlow or PyTorch). The model analyzes the data and identifies risk factors and potential problems.

[1675] Output: A risk list is generated as an analysis result.

[1676] Step 4: The server notifies the user of the risk list.

[1677] Input: Generated risk list.

[1678] Specific operation: The server sends the risk list to the user's dashboard. The user is then able to view the risk list.

[1679] Output: The risk list is displayed on the user's dashboard.

[1680] Step 5: The user enters the tasks and dependencies.

[1681] Input: The user enters the project task list and dependencies.

[1682] Specific operation: The terminal sends the entered data to the server. The server saves this data to the database.

[1683] Output: The task list and dependencies are saved to the database.

[1684] Step 6: The server optimizes the schedule.

[1685] Input: Saved task list and dependencies.

[1686] Specific operation: The server uses an AI model to optimize the schedule. The model generates the optimal schedule by considering task dependencies and resource constraints.

[1687] Output: Optimized schedule.

[1688] Step 7: The server notifies the user of the schedule.

[1689] Input: Generated schedule.

[1690] Specific operation: The server sends the schedule to the user, and it is displayed on the dashboard.

[1691] Output: The schedule displayed on the dashboard.

[1692] Step 8: The user posts a question in the chat interface.

[1693] Input: The user enters a question in text format via the chat interface.

[1694] Specific operation: The terminal sends a question to the server. The server has a natural language processing model (e.g., GPT-3 or BERT) analyze the question.

[1695] Output: The intent of the analyzed question.

[1696] Step 9: The server generates the answer to the question.

[1697] Input: The intent of the analyzed question.

[1698] Specific operation: The server accesses the schedule database and retrieves relevant information. Based on the retrieved information, the server generates a response and converts it to text format.

[1699] Output: Generated answer.

[1700] Step 10: The server notifies the user of the answer.

[1701] Input: Generated response.

[1702] Specific operation: The server notifies the user of the answer via the chat interface.

[1703] Output: The response displayed in the chat interface.

[1704] (Application Example 1)

[1705] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1706] In modern factories, risk management is a crucial issue alongside improving production efficiency. However, conventional factory management systems have been unable to fully utilize historical data, making it difficult to identify risks and optimize schedules. Furthermore, the lack of real-time risk management and smooth information sharing with factory staff has made it difficult to maximize the efficiency of production lines. This invention aims to solve these problems.

[1707] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1708] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, factory management means for acquiring data and identifying risk factors in real time, factory operation means for optimizing the schedule, means for inputting prompt sentences into a generation AI model based on questions to generate answers, and means for notifying factory staff of the generated answers. This enables real-time risk management, optimization of production schedules, and more efficient information sharing within the factory.

[1709] A "past database" refers to a database containing historical information about previous projects and work.

[1710] "Historical data" refers to data recorded in the past, such as the progress of a project, completed tasks, resources used, and risk factors encountered.

[1711] "Risk factors" refer to potential problems or obstacles that could hinder the progress of a project or work.

[1712] A "potential problem" refers to an element that is not currently apparent but could potentially become a problem in the future.

[1713] A "risk list" refers to a list that compiles identified risk factors and problems in a list format.

[1714] "Project tasks" refer to the specific tasks and activities necessary to move a project forward.

[1715] A "dependency" refers to a relationship in which one task depends on the completion of another task.

[1716] "Scheduling" refers to time management that involves efficiently allocating tasks and resources and proceeding in a planned manner.

[1717] A "chat interface" refers to an interface that allows users and systems to communicate in real time using text.

[1718] A "generative AI model" refers to a model that uses artificial intelligence technology to generate text and responses.

[1719] A "prompt" refers to the text input to an AI model in order to generate an appropriate response.

[1720] "Factory management methods" refer to techniques and systems for managing the operation and production processes of a factory.

[1721] "Factory operation methods" refer to the techniques and systems used to efficiently manage the overall operations of a factory.

[1722] This invention is a system aimed at efficient factory operation and risk management. This system has the ability to access historical databases to retrieve historical data, analyze it to identify risk factors and potential problems, and generate and notify users of risk lists. Furthermore, it allows users to input project tasks and dependencies, optimize scheduling based on this information, and notify users of the generated schedule. It also has a function to receive questions from factory staff in real time using a chat interface, generate appropriate answers accordingly, and notify users.

[1723] The following key hardware and software are required to implement this system.

