system

Abstract

We provide the system. [Solution] A means of receiving information on special cases and referring to a database of past cases, A method for automatically generating task lists from similar cases using a generative AI model, A method for automatically creating a project work breakdown structure based on the above task list, A method for selecting necessary document templates based on project information and generating documents through automatic input, A system that includes this.

Description

Technical Field

[0001] The technology of the present 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 and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In many companies, when dealing with special cases, special responses that cannot be supplemented by standard procedures or deliverables are required. As a result, the diversity and complexity of tasks increase, and when successors take over the work, there is a dependence on personal knowledge. Consequently, there are problems such as work omissions and mistakes being likely to occur, and business efficiency decreasing. Therefore, it is required to efficiently manage tasks for special cases, reduce mistakes, and further automate the work involved in document creation.

Means for Solving the Problems

[0005] This invention provides a system that automatically identifies tasks for special cases and generates the necessary documents. Specifically, it includes means for receiving information on special cases and referencing data from similar past cases. Furthermore, it includes means for automatically generating a list of relevant tasks from past cases using a generation AI model. Based on this task list, it provides a mechanism to automatically create a work breakdown structure for the project, select the necessary document templates for the case, and automatically input them to generate the documents. It also includes a function to save the generated information in a database and update the learning model so that it can be effectively utilized in future case processing.

[0006] A "special case" is a task that cannot be handled using standard procedures or responses, and requires special measures or customized responses.

[0007] "Means of receiving information" refers to a function or device for collecting and receiving input information or data from users or systems.

[0008] A "generative AI model" is an artificial intelligence model that learns from data and performs tasks automatically and analyzes information.

[0009] The "method for automatically generating task lists from similar projects" is a function that analyzes past project data and lists the necessary tasks related to the current project.

[0010] A "work breakdown structure" is a structure that subdivides a project or task, clarifying the schedule and dependencies of each task.

[0011] A "document template" is a pre-defined document with a specific format and structure, which is completed by filling in the necessary information.

[0012] "Means of storing information in a database" refers to systems and processes for systematically storing information and managing it in a way that allows it to be retrieved as needed.

[0013] The "function to update learning models" is a process for improving the accuracy and performance of artificial intelligence models by incorporating new data and examples. [Brief explanation of the drawing]

[0014] [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] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] 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.

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

[0017] 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), etc.

[0018] 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.

[0019] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

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

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is designed as a system for the efficient management of special cases and the automatic generation of documents. Its embodiments are described below.

[0036] First, the user inputs information about the special case into the interface via their terminal. This information includes the case name, deadline, and detailed information about the client. The terminal then sends this information to the server.

[0037] The server references a database of past cases based on the received case information. It searches for similar past cases and automatically generates a task list using a generative AI model. The generative AI model used here learns from past case data using machine learning techniques and has the ability to extract tasks suitable for a specific case.

[0038] Next, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated task list. The WBS includes information about the start and end dates, dependencies, and resources responsible for each task.

[0039] Furthermore, the server selects the necessary document templates based on project information and schedules, automatically inputs the information, and generates the documents. This process may include documents such as special permit applications and contracts.

[0040] Once generation is complete, the terminal presents the WBS and documents to the user. The user reviews them, makes corrections if necessary, and performs a final check. This makes it possible to improve the accuracy of tasks while increasing work efficiency.

[0041] Finally, the server saves the generated information to a database and registers it as a case record. This data is also used as training data for the generating AI model to help handle future special cases. Through this cycle, the system continuously improves and optimizes itself, enabling it to make higher-quality proposals.

[0042] As a concrete example, consider a project to implement a new software system. In this case, the server compares past similar system implementation projects and generates a list of tasks required for implementation, such as system testing, user training, and data migration. Based on these tasks, it automatically generates necessary documents, such as usage permission applications and meeting minutes, supporting smooth project progress. By consistently automating the process, the workload is reduced, and high-quality project management is achieved.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The user accesses the terminal interface and enters basic information for a new special case. This includes the case name, deadline, client information, and related details.

[0046] Step 2:

[0047] The terminal sends the entered case information to the server. This establishes baseline data for processing and managing cases.

[0048] Step 3:

[0049] Based on the received case information, the server queries the past case database to search for similar past case examples.

[0050] Step 4:

[0051] The server uses a generative AI model to analyze and extract task lists of similar cases from the search results. This model has been trained on historical data using machine learning.

[0052] Step 5:

[0053] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the extracted task list. Each task is assigned a start date, an end date, and dependencies.

[0054] Step 6:

[0055] The server selects the necessary document template based on the project information and task list, automatically fills in the required fields, and generates the document.

[0056] Step 7:

[0057] The terminal presents the generated WBS and documentation to the user. The user can review them and make modifications if necessary.

[0058] Step 8:

[0059] The server saves the finalized WBS and documents to a database, recording them as project achievements. This information is used for future project processing and also for training generative AI models.

[0060] (Example 1)

[0061] 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."

[0062] Traditional manual processes for managing specialized tasks and generating related documentation are time-consuming and labor-intensive, posing challenges to efficiency and accuracy. In particular, the time required for learning from similar past tasks and designing new work items complicates project management. Therefore, there is a need for a system that efficiently and accurately manages specialized tasks and automatically generates documentation.

[0063] 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.

[0064] In this invention, the server includes a device that receives information on special tasks and references past task data, a device that automatically generates a task list from similar past tasks using a machine learning model, and a device that automatically creates a project structure based on the automatically generated task list. This streamlines the management of special tasks and the document generation process, enabling rapid and accurate project progress.

[0065] "Specialized work" refers to tasks or projects performed based on specific requirements or objectives, requiring special management and documentation that differs from normal business processes.

[0066] A "device that receives information" is a device that has the function of acquiring data input from a user and incorporating it into the system.

[0067] "Past work data" refers to a database containing records of similar tasks completed in the past, providing information that can be used in the current work.

[0068] A "machine learning model" is a form of artificial intelligence that has an algorithm to learn patterns from past data and generate a new list of tasks.

[0069] A "task list" refers to a list that enumerates and organizes the tasks required for a specific project, and its purpose is to improve the efficiency of project management.

[0070] "Project structure" refers to a hierarchical configuration that shows the dependencies and schedules of tasks in a project plan, visually representing the sequence of work and the timeline.

[0071] A "document template" refers to a pre-prepared document model tailored to a specific purpose, providing a foundation for quickly entering necessary information to complete the final document.

[0072] A "document generation device" is a device that has the function of creating a document in a specific format based on the input information.

[0073] This invention is a system for managing special tasks and automatically generating related documents. The embodiments thereof are described below.

[0074] First, the user inputs information about a specific task into the interface via the terminal. The terminal provides a form-based interface, and the user obtains the necessary information by typing on the keyboard. This information is validated and then sent to the server. Data transmission from the terminal is performed via HTTP requests using a secure SSL / TLS connection.

[0075] Based on the received information, the server uses SQL queries to access a database of past work. This extracts similar past work and prompts a generative AI model to generate a new list of work. The generative AI model used is equipped with machine learning algorithms that learn from historical data and have the ability to extract tasks suitable for specific work.

[0076] Based on the generated task list, the server automatically creates the project structure using a dedicated algorithm. The project structure is visualized in a Gantt chart format, showing task dependencies and schedules. This automatically generated structure contributes to more efficient and accurate project management.

[0077] Furthermore, the server selects the necessary document template based on specific work information, automatically inputs the information, and creates the document. Libraries such as PDFKit are used for document generation, and the final document is provided in PDF format.

[0078] Users can view the generated documents and project structure through their terminal. The system displays the generated information on the screen, and users can review and modify it on the interface. If necessary, the terminal resends the modifications to the server.

[0079] After this series of processes is complete, the server saves all generated information to a recording device. The saved data will be used as training data for generative AI models in future specialized tasks and will be utilized to improve the system's functionality.

[0080] A concrete example is the implementation of a new software system. In this case, the server refers to past system implementation data and generates a work list that includes tasks such as system testing, user training, and data migration. Based on the generated tasks, necessary documents such as usage permission applications and meeting minutes are automatically generated, enabling smooth project management. An example of a prompt to be entered into the generation AI model is "Please list the tasks appropriate for this project." This prompt allows the generation AI model to create an accurate work list based on past data.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The user enters project information into the interface via their terminal. This information includes project name, deadline, and client details. This input data is validated in real-time on the terminal and sent to the server only after it has been completed. The terminal uses a secure SSL / TLS connection to send information to the server via HTTP requests.

[0084] Step 2:

[0085] The server retrieves case information received from the terminal and references the past work database using SQL queries. This database search allows the server to extract similar past cases and obtain relevant data. The extracted data is then prepared for generating a new work list.

[0086] Step 3:

[0087] The server sends a prompt to the generative AI model, which generates a new task list. For example, with the prompt "List tasks suitable for this case," the server inputs case information and historical data into the generative AI model, and uses machine learning techniques to generate a task list. The generated task list is returned to the server in JSON format and used for further processing.

[0088] Step 4:

[0089] The server automatically creates the project structure based on the generated task list. Using a dedicated algorithm, the server analyzes the task list and builds a schedule and dependencies in Gantt chart format. This determines the start date, end date, and resource allocation for each task, visualizing the overall project structure.

[0090] Step 5:

[0091] The server selects the necessary document template based on project information and schedule, automatically inputs the information, and generates the document. In this process, the server uses a library (e.g., PDFKit) to embed the necessary information into the document template, preparing it for the final PDF document generation.

[0092] Step 6:

[0093] The terminal displays the structure of the generated documents and projects to the user and prompts for confirmation. The user can review the details of each document and project through the interface and make modifications as needed. The terminal resends the user's changes to the server for final confirmation.

[0094] Step 7:

[0095] The server stores the finalized information in a database. The stored data includes the final version of the document, work lists, and project structure. Furthermore, the stored data is used as training data for generating AI models for future projects, contributing to the continuous improvement and optimization of the models.

[0096] (Application Example 1)

[0097] 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."

[0098] In industrial environments, managing specialized projects requires processing large amounts of information and efficiently managing multiple processes. However, current systems require significant effort to create task lists and generate documents, potentially leading to inefficiencies and errors. This results in challenges such as work delays and decreased quality.

[0099] 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.

[0100] This invention includes a server that includes means for acquiring information for specific cases and referencing a database of past cases, means for automatically creating task lists from similar cases using generative AI technology, and means for coordinating and scheduling specific tasks within equipment used in industrial environments. This enables efficient management of related tasks and rapid automation of necessary procedures and safety standards.

[0101] A "special case" is a case that differs from normal work or projects and involves special requirements or conditions.

[0102] A "case study database" is a database that organizes, stores, and makes searchable information about past projects and operations.

[0103] "Generative AI technology" is a technique that uses machine learning models to generate new tasks and predictions based on past data.

[0104] A "task list" is a list that organizes the specific tasks and processes that need to be performed in a project or job.

[0105] A "work assignment structure" is a plan that clearly defines the relationships, sequence, and responsibilities of each task within a project.

[0106] "Specific tasks within a device" refers to specific tasks or processes performed by machines or robots used in industrial environments.

[0107] "Scheduling" refers to planning the timing and order of each task and organizing them as a schedule.

[0108] A "procedure manual" is a document that describes in detail how to perform a specific task or operation.

[0109] "Safety standards" are regulations and guidelines designed to ensure safety in industries and workplaces.

[0110] To implement this invention, a system is constructed in which a server, a data input terminal, and equipment used in an industrial environment work together. The server manages information on special cases and uses a database of past cases to generate task lists and work assignment structures using generative AI technology.

[0111] The server executes processing using programming languages ​​and frameworks such as Python and PyTorch. SQLite is used as the database to store historical data for each case. A data entry terminal is used by users to input information, which is then sent to the server. Based on the received information, the server applies a learning model and automatically generates necessary procedures and safety standards using templates. This utilizes the Jinja2 template engine.

[0112] As a concrete example, consider a project to introduce a new product line. In this case, project information is sent from a terminal to a server, which then refers to a database of similar past projects to extract the necessary processes and safety standards. Based on the generated plan and documentation, a schedule is created to ensure that the equipment efficiently performs specific tasks. This is expected to ensure that the project is completed efficiently and on time.

[0113] By using a generative AI model, task lists and plans can be effectively generated by inputting specific prompts. The following are examples of prompts:

[0114] "Automatically create a task list related to the new product line implementation project. This will generate an efficient WBS and related documentation, supporting the smooth progress of the project."

[0115] This system is an effective tool for supporting project management in industry.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The user uses a data entry terminal to input information about a special case (such as the case name, deadline, and detailed information about the client). This information is sent to the server as input. The server, upon receiving the information, temporarily records it.

