system

Abstract

We provide the system. [Solution] A means of receiving project information, A means of searching a database of past project data and regulations, A means of generating the optimal project management method based on project conditions using a generative artificial intelligence model, A means of presenting the generated project management method to the user, A means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback, A means to optimize factory work schedules and dynamically adjust resource allocation, 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 recent years, the environment surrounding projects has changed drastically. In order to lead a project to success in such an environment, flexible and rapid adaptation is required. Enterprises have to respond to uncertain requirements among different departments and stakeholders in such a diverse environment, but there is a problem that it is very difficult to diversify project management methods and make appropriate selections. New methods are needed to solve these problems and contribute to achieving the objectives of projects.

Means for Solving the Problems

[0005] This invention analyzes the current state of a project by receiving project information and searching a database of past project data and specified information. Furthermore, it solves this problem by using a generative artificial intelligence model to generate an optimal project management method based on this information. The generated method is presented to the user, and the generative artificial intelligence model is readjusted based on user feedback, and the method is regenerated as needed. In this way, project management that can flexibly adapt even in dynamic environments is realized.

[0006] "Project information" refers to the basic background information, objectives, constraints, and stakeholder requirements necessary to carry out the project.

[0007] A "database" refers to a collection of information that systematically organizes and stores past project data and regulations.

[0008] A "generative artificial intelligence model" refers to a machine learning algorithm that generates the optimal solution for a given purpose based on collected data.

[0009] "Project management methodology" refers to a methodology that comprises the means, strategies, and processes necessary to achieve the objectives of a project.

[0010] A "user" refers to the entity that operates the system and receives project management guidelines.

[0011] "Feedback" refers to the opinions and suggestions for improvement that users provide regarding the generated proposals. [Brief explanation of the drawing]

[0012] [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]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0013] 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.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage 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.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The present invention provides a system aimed at effectively managing projects in a dynamic environment by applying a generated project management method. This system consists of a server, terminals, and users, and operates as follows.

[0034] The server receives project information entered by the user via a terminal at the start of the project. This includes the project background, goals, constraints, and stakeholder requirements. Based on the received information, the server searches its database to extract data from similar past projects, company-specific rules, and industry best practices.

[0035] Next, the server uses a generative artificial intelligence model to analyze and process the information received from the database. This model takes into account the project's characteristics and environmental factors to generate an optimal project management methodology. This methodology includes a flexible framework for efficiently managing project progress, resource allocation, schedule management, and risk management measures.

[0036] The generated project management methodology is presented to the user via a terminal. The user reviews this proposal and makes decisions regarding the implementation of the project. During this process, the user can provide feedback, which is then returned to the server.

[0037] The server improves the proposed method by readjusting the generated AI model based on user feedback, and regenerates it as needed. This regeneration process is designed to flexibly respond to new conditions and constraints that become apparent as the project progresses.

[0038] To give a concrete example, in a new product development project, the user inputs the project goals and market conditions into the server. Based on past successful product development examples, the server presents the optimal management method derived from an AI model. For risk management, agile methodologies are adopted to respond to technological changes during development and unexpected market changes, providing a concrete path to project success.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses a terminal to input the project's basic information, objectives, conditions, and constraints, and then sends them to the server.

[0042] Step 2:

[0043] The server analyzes the received project information based on its database. It searches past project data and company regulations to extract relevant information.

[0044] Step 3:

[0045] The server processes the analyzed data using a generative artificial intelligence model and generates a management methodology that best suits the project's characteristics. This generation process also takes into account resource allocation plans and risk management policies tailored to the project's specific conditions.

[0046] Step 4:

[0047] The generated project management methodology is sent from the server to the terminal and displayed to the user. The user reviews the presented methodology and confirms its contents.

[0048] Step 5:

[0049] Users send feedback to the server via their device, indicating their satisfaction level and areas for improvement for each element of the project proposal. This feedback may include suggestions for improvement or additional conditions.

[0050] Step 6:

[0051] The server readjusts the generated AI model based on user feedback and regenerates the project management methodology as needed. The improved suggestions are then sent back to the terminal and presented to the user. This cycle is repeated until the optimal management methodology is established.

[0052] (Example 1)

[0053] 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."

[0054] In projects operating in dynamic environments, selecting methods for quickly and appropriately managing resources and schedules is challenging. Furthermore, it's essential to effectively readjust management methods to flexibly respond to new conditions and constraints. This necessitates addressing project-related uncertainties and achieving optimal management.