[1724] 1. Hardware:

[1725] Factory robots (including various sensors and database access functions)

[1726] Server (for data analysis and scheduling processing)

[1727] 2. Software:

[1728] SQLite: Database Management System

[1729] scikit-learn: Machine learning library (RandomForestClassifier)

[1730] OpenAI API: AI model for generating chat interfaces

[1731] Python: A programming language

[1732] The server accesses the factory's historical database to retrieve historical data. This includes information such as project progress, completed tasks, resources used, and risk factors encountered. For analysis, machine learning models such as RandomForestClassifier from the scikit-learn library are used to identify risk factors and potential problems. The identified risk factors are generated as a risk list and notified to the user.

[1733] Next, the user inputs the project's task list, its dependencies, and resource information from their device. This input data is sent to the server, where an AI model is used to perform scheduling. After the schedule is generated, the user is notified and it is visualized on a dashboard.

[1734] The server also accepts questions from factory staff via a chat interface. For these questions, it uses a generative AI model (OpenAI API) to generate appropriate answers, prompting the user to input prompts. These answers are then notified to the factory staff in real time.

[1735] As a concrete example, the following process can be considered, which involves identifying the risk of a part of the manufacturing line failing and then developing countermeasures.

[1736] 1. Historical data acquisition: Acquire past manufacturing data.

[1737] 2. Risk Factor Analysis: Identify the risk factors.

[1738] 3. Schedule Optimization: Optimize the schedule.

[1739] 4. Chat Response: Generate responses to questions.

[1740] Examples of prompt messages include the following:

[1741] "What is the schedule for the next maintenance?"

[1742] "What is the progress on Line A?"

[1743] "What is the estimated completion date for manufacturing task B?"

[1744] These prompts enable the system to manage risks in real time, optimize production schedules, and streamline information sharing within the factory.

[1745] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1746] Step 1:

[1747] The server accesses the past database to retrieve historical data.

[1748] Specific operation: The server sends queries to the SQLite database to retrieve data such as project progress, completed tasks, resources used, and risk factors encountered.

[1749] Input: Database query request

[1750] Output: Historical data

[1751] Step 2:

[1752] The server analyzes the acquired historical data to identify risk factors and potential problems.

[1753] Specific operation: The server uses machine learning models such as RandomForestClassifier from the scikit-learn library to identify risk factors and potential problems based on historical data.

[1754] Input: Historical data

[1755] Output: Risk List

[1756] Step 3:

[1757] The server generates a risk list and notifies the user.

[1758] Specific action: The server compiles identified risk factors into a list format and updates the UI to notify the user.

[1759] Input: Risk list

[1760] Output: Updated UI

[1761] Step 4:

[1762] The user inputs the project's task list, its dependencies, and resource information from their terminal.

[1763] Specific operation: The user uses a terminal to input the necessary tasks, dependencies, and resource information through the screen interface.

[1764] Input: Task list, dependencies, resource information

[1765] Output: Input is sent to the server.

[1766] Step 5:

[1767] The server performs scheduling based on the entered task list and dependencies.

[1768] Specific operation: The server uses an AI model to consider task priorities and dependencies and generate an optimal schedule.

[1769] Input: Task list, dependencies, resource information

[1770] Output: Generated schedule

[1771] Step 6:

[1772] The server notifies the user of the generated schedule and visualizes it on the dashboard.

[1773] Specific operation: The server displays the generated schedule on the user's dashboard, making it easy for the user to check.

[1774] Input: Generated schedule

[1775] Output: Updated dashboard

[1776] Step 7:

[1777] Factory staff enter questions using a chat interface.

[1778] Specific action: Factory staff open the chat interface on their terminal and enter their question.

[1779] Input: Question from the chat interface

[1780] Output: The question is sent to the server.

[1781] Step 8:

[1782] The server uses a generative AI model to generate appropriate answers to questions.

[1783] Specific operation: The server inputs the question as a prompt into the AI ​​model (OpenAI API) and generates an appropriate answer.

[1784] Input: Questions and prompts from the chat interface.

[1785] Output: Generated answer

[1786] Step 9:

[1787] The server notifies factory staff of the generated response via a chat interface.

[1788] Specific operation: The server notifies factory staff in real time of the generated responses via a chat interface.

[1789] Input: Generated answer

[1790] Output: Chat interface updates and notifications

[1791] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1792] This invention is a system for further streamlining project management and responding to the user's psychological state. It accesses a historical database to retrieve historical data, analyzes that data to identify risk factors and potential problems, and inputs project tasks and dependencies, optimizing the schedule based on that data and providing it to the user. Furthermore, by utilizing a chat interface to respond to team members' questions in real time and combining it with an emotion engine that recognizes the user's emotions, it is possible to respond in a way that takes into account the user's psychological state during project progress and decision-making.