[0119] Step 2:

[0120] The server references a database of past cases based on the received case information. To identify similar cases, it performs a similarity search using the metadata of the input information and extracts highly relevant past case data. In this process, the input is the configured metadata, and the output is a list of similar cases.

[0121] Step 3:

[0122] The server uses a generative AI model to automatically generate task lists based on extracted similar cases. The input is data from past cases, and the output is a set of task lists suitable for the current case. In this process, the AI ​​model uses patterns learned from past cases to refine the tasks.

[0123] Step 4:

[0124] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the generated task list. The task list is provided as input, and based on that, it meticulously organizes the order, dependencies, and assignees of each task, outputting the WBS. This clarifies the overall picture of the project.

[0125] Step 5:

[0126] The server uses the Work Breakdown Structure (WBS) and project information to automatically generate necessary documents such as procedure manuals and safety standards. The inputs are the WBS and project information, and the Jinja2 template engine is used to apply this data to templates, resulting in completed documents as output.

[0127] Step 6:

[0128] The generated WBS and documents are sent to the user's terminal, where the user can refer to them and make corrections and verifications as needed. The input is the output, and the output is the final, verified document and WBS with the user's feedback.

[0129] Step 7:

[0130] Ultimately, the server stores the user-confirmed information in a database and updates the generated AI model for handling future special cases. The input is confirmed information data, which is used to expand the model's training data, resulting in an updated model as output.

[0131] 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.

[0132] This invention combines an emotion engine with a system that enhances the efficiency of managing special cases, thereby realizing project management that takes user emotions into consideration.

[0133] First, the user inputs basic information about the special case through the terminal interface. The terminal sends this information to the emotion engine. The emotion engine analyzes the user's emotions from the input data and selection actions. This analysis identifies the user's emotional state, such as stress level, anxiety, and satisfaction.

[0134] Subsequently, the terminal transfers the case information along with the sentiment analysis results sent from the sentiment engine to the server. Based on the received information, the server searches the past case database and identifies similar cases. The server utilizes a generative AI model to automatically generate a task list from similar cases and considers prioritizing and reallocating tasks based on the user's emotional state.

[0135] Next, the server generates a Work Breakdown Structure (WBS) for the project. In doing so, it takes into account the user's emotions, as recognized by the emotion engine, and adjusts task allocation and scheduling flexibility to provide a plan that minimizes user stress.

[0136] Even in the automated document generation process, user emotions are reflected. The server selects a document template and generates the necessary document, adjusting the tone and wording based on the user's current emotions. The generated document is then presented to the user via their terminal.

[0137] Furthermore, the emotion engine captures real-time user feedback and incorporates it into the project plan. This allows project management to continuously evolve and be optimized through interaction with users.

[0138] For example, if a user is experiencing high stress levels due to a busy schedule, the emotion engine recognizes this situation and instructs the server to postpone lower-priority tasks to later dates, adjusting the Work Breakdown Structure (WBS) to allow the user to focus on important tasks. Furthermore, the generated reports are written with emotionally sensitive language, including encouraging messages. In this way, the system harmonizes user emotions with project progress, improving the user experience and optimizing operational efficiency.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] Users input basic information about special cases through a terminal interface. During this process, the terminal also collects data on the user's keyboard and mouse movements, as well as their input speed, as indicators of their emotional state.

[0142] Step 2:

[0143] The terminal sends the entered case information and data that serves as an indicator of emotion to the emotion engine. The emotion engine analyzes this data and evaluates the user's emotional state (e.g., stress, exhilaration, concentration, etc.).

[0144] Step 3:

[0145] The emotion engine returns the analysis results to the server, reporting the user's emotional state. This result becomes an important parameter in case processing.

[0146] Step 4:

[0147] The server receives the user's case information and sentiment data, and searches for similar cases by referring to a database of past cases. Simultaneously, it uses a generative AI model to automatically generate a task list suitable for that case.

[0148] Step 5:

[0149] The server creates a Work Breakdown Structure (WBS) for the project based on the task list. During this process, it takes feedback from the emotion engine into consideration, adjusting task priorities and schedules to reduce user stress.

[0150] Step 6:

[0151] The server uses case information to select the necessary document templates, and based on the results of the sentiment engine, generates text to give the user a sense of security and satisfaction, and then creates the document.

[0152] Step 7:

[0153] The terminal presents the generated WBS and document to the user. The user can review the content and make revisions if necessary. Sentimental data is also collected during the revision process and analyzed again by the sentiment engine.

[0154] Step 8:

[0155] The server saves the finalized project information to a database, which is then used as training data for the emotion engine in future projects. This allows the system to continuously improve its ability to handle emotions.

[0156] (Example 2)

[0157] 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 will be referred to as the "terminal."

[0158] In managing special projects, it is essential to plan and execute work efficiently while considering the user's emotions. However, current systems fail to adequately reflect the user's emotional state in planning adjustments, which can increase stress and lead to a lack of flexibility in scheduling. To solve these problems, project management that takes emotional states into account in real time is necessary.

[0159] 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.

[0160] In this invention, the server includes means for receiving information on special cases and referring to a historical database; means for automatically generating a list of tasks from similar histories using a generative AI model; means for analyzing the user's emotional state and adjusting the priority of the task list; and means for adjusting the allocation of tasks to minimize the user's stress level. This enables efficient project management that takes the user's emotions into consideration.

[0161] "Special cases" refer to projects or tasks that require special handling by the user in order to improve management efficiency.

[0162] A "history database" is a collection of data that summarizes information about projects and tasks that have been carried out in the past.

[0163] A "generative AI model" is a form of artificial intelligence that automatically generates task lists and other outputs based on data.

[0164] A "task list" is a list that enumerates the tasks that need to be performed in a project or work.

[0165] "Stratified structure" is a structure for breaking down a project into stages, organizing and visualizing it.

[0166] "Emotional evaluation" is the process of identifying and evaluating a user's emotional state using numerical values ​​or categories.

[0167] "Document format" refers to the form and style of the generated document, and is a template that enables consistent expression.

[0168] "Priority adjustment" refers to the process of setting and adjusting the order in which tasks are performed based on their importance and urgency.

[0169] "Stress level" is an indicator that shows the psychological burden a user feels and is a factor that affects the performance of their work.

[0170] This invention provides a system for project management that takes user emotions into consideration. This system is implemented using a terminal, a server, an emotion engine, and a generative AI model.

[0171] First, the user enters basic information about the special case through the terminal. The terminal is equipped with an input interface that allows the user to easily enter information such as the case name, deadline, and required resources. The terminal then sends this case information to the emotion engine.

[0172] The emotion engine analyzes user input data and performs the necessary data calculations to identify the user's emotional state. Here, the emotion engine determines the user's stress level, satisfaction level, etc., and transmits the results to the server via the terminal. The emotion engine utilizes natural language processing technology to identify emotions based on the user's input data and operation history.

[0173] The server searches the history database based on the received case information and sentiment data. The history database stores past similar cases and their results, enabling similarity analysis. Using a generative AI model, the server generates a list of tasks based on knowledge gained from past similar cases, supporting optimal project management for the user.

[0174] For example, if a user is busy and experiencing high stress levels, the emotion engine recognizes this state and the server prioritizes lower-priority tasks, redistributing the workload so that the user can focus on important tasks. Furthermore, the generated documents automatically include encouraging messages that take the user's emotions into consideration.

[0175] An example of a prompt message would be, "Determine the optimal task order based on the user's sentiment analysis results."

[0176] Thus, the present invention appropriately considers the user's emotions and realizes more efficient and less stressful project management.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The user inputs basic information about a special case through the terminal. The terminal then transmits the information received from the user, such as the case name, deadline, and required resources, to the sentiment engine. The input information is used as basic data for sentiment analysis.

[0180] Step 2:

[0181] The device sends input data to the emotion engine, which analyzes the user's emotional state. Based on the user's input and past operation patterns, the emotion engine identifies the user's stress level and satisfaction level. It quantifies the emotional state through data calculations and sends this quantified value to the server via the device.

[0182] Step 3:

[0183] The server uses the received case information and sentiment data to refer to the historical database and search for similar cases. This extracts data on similar cases and prepares it for the next generation AI model. Similarity analysis is performed within the database based on the input data.

[0184] Step 4:

[0185] The server uses a generative AI model to automatically generate a list of tasks from similar cases. Based on the input data of similar cases, the AI ​​outputs the optimal task list and determines its priority. The output task list is optimized according to the user's emotional state.

[0186] Step 5:

[0187] The server analyzes the user's emotional state and automatically creates a Work Breakdown Structure (WBS) based on the generated task list. Prompts adjust the order and importance of tasks to minimize user stress, resulting in an efficient project plan presented to the user.

[0188] (Application Example 2)

[0189] 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 device 14 will be referred to as the "terminal."

[0190] In managing specialized projects, the challenge lies in reducing the emotional burden faced by users and optimizing project progress efficiency. Furthermore, it is necessary to reduce the mental stress on factory workers and ensure the efficient operation of support equipment.

[0191] 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.

[0192] In this invention, the server includes means for acquiring information on special cases and referring to a collection of past case information, means for automatically generating task lists from similar cases using a generation AI model, and means for performing sentiment analysis and adjusting the flexibility of work breakdown configurations and schedules based on the user's emotional state. This enables flexible project management and optimization of workload in accordance with the user's emotions.

[0193] A "special case" refers to a project or task that includes special requirements or conditions that differ from normal operations.

[0194] An "information collection" is a database containing data on past projects and tasks.

[0195] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate task lists from similar cases.

[0196] A "task list" is a list that compiles the individual tasks required for a project or task.

[0197] "Work breakdown structure" refers to a systematic organization of a project by dividing the entire project into smaller tasks.

[0198] A "document template" is a pre-defined format used when creating a document, designed to quickly generate content.

[0199] "Emotional analysis" is a process that analyzes the emotional state of a user based on their input data to determine their stress level and satisfaction level.

[0200] "Assistive devices" are automated devices or systems used to reduce the burden on workers.

[0201] This invention realizes a project management system that takes user emotions into consideration. The system first sends information about a special case entered by the user via a terminal to a server. Based on this information, the server searches a database of past case information and identifies similar cases. The server then uses a generative AI model to automatically generate a task list from similar cases. Here, the task list organizes the individual tasks required for the project. At this time, a work breakdown structure is created based on the task list, and the entire project is systematically divided.

[0202] The system also incorporates an emotion analysis function, which analyzes data entered by the user from their device to understand the user's emotional state (such as stress level and satisfaction level). This emotion analysis can be performed using a device with specific emotion analysis software installed or a cloud-based service. A concrete example is the use of Microsoft® Azure® emotion analysis APIs.

[0203] Based on the results of sentiment analysis, the server adjusts the task breakdown structure to suit the user. This makes it possible to provide a project plan that takes into account the flexibility of the task list and schedule in order to reduce user stress. For example, if the user is in a high-stress state, the server will adjust by postponing lower-priority tasks and focusing on important tasks.

[0204] Furthermore, the server selects a dedicated document template and automatically generates documents with a tone and language that matches the user's emotions. This allows information to be provided in a considerate manner to the user.

[0205] The system also takes into account adjustments to assistive devices, allowing the server to provide instructions to optimize the operation of robots and other assistive devices based on the worker's emotions. This reduces the burden on workers and supports efficient work in factory and other work environments.

[0206] A concrete example of a prompt message would be: "Factory worker's emotional analysis result: High stress level. We want to redistribute tasks for the next shift and maximize the use of assistive devices. Please generate specific suggestions." This system aims to harmonize the user's emotions with the progress of the project, thereby improving work efficiency.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The user uses a terminal to input information about a special case. This information includes the project name, deadline, and resource usage. The terminal then sends this information to the server. As output, the terminal sends digital data of the case information to the server.

[0210] Step 2:

[0211] The server searches the case information database based on the received special case information and identifies similar cases. This search process uses database queries and compares them with past case information. A list of similar cases is generated as output.

[0212] Step 3:

[0213] The server uses a generative AI model to automatically generate a task list from identified similar cases. The input is the list of similar cases obtained in step 2, and the generative AI model receives prompts based on this and constructs the task list. A recommended task list is provided as output.

[0214] Step 4:

[0215] Based on data provided by the user, the device performs sentiment analysis to determine the user's emotional state (such as stress level and satisfaction level). A sentiment analysis API is used for this determination. The device's output is the analyzed data regarding the user's emotional state.