[0055] 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.

[0056] In this invention, the server includes means for acquiring background information, objectives, limitations, and stakeholder requirements related to the project; means for searching a database containing data from previous similar cases, the organization's own guidelines, and optimal implementations of the technical domain; and means for designing the most suitable management method for the project using a machine learning algorithm. This enables efficient and flexible project management in a dynamic environment.

[0057] "Project-related background information" refers to basic information necessary to achieve the project's objectives and goals, including explanations of the project's needs, limitations, and stakeholder requirements.

[0058] "Data on similar cases" refers to data from past projects that have similar conditions and objectives to the current project.

[0059] "Organization-specific guidelines" refer to internal regulations established by a particular organization regarding its operation and management, and they indicate methods based on the organization's policies and rules.

[0060] "Optimal implementation of a technology" refers to generally recognized best practices in that field, and methods for achieving the highest levels of efficiency and effectiveness.

[0061] A "machine learning algorithm" is a set of mathematical models and procedures used to extract insights by analyzing large amounts of data and to automate specific tasks.

[0062] "Management methods" refer to methodologies and tools used to plan, implement, monitor, and control a project in order to achieve its objectives.

[0063] An "information display device" refers to a terminal or device used to visually present data and information to users, and includes computer monitors and smartphone screens.

[0064] This invention provides a system for effectively managing projects in a dynamic environment. This system consists of a server, terminals, and users, and utilizes a generative AI model to optimize project management methods.

[0065] The server receives project background information, goals, limitations, and stakeholder requirements entered by the user through their terminal. The server searches a database to extract data from similar past cases, organization-specific guidelines, and best practices in the technical domain. Specific systems that can be used include cloud-based database management systems and generative artificial intelligence models such as the Google® Cloud AI platform.

[0066] Based on the received and extracted data, the server uses an AI model to analyze and generate an optimal project management method. This model utilizes machine learning libraries such as TENSORFLOW® and PyTorch. The AI ​​model includes a variable structure, resource allocation method, and risk management measures for efficiently managing project progress.

[0067] The generated project management methodology is presented to the user via a terminal. The terminal has a display that can visually show the progress of the project and communicates the specific details of the management methodology to the user.

[0068] Users can evaluate the presented management methods and provide feedback back to the server via their device. The server then feeds this feedback information back into the AI ​​model and readjusts the generation method as needed. This enables project management that can flexibly adapt to new conditions and constraints.

[0069] As a concrete example, in a new product development project, the user inputs market conditions and development goals into a server. The server retrieves past successful development examples from a database, analyzes them using a generative AI model, and then presents a management method incorporating agile methodologies. This makes it possible to respond flexibly to technological changes and market fluctuations.

[0070] As an example of a prompt, the AI ​​model can be given input such as, "Generate the optimal project management methodology for achieving goals in a new product development project, paying particular attention to schedule management and risk management in an uncertain market environment," and a specific response can be obtained.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The user enters project background information, objectives, limitations, and stakeholder requirements into a terminal. This input is sent to the server as text data.

[0074] Step 2:

[0075] The server searches its internal database based on the received input data. The database contains data on similar past cases, organization-specific guidelines, and best practices in the technical domain. SQL queries are used to extract relevant data. The output consists of past project data and related information as search results.

[0076] Step 3:

[0077] The server inputs the extracted data into a generating AI model. This model, built using machine learning frameworks such as TensorFlow and PyTorch, analyzes the input data and generates the optimal management method for the project. Specific data processing includes feature extraction and analysis. The output is an optimized project management method.

[0078] Step 4:

[0079] The server sends the generated project management methodology to the terminal. Specifically, this involves converting the data so that the methodology is displayed on the terminal in a visualized format (e.g., a Gantt chart or a risk management list).

[0080] Step 5:

[0081] The terminal presents the user with project management methodologies sent from the server. The user reviews the details of the methodologies via the display. The presented information includes schedules, resource allocation, and risk management measures.

[0082] Step 6:

[0083] Users evaluate the presented management methods and send feedback to the server via their device. This feedback is entered as specific comments and requests for corrections.

[0084] Step 7:

[0085] The server receives feedback from the user and readjusts the generated AI model. Specifically, it inputs the feedback into the model and retrains it to regenerate project management methods. The model creates a new management method that reflects the feedback and sends it to the terminal.