[1793] Basic System Configuration

[1794] 1. Data acquisition function

[1795] The server accesses the past project database to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered.

[1796] 2. Data Analysis Function

[1797] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[1798] 3. Task Input Function

[1799] The user enters the project's task list, its dependencies, and resource information from their terminal. This input data is sent to the server and serves as the basis for scheduling.

[1800] 4. Schedule Optimization Function

[1801] The server uses an AI model to perform scheduling based on the input information. This process takes into account task dependencies and resource constraints to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[1802] 5. Chat Interface

[1803] The system allows team members to post questions via a chat interface. The server uses generative AI to analyze the questions, generate appropriate answers, and notify users of these answers in real time through the chat interface.

[1804] 6. Emotional Engine

[1805] The server includes an emotion engine that recognizes user emotions. This emotion engine analyzes user interactions, comments, chat messages, etc., to understand the user's current emotional state. This improves the accuracy of risk prediction and countermeasures.

[1806] Specific example

[1807] For example, when a user starts a new software development project, they can use the system by following these steps:

[1808] 1. Risk prediction and analysis

[1809] The user logs into the system and requests a risk analysis based on past project data.

[1810] The server accesses the database to retrieve historical data, which is then analyzed using a machine learning model.

[1811] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1812] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[1813] 2. Adjusting the project schedule

[1814] The user enters the project's task list and its dependencies from the terminal.

[1815] The server optimizes the schedule using an AI model based on the input information.

[1816] The server sends the generated schedule to the user, and it is visualized on the dashboard.

[1817] The emotion engine provides feedback about the schedule based on the user's emotions.

[1818] 3. Information sharing

[1819] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[1820] The server receives the question and analyzes it using an NLP model.

[1821] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[1822] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[1823] As described above, the present invention can comprehensively address risk identification and countermeasures, optimize schedules, and share information in project management, and further improve the quality and efficiency of project management by taking user emotions into consideration.

[1824] The following describes the processing flow.

[1825] A process that combines risk prediction, analysis, and sentiment recognition.

[1826] Step 1:

[1827] The user logs into the system and requests a risk analysis based on past project data. Specifically, they enter the required authentication information on the login screen and click the risk analysis button.

[1828] Step 2:

[1829] The server accesses the database to retrieve historical data. Specifically, it executes SQL queries to extract information such as past project progress, completed tasks, resources used, and risk factors encountered.

[1830] Step 3:

[1831] The server preprocesses the historical data it acquires. Specifically, it performs data cleaning, imputation of missing values, and format conversion to prepare the data for analysis by machine learning models.

[1832] Step 4:

[1833] The server preprocesses the data, which is then fed into a machine learning model to analyze risk factors and potential problems. For example, a model that has learned patterns of delays and failures from historical data is used.

[1834] Step 5:

[1835] The server extracts risk factors from the analysis results and compiles them into a risk list. Specifically, it scores and ranks the risk factors and prioritizes extracting high-risk items.

[1836] Step 6:

[1837] The server generates a risk list and uses an emotion engine to analyze the user's current emotional state. Specifically, it recognizes emotions from the user's past comments and current activity.

[1838] Step 7:

[1839] The server reflects the results of the emotion engine and adjusts the priority of the risk list and the notification method. For example, if the user is stressed, less urgent risk factors may be postponed.

[1840] Step 8:

[1841] The server notifies the user of the adjusted risk list. Specifically, the risk list is converted to JSON format and displayed on the web application's dashboard.

[1842] A process that combines project schedule adjustment and emotion recognition.

[1843] Step 1:

[1844] The user inputs the project's task list, its dependencies, and resource information from their device. Specifically, they enter information such as the task name, start date, end date, dependent task IDs, and required resources into an input form.

[1845] Step 2:

[1846] The server receives the input information and saves it to the database. The saved information is used as basic data for scheduling.

[1847] Step 3:

[1848] The server inputs stored data into an AI model to generate an optimal schedule. The AI ​​model takes into account task dependencies and resource constraints to propose an efficient schedule.

[1849] Step 4:

[1850] The server passes the generated schedule to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is overloaded, it might suggest distributing tasks.

[1851] Step 5:

[1852] The server sends the adjusted schedule to the user. The schedule is converted to the appropriate format for display as a Gantt chart or calendar view.