[0216] Step 5:

[0217] The server adjusts the work breakdown structure based on the task list generated in step 3 and the user's emotional state determined in step 4. Here, it performs calculations to re-evaluate task priorities in order to reduce user stress. The output is the adjusted work breakdown structure.

[0218] Step 6:

[0219] The server selects a document template and automatically generates a document in a tone appropriate to the user's emotional state. This uses a template selection algorithm and natural language generation software. As output, a document in a user-friendly format is generated and sent to the terminal.

[0220] Step 7:

[0221] The server generates instructions to optimize the operation of assistive devices based on the user's emotional state. Specifically, it issues operational instructions that assign tasks to the assistive devices that reduce the user's burden. The server's output is data of operational instructions for the assistive devices.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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).

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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".

[0238] This invention is designed as a system for the efficient management of special cases and the automatic generation of documents. Its embodiments are described below.

[0239] First, the user inputs information about the special case into the interface via their terminal. This information includes the case name, deadline, and detailed information about the client. The terminal then sends this information to the server.

[0240] The server references a database of past cases based on the received case information. It searches for similar past cases and automatically generates a task list using a generative AI model. The generative AI model used here learns from past case data using machine learning techniques and has the ability to extract tasks suitable for a specific case.

[0241] Next, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated task list. The WBS includes information about the start and end dates, dependencies, and resources responsible for each task.

[0242] Furthermore, the server selects the necessary document templates based on project information and schedules, automatically inputs the information, and generates the documents. This process may include documents such as special permit applications and contracts.

[0243] Once generation is complete, the terminal presents the WBS and documents to the user. The user reviews them, makes corrections if necessary, and performs a final check. This makes it possible to improve the accuracy of tasks while increasing work efficiency.

[0244] Finally, the server saves the generated information to a database and registers it as a case record. This data is also used as training data for the generating AI model to help handle future special cases. Through this cycle, the system continuously improves and optimizes itself, enabling it to make higher-quality proposals.

[0245] As a concrete example, consider a project to implement a new software system. In this case, the server compares past similar system implementation projects and generates a list of tasks required for implementation, such as system testing, user training, and data migration. Based on these tasks, it automatically generates necessary documents, such as usage permission applications and meeting minutes, supporting smooth project progress. By consistently automating the process, the workload is reduced, and high-quality project management is achieved.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] The user accesses the terminal interface and enters basic information for a new special case. This includes the case name, deadline, client information, and related details.

[0249] Step 2:

[0250] The terminal sends the entered case information to the server. This establishes baseline data for processing and managing cases.

[0251] Step 3:

[0252] Based on the received case information, the server queries the past case database to search for similar past case examples.

[0253] Step 4:

[0254] The server uses a generative AI model to analyze and extract task lists of similar cases from the search results. This model has been trained on historical data using machine learning.

[0255] Step 5:

[0256] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the extracted task list. Each task is assigned a start date, an end date, and dependencies.

[0257] Step 6:

[0258] The server selects the necessary document template based on the project information and task list, automatically fills in the required fields, and generates the document.

[0259] Step 7:

[0260] The terminal presents the generated WBS and documentation to the user. The user can review them and make modifications if necessary.

[0261] Step 8:

[0262] The server saves the finalized WBS and documents to a database, recording them as project achievements. This information is used for future project processing and also for training generative AI models.

[0263] (Example 1)

[0264] 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."

[0265] Traditional manual processes for managing specialized tasks and generating related documentation are time-consuming and labor-intensive, posing challenges to efficiency and accuracy. In particular, the time required for learning from similar past tasks and designing new work items complicates project management. Therefore, there is a need for a system that efficiently and accurately manages specialized tasks and automatically generates documentation.

[0266] 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.

[0267] In this invention, the server includes a device that receives information on special tasks and references past task data, a device that automatically generates a task list from similar past tasks using a machine learning model, and a device that automatically creates a project structure based on the automatically generated task list. This streamlines the management of special tasks and the document generation process, enabling rapid and accurate project progress.

[0268] "Specialized work" refers to tasks or projects performed based on specific requirements or objectives, requiring special management and documentation that differs from normal business processes.

[0269] A "device that receives information" is a device that has the function of acquiring data input from a user and incorporating it into the system.

[0270] "Past work data" refers to a database containing records of similar tasks completed in the past, providing information that can be used in the current work.

[0271] A "machine learning model" is a form of artificial intelligence that has an algorithm to learn patterns from past data and generate a new list of tasks.

[0272] A "task list" refers to a list that enumerates and organizes the tasks required for a specific project, and its purpose is to improve the efficiency of project management.

[0273] "Project structure" refers to a hierarchical configuration that shows the dependencies and schedules of tasks in a project plan, visually representing the sequence of work and the timeline.

[0274] A "document template" refers to a pre-prepared document model tailored to a specific purpose, providing a foundation for quickly entering necessary information to complete the final document.

[0275] A "document generation device" is a device that has the function of creating a document in a specific format based on the input information.

[0276] This invention is a system for managing special tasks and automatically generating related documents. The embodiments thereof are described below.

[0277] First, the user inputs information about a specific task into the interface via the terminal. The terminal provides a form-based interface, and the user obtains the necessary information by typing on the keyboard. This information is validated and then sent to the server. Data transmission from the terminal is performed via HTTP requests using a secure SSL / TLS connection.

[0278] Based on the received information, the server uses SQL queries to access a database of past work. This extracts similar past work and prompts a generative AI model to generate a new list of work. The generative AI model used is equipped with machine learning algorithms that learn from historical data and have the ability to extract tasks suitable for specific work.

[0279] Based on the generated task list, the server automatically creates the project structure using a dedicated algorithm. The project structure is visualized in a Gantt chart format, showing task dependencies and schedules. This automatically generated structure contributes to more efficient and accurate project management.

[0280] Furthermore, the server selects the necessary document template based on specific work information, automatically inputs the information, and creates the document. Libraries such as PDFKit are used for document generation, and the final document is provided in PDF format.

[0281] The user can check the documents and project structure generated through the terminal. The system displays the generated information on the screen, and the user can check and modify it on the interface. If necessary, the terminal sends the modified content back to the server again.

[0282] After this series of processes is completed, the server stores all the generated information in the recording device. The stored data is used as learning data for the generated AI model in future special operations and is utilized to improve the system's functionality.

[0283] As a specific example, there is a case of introducing a new software system. In this case, the server refers to past system introduction data and generates a task list including tasks such as system testing, user training, and data migration. Based on the generated tasks, necessary documents such as license applications and meeting minutes are automatically generated, enabling smooth project operation. An example of the prompt text input to the generated AI model is "Please list the tasks suitable for this case." With this prompt, the generated AI model can create an accurate task list based on past data.

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] The user inputs the case information into the interface through the terminal. The information to be input includes the case name, due date, details about the client, etc. This input data is validated in real-time on the terminal and sent to the server in a complete state. The terminal uses a secure SSL / TLS connection to send the information to the server via an HTTP request.

[0287] Step 2:

[0288] The server retrieves case information received from the terminal and references the past work database using SQL queries. This database search allows the server to extract similar past cases and obtain relevant data. The extracted data is then prepared for generating a new work list.

[0289] Step 3:

[0290] The server sends a prompt to the generative AI model, which generates a new task list. For example, with the prompt "List tasks suitable for this case," the server inputs case information and historical data into the generative AI model, and uses machine learning techniques to generate a task list. The generated task list is returned to the server in JSON format and used for further processing.

[0291] Step 4:

[0292] The server automatically creates the project structure based on the generated task list. Using a dedicated algorithm, the server analyzes the task list and builds a schedule and dependencies in Gantt chart format. This determines the start date, end date, and resource allocation for each task, visualizing the overall project structure.

[0293] Step 5:

[0294] The server selects the necessary document template based on project information and schedule, automatically inputs the information, and generates the document. In this process, the server uses a library (e.g., PDFKit) to embed the necessary information into the document template, preparing it for the final PDF document generation.

[0295] Step 6:

[0296] The terminal displays the structure of the generated documents and projects to the user and prompts for confirmation. The user can review the details of each document and project through the interface and make modifications as needed. The terminal resends the user's changes to the server for final confirmation.

[0297] Step 7:

[0298] The server stores the finalized information in a database. The stored data includes the final version of the document, work lists, and project structure. Furthermore, the stored data is used as training data for generating AI models for future projects, contributing to the continuous improvement and optimization of the models.

[0299] (Application Example 1)

[0300] 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."

[0301] In industrial environments, managing specialized projects requires processing large amounts of information and efficiently managing multiple processes. However, current systems require significant effort to create task lists and generate documents, potentially leading to inefficiencies and errors. This results in challenges such as work delays and decreased quality.

[0302] 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.

[0303] This invention includes a server that includes means for acquiring information for specific cases and referencing a database of past cases, means for automatically creating task lists from similar cases using generative AI technology, and means for coordinating and scheduling specific tasks within equipment used in industrial environments. This enables efficient management of related tasks and rapid automation of necessary procedures and safety standards.

[0304] A "special case" refers to a case with special requirements or conditions, which is different from normal operations or projects.

[0305] An "example database" is a database that organizes and stores information on past projects and operations and is searchable.

[0306] "Generative AI technology" is a technology that uses machine learning models to generate new tasks or predictions based on past data.

[0307] A "task list" is a list that organizes the specific tasks and processes to be carried out in a project or operation.

[0308] A "work sharing structure" is a plan document that clarifies the relationships, order, and responsible persons among tasks within a project.

[0309] "Specific operations within a device" refer to specific operations or processes performed by machines or robots used in industrial environments.

[0310] "Scheduling" refers to planning the implementation time and order of each task and organizing them as a schedule.

[0311] A "procedure manual" is a document that details the methods for performing specific operations or tasks.

[0312] "Safety standards" are regulations and guidelines for ensuring safety in industries and workplaces.

[0313] To implement this invention, a system is constructed in which a server, a data input terminal, and a device used in an industrial environment cooperate. The server manages information on special cases and uses the past example database to generate a task list and a work sharing structure by making full use of generative AI technology.

[0314] The server executes processing using programming languages ​​and frameworks such as Python and PyTorch. SQLite is used as the database to store historical data for each case. A data entry terminal is used by users to input information, which is then sent to the server. Based on the received information, the server applies a learning model and automatically generates necessary procedures and safety standards using templates. This utilizes the Jinja2 template engine.

[0315] As a concrete example, consider a project to introduce a new product line. In this case, project information is sent from a terminal to a server, which then refers to a database of similar past projects to extract the necessary processes and safety standards. Based on the generated plan and documentation, a schedule is created to ensure that the equipment efficiently performs specific tasks. This is expected to ensure that the project is completed efficiently and on time.

[0316] By using a generative AI model, task lists and plans can be effectively generated by inputting specific prompts. The following are examples of prompts:

[0317] "Automatically create a task list related to the new product line implementation project. This will generate an efficient WBS and related documentation, supporting the smooth progress of the project."

[0318] This system is an effective tool for supporting project management in industry.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The user uses a data entry terminal to input information about a special case (such as the case name, deadline, and detailed information about the client). This information is sent to the server as input. The server, upon receiving the information, temporarily records it.

[0322] Step 2:

[0323] The server references a database of past cases based on the received case information. To identify similar cases, it performs a similarity search using the metadata of the input information and extracts highly relevant past case data. In this process, the input is the configured metadata, and the output is a list of similar cases.

[0324] Step 3:

[0325] The server uses a generative AI model to automatically generate task lists based on extracted similar cases. The input is data from past cases, and the output is a set of task lists suitable for the current case. In this process, the AI ​​model uses patterns learned from past cases to refine the tasks.

[0326] Step 4:

[0327] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the generated task list. The task list is provided as input, and based on that, it meticulously organizes the order, dependencies, and assignees of each task, outputting the WBS. This clarifies the overall picture of the project.

[0328] Step 5:

[0329] The server uses the Work Breakdown Structure (WBS) and project information to automatically generate necessary documents such as procedure manuals and safety standards. The inputs are the WBS and project information, and the Jinja2 template engine is used to apply this data to templates, resulting in completed documents as output.

[0330] Step 6:

[0331] The generated WBS and documents are sent to the user's terminal, where the user can refer to them and make corrections and verifications as needed. The input is the output, and the output is the final, verified document and WBS with the user's feedback.

[0332] Step 7:

[0333] Ultimately, the server stores the user-confirmed information in a database and updates the generated AI model for handling future special cases. The input is confirmed information data, which is used to expand the model's training data, resulting in an updated model as output.

[0334] 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.

[0335] This invention combines an emotion engine with a system that enhances the efficiency of managing special cases, thereby realizing project management that takes user emotions into consideration.