[0086] (Application Example 1)

[0087] 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."

[0088] In modern manufacturing, factories are required to respond quickly to fluctuating production needs. However, traditional static work schedule management methods have limitations in terms of production line flexibility and resource allocation optimization, making efficient production operations difficult.

[0089] 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.

[0090] In this invention, the server includes means for receiving project information, means for searching a database of past project data, and means for generating an optimal project management method based on project conditions using a generative artificial intelligence model. This enables the optimization of work schedules in factories and the adjustment of dynamic resource allocation.

[0091] "Means for receiving project information" refers to a system that has the function of collecting information, including the project's background, goals, constraints, and stakeholder requirements, via a terminal.

[0092] A "database search method" refers to a function that allows for the rapid and effective extraction of information, including data from similar past projects, company-specific regulations, and industry best practices.

[0093] A "generative artificial intelligence model" is an algorithm that analyzes input project information and information obtained from a database to generate the optimal management method for a project.

[0094] "Means for optimizing factory work schedules" refers to a function that designs efficient work sequences and timings in production activities within a factory, thereby ensuring maximum productivity.

[0095] "Means for dynamically adjusting resource allocation" refers to a function that flexibly reallocates resources such as personnel, equipment, and materials within a factory according to the situation, in order to always utilize them in the most efficient manner.

[0096] "Means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback" refers to a function for receiving opinions and information provided by users, updating the generated AI model based on them, and improving the proposed project management method.

[0097] This invention provides a system for realizing dynamic project management in a factory. This system consists of three main components: a server, a terminal, and a user.

[0098] First, the server receives project information provided by the user via the terminal. This project information includes the work background, specific goals, constraints, and stakeholder requirements. Next, the server rapidly searches the database to extract data on similar past projects, company-specific norms, and industry best practices. Using this information, the server builds a generative AI model to generate optimal management methods tailored to the project's characteristics. This AI model uses Python as its programming language and utilizes the TensorFlow library for execution.

[0099] The generated project management methodology is presented to the user via a terminal. This methodology includes specific instructions regarding efficient work scheduling and dynamic resource allocation in the factory. The user can review this management methodology and decide whether to apply it to the field.

[0100] The feedback provided by the user is sent back to the server. Based on the received feedback, the server readjusts the generated AI model and regenerates the suggested management methods as needed. This process improves production efficiency within the factory and enables rapid response to abnormal situations and problems.

[0101] As a concrete example of its operation, during the Christmas season, production volume increases, so the server adjusts resource allocation based on this information. Also, if there are machines requiring maintenance, the system can receive this information in advance and incorporate it into the work schedule.

[0102] As an example of a prompt, we will use the following: "Based on the current production schedule, please suggest the optimal resource allocation for next week." This prompt will be input into the AI ​​model, which will then generate suggestions to improve the efficiency of factory operations.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server receives project information from the user via the terminal. This input includes the project's background, goals, constraints, and stakeholder requirements. Based on this information, the server prepares for database searches.

[0106] Step 2:

[0107] The server searches the database and extracts data and relevant normative information for similar projects that have been completed in the past. At this stage, project information received from the user is used as input, and the server obtains data that matches those criteria as output.

[0108] Step 3:

[0109] The server takes project information and data obtained from the database as input and processes it through a generative AI model. This AI model analyzes the data and generates the optimal project management method as output. The model is programmed in Python and uses the TensorFlow library.

[0110] Step 4:

[0111] The server presents the generated project management methodology to the user via the terminal. The user then reviews the outputted management methodology and decides whether to apply it. This process includes proposals for specific work schedules and resource allocations.

[0112] Step 5:

[0113] Users send feedback from their devices to the server as a result of the review. The feedback, as input, includes opinions and suggestions for improvement regarding management methods, and the output is used to adjust the AI ​​model.

[0114] Step 6:

[0115] The server readjusts the generated artificial intelligence model based on user feedback. This process allows the system to regenerate project management methods to accommodate new conditions and provide them to the user as output. For example, resource allocation adjustments are made to accommodate increased production volume.

[0116] 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.

[0117] This invention aims to effectively support the achievement of project objectives by combining an emotion engine with a project management system. This system consists of a server, terminals, and users, each functioning according to its respective role as follows:

[0118] The server receives project information from users via their terminals. This information includes the project's basic background, requirements, and stakeholder expectations. Next, the server searches past project databases and company regulations, extracts relevant information, and analyzes it to understand the project's current status.