[1853] Step 6:

[1854] The user checks the received schedule on their device and provides feedback as needed. The server collects the user's feedback and readjusts the schedule as necessary.

[1855] A process that combines information sharing and emotion recognition.

[1856] Step 1:

[1857] Team members (users) post questions through the chat interface. For example, they might type, "When is the next meeting scheduled?"

[1858] Step 2:

[1859] The server receives the question and analyzes it using generative AI. Natural language processing (NLP) models are used to understand the intent of the question and identify relevant information.

[1860] Step 3:

[1861] The server accesses the relevant database to find the appropriate answer to the question. For example, to find the date of the next meeting, it would refer to the schedule database.

[1862] Step 4:

[1863] Based on the information acquired by the server, a generative AI generates an appropriate response. The response is formatted in a way that is easy for the user to understand.

[1864] Step 5:

[1865] The server passes the generated response to the emotion engine, which adjusts it based on the user's emotional state. For example, if the user is anxious, the response will be provided in a calm tone.

[1866] Step 6:

[1867] The server notifies team members of the generated answers via the chat interface. Users can view the answers in real time on the chat interface.

[1868] (Example 2)

[1869] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1870] In project management, identifying and managing risks, effective scheduling, and real-time information sharing are crucial elements. However, traditional systems struggled to manage these elements in an integrated manner, particularly failing to consider the emotional state of users. This led to problems such as project delays and difficulties in smooth communication among team members.

[1871] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1872] In this invention, the server includes means for accessing a database and acquiring historical data, means for analyzing the acquired data to identify risk factors and potential problems, means for inputting project tasks and dependencies, means for scheduling, means for notifying the user, means for receiving questions using a chat interface, means for generating appropriate answers, means for analyzing and recognizing the user's emotions, and means for dynamically adjusting the priority of the risk list and schedule based on the user's emotions. This enables not only risk management and schedule optimization, but also project management that takes into account the user's psychological state.

[1873] A "database" is a system for systematically storing and managing collections of data.

[1874] "Historical data" refers to data that includes information such as the progress of past projects, completed tasks, resources used, and risk factors.

[1875] "Risk factors" refer to elements or events that could potentially hinder the progress of a project.

[1876] A "potential problem" refers to an event or situation that is not currently apparent but has the potential to become a problem in the future.

[1877] A "risk list" is a compilation of analyzed risk factors in a list format.

[1878] A "task" refers to an individual task or job performed as part of a project.

[1879] A "dependency" refers to a relationship where one task depends on the start or completion of another task.

[1880] "Scheduling" refers to the act of creating a plan to efficiently allocate project tasks and resources over time.

[1881] A "chat interface" refers to a communication method that allows for the sending and receiving of messages in real time.

[1882] A "generative AI model" refers to an artificial intelligence algorithm that generates appropriate output based on user input and past data.

[1883] "Emotion recognition" is a technology that analyzes a user's emotional state and adjusts its response based on that information.

[1884] "Dynamic prioritization" refers to changing the importance of risk lists and schedules in real time based on the project status and the users' emotional state.

[1885] "Notification" refers to the act of communicating important information or results to a user.

[1886] "Terminal" refers to a computer or mobile device used by a user for operation.

[1887] This invention is a system for streamlining risk management, schedule optimization, and information sharing in project management. Furthermore, by considering the user's psychological state, it can make project progress smoother. This system consists of server, terminal, and user elements, all of which work together. The following describes each element and its specific operation.

[1888] Required hardware and software

[1889] Server: Use a server equipped with a high-performance processor and large-capacity storage.

[1890] Database management systems: Relational database management systems such as MySQL and PostgreSQL.

[1891] Machine learning libraries: TensorFlow, Scikit-learn, Pandas.

[1892] User interface: Web browser, chat interface (JavaScript framework, WebSocket).

[1893] Communication method: HTTP or HTTPS protocol between the server and the terminal.

[1894] Specific examples of data acquisition and preprocessing

[1895] The server accesses a database of past projects to retrieve historical data. This data includes project progress, completed tasks, resources used, and risk factors encountered. After retrieving the data, the Pandas library is used to cleanse the data, removing unnecessary data and imputing missing values.

[1896] Specific examples of risk analysis

[1897] The server passes the preprocessed data to machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Based on the analysis results, a risk list is generated and notified to the user.

[1898] Example of a prompt

[1899] "Please conduct a risk analysis for the new project."