[0336] First, the user inputs basic information about the special case through the terminal interface. The terminal sends this information to the emotion engine. The emotion engine analyzes the user's emotions from the input data and selection actions. This analysis identifies the user's emotional state, such as stress level, anxiety, and satisfaction.

[0337] Subsequently, the terminal transfers the case information along with the sentiment analysis results sent from the sentiment engine to the server. Based on the received information, the server searches the past case database and identifies similar cases. The server utilizes a generative AI model to automatically generate a task list from similar cases and considers prioritizing and reallocating tasks based on the user's emotional state.

[0338] Next, the server generates a Work Breakdown Structure (WBS) for the project. In doing so, it takes into account the user's emotions, as recognized by the emotion engine, and adjusts task allocation and scheduling flexibility to provide a plan that minimizes user stress.

[0339] Even in the automated document generation process, user emotions are reflected. The server selects a document template and generates the necessary document, adjusting the tone and wording based on the user's current emotions. The generated document is then presented to the user via their terminal.

[0340] Furthermore, the emotion engine captures real-time user feedback and incorporates it into the project plan. This allows project management to continuously evolve and be optimized through interaction with users.

[0341] For example, if a user is experiencing high stress levels due to a busy schedule, the emotion engine recognizes this situation and instructs the server to postpone lower-priority tasks to later dates, adjusting the Work Breakdown Structure (WBS) to allow the user to focus on important tasks. Furthermore, the generated reports are written with emotionally sensitive language, including encouraging messages. In this way, the system harmonizes user emotions with project progress, improving the user experience and optimizing operational efficiency.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] Users input basic information about special cases through a terminal interface. During this process, the terminal also collects data on the user's keyboard and mouse movements, as well as their input speed, as indicators of their emotional state.

[0345] Step 2:

[0346] The terminal sends the entered case information and data that serves as an indicator of emotion to the emotion engine. The emotion engine analyzes this data and evaluates the user's emotional state (e.g., stress, exhilaration, concentration, etc.).

[0347] Step 3:

[0348] The emotion engine returns the analysis results to the server, reporting the user's emotional state. This result becomes an important parameter in case processing.

[0349] Step 4:

[0350] The server receives the user's case information and sentiment data, and searches for similar cases by referring to a database of past cases. Simultaneously, it uses a generative AI model to automatically generate a task list suitable for that case.

[0351] Step 5:

[0352] The server creates a Work Breakdown Structure (WBS) for the project based on the task list. During this process, it takes feedback from the emotion engine into consideration, adjusting task priorities and schedules to reduce user stress.

[0353] Step 6:

[0354] The server uses case information to select the necessary document templates, and based on the results of the sentiment engine, generates text to give the user a sense of security and satisfaction, and then creates the document.

[0355] Step 7:

[0356] The terminal presents the generated WBS and document to the user. The user can review the content and make revisions if necessary. Sentimental data is also collected during the revision process and analyzed again by the sentiment engine.

[0357] Step 8:

[0358] The server saves the finalized project information to a database, which is then used as training data for the emotion engine in future projects. This allows the system to continuously improve its ability to handle emotions.

[0359] (Example 2)

[0360] 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".

[0361] In managing special projects, it is essential to plan and execute work efficiently while considering the user's emotions. However, current systems fail to adequately reflect the user's emotional state in planning adjustments, which can increase stress and lead to a lack of flexibility in scheduling. To solve these problems, project management that takes emotional states into account in real time is necessary.

[0362] 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.

[0363] In this invention, the server includes means for receiving information on special cases and referring to a historical database; means for automatically generating a list of tasks from similar histories using a generative AI model; means for analyzing the user's emotional state and adjusting the priority of the task list; and means for adjusting the allocation of tasks to minimize the user's stress level. This enables efficient project management that takes the user's emotions into consideration.

[0364] "Special cases" refer to projects or tasks that require special handling by the user in order to improve management efficiency.

[0365] A "history database" is a collection of data that summarizes information about projects and tasks that have been carried out in the past.

[0366] A "generative AI model" is a form of artificial intelligence that automatically generates task lists and other outputs based on data.

[0367] A "task list" is a list that enumerates the tasks that need to be performed in a project or work.

[0368] "Stratified structure" is a structure for breaking down a project into stages, organizing and visualizing it.

[0369] "Emotional evaluation" is the process of identifying and evaluating a user's emotional state using numerical values ​​or categories.

[0370] "Document format" refers to the form and style of the generated document, and is a template that enables consistent expression.

[0371] "Priority adjustment" refers to the process of setting and adjusting the order in which tasks are performed based on their importance and urgency.

[0372] "Stress level" is an indicator that shows the psychological burden a user feels and is a factor that affects the performance of their work.

[0373] This invention provides a system for project management that takes user emotions into consideration. This system is implemented using a terminal, a server, an emotion engine, and a generative AI model.

[0374] First, the user enters basic information about the special case through the terminal. The terminal is equipped with an input interface that allows the user to easily enter information such as the case name, deadline, and required resources. The terminal then sends this case information to the emotion engine.

[0375] The emotion engine analyzes user input data and performs the necessary data calculations to identify the user's emotional state. Here, the emotion engine determines the user's stress level, satisfaction level, etc., and transmits the results to the server via the terminal. The emotion engine utilizes natural language processing technology to identify emotions based on the user's input data and operation history.

[0376] The server searches the history database based on the received case information and sentiment data. The history database stores past similar cases and their results, enabling similarity analysis. Using a generative AI model, the server generates a list of tasks based on knowledge gained from past similar cases, supporting optimal project management for the user.

[0377] For example, if a user is busy and experiencing high stress levels, the emotion engine recognizes this state and the server prioritizes lower-priority tasks, redistributing the workload so that the user can focus on important tasks. Furthermore, the generated documents automatically include encouraging messages that take the user's emotions into consideration.

[0378] An example of a prompt message would be, "Determine the optimal task order based on the user's sentiment analysis results."

[0379] Thus, the present invention appropriately considers the user's emotions and realizes more efficient and less stressful project management.

[0380] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0381] Step 1:

[0382] The user inputs basic information about a special case through the terminal. The terminal then transmits the information received from the user, such as the case name, deadline, and required resources, to the sentiment engine. The input information is used as basic data for sentiment analysis.

[0383] Step 2:

[0384] The device sends input data to the emotion engine, which analyzes the user's emotional state. Based on the user's input and past operation patterns, the emotion engine identifies the user's stress level and satisfaction level. It quantifies the emotional state through data calculations and sends this quantified value to the server via the device.

[0385] Step 3:

[0386] The server uses the received case information and sentiment data to refer to the historical database and search for similar cases. This extracts data on similar cases and prepares it for the next generation AI model. Similarity analysis is performed within the database based on the input data.

[0387] Step 4:

[0388] The server uses a generative AI model to automatically generate a list of tasks from similar cases. Based on the input data of similar cases, the AI ​​outputs the optimal task list and determines its priority. The output task list is optimized according to the user's emotional state.

[0389] Step 5:

[0390] The server analyzes the user's emotional state and automatically creates a Work Breakdown Structure (WBS) based on the generated task list. Prompts adjust the order and importance of tasks to minimize user stress, resulting in an efficient project plan presented to the user.

[0391] (Application Example 2)

[0392] 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."

[0393] In managing specialized projects, the challenge lies in reducing the emotional burden faced by users and optimizing project progress efficiency. Furthermore, it is necessary to reduce the mental stress on factory workers and ensure the efficient operation of support equipment.

[0394] 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.

[0395] In this invention, the server includes means for acquiring information on special cases and referring to a collection of past case information, means for automatically generating task lists from similar cases using a generation AI model, and means for performing sentiment analysis and adjusting the flexibility of work breakdown configurations and schedules based on the user's emotional state. This enables flexible project management and optimization of workload in accordance with the user's emotions.

[0396] A "special case" refers to a project or task that includes special requirements or conditions that differ from normal operations.

[0397] An "information collection" is a database containing data on past projects and tasks.

[0398] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate task lists from similar cases.

[0399] A "task list" is a list that compiles the individual tasks required for a project or task.

[0400] "Work breakdown structure" refers to a systematic organization of a project by dividing the entire project into smaller tasks.

[0401] A "document template" is a pre-defined format used when creating a document, designed to quickly generate content.

[0402] "Emotional analysis" is a process that analyzes the emotional state of a user based on their input data to determine their stress level and satisfaction level.

[0403] "Assistive devices" are automated devices or systems used to reduce the burden on workers.

[0404] This invention realizes a project management system that takes user emotions into consideration. The system first sends information about a special case entered by the user via a terminal to a server. Based on this information, the server searches a database of past case information and identifies similar cases. The server then uses a generative AI model to automatically generate a task list from similar cases. Here, the task list organizes the individual tasks required for the project. At this time, a work breakdown structure is created based on the task list, and the entire project is systematically divided.

[0405] The system also incorporates an emotion analysis function, which analyzes data entered by the user from their device to understand the user's emotional state (such as stress levels and satisfaction levels). This emotion analysis can be performed using a device with specific emotion analysis software installed or a cloud-based service. A concrete example is the use of Microsoft Azure's emotion analysis API.

[0406] Based on the results of sentiment analysis, the server adjusts the task breakdown structure to suit the user. This makes it possible to provide a project plan that takes into account the flexibility of the task list and schedule in order to reduce user stress. For example, if the user is in a high-stress state, the server will adjust by postponing lower-priority tasks and focusing on important tasks.

[0407] Furthermore, the server selects a dedicated document template and automatically generates documents with a tone and language that matches the user's emotions. This allows information to be provided in a considerate manner to the user.

[0408] The system also takes into account adjustments to assistive devices, allowing the server to provide instructions to optimize the operation of robots and other assistive devices based on the worker's emotions. This reduces the burden on workers and supports efficient work in factory and other work environments.

[0409] A concrete example of a prompt message would be: "Factory worker's emotional analysis result: High stress level. We want to redistribute tasks for the next shift and maximize the use of assistive devices. Please generate specific suggestions." This system aims to harmonize the user's emotions with the progress of the project, thereby improving work efficiency.

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The user uses a terminal to input information about a special case. This information includes the project name, deadline, and resource usage. The terminal then sends this information to the server. As output, the terminal sends digital data of the case information to the server.

[0413] Step 2:

[0414] The server searches the case information database based on the received special case information and identifies similar cases. This search process uses database queries and compares them with past case information. A list of similar cases is generated as output.

[0415] Step 3:

[0416] The server uses a generative AI model to automatically generate a task list from identified similar cases. The input is the list of similar cases obtained in step 2, and the generative AI model receives prompts based on this and constructs the task list. A recommended task list is provided as output.

[0417] Step 4:

[0418] Based on data provided by the user, the device performs sentiment analysis to determine the user's emotional state (such as stress level and satisfaction level). A sentiment analysis API is used for this determination. The device's output is the analyzed data regarding the user's emotional state.

[0419] Step 5:

[0420] The server adjusts the work breakdown structure based on the task list generated in step 3 and the user's emotional state determined in step 4. Here, it performs calculations to re-evaluate task priorities in order to reduce user stress. The output is the adjusted work breakdown structure.

[0421] Step 6:

[0422] The server selects a document template and automatically generates a document in a tone appropriate to the user's emotional state. This uses a template selection algorithm and natural language generation software. As output, a document in a user-friendly format is generated and sent to the terminal.

[0423] Step 7:

[0424] The server generates instructions to optimize the operation of assistive devices based on the user's emotional state. Specifically, it issues operational instructions that assign tasks to the assistive devices that reduce the user's burden. The server's output is data of operational instructions for the assistive devices.

[0425] 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.

[0426] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0427] 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.

[0428] [Third Embodiment]

[0429] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0430] 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.

[0431] 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).

[0432] 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.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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".

[0441] This invention is designed as a system for the efficient management of special cases and the automatic generation of documents. Its embodiments are described below.

[0442] First, the user inputs information about the special case into the interface via their terminal. This information includes the case name, deadline, and detailed information about the client. The terminal then sends this information to the server.

[0443] The server references a database of past cases based on the received case information. It searches for similar past cases and automatically generates a task list using a generative AI model. The generative AI model used here learns from past case data using machine learning techniques and has the ability to extract tasks suitable for a specific case.

[0444] Next, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated task list. The WBS includes information about the start and end dates, dependencies, and resources responsible for each task.

[0445] Furthermore, the server selects the necessary document templates based on project information and schedules, automatically inputs the information, and generates the documents. This process may include documents such as special permit applications and contracts.

[0446] Once generation is complete, the terminal presents the WBS and documents to the user. The user reviews them, makes corrections if necessary, and performs a final check. This makes it possible to improve the accuracy of tasks while increasing work efficiency.