[0119] Based on the extracted information, the server utilizes a generative artificial intelligence model to generate an optimal project management methodology. This generation process proposes a flexible framework that includes resource allocation and risk management policies tailored to project-specific conditions.

[0120] The generated project management methodology is presented to the user via a terminal. Here, an emotion engine is utilized to analyze the user's emotions. It recognizes how the user feels about the displayed methodology and adjusts the proposed content based on those emotions. This process proceeds by determining how interested or dissatisfied the user is with the presented methodology and analyzing the emotional information contained in the feedback for improvement on the server.

[0121] Based on user emotional feedback, the server readjusts the generated artificial intelligence model and regenerates the methodology as needed. This allows the project management methodology to evolve and optimize while reflecting user emotions.

[0122] As a concrete example, let's consider a new product development project. In this project, the user provides the server with details about the target market and product features. After analysis, the server generates the optimal development methodology and evaluates the user's initial reaction through the emotion engine. For example, if the user shows a positive reaction to the proposed agile development methodology, it proceeds as is. On the other hand, if concerns are expressed, the server proposes an alternative methodology, such as a waterfall approach, and finds the optimal solution based on the user's emotions.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] Users use their devices to input project background information, goals, and stakeholder requirements, and then send them to the server.

[0126] Step 2:

[0127] Based on the received project information, the server searches a database containing past project data and company regulations, and extracts relevant data. This information is then analyzed to understand the characteristics of the project.

[0128] Step 3:

[0129] The server uses a generative artificial intelligence model to generate an optimal project management method based on extracted and analyzed data. This generation considers a framework that includes resource allocation, schedule management, and risk management.

[0130] Step 4:

[0131] The generated project management methodology is presented to the user via the terminal. Simultaneously, the emotion engine begins the process of recognizing the user's emotions from their facial expressions, tone of voice, and other factors.

[0132] Step 5:

[0133] Users input their feelings and feedback regarding the presented management methods via their device and send it to the server. This feedback includes specific opinions and requests.

[0134] Step 6:

[0135] Based on user feedback and sentiment analysis results, the server readjusts the generated artificial intelligence model and regenerates the project management methodology as needed. This regenerated methodology is then sent back to the terminal and presented to the user.

[0136] Step 7:

[0137] This process is repeated until the management method that best suits the user's emotions is found, helping to ensure the project runs smoothly.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] Traditional project management systems have struggled to efficiently generate methodologies optimized for project conditions and to adjust and revise them based on user feedback. Such systems require performance optimization that fully considers user satisfaction.

[0141] 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.

[0142] In this invention, the server includes means for receiving project information, means for searching storage areas for past similar data and specified information, means for generating an optimal management method based on conditions using a generative machine learning model, means for analyzing user emotions, and means for receiving feedback from users and readjusting the generative machine learning model based on said feedback. As a result, the project management method is optimized to take into account the emotional responses of users, enabling efficient project operation.

[0143] "Means for receiving project information" refers to a device or function for receiving information from users via a terminal, including the project's background, requirements, and stakeholder expectations.

[0144] "Means for searching past similar data and prescribed information storage areas" refers to a device or function for searching a database that stores data related to past projects and prescribed information of the organization, and for extracting highly relevant information.

[0145] "Means for generating optimal management methods based on conditions using generative machine learning models" refers to a device or function that uses machine learning to generate management methods optimized for specific project conditions.

[0146] "Means for analyzing user emotions" refers to a device or function that acquires and analyzes the emotions that users express in response to the management methods presented.

[0147] "Means for receiving feedback from users and readjusting the generated machine learning model based on said feedback" refers to a device or function for receiving feedback information obtained from users and readjusting the machine learning model taking that information into consideration.

[0148] This system is designed to streamline project management. Its specific implementation is described below.

[0149] The server receives project information provided by users from terminals via the network. This information includes the project's background, requirements, and stakeholder expectations, which are crucial elements for initial project setup.

[0150] Upon receiving the data, the server searches a database containing previously accumulated project data and specified information. For this purpose, SQL or NoSQL database technology is commonly used. The search results extract relevant information useful for understanding the project's current status, preparing it for subsequent analysis.

[0151] The server utilizes a pre-trained generative AI model to generate the optimal management method based on the specific conditions of the project. This AI model employs natural language processing technology and has the ability to automatically derive relevant management methods by inputting prompts.