[1900] Specific examples of task input and schedule optimization

[1901] Users input project task lists, dependencies, and resource information from their devices. This input data is sent to a server, where an AI model is used to perform scheduling. An optimal schedule is generated, taking into account task dependencies and resource constraints, and visualized on a dashboard.

[1902] Examples of chat interfaces and emotion recognition

[1903] When a user posts a question through the chat interface, the server uses a generative AI model to analyze the question and generate an appropriate answer. This answer is then notified to the user in real time through the chat interface. Additionally, an emotion recognition engine is used to analyze the user's emotions and dynamically adjust the priority of risk lists and schedules.

[1904] Example of a prompt

[1905] "When is the next project meeting?"

[1906] Thus, the present invention is a system that comprehensively addresses risk identification and countermeasures, schedule optimization, and information sharing in project management. Furthermore, by considering user emotions, the quality and efficiency of project management are improved.

[1907] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1908] Step 1:

[1909] Data acquisition

[1910] The server connects to the database and retrieves historical data. Specifically, it executes SQL queries to extract data such as project progress, completed tasks, resources used, and risk factors.

[1911] Input: Database connection information and queries

[1912] Data processing: Execute SQL queries and retrieve result sets.

[1913] Output: Historical data

[1914] Step 2:

[1915] Data preprocessing

[1916] The historical data acquired by the server is preprocessed using the Python Pandas library. Specifically, this involves imputing missing values ​​and removing unnecessary data.

[1917] Input: Historical data

[1918] Data processing: Data cleansing (imputing missing values, removing unnecessary data)

[1919] Output: Preprocessed data

[1920] Step 3:

[1921] Risk analysis

[1922] The server inputs pre-processed data into machine learning models using TensorFlow or Scikit-learn to analyze risk factors and potential problems. Specifically, it uses machine learning algorithms to analyze patterns in the data and identify risk factors.

[1923] Input: Preprocessed data

[1924] Data processing: Analysis using machine learning models

[1925] Output: List of risk factors

[1926] Step 4:

[1927] Task entry

[1928] The user inputs the project's task list, dependencies, and resource information from their device and sends it to the server. Specifically, they input task information using a web form and press the "Submit" button.

[1929] Input: User's task list, dependencies, and resource information

[1930] Data processing: Send data to the server

[1931] Output: Task data

[1932] Step 5:

[1933] Schedule optimization

[1934] The server uses an AI model to schedule tasks based on the input task information. Specifically, it considers task dependencies and resource constraints to generate the optimal schedule.

[1935] Input: Task data

[1936] Data processing: Scheduling in AI models

[1937] Output: Optimized schedule

[1938] Step 6:

[1939] Notification and visualization of results

[1940] The server notifies the user of the generated schedule information and visualizes it on a dashboard. Specifically, it uses data visualization libraries such as D3.js.

[1941] Input: Optimized schedule

[1942] Data processing: Visualization of schedule information

[1943] Output: Gantt chart on the dashboard

[1944] Step 7:

[1945] Chat interface

[1946] The user enters a question into a chat box, and the server generates an appropriate answer using an AI model. Specifically, the user might type "When is the next meeting?" into the chat, and the server generates an answer and notifies the user in real time.

[1947] Input: User's question

[1948] Data processing: Analysis using NLP models, response generation.

[1949] Output: Answer on the chat interface

[1950] Step 8:

[1951] Recognition of emotions

[1952] The server runs an emotion recognition engine to understand the user's emotional state by analyzing their comments and messages. Specifically, it analyzes the user's input data and dynamically adjusts the priority of the risk list and schedule.

[1953] Input: User comments or messages

[1954] Data processing: Analysis using emotion recognition algorithms

[1955] Output: Prioritized risk list and schedule

[1956] The above outlines the specific processing steps of this system. Each step clearly indicates the input and output and provides a detailed explanation of the data processing and calculations performed.

[1957] (Application Example 2)

[1958] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1959] Traditional factory project management systems have struggled not only to streamline production processes but also to identify risk factors, optimize schedules, share information in real time, and even address the emotions of workers. Furthermore, early detection and intervention of problems are crucial, especially in production environments, and a lack of efficient project management can lead to decreased productivity and increased risks. Against this backdrop, there is a need for a system that improves the quality and efficiency of project management in factories.