[0447] Finally, the server saves the generated information to a database and registers it as a case record. This data is also used as training data for the generating AI model to help handle future special cases. Through this cycle, the system continuously improves and optimizes itself, enabling it to make higher-quality proposals.

[0448] As a concrete example, consider a project to implement a new software system. In this case, the server compares past similar system implementation projects and generates a list of tasks required for implementation, such as system testing, user training, and data migration. Based on these tasks, it automatically generates necessary documents, such as usage permission applications and meeting minutes, supporting smooth project progress. By consistently automating the process, the workload is reduced, and high-quality project management is achieved.

[0449] The following describes the processing flow.

[0450] Step 1:

[0451] The user accesses the terminal interface and enters basic information for a new special case. This includes the case name, deadline, client information, and related details.

[0452] Step 2:

[0453] The terminal sends the entered case information to the server. This establishes baseline data for processing and managing cases.

[0454] Step 3:

[0455] Based on the received case information, the server queries the past case database to search for similar past case examples.

[0456] Step 4:

[0457] The server uses a generative AI model to analyze and extract task lists of similar cases from the search results. This model has been trained on historical data using machine learning.

[0458] Step 5:

[0459] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the extracted task list. Each task is assigned a start date, an end date, and dependencies.

[0460] Step 6:

[0461] The server selects the necessary document template based on the project information and task list, automatically fills in the required fields, and generates the document.

[0462] Step 7:

[0463] The terminal presents the generated WBS and documentation to the user. The user can review them and make modifications if necessary.

[0464] Step 8:

[0465] The server saves the finalized WBS and documents to a database, recording them as project achievements. This information is used for future project processing and also for training generative AI models.

[0466] (Example 1)

[0467] 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."

[0468] Traditional manual processes for managing specialized tasks and generating related documentation are time-consuming and labor-intensive, posing challenges to efficiency and accuracy. In particular, the time required for learning from similar past tasks and designing new work items complicates project management. Therefore, there is a need for a system that efficiently and accurately manages specialized tasks and automatically generates documentation.

[0469] 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.

[0470] In this invention, the server includes a device that receives information on special tasks and references past task data, a device that automatically generates a task list from similar past tasks using a machine learning model, and a device that automatically creates a project structure based on the automatically generated task list. This streamlines the management of special tasks and the document generation process, enabling rapid and accurate project progress.

[0471] "Specialized work" refers to tasks or projects performed based on specific requirements or objectives, requiring special management and documentation that differs from normal business processes.

[0472] A "device that receives information" is a device that has the function of acquiring data input from a user and incorporating it into the system.

[0473] "Past work data" refers to a database containing records of similar tasks completed in the past, providing information that can be used in the current work.

[0474] A "machine learning model" is a form of artificial intelligence that has an algorithm to learn patterns from past data and generate a new list of tasks.

[0475] A "task list" refers to a list that enumerates and organizes the tasks required for a specific project, and its purpose is to improve the efficiency of project management.

[0476] "Project structure" refers to a hierarchical configuration that shows the dependencies and schedules of tasks in a project plan, visually representing the sequence of work and the timeline.

[0477] A "document template" refers to a pre-prepared document model tailored to a specific purpose, providing a foundation for quickly entering necessary information to complete the final document.

[0478] A "document generation device" is a device that has the function of creating a document in a specific format based on the input information.

[0479] This invention is a system for managing special tasks and automatically generating related documents. The embodiments thereof are described below.

[0480] First, the user inputs information about a specific task into the interface via the terminal. The terminal provides a form-based interface, and the user obtains the necessary information by typing on the keyboard. This information is validated and then sent to the server. Data transmission from the terminal is performed via HTTP requests using a secure SSL / TLS connection.

[0481] Based on the received information, the server uses SQL queries to access a database of past work. This extracts similar past work and prompts a generative AI model to generate a new list of work. The generative AI model used is equipped with machine learning algorithms that learn from historical data and have the ability to extract tasks suitable for specific work.

[0482] Based on the generated task list, the server automatically creates the project structure using a dedicated algorithm. The project structure is visualized in a Gantt chart format, showing task dependencies and schedules. This automatically generated structure contributes to more efficient and accurate project management.

[0483] Furthermore, the server selects the necessary document template based on specific work information, automatically inputs the information, and creates the document. Libraries such as PDFKit are used for document generation, and the final document is provided in PDF format.

[0484] Users can view the generated documents and project structure through their terminal. The system displays the generated information on the screen, and users can review and modify it on the interface. If necessary, the terminal resends the modifications to the server.

[0485] After this series of processes is complete, the server saves all generated information to a recording device. The saved data will be used as training data for generative AI models in future specialized tasks and will be utilized to improve the system's functionality.

[0486] A concrete example is the implementation of a new software system. In this case, the server refers to past system implementation data and generates a work list that includes tasks such as system testing, user training, and data migration. Based on the generated tasks, necessary documents such as usage permission applications and meeting minutes are automatically generated, enabling smooth project management. An example of a prompt to be entered into the generation AI model is "Please list the tasks appropriate for this project." This prompt allows the generation AI model to create an accurate work list based on past data.

[0487] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0488] Step 1:

[0489] The user enters project information into the interface via their terminal. This information includes project name, deadline, and client details. This input data is validated in real-time on the terminal and sent to the server only after it has been completed. The terminal uses a secure SSL / TLS connection to send information to the server via HTTP requests.

[0490] Step 2:

[0491] The server retrieves case information received from the terminal and references the past work database using SQL queries. This database search allows the server to extract similar past cases and obtain relevant data. The extracted data is then prepared for generating a new work list.

[0492] Step 3:

[0493] The server sends a prompt to the generative AI model, which generates a new task list. For example, with the prompt "List tasks suitable for this case," the server inputs case information and historical data into the generative AI model, and uses machine learning techniques to generate a task list. The generated task list is returned to the server in JSON format and used for further processing.

[0494] Step 4:

[0495] The server automatically creates the project structure based on the generated task list. Using a dedicated algorithm, the server analyzes the task list and builds a schedule and dependencies in Gantt chart format. This determines the start date, end date, and resource allocation for each task, visualizing the overall project structure.

[0496] Step 5:

[0497] The server selects the necessary document template based on project information and schedule, automatically inputs the information, and generates the document. In this process, the server uses a library (e.g., PDFKit) to embed the necessary information into the document template, preparing it for the final PDF document generation.

[0498] Step 6:

[0499] The terminal displays the structure of the generated documents and projects to the user and prompts for confirmation. The user can review the details of each document and project through the interface and make modifications as needed. The terminal resends the user's changes to the server for final confirmation.

[0500] Step 7:

[0501] The server stores the finalized information in a database. The stored data includes the final version of the document, work lists, and project structure. Furthermore, the stored data is used as training data for generating AI models for future projects, contributing to the continuous improvement and optimization of the models.

[0502] (Application Example 1)

[0503] 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."

[0504] In industrial environments, managing specialized projects requires processing large amounts of information and efficiently managing multiple processes. However, current systems require significant effort to create task lists and generate documents, potentially leading to inefficiencies and errors. This results in challenges such as work delays and decreased quality.

[0505] 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.

[0506] This invention includes a server that includes means for acquiring information for specific cases and referencing a database of past cases, means for automatically creating task lists from similar cases using generative AI technology, and means for coordinating and scheduling specific tasks within equipment used in industrial environments. This enables efficient management of related tasks and rapid automation of necessary procedures and safety standards.

[0507] A "special case" is a case that differs from normal work or projects and involves special requirements or conditions.

[0508] A "case study database" is a database that organizes, stores, and makes searchable information about past projects and operations.

[0509] "Generative AI technology" is a technique that uses machine learning models to generate new tasks and predictions based on past data.

[0510] A "task list" is a list that organizes the specific tasks and processes that need to be performed in a project or job.

[0511] A "work assignment structure" is a plan that clearly defines the relationships, sequence, and responsibilities of each task within a project.

[0512] "Specific tasks within a device" refers to specific tasks or processes performed by machines or robots used in industrial environments.

[0513] "Scheduling" refers to planning the timing and order of each task and organizing them as a schedule.

[0514] A "procedure manual" is a document that describes in detail how to perform a specific task or operation.

[0515] "Safety standards" are regulations and guidelines designed to ensure safety in industries and workplaces.

[0516] To implement this invention, a system is constructed in which a server, a data input terminal, and equipment used in an industrial environment work together. The server manages information on special cases and uses a database of past cases to generate task lists and work assignment structures using generative AI technology.

[0517] The server executes processing using programming languages ​​and frameworks such as Python and PyTorch. SQLite is used as the database to store historical data for each case. A data entry terminal is used by users to input information, which is then sent to the server. Based on the received information, the server applies a learning model and automatically generates necessary procedures and safety standards using templates. This utilizes the Jinja2 template engine.

[0518] As a concrete example, consider a project to introduce a new product line. In this case, project information is sent from a terminal to a server, which then refers to a database of similar past projects to extract the necessary processes and safety standards. Based on the generated plan and documentation, a schedule is created to ensure that the equipment efficiently performs specific tasks. This is expected to ensure that the project is completed efficiently and on time.

[0519] By using a generative AI model, task lists and plans can be effectively generated by inputting specific prompts. The following are examples of prompts:

[0520] "Automatically create a task list related to the new product line implementation project. This will generate an efficient WBS and related documentation, supporting the smooth progress of the project."

[0521] This system is an effective tool for supporting project management in industry.

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The user uses a data entry terminal to input information about a special case (such as the case name, deadline, and detailed information about the client). This information is sent to the server as input. The server, upon receiving the information, temporarily records it.

[0525] Step 2:

[0526] The server references a database of past cases based on the received case information. To identify similar cases, it performs a similarity search using the metadata of the input information and extracts highly relevant past case data. In this process, the input is the configured metadata, and the output is a list of similar cases.

[0527] Step 3:

[0528] The server uses a generative AI model to automatically generate task lists based on extracted similar cases. The input is data from past cases, and the output is a set of task lists suitable for the current case. In this process, the AI ​​model uses patterns learned from past cases to refine the tasks.

[0529] Step 4:

[0530] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the generated task list. The task list is provided as input, and based on that, it meticulously organizes the order, dependencies, and assignees of each task, outputting the WBS. This clarifies the overall picture of the project.

[0531] Step 5:

[0532] The server uses the Work Breakdown Structure (WBS) and project information to automatically generate necessary documents such as procedure manuals and safety standards. The inputs are the WBS and project information, and the Jinja2 template engine is used to apply this data to templates, resulting in completed documents as output.

[0533] Step 6:

[0534] The generated WBS and documents are sent to the user's terminal, where the user can refer to them and make corrections and verifications as needed. The input is the output, and the output is the final, verified document and WBS with the user's feedback.

[0535] Step 7:

[0536] Ultimately, the server stores the user-confirmed information in a database and updates the generated AI model for handling future special cases. The input is confirmed information data, which is used to expand the model's training data, resulting in an updated model as output.

[0537] 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.

[0538] This invention combines an emotion engine with a system that enhances the efficiency of managing special cases, thereby realizing project management that takes user emotions into consideration.

[0539] First, the user inputs basic information about the special case through the terminal interface. The terminal sends this information to the emotion engine. The emotion engine analyzes the user's emotions from the input data and selection actions. This analysis identifies the user's emotional state, such as stress level, anxiety, and satisfaction.

[0540] Subsequently, the terminal transfers the case information along with the sentiment analysis results sent from the sentiment engine to the server. Based on the received information, the server searches the past case database and identifies similar cases. The server utilizes a generative AI model to automatically generate a task list from similar cases and considers prioritizing and reallocating tasks based on the user's emotional state.

[0541] Next, the server generates a Work Breakdown Structure (WBS) for the project. In doing so, it takes into account the user's emotions, as recognized by the emotion engine, and adjusts task allocation and scheduling flexibility to provide a plan that minimizes user stress.

[0542] Even in the automated document generation process, user emotions are reflected. The server selects a document template and generates the necessary document, adjusting the tone and wording based on the user's current emotions. The generated document is then presented to the user via their terminal.

[0543] Furthermore, the emotion engine captures real-time user feedback and incorporates it into the project plan. This allows project management to continuously evolve and be optimized through interaction with users.

[0544] For example, if a user is experiencing high stress levels due to a busy schedule, the emotion engine recognizes this situation and instructs the server to postpone lower-priority tasks to later dates, adjusting the Work Breakdown Structure (WBS) to allow the user to focus on important tasks. Furthermore, the generated reports are written with emotionally sensitive language, including encouraging messages. In this way, the system harmonizes user emotions with project progress, improving the user experience and optimizing operational efficiency.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] Users input basic information about special cases through a terminal interface. During this process, the terminal also collects data on the user's keyboard and mouse movements, as well as their input speed, as indicators of their emotional state.