[0152] The generated project management methodology is presented to the user via a terminal, where the emotion engine is utilized. Facial recognition and speech recognition technologies can be used for emotion analysis. The server obtains feedback by acquiring and analyzing the emotions the user shows in response to the presented content in real time.

[0153] Based on the feedback, the server readjusts the generated AI model as needed and regenerates the revised management methods. In this way, the system can leverage user sentiment information to evolve and optimize the optimal project management methods.

[0154] As a concrete example, in a new product development project, the user provides the server with detailed information about the target market and product features. The server analyzes this information and inputs a prompt into an AI model, such as, "The target market is Europe and the US; please propose an agile methodology for rapid market entry." The management methodology derived from this is then presented to the user, and based on the feedback, the methodology can be adjusted and improved as needed.

[0155] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0156] Step 1:

[0157] The user sends basic project information to the server via their terminal. This information includes the project's background, objectives, requirements, and stakeholder expectations. This information is stored in temporary storage for the server to use in subsequent analysis. Specifically, the user transfers the information by entering it into a form using their terminal and pressing the submit button.

[0158] Step 2:

[0159] The server searches a database containing historically similar data and company policy information based on the received project information. The input is project information, and a database query is executed to extract relevant information. The output is a list of relevant information, which is sent to the analysis module within the server. Specifically, SQL queries are executed to retrieve the necessary information from the database.

[0160] Step 3:

[0161] The server uses a generative AI model based on extracted relevant information to generate the optimal project management method. The input consists of data from similar past projects and current project information. The generative AI model receives these inputs, creates prompt statements, and calculates the optimal method. The output is a flexible set of management methods. Specifically, the AI ​​model performs natural language processing based on the prompt statements to generate a list of recommended management methods.

[0162] Step 4:

[0163] The server transfers the generated project management methodology to the terminal and presents it to the user. The input here is the generated management methodology, and the output is the visual information displayed on the user interface. Specifically, the generated methodology is displayed on the terminal screen as text and graphics, providing the user with detailed information.

[0164] Step 5:

[0165] The device analyzes the user's emotions using an emotion engine. Input is the user's visual or auditory responses, and an emotion recognition algorithm is executed as data processing. Output is a judgment of the emotional tendency (e.g., positive, negative, neutral). Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice characteristics in real time.

[0166] Step 6:

[0167] The server receives the sentiment analysis results and direct feedback from the user, and readjusts the generative AI model. The input is the sentiment analysis results and feedback, and the AI ​​model is retrained or adjusted based on this information. The output is a new set of improved project management techniques. Specifically, the feedback data is input to the AI, new prompt sentences are generated, and the techniques are recalculated based on these.

[0168] (Application Example 2)

[0169] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0170] In modern manufacturing, there is a demand for increased efficiency in production processes and improved quality. However, conventional production management systems struggle to respond flexibly to the specific circumstances of the factory floor. Furthermore, the lack of systems that provide optimal management methods that take into account the feelings of on-site personnel limits the potential for productivity improvement.

[0171] 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.

[0172] In this invention, the server includes means for receiving production information, means for searching a database of past production data and guideline information, means for generating an optimal production management method based on production conditions using a generative artificial intelligence model, means for presenting the generated production management method to the person in charge, means for evaluating the person in charge's emotions using an emotion engine, and means for receiving feedback from the person in charge and readjusting the generative artificial intelligence model based on the feedback. This enables flexible and optimal production management that reflects the emotions of the person in charge on site, and makes it possible to build an efficient and high-quality manufacturing process.

[0173] "Production information" refers to data related to the production process in factories and manufacturing sites, including progress and resource usage.

[0174] "Guideline information" refers to guidelines and standards that have been predetermined for a company or industry.

[0175] A "generative artificial intelligence model" is an artificial intelligence structure that uses machine learning algorithms to analyze data and derive optimal solutions and strategies.

[0176] "Production management methods" refer to management techniques and processes for efficiently carrying out production processes and optimally allocating resources.

[0177] "Person in charge" refers to a person responsible for performing specific tasks or managing tasks within a production site or project.

[0178] An "emotion engine" is a system or program that analyzes data such as text, voice, and facial expressions to recognize human emotions.

[0179] "Feedback" refers to evaluations and opinions on a system or proposed method, and it provides valuable information for improvement.