[1960] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1961] In this invention, the server includes means for accessing a past database to acquire historical data, means for analyzing the acquired historical data to identify risk factors and potential problems, means for generating and notifying a risk list, means for inputting project tasks and dependencies, means for scheduling based on the input information, means for notifying the user of the generated schedule, means for receiving questions using a chat interface, means for analyzing questions to generate appropriate answers, means for notifying the user of the generated answers via the chat interface, means for recognizing the user's emotions and adjusting the tone of responses based on emotion analysis, and means for visualizing the optimal production schedule in real time and managing the factory's production process. This enables comprehensive risk identification and countermeasures, schedule optimization, and information sharing in factory project management, and further allows for responses that take user emotions into consideration.

[1962] "Historical data" refers to various types of information collected during past projects and work, including progress, completed tasks, resources used, and risk factors encountered.

[1963] A "risk list" refers to a list of risk factors extracted based on the analysis of historical data. This allows users to identify potential problems and risks in advance.

[1964] A "task" refers to an individual job or activity that needs to be performed in a project or production process. Each task is defined as a specific action or unit of work.

[1965] "Dependencies" refer to situations where multiple tasks in a project are related to each other, with one task influencing or being influenced by another. This helps manage the order and progress of tasks.

[1966] "Scheduling" refers to the process of optimally allocating and planning the timing of each task in a project or production process. This ensures the efficient use of resources and the smooth progress of the project.

[1967] A "chat interface" refers to an interactive interface that allows users to ask questions and exchange information in real time. This enables rapid communication.

[1968] "Emotional analysis" refers to the technology that recognizes and analyzes emotions and emotional states from a user's text and comments. This allows the system to respond in a way that is appropriate to the user's psychological state.

[1969] An "AI model" refers to a collection of algorithms that use artificial intelligence to solve problems and analyze data. This allows the model to learn patterns from data and provide optimal solutions.

[1970] "Visualization" refers to a technique that makes data and information easier for users to understand by displaying them graphically. This makes it easier to grasp complex information.

[1971] System Implementation Overview

[1972] This invention is a system designed to improve efficiency in factory project management and to address risk factors and the emotional state of workers. This system includes the following main functions:

[1973] Data acquisition function

[1974] The server accesses a database of past projects to retrieve historical data. This data includes information such as project progress, completed tasks, resources used, and risk factors encountered. The software used is a database management system (DBMS) and the Python pandas library.

[1975] Data analysis function

[1976] The server preprocesses the acquired historical data and passes it to a machine learning model to analyze risk factors and potential problems. This analysis uses a random forest model based on the scikit-learn library. The risk list generated based on the analysis results is then notified to the user.

[1977] Task input function

[1978] Users input project task lists, their dependencies, and resource information via their devices. This input data is sent to a server and forms the basis for scheduling. For this purpose, smartphones and tablets are expected to be used as the interface.

[1979] Schedule optimization function

[1980] The server uses an AI model to perform scheduling based on the input information. The AI ​​model used is SVR (Support Vector Regression) from the scikit-learn library. In this process, task dependencies and resource constraints are taken into consideration to generate an optimal schedule. The generated schedule is sent to the user and visualized on a dashboard.

[1981] Chat interface

[1982] The system allows team members to post questions via a chat interface. The server uses a generative AI model (OpenAI's GPT-3) to analyze the questions, generate appropriate answers, and notifies users of these answers in real time via the chat interface.

[1983] Emotional Engine

[1984] The server includes an emotion engine (TextBlob library) that recognizes the user's emotions. This emotion engine analyzes the user's business negotiations, comments, chat messages, etc., to understand the user's current emotional state and adjust the priority of the risk list and the tone of responses accordingly.

[1985] Specific example

[1986] For example, when a user starts a new production project, they can use the system by following these steps:

[1987] 1. Risk prediction and analysis:

[1988] The user logs into the system and requests a risk analysis based on past project data.

[1989] The server accesses the database to retrieve historical data and analyzes it using a machine learning model.

[1990] The server extracts risk factors from the analysis results and provides them to the user as a risk list.

[1991] The emotion engine recognizes the user's current emotional state and adjusts the priority of the risk list accordingly.

[1992] 2. Adjusting the project schedule:

[1993] The user enters the project's task list and its dependencies from the terminal.

[1994] The server uses an AI model to optimize the schedule based on the input information.

[1995] The server sends the generated schedule to the user and visualizes it on the dashboard.

[1996] The emotion engine provides feedback about the schedule based on the user's emotions.

[1997] 3. Information sharing:

[1998] A team member (user) uses the chat interface to ask, "When is the next meeting scheduled?"

[1999] The server receives the question and analyzes it using a generative AI model (OpenAI's GPT-3).

[2000] The server accesses the schedule database to retrieve information about the next meeting and notifies the user of the generated response via the chat interface.