[0548] Step 2:

[0549] The terminal sends the entered case information and data that serves as an indicator of emotion to the emotion engine. The emotion engine analyzes this data and evaluates the user's emotional state (e.g., stress, exhilaration, concentration, etc.).

[0550] Step 3:

[0551] The emotion engine returns the analysis results to the server, reporting the user's emotional state. This result becomes an important parameter in case processing.

[0552] Step 4:

[0553] The server receives the user's case information and sentiment data, and searches for similar cases by referring to a database of past cases. Simultaneously, it uses a generative AI model to automatically generate a task list suitable for that case.

[0554] Step 5:

[0555] The server creates a Work Breakdown Structure (WBS) for the project based on the task list. During this process, it takes feedback from the emotion engine into consideration, adjusting task priorities and schedules to reduce user stress.

[0556] Step 6:

[0557] The server uses case information to select the necessary document templates, and based on the results of the sentiment engine, generates text to give the user a sense of security and satisfaction, and then creates the document.

[0558] Step 7:

[0559] The terminal presents the generated WBS and document to the user. The user can review the content and make revisions if necessary. Sentimental data is also collected during the revision process and analyzed again by the sentiment engine.

[0560] Step 8:

[0561] The server saves the finalized project information to a database, which is then used as training data for the emotion engine in future projects. This allows the system to continuously improve its ability to handle emotions.

[0562] (Example 2)

[0563] 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."

[0564] In managing special projects, it is essential to plan and execute work efficiently while considering the user's emotions. However, current systems fail to adequately reflect the user's emotional state in planning adjustments, which can increase stress and lead to a lack of flexibility in scheduling. To solve these problems, project management that takes emotional states into account in real time is necessary.

[0565] 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.

[0566] In this invention, the server includes means for receiving information on special cases and referring to a historical database; means for automatically generating a list of tasks from similar histories using a generative AI model; means for analyzing the user's emotional state and adjusting the priority of the task list; and means for adjusting the allocation of tasks to minimize the user's stress level. This enables efficient project management that takes the user's emotions into consideration.

[0567] "Special cases" refer to projects or tasks that require special handling by the user in order to improve management efficiency.

[0568] A "history database" is a collection of data that summarizes information about projects and tasks that have been carried out in the past.

[0569] A "generative AI model" is a form of artificial intelligence that automatically generates task lists and other outputs based on data.

[0570] A "task list" is a list that enumerates the tasks that need to be performed in a project or work.

[0571] "Stratified structure" is a structure for breaking down a project into stages, organizing and visualizing it.

[0572] "Emotional evaluation" is the process of identifying and evaluating a user's emotional state using numerical values ​​or categories.

[0573] "Document format" refers to the form and style of the generated document, and is a template that enables consistent expression.

[0574] "Priority adjustment" refers to the process of setting and adjusting the order in which tasks are performed based on their importance and urgency.

[0575] "Stress level" is an indicator that shows the psychological burden a user feels and is a factor that affects the performance of their work.

[0576] This invention provides a system for project management that takes user emotions into consideration. This system is implemented using a terminal, a server, an emotion engine, and a generative AI model.

[0577] First, the user enters basic information about the special case through the terminal. The terminal is equipped with an input interface that allows the user to easily enter information such as the case name, deadline, and required resources. The terminal then sends this case information to the emotion engine.

[0578] The emotion engine analyzes user input data and performs the necessary data calculations to identify the user's emotional state. Here, the emotion engine determines the user's stress level, satisfaction level, etc., and transmits the results to the server via the terminal. The emotion engine utilizes natural language processing technology to identify emotions based on the user's input data and operation history.

[0579] The server searches the history database based on the received case information and sentiment data. The history database stores past similar cases and their results, enabling similarity analysis. Using a generative AI model, the server generates a list of tasks based on knowledge gained from past similar cases, supporting optimal project management for the user.

[0580] For example, if a user is busy and experiencing high stress levels, the emotion engine recognizes this state and the server prioritizes lower-priority tasks, redistributing the workload so that the user can focus on important tasks. Furthermore, the generated documents automatically include encouraging messages that take the user's emotions into consideration.

[0581] An example of a prompt message would be, "Determine the optimal task order based on the user's sentiment analysis results."

[0582] Thus, the present invention appropriately considers the user's emotions and realizes more efficient and less stressful project management.

[0583] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0584] Step 1:

[0585] The user inputs basic information about a special case through the terminal. The terminal then transmits the information received from the user, such as the case name, deadline, and required resources, to the sentiment engine. The input information is used as basic data for sentiment analysis.

[0586] Step 2:

[0587] The device sends input data to the emotion engine, which analyzes the user's emotional state. Based on the user's input and past operation patterns, the emotion engine identifies the user's stress level and satisfaction level. It quantifies the emotional state through data calculations and sends this quantified value to the server via the device.

[0588] Step 3:

[0589] The server uses the received case information and sentiment data to refer to the historical database and search for similar cases. This extracts data on similar cases and prepares it for the next generation AI model. Similarity analysis is performed within the database based on the input data.

[0590] Step 4:

[0591] The server uses a generative AI model to automatically generate a list of tasks from similar cases. Based on the input data of similar cases, the AI ​​outputs the optimal task list and determines its priority. The output task list is optimized according to the user's emotional state.

[0592] Step 5:

[0593] The server analyzes the user's emotional state and automatically creates a Work Breakdown Structure (WBS) based on the generated task list. Prompts adjust the order and importance of tasks to minimize user stress, resulting in an efficient project plan presented to the user.

[0594] (Application Example 2)

[0595] 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."

[0596] In managing specialized projects, the challenge lies in reducing the emotional burden faced by users and optimizing project progress efficiency. Furthermore, it is necessary to reduce the mental stress on factory workers and ensure the efficient operation of support equipment.

[0597] 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.

[0598] In this invention, the server includes means for acquiring information on special cases and referring to a collection of past case information, means for automatically generating task lists from similar cases using a generation AI model, and means for performing sentiment analysis and adjusting the flexibility of work breakdown configurations and schedules based on the user's emotional state. This enables flexible project management and optimization of workload in accordance with the user's emotions.

[0599] A "special case" refers to a project or task that includes special requirements or conditions that differ from normal operations.

[0600] An "information collection" is a database containing data on past projects and tasks.

[0601] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate task lists from similar cases.

[0602] A "task list" is a list that compiles the individual tasks required for a project or task.

[0603] "Work breakdown structure" refers to a systematic organization of a project by dividing the entire project into smaller tasks.

[0604] A "document template" is a pre-defined format used when creating a document, designed to quickly generate content.

[0605] "Emotional analysis" is a process that analyzes the emotional state of a user based on their input data to determine their stress level and satisfaction level.

[0606] "Assistive devices" are automated devices or systems used to reduce the burden on workers.

[0607] This invention realizes a project management system that takes user emotions into consideration. The system first sends information about a special case entered by the user via a terminal to a server. Based on this information, the server searches a database of past case information and identifies similar cases. The server then uses a generative AI model to automatically generate a task list from similar cases. Here, the task list organizes the individual tasks required for the project. At this time, a work breakdown structure is created based on the task list, and the entire project is systematically divided.

[0608] The system also incorporates an emotion analysis function, which analyzes data entered by the user from their device to understand the user's emotional state (such as stress levels and satisfaction levels). This emotion analysis can be performed using a device with specific emotion analysis software installed or a cloud-based service. A concrete example is the use of Microsoft Azure's emotion analysis API.

[0609] Based on the results of sentiment analysis, the server adjusts the task breakdown structure to suit the user. This makes it possible to provide a project plan that takes into account the flexibility of the task list and schedule in order to reduce user stress. For example, if the user is in a high-stress state, the server will adjust by postponing lower-priority tasks and focusing on important tasks.

[0610] Furthermore, the server selects a dedicated document template and automatically generates documents with a tone and language that matches the user's emotions. This allows information to be provided in a considerate manner to the user.

[0611] The system also takes into account adjustments to assistive devices, allowing the server to provide instructions to optimize the operation of robots and other assistive devices based on the worker's emotions. This reduces the burden on workers and supports efficient work in factory and other work environments.

[0612] A concrete example of a prompt message would be: "Factory worker's emotional analysis result: High stress level. We want to redistribute tasks for the next shift and maximize the use of assistive devices. Please generate specific suggestions." This system aims to harmonize the user's emotions with the progress of the project, thereby improving work efficiency.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The user uses a terminal to input information about a special case. This information includes the project name, deadline, and resource usage. The terminal then sends this information to the server. As output, the terminal sends digital data of the case information to the server.

[0616] Step 2:

[0617] The server searches the case information database based on the received special case information and identifies similar cases. This search process uses database queries and compares them with past case information. A list of similar cases is generated as output.

[0618] Step 3:

[0619] The server uses a generative AI model to automatically generate a task list from identified similar cases. The input is the list of similar cases obtained in step 2, and the generative AI model receives prompts based on this and constructs the task list. A recommended task list is provided as output.

[0620] Step 4:

[0621] Based on data provided by the user, the device performs sentiment analysis to determine the user's emotional state (such as stress level and satisfaction level). A sentiment analysis API is used for this determination. The device's output is the analyzed data regarding the user's emotional state.

[0622] Step 5:

[0623] The server adjusts the work breakdown structure based on the task list generated in step 3 and the user's emotional state determined in step 4. Here, it performs calculations to re-evaluate task priorities in order to reduce user stress. The output is the adjusted work breakdown structure.

[0624] Step 6:

[0625] The server selects a document template and automatically generates a document in a tone appropriate to the user's emotional state. This uses a template selection algorithm and natural language generation software. As output, a document in a user-friendly format is generated and sent to the terminal.

[0626] Step 7:

[0627] The server generates instructions to optimize the operation of assistive devices based on the user's emotional state. Specifically, it issues operational instructions that assign tasks to the assistive devices that reduce the user's burden. The server's output is data of operational instructions for the assistive devices.

[0628] 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.

[0629] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0630] 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.

[0631] [Fourth Embodiment]

[0632] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0633] 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.

[0634] 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).

[0635] 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.

[0636] 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.

[0637] 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).

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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".

[0645] This invention is designed as a system for the efficient management of special cases and the automatic generation of documents. Its embodiments are described below.

[0646] First, the user inputs information about the special case into the interface via their terminal. This information includes the case name, deadline, and detailed information about the client. The terminal then sends this information to the server.

[0647] The server references a database of past cases based on the received case information. It searches for similar past cases and automatically generates a task list using a generative AI model. The generative AI model used here learns from past case data using machine learning techniques and has the ability to extract tasks suitable for a specific case.

[0648] Next, the server automatically creates a Work Breakdown Structure (WBS) for the project based on the generated task list. The WBS includes information about the start and end dates, dependencies, and resources responsible for each task.

[0649] Furthermore, the server selects the necessary document templates based on project information and schedules, automatically inputs the information, and generates the documents. This process may include documents such as special permit applications and contracts.

[0650] Once generation is complete, the terminal presents the WBS and documents to the user. The user reviews them, makes corrections if necessary, and performs a final check. This makes it possible to improve the accuracy of tasks while increasing work efficiency.

[0651] Finally, the server saves the generated information to a database and registers it as a case record. This data is also used as training data for the generating AI model to help handle future special cases. Through this cycle, the system continuously improves and optimizes itself, enabling it to make higher-quality proposals.

[0652] As a concrete example, consider a project to implement a new software system. In this case, the server compares past similar system implementation projects and generates a list of tasks required for implementation, such as system testing, user training, and data migration. Based on these tasks, it automatically generates necessary documents, such as usage permission applications and meeting minutes, supporting smooth project progress. By consistently automating the process, the workload is reduced, and high-quality project management is achieved.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] The user accesses the terminal interface and enters basic information for a new special case. This includes the case name, deadline, client information, and related details.

[0656] Step 2:

[0657] The terminal sends the entered case information to the server. This establishes baseline data for processing and managing cases.

[0658] Step 3:

[0659] Based on the received case information, the server queries the past case database to search for similar past case examples.

[0660] Step 4:

[0661] The server uses a generative AI model to analyze and extract task lists of similar cases from the search results. This model has been trained on historical data using machine learning.

[0662] Step 5:

[0663] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the extracted task list. Each task is assigned a start date, an end date, and dependencies.

[0664] Step 6:

[0665] The server selects the necessary document template based on the project information and task list, automatically fills in the required fields, and generates the document.

[0666] Step 7:

[0667] The terminal presents the generated WBS and documentation to the user. The user can review them and make modifications if necessary.

[0668] Step 8:

[0669] The server saves the finalized WBS and documents to a database, recording them as project achievements. This information is used for future project processing and also for training generative AI models.

[0670] (Example 1)

[0671] 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".

[0672] Traditional manual processes for managing specialized tasks and generating related documentation are time-consuming and labor-intensive, posing challenges to efficiency and accuracy. In particular, the time required for learning from similar past tasks and designing new work items complicates project management. Therefore, there is a need for a system that efficiently and accurately manages specialized tasks and automatically generates documentation.

[0673] 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.

[0674] In this invention, the server includes a device that receives information on special tasks and references past task data, a device that automatically generates a task list from similar past tasks using a machine learning model, and a device that automatically creates a project structure based on the automatically generated task list. This streamlines the management of special tasks and the document generation process, enabling rapid and accurate project progress.

[0675] "Specialized work" refers to tasks or projects performed based on specific requirements or objectives, requiring special management and documentation that differs from normal business processes.

[0676] A "device that receives information" is a device that has the function of acquiring data input from a user and incorporating it into the system.

[0677] "Past work data" refers to a database containing records of similar tasks completed in the past, providing information that can be used in the current work.

[0678] A "machine learning model" is a form of artificial intelligence that has an algorithm to learn patterns from past data and generate a new list of tasks.

[0679] A "task list" refers to a list that enumerates and organizes the tasks required for a specific project, and its purpose is to improve the efficiency of project management.

[0680] "Project structure" refers to a hierarchical configuration that shows the dependencies and schedules of tasks in a project plan, visually representing the sequence of work and the timeline.

[0681] A "document template" refers to a pre-prepared document model tailored to a specific purpose, providing a foundation for quickly entering necessary information to complete the final document.

[0682] A "document generation device" is a device that has the function of creating a document in a specific format based on the input information.

[0683] This invention is a system for managing special tasks and automatically generating related documents. The embodiments thereof are described below.

[0684] First, the user inputs information about a specific task into the interface via the terminal. The terminal provides a form-based interface, and the user obtains the necessary information by typing on the keyboard. This information is validated and then sent to the server. Data transmission from the terminal is performed via HTTP requests using a secure SSL / TLS connection.

[0685] Based on the received information, the server uses SQL queries to access a database of past work. This extracts similar past work and prompts a generative AI model to generate a new list of work. The generative AI model used is equipped with machine learning algorithms that learn from historical data and have the ability to extract tasks suitable for specific work.

[0686] Based on the generated task list, the server automatically creates the project structure using a dedicated algorithm. The project structure is visualized in a Gantt chart format, showing task dependencies and schedules. This automatically generated structure contributes to more efficient and accurate project management.

[0687] Furthermore, the server selects the necessary document template based on specific work information, automatically inputs the information, and creates the document. Libraries such as PDFKit are used for document generation, and the final document is provided in PDF format.

[0688] Users can view the generated documents and project structure through their terminal. The system displays the generated information on the screen, and users can review and modify it on the interface. If necessary, the terminal resends the modifications to the server.

[0689] After this series of processes is complete, the server saves all generated information to a recording device. The saved data will be used as training data for generative AI models in future specialized tasks and will be utilized to improve the system's functionality.

[0690] A concrete example is the implementation of a new software system. In this case, the server refers to past system implementation data and generates a work list that includes tasks such as system testing, user training, and data migration. Based on the generated tasks, necessary documents such as usage permission applications and meeting minutes are automatically generated, enabling smooth project management. An example of a prompt to be entered into the generation AI model is "Please list the tasks appropriate for this project." This prompt allows the generation AI model to create an accurate work list based on past data.

[0691] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0692] Step 1:

[0693] The user enters project information into the interface via their terminal. This information includes project name, deadline, and client details. This input data is validated in real-time on the terminal and sent to the server only after it has been completed. The terminal uses a secure SSL / TLS connection to send information to the server via HTTP requests.

[0694] Step 2:

[0695] The server retrieves case information received from the terminal and references the past work database using SQL queries. This database search allows the server to extract similar past cases and obtain relevant data. The extracted data is then prepared for generating a new work list.

[0696] Step 3:

[0697] The server sends a prompt to the generative AI model, which generates a new task list. For example, with the prompt "List tasks suitable for this case," the server inputs case information and historical data into the generative AI model, and uses machine learning techniques to generate a task list. The generated task list is returned to the server in JSON format and used for further processing.

[0698] Step 4:

[0699] The server automatically creates the project structure based on the generated task list. Using a dedicated algorithm, the server analyzes the task list and builds a schedule and dependencies in Gantt chart format. This determines the start date, end date, and resource allocation for each task, visualizing the overall project structure.

[0700] Step 5:

[0701] The server selects the necessary document template based on project information and schedule, automatically inputs the information, and generates the document. In this process, the server uses a library (e.g., PDFKit) to embed the necessary information into the document template, preparing it for the final PDF document generation.

[0702] Step 6:

[0703] The terminal displays the structure of the generated documents and projects to the user and prompts for confirmation. The user can review the details of each document and project through the interface and make modifications as needed. The terminal resends the user's changes to the server for final confirmation.

[0704] Step 7:

[0705] The server stores the finalized information in a database. The stored data includes the final version of the document, work lists, and project structure. Furthermore, the stored data is used as training data for generating AI models for future projects, contributing to the continuous improvement and optimization of the models.

[0706] (Application Example 1)

[0707] 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".

[0708] In industrial environments, managing specialized projects requires processing large amounts of information and efficiently managing multiple processes. However, current systems require significant effort to create task lists and generate documents, potentially leading to inefficiencies and errors. This results in challenges such as work delays and decreased quality.

[0709] 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.

[0710] This invention includes a server that includes means for acquiring information for specific cases and referencing a database of past cases, means for automatically creating task lists from similar cases using generative AI technology, and means for coordinating and scheduling specific tasks within equipment used in industrial environments. This enables efficient management of related tasks and rapid automation of necessary procedures and safety standards.

[0711] A "special case" is a case that differs from normal work or projects and involves special requirements or conditions.

[0712] A "case study database" is a database that organizes, stores, and makes searchable information about past projects and operations.

[0713] "Generative AI technology" is a technique that uses machine learning models to generate new tasks and predictions based on past data.

[0714] A "task list" is a list that organizes the specific tasks and processes that need to be performed in a project or job.

[0715] A "work assignment structure" is a plan that clearly defines the relationships, sequence, and responsibilities of each task within a project.

[0716] "Specific tasks within a device" refers to specific tasks or processes performed by machines or robots used in industrial environments.

[0717] "Scheduling" refers to planning the timing and order of each task and organizing them as a schedule.

[0718] A "procedure manual" is a document that describes in detail how to perform a specific task or operation.

[0719] "Safety standards" are regulations and guidelines designed to ensure safety in industries and workplaces.

[0720] To implement this invention, a system is constructed in which a server, a data input terminal, and equipment used in an industrial environment work together. The server manages information on special cases and uses a database of past cases to generate task lists and work assignment structures using generative AI technology.

[0721] The server executes processing using programming languages ​​and frameworks such as Python and PyTorch. SQLite is used as the database to store historical data for each case. A data entry terminal is used by users to input information, which is then sent to the server. Based on the received information, the server applies a learning model and automatically generates necessary procedures and safety standards using templates. This utilizes the Jinja2 template engine.

[0722] As a concrete example, consider a project to introduce a new product line. In this case, project information is sent from a terminal to a server, which then refers to a database of similar past projects to extract the necessary processes and safety standards. Based on the generated plan and documentation, a schedule is created to ensure that the equipment efficiently performs specific tasks. This is expected to ensure that the project is completed efficiently and on time.

[0723] By using a generative AI model, task lists and plans can be effectively generated by inputting specific prompts. The following are examples of prompts:

[0724] "Automatically create a task list related to the new product line implementation project. This will generate an efficient WBS and related documentation, supporting the smooth progress of the project."

[0725] This system is an effective tool for supporting project management in industry.

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The user uses a data entry terminal to input information about a special case (such as the case name, deadline, and detailed information about the client). This information is sent to the server as input. The server, upon receiving the information, temporarily records it.

[0729] Step 2:

[0730] The server references a database of past cases based on the received case information. To identify similar cases, it performs a similarity search using the metadata of the input information and extracts highly relevant past case data. In this process, the input is the configured metadata, and the output is a list of similar cases.

[0731] Step 3:

[0732] The server uses a generative AI model to automatically generate task lists based on extracted similar cases. The input is data from past cases, and the output is a set of task lists suitable for the current case. In this process, the AI ​​model uses patterns learned from past cases to refine the tasks.

[0733] Step 4:

[0734] The server automatically generates a Work Breakdown Structure (WBS) for the project based on the generated task list. The task list is provided as input, and based on that, it meticulously organizes the order, dependencies, and assignees of each task, outputting the WBS. This clarifies the overall picture of the project.

[0735] Step 5:

[0736] The server uses the Work Breakdown Structure (WBS) and project information to automatically generate necessary documents such as procedure manuals and safety standards. The inputs are the WBS and project information, and the Jinja2 template engine is used to apply this data to templates, resulting in completed documents as output.

[0737] Step 6:

[0738] The generated WBS and documents are sent to the user's terminal, where the user can refer to them and make corrections and verifications as needed. The input is the output, and the output is the final, verified document and WBS with the user's feedback.

[0739] Step 7:

[0740] Ultimately, the server stores the user-confirmed information in a database and updates the generated AI model for handling future special cases. The input is confirmed information data, which is used to expand the model's training data, resulting in an updated model as output.

[0741] 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.

[0742] This invention combines an emotion engine with a system that enhances the efficiency of managing special cases, thereby realizing project management that takes user emotions into consideration.

[0743] First, the user inputs basic information about the special case through the terminal interface. The terminal sends this information to the emotion engine. The emotion engine analyzes the user's emotions from the input data and selection actions. This analysis identifies the user's emotional state, such as stress level, anxiety, and satisfaction.

[0744] Subsequently, the terminal transfers the case information along with the sentiment analysis results sent from the sentiment engine to the server. Based on the received information, the server searches the past case database and identifies similar cases. The server utilizes a generative AI model to automatically generate a task list from similar cases and considers prioritizing and reallocating tasks based on the user's emotional state.

[0745] Next, the server generates a Work Breakdown Structure (WBS) for the project. In doing so, it takes into account the user's emotions, as recognized by the emotion engine, and adjusts task allocation and scheduling flexibility to provide a plan that minimizes user stress.

[0746] Even in the automated document generation process, user emotions are reflected. The server selects a document template and generates the necessary document, adjusting the tone and wording based on the user's current emotions. The generated document is then presented to the user via their terminal.

[0747] Furthermore, the emotion engine captures real-time user feedback and incorporates it into the project plan. This allows project management to continuously evolve and be optimized through interaction with users.

[0748] For example, if a user is experiencing high stress levels due to a busy schedule, the emotion engine recognizes this situation and instructs the server to postpone lower-priority tasks to later dates, adjusting the Work Breakdown Structure (WBS) to allow the user to focus on important tasks. Furthermore, the generated reports are written with emotionally sensitive language, including encouraging messages. In this way, the system harmonizes user emotions with project progress, improving the user experience and optimizing operational efficiency.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] Users input basic information about special cases through a terminal interface. During this process, the terminal also collects data on the user's keyboard and mouse movements, as well as their input speed, as indicators of their emotional state.

[0752] Step 2:

[0753] The terminal sends the entered case information and data that serves as an indicator of emotion to the emotion engine. The emotion engine analyzes this data and evaluates the user's emotional state (e.g., stress, exhilaration, concentration, etc.).

[0754] Step 3:

[0755] The emotion engine returns the analysis results to the server, reporting the user's emotional state. This result becomes an important parameter in case processing.

[0756] Step 4:

[0757] The server receives the user's case information and sentiment data, and searches for similar cases by referring to a database of past cases. Simultaneously, it uses a generative AI model to automatically generate a task list suitable for that case.

[0758] Step 5:

[0759] The server creates a Work Breakdown Structure (WBS) for the project based on the task list. During this process, it takes feedback from the emotion engine into consideration, adjusting task priorities and schedules to reduce user stress.

[0760] Step 6:

[0761] The server uses case information to select the necessary document templates, and based on the results of the sentiment engine, generates text to give the user a sense of security and satisfaction, and then creates the document.

[0762] Step 7:

[0763] The terminal presents the generated WBS and document to the user. The user can review the content and make revisions if necessary. Sentimental data is also collected during the revision process and analyzed again by the sentiment engine.