[2001] The emotion engine recognizes the user's emotions and provides responses in an appropriate tone.

[2002] Example of a prompt

[2003] When is the next maintenance task?

[2004] Hardware and software used

[2005] Hardware: Smartphones, tablets, dedicated devices

[2006] software:

[2007] Python

[2008] pandas

[2009] scikit-learn

[2010] TextBlob

[2011] OpenAI's GPT-3

[2012] Database Management System (DBMS)

[2013] Thus, the present invention can streamline factory project management and improve the quality and efficiency of project management by comprehensively facilitating risk identification and countermeasures, schedule optimization, and information sharing.

[2014] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2015] Step 1:

[2016] Retrieving past project data

[2017] The server accesses the database to retrieve historical data from past projects. The user then logs into the system and requests a risk analysis. The server uses the database management system to extract the historical project data. Inputs include past project IDs and time periods, while output is the historical data.

[2018] Step 2:

[2019] Analysis of risk factors

[2020] The server passes the acquired historical data to a machine learning model for analysis. Specifically, it preprocesses the historical data and analyzes risk factors and potential problems using a scikit-learn random forest model. The input is preprocessed historical data, and the output is a list of risk factors. The server generates a risk list and notifies the user of it.

[2021] Step 3:

[2022] Task and dependency input

[2023] The user enters the project's task list and its dependencies from their device. The user uses a smartphone or tablet interface to enter detailed task information (task name, duration, resources, etc.). Input consists of task information and dependencies, while output is data sent to the server.

[2024] Step 4:

[2025] Schedule optimization

[2026] The server optimizes the schedule using an AI model based on the input task information. This process utilizes scikit-learn's SVR (Support Vector Regression) to calculate the optimal start and end times, taking into account task dependencies and resource constraints. The input consists of task and resource information, and the output is the optimized schedule.

[2027] Step 5:

[2028] Schedule notifications and visualization

[2029] The server sends the generated schedule to the user and visualizes it on a dashboard. Users can check the schedule in real time through their device. The input is an optimized schedule, and the output is visualized schedule data.

[2030] Step 6:

[2031] Accepting questions via the chat interface

[2032] Users post questions to the system using a chat interface. Users use smartphones or tablets to input questions such as, "What is the schedule for the next meeting?" The input is the user's question, and the output is the question data sent to the chat interface.

[2033] Step 7:

[2034] Question analysis and answer generation

[2035] The server receives the user's question, analyzes it using a generative AI model (OpenAI's GPT-3), and generates an appropriate answer. The server uses NLP (Natural Language Processing) techniques to understand the user's question and generate an appropriate answer. The input is the user's question, and the output is the generated answer.

[2036] Step 8:

[2037] Emotion analysis

[2038] The server uses the TextBlob library to analyze the sentiment of user comments and questions. The sentiment engine recognizes the user's emotional state and adjusts the tone of the response accordingly. The input is the user's comments and questions, and the output is the result of the sentiment analysis.

[2039] Step 9:

[2040] Response notification and emotion-based adjustment

[2041] The server adjusts the generated response to an appropriate tone based on the user's sentiment analysis results and notifies the user via the chat interface. The user can receive the response in real time. The input is the generated response and the sentiment analysis results, and the output is the adjusted response.

[2042] In this way, a system that effectively supports factory project management can be realized through the specific actions performed at each step.

[2043] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2044] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2045] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2046] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2047] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2048] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2049] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2050] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2051] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2052] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2053] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2054] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2055] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2056] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2057] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2058] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[2059] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[2060] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[2061] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[2062] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2063] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[2064] The following is further disclosed regarding the embodiments described above.

[2065] (Claim 1)

[2066] A means of accessing past databases to retrieve historical data,

[2067] A means of analyzing acquired historical data to identify risk factors and potential problems,

[2068] A means of generating and notifying a risk list,

[2069] A means of inputting project tasks and dependencies,

[2070] A means of scheduling based on the input information,

[2071] A means of notifying the user of the generated schedule,

[2072] A means of receiving questions using a chat interface,

[2073] A means of analyzing a question and generating an appropriate answer,

[2074] A means of notifying the generated response via a chat interface,

[2075] A system that includes this.

[2076] (Claim 2)

[2077] The system according to claim 1, which analyzes historical data using a machine learning model.

[2078] (Claim 3)

[2079] The system according to claim 1, which uses an AI model to optimize scheduling.

[2080] "Example 1"

[2081] (Claim 1)

[2082] A means of accessing past databases to retrieve historical data,

[2083] A means of inputting acquired historical data into a machine learning model to identify risk factors and potential problems,

[2084] A means of generating and notifying a risk list,

[2085] A means of inputting project tasks and dependencies,

[2086] A means of optimizing scheduling using an AI model based on input information,

[2087] A means of notifying users of the generated schedule and visualizing it on a dashboard,

[2088] A means of receiving questions using a chat interface,

[2089] A means of analyzing a question using a natural language processing model to generate an appropriate answer,

[2090] A means of notifying the generated response via a chat interface,

[2091] A system that includes this.

[2092] (Claim 2)

[2093] The system according to claim 1, which analyzes historical data using a machine learning model and generates a risk list.

[2094] (Claim 3)

[2095] The system according to claim 1, which optimizes the project schedule from input information using an AI model.

[2096] "Application Example 1"

[2097] (Claim 1)

[2098] A means of accessing past databases to retrieve historical data,

[2099] A means of analyzing acquired historical data to identify risk factors and potential problems,

[2100] A means of generating and notifying a risk list,

[2101] A means of inputting project tasks and dependencies,

[2102] A means of scheduling based on the input information,

[2103] A means of notifying the user of the generated schedule,

[2104] A means of receiving questions using a chat interface,

[2105] A means of analyzing a question and generating an appropriate answer,

[2106] A means of notifying the generated response via a chat interface,

[2107] A factory management system that acquires data and identifies risk factors in real time,

[2108] A factory operation method to optimize the schedule,

[2109] A means of inputting prompt sentences into a generative AI model based on a question and generating an answer,

[2110] A means of notifying factory staff of the generated responses,

[2111] A system that includes this.

[2112] (Claim 2)

[2113] The system according to claim 1, which analyzes historical data using a machine learning model.

[2114] (Claim 3)

[2115] The system according to claim 1, which uses an AI model to optimize scheduling.

[2116] "Example 2 of combining an emotion engine"

[2117] (Claim 1)

[2118] A means of accessing past databases to retrieve historical data,

[2119] A means of analyzing acquired historical data to identify risk factors and potential problems,

[2120] A means of generating and notifying a risk list,

[2121] A means of inputting project tasks and dependencies,

[2122] A means of scheduling based on the input information,

[2123] A means of notifying the user of the generated schedule,

[2124] A means of receiving questions using a chat interface,

[2125] A means of analyzing a question and generating an appropriate answer,

[2126] A means of notifying the generated response via a chat interface,

[2127] A means of analyzing and recognizing user emotions,

[2128] A means of dynamically adjusting the priority of risk lists and schedules based on user emotions,

[2129] A system that includes this.

[2130] (Claim 2)

[2131] The system according to claim 1, which analyzes historical data using a machine learning model.

[2132] (Claim 3)

[2133] The system according to claim 1, which uses an AI model to optimize scheduling.

[2134] "Application example 2 of combining emotional engines"

[2135] (Claim 1)

[2136] A means of accessing past databases to retrieve historical data,

[2137] A means of analyzing acquired historical data to identify risk factors and potential problems,

[2138] A means of generating and notifying a risk list,

[2139] A means of inputting project tasks and dependencies,

[2140] A means of scheduling based on the input information,

[2141] A means of notifying the user of the generated schedule,

[2142] A means of receiving questions using a chat interface,

[2143] A means of analyzing a question and generating an appropriate answer,

[2144] A means of notifying the generated response via a chat interface,

[2145] A means for recognizing the user's emotions and adjusting the tone of response based on emotion analysis,

[2146] A means of visualizing the optimal production schedule in real time and managing the factory's production process,

[2147] A system that includes this.

[2148] (Claim 2)

[2149] The system according to claim 1, which analyzes historical data using a machine learning model.

[2150] (Claim 3)

[2151] The system according to claim 1, which uses an AI model to optimize scheduling. [Explanation of Symbols]

[2152] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of accessing past databases to retrieve historical data, A means of analyzing acquired historical data to identify risk factors and potential problems, A means of generating and notifying a risk list, A means of inputting project tasks and dependencies, A means of scheduling based on the input information, A means of notifying the user of the generated schedule, A means of receiving questions using a chat interface, A means of analyzing a question and generating an appropriate answer, A means of notifying the generated response via a chat interface, A system that includes this.

2. The system according to claim 1, which analyzes historical data using a machine learning model.

3. The system according to claim 1, which uses an AI model to optimize scheduling.

Images