[0764] Step 8:

[0765] The server saves the finalized project information to a database, which is then used as training data for the emotion engine in future projects. This allows the system to continuously improve its ability to handle emotions.

[0766] (Example 2)

[0767] 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".

[0768] In managing special projects, it is essential to plan and execute work efficiently while considering the user's emotions. However, current systems fail to adequately reflect the user's emotional state in planning adjustments, which can increase stress and lead to a lack of flexibility in scheduling. To solve these problems, project management that takes emotional states into account in real time is necessary.

[0769] 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.

[0770] In this invention, the server includes means for receiving information on special cases and referring to a historical database; means for automatically generating a list of tasks from similar histories using a generative AI model; means for analyzing the user's emotional state and adjusting the priority of the task list; and means for adjusting the allocation of tasks to minimize the user's stress level. This enables efficient project management that takes the user's emotions into consideration.

[0771] "Special cases" refer to projects or tasks that require special handling by the user in order to improve management efficiency.

[0772] A "history database" is a collection of data that summarizes information about projects and tasks that have been carried out in the past.

[0773] A "generative AI model" is a form of artificial intelligence that automatically generates task lists and other outputs based on data.

[0774] A "task list" is a list that enumerates the tasks that need to be performed in a project or work.

[0775] "Stratified structure" is a structure for breaking down a project into stages, organizing and visualizing it.

[0776] "Emotional evaluation" is the process of identifying and evaluating a user's emotional state using numerical values ​​or categories.

[0777] "Document format" refers to the form and style of the generated document, and is a template that enables consistent expression.

[0778] "Priority adjustment" refers to the process of setting and adjusting the order in which tasks are performed based on their importance and urgency.

[0779] "Stress level" is an indicator that shows the psychological burden a user feels and is a factor that affects the performance of their work.

[0780] This invention provides a system for project management that takes user emotions into consideration. This system is implemented using a terminal, a server, an emotion engine, and a generative AI model.

[0781] First, the user enters basic information about the special case through the terminal. The terminal is equipped with an input interface that allows the user to easily enter information such as the case name, deadline, and required resources. The terminal then sends this case information to the emotion engine.

[0782] The emotion engine analyzes user input data and performs the necessary data calculations to identify the user's emotional state. Here, the emotion engine determines the user's stress level, satisfaction level, etc., and transmits the results to the server via the terminal. The emotion engine utilizes natural language processing technology to identify emotions based on the user's input data and operation history.

[0783] The server searches the history database based on the received case information and sentiment data. The history database stores past similar cases and their results, enabling similarity analysis. Using a generative AI model, the server generates a list of tasks based on knowledge gained from past similar cases, supporting optimal project management for the user.

[0784] For example, if a user is busy and experiencing high stress levels, the emotion engine recognizes this state and the server prioritizes lower-priority tasks, redistributing the workload so that the user can focus on important tasks. Furthermore, the generated documents automatically include encouraging messages that take the user's emotions into consideration.

[0785] An example of a prompt message would be, "Determine the optimal task order based on the user's sentiment analysis results."

[0786] Thus, the present invention appropriately considers the user's emotions and realizes more efficient and less stressful project management.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The user inputs basic information about a special case through the terminal. The terminal then transmits the information received from the user, such as the case name, deadline, and required resources, to the sentiment engine. The input information is used as basic data for sentiment analysis.

[0790] Step 2:

[0791] The device sends input data to the emotion engine, which analyzes the user's emotional state. Based on the user's input and past operation patterns, the emotion engine identifies the user's stress level and satisfaction level. It quantifies the emotional state through data calculations and sends this quantified value to the server via the device.

[0792] Step 3:

[0793] The server uses the received case information and sentiment data to refer to the historical database and search for similar cases. This extracts data on similar cases and prepares it for the next generation AI model. Similarity analysis is performed within the database based on the input data.

[0794] Step 4:

[0795] The server uses a generative AI model to automatically generate a list of tasks from similar cases. Based on the input data of similar cases, the AI ​​outputs the optimal task list and determines its priority. The output task list is optimized according to the user's emotional state.

[0796] Step 5:

[0797] The server analyzes the user's emotional state and automatically creates a Work Breakdown Structure (WBS) based on the generated task list. Prompts adjust the order and importance of tasks to minimize user stress, resulting in an efficient project plan presented to the user.

[0798] (Application Example 2)

[0799] 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".

[0800] In managing specialized projects, the challenge lies in reducing the emotional burden faced by users and optimizing project progress efficiency. Furthermore, it is necessary to reduce the mental stress on factory workers and ensure the efficient operation of support equipment.

[0801] 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.

[0802] In this invention, the server includes means for acquiring information on special cases and referring to a collection of past case information, means for automatically generating task lists from similar cases using a generation AI model, and means for performing sentiment analysis and adjusting the flexibility of work breakdown configurations and schedules based on the user's emotional state. This enables flexible project management and optimization of workload in accordance with the user's emotions.

[0803] A "special case" refers to a project or task that includes special requirements or conditions that differ from normal operations.

[0804] An "information collection" is a database containing data on past projects and tasks.

[0805] A "generative AI model" is an artificial intelligence model that uses machine learning to automatically generate task lists from similar cases.

[0806] A "task list" is a list that compiles the individual tasks required for a project or task.

[0807] "Work breakdown structure" refers to a systematic organization of a project by dividing the entire project into smaller tasks.

[0808] A "document template" is a pre-defined format used when creating a document, designed to quickly generate content.

[0809] "Emotional analysis" is a process that analyzes the emotional state of a user based on their input data to determine their stress level and satisfaction level.

[0810] "Assistive devices" are automated devices or systems used to reduce the burden on workers.

[0811] This invention realizes a project management system that takes user emotions into consideration. The system first sends information about a special case entered by the user via a terminal to a server. Based on this information, the server searches a database of past case information and identifies similar cases. The server then uses a generative AI model to automatically generate a task list from similar cases. Here, the task list organizes the individual tasks required for the project. At this time, a work breakdown structure is created based on the task list, and the entire project is systematically divided.

[0812] The system also incorporates an emotion analysis function, which analyzes data entered by the user from their device to understand the user's emotional state (such as stress levels and satisfaction levels). This emotion analysis can be performed using a device with specific emotion analysis software installed or a cloud-based service. A concrete example is the use of Microsoft Azure's emotion analysis API.

[0813] Based on the results of sentiment analysis, the server adjusts the task breakdown structure to suit the user. This makes it possible to provide a project plan that takes into account the flexibility of the task list and schedule in order to reduce user stress. For example, if the user is in a high-stress state, the server will adjust by postponing lower-priority tasks and focusing on important tasks.

[0814] Furthermore, the server selects a dedicated document template and automatically generates documents with a tone and language that matches the user's emotions. This allows information to be provided in a considerate manner to the user.

[0815] The system also takes into account adjustments to assistive devices, allowing the server to provide instructions to optimize the operation of robots and other assistive devices based on the worker's emotions. This reduces the burden on workers and supports efficient work in factory and other work environments.

[0816] A concrete example of a prompt message would be: "Factory worker's emotional analysis result: High stress level. We want to redistribute tasks for the next shift and maximize the use of assistive devices. Please generate specific suggestions." This system aims to harmonize the user's emotions with the progress of the project, thereby improving work efficiency.

[0817] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0818] Step 1:

[0819] The user uses a terminal to input information about a special case. This information includes the project name, deadline, and resource usage. The terminal then sends this information to the server. As output, the terminal sends digital data of the case information to the server.

[0820] Step 2:

[0821] The server searches the case information database based on the received special case information and identifies similar cases. This search process uses database queries and compares them with past case information. A list of similar cases is generated as output.

[0822] Step 3:

[0823] The server uses a generative AI model to automatically generate a task list from identified similar cases. The input is the list of similar cases obtained in step 2, and the generative AI model receives prompts based on this and constructs the task list. A recommended task list is provided as output.

[0824] Step 4:

[0825] Based on data provided by the user, the device performs sentiment analysis to determine the user's emotional state (such as stress level and satisfaction level). A sentiment analysis API is used for this determination. The device's output is the analyzed data regarding the user's emotional state.

[0826] Step 5:

[0827] The server adjusts the work breakdown structure based on the task list generated in step 3 and the user's emotional state determined in step 4. Here, it performs calculations to re-evaluate task priorities in order to reduce user stress. The output is the adjusted work breakdown structure.

[0828] Step 6:

[0829] The server selects a document template and automatically generates a document in a tone appropriate to the user's emotional state. This uses a template selection algorithm and natural language generation software. As output, a document in a user-friendly format is generated and sent to the terminal.

[0830] Step 7:

[0831] The server generates instructions to optimize the operation of assistive devices based on the user's emotional state. Specifically, it issues operational instructions that assign tasks to the assistive devices that reduce the user's burden. The server's output is data of operational instructions for the assistive devices.

[0832] 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.

[0833] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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."

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] The following is further disclosed regarding the embodiments described above.

[0854] (Claim 1)

[0855] A means of receiving information on special cases and referring to a database of past cases,

[0856] A method for automatically generating task lists from similar cases using a generative AI model,

[0857] A method for automatically creating a project work breakdown structure based on the above task list,

[0858] A method for selecting necessary document templates based on project information and generating documents through automatic input,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, which provides a means for displaying and allowing the user to confirm the contents of a document after it has been generated.

[0862] (Claim 3)

[0863] The system according to claim 1, comprising means for saving generated items and tasks in a database and updating a learning model for future projects.

[0864] "Example 1"

[0865] (Claim 1)

[0866] A device that receives information on special tasks and references past work data,

[0867] A device that automatically generates a list of tasks from similar past tasks using a machine learning model,

[0868] A device that automatically creates a project structure based on an automatically generated work list,

[0869] A device that selects the necessary document template based on work information and generates a document through automatic input,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] A system according to claim 1, which displays the contents of a document to the user after it has been generated and allows the user to confirm it.

[0873] (Claim 3)

[0874] A system according to claim 1, which stores generated work items and tasks in a recording device and updates a learning model for future work.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] A means of obtaining information for special cases and referring to a database of past cases,

[0878] A method for automatically creating task lists from similar cases using generative AI technology,

[0879] A method for automatically generating the project's work assignment structure based on the above task library,

[0880] A means of coordinating and scheduling specific tasks within equipment used in industrial environments,

[0881] A means for automatically generating process procedures and safety standards,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, which provides the generated document content to the user and enables them to modify and approve it.

[0885] (Claim 3)

[0886] The system according to claim 1, comprising means for saving generated elements and operations and improving the learning model in preparation for future cases.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] A means of receiving information on special cases and referring to a historical database,

[0890] A method for automatically generating a list of tasks from similar history using a generative AI model,

[0891] A means to automatically create a hierarchical structure of tasks based on the above list of tasks,

[0892] A method for selecting the necessary document format based on case information and sentiment evaluation, and generating the document through automatic input,

[0893] A means to analyze the user's emotional state and adjust the priority of the task list,

[0894] A means of adjusting the workload to minimize the user's stress level,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, providing a means for displaying and allowing a user to review the generated document.

[0898] (Claim 3)

[0899] The system according to claim 1, comprising means for saving generated items and tasks to a recording medium and updating a learning model for future projects.

[0900] "Application example 2 when combining with an emotional engine"

[0901] (Claim 1)

[0902] A means of obtaining information on special cases and referring to past case information collections,

[0903] A method for automatically generating task lists from similar cases using a generative AI model,

[0904] A method for mechanically creating a project work breakdown structure based on the above task list,

[0905] A method for selecting necessary document templates based on project information and generating documents through automatic input,

[0906] A means of performing emotion analysis and adjusting the flexibility of the work breakdown structure and schedule based on the user's emotional state,

[0907] A means of giving instructions to adjust the operation of assistive devices according to the worker's emotions,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] The system according to claim 1, which provides a means for displaying and allowing users to confirm the content after document generation.

[0911] (Claim 3)

[0912] The system according to claim 1, which includes means for saving generated items and tasks in an information collection and updating the learning model for the next project. [Explanation of Symbols]

[0913] 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 receiving information on special cases and referring to a database of past cases, A method for automatically generating task lists from similar cases using a generative AI model, A method for automatically creating a project work breakdown structure based on the above task list, A method for selecting necessary document templates based on project information and generating documents through automatic input, A system that includes this.

2. The system according to claim 1, which provides a means for displaying and allowing the user to confirm the contents of a document after it has been generated.

3. The system according to claim 1, which includes means for saving generated items and tasks in a database and updating a learning model for future projects.

Images