[0180] A "flexible framework" refers to a work structure or framework that is flexible enough to adapt to various situations.

[0181] A "resource allocation strategy" refers to a strategy or plan for systematically allocating available resources.

[0182] This invention provides a system aimed at improving the efficiency and quality of production processes. The system consists of a server, terminals, and personnel.

[0183] The server is responsible for receiving production information, collecting data from sensors and terminals used on the production line. This production information includes data on product progress and resources used. The server also has the ability to search past production databases and company guidelines, and extract necessary information. Based on this information, it utilizes generative artificial intelligence models (e.g., TensorFlow) to generate optimal production management methods tailored to production conditions.

[0184] The generated production management methods are presented to on-site personnel via a terminal. The personnel's feelings towards the proposed methods are analyzed by an emotion engine installed on the terminal (e.g., Microsoft® Azure® Cognitive Services). It senses the personnel's facial expressions and voice and evaluates how satisfied they are with the proposal. Based on this emotion information, feedback is sent to the server, which readjusts the generated artificial intelligence model and regenerates the management methods as needed.

[0185] As a concrete example, if a production delay occurs at a factory, the server will analyze the cause of the delay and propose the optimal solution. For instance, it might devise methods to increase the speed of the production line or prioritize other processes, and present them to the person in charge. If the person in charge readily accepts, the solution will be implemented. An example of a prompt message would be, "Please propose the optimal management method to resolve the current production delay."

[0186] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0187] Step 1:

[0188] The server receives production information from sensors and terminals within the factory. The inputs include data on product progress and resource usage. Based on this data, the server processes it to understand the current state of the production process and formats it into an analyzable format.

[0189] Step 2:

[0190] The server searches historical production databases and guideline information. The input is the production information formatted in step 1, and the output is reference data based on similar past situations and standards. The data calculation performed here is a comparison of past results and current conditions on the production line.

[0191] Step 3:

[0192] The server uses a generative artificial intelligence model to generate an optimal production management method based on production conditions. The input is the reference data obtained in step 2, and the output is the proposed management method. Through the generative AI model, an optimal production management framework is constructed.

[0193] Step 4:

[0194] The terminal presents the generated production management method to the on-site staff. The input is the management method generated in step 3, and the output is information provided to the staff. The terminal conveys information through a visually easy-to-understand interface.

[0195] Step 5:

[0196] Using an emotion engine, the device evaluates the operator's emotions in response to the presented method. Input is reaction data such as the operator's facial expressions and voice, and output is the degree or tendency of those emotions. Sensors collect data in real time, and the emotion engine performs the analysis.

[0197] Step 6:

[0198] The system receives emotional feedback from the user (representative) via a terminal and sends it to the server. The input is the representative's feedback data, and the output is data transmission to the server. The terminal efficiently sends the feedback to the server using a data transmission protocol.

[0199] Step 7:

[0200] The server readjusts the generated artificial intelligence model based on the received feedback and regenerates the management method as needed. The input is the feedback data, and the output is the new management method. This readjustment generates the optimal method again, taking into account the emotions of the person in charge.

[0201] 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.

[0202] Data generation model 58 is a type of 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 those described above. 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 shown 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.

[0203] 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.

[0204] [Second Embodiment]

[0205] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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).

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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".

[0217] The present invention provides a system aimed at effectively managing projects in a dynamic environment by applying a generated project management method. This system consists of a server, terminals, and users, and operates as follows.

[0218] The server receives project information entered by the user via a terminal at the start of the project. This includes the project background, goals, constraints, and stakeholder requirements. Based on the received information, the server searches its database to extract data from similar past projects, company-specific rules, and industry best practices.

[0219] Next, the server uses a generative artificial intelligence model to analyze and process the information received from the database. This model takes into account the project's characteristics and environmental factors to generate an optimal project management methodology. This methodology includes a flexible framework for efficiently managing project progress, resource allocation, schedule management, and risk management measures.

[0220] The generated project management methodology is presented to the user via a terminal. The user reviews this proposal and makes decisions regarding the implementation of the project. During this process, the user can provide feedback, which is then returned to the server.

[0221] The server improves the proposed method by readjusting the generated AI model based on user feedback, and regenerates it as needed. This regeneration process is designed to flexibly respond to new conditions and constraints that become apparent as the project progresses.

[0222] To give a concrete example, in a new product development project, the user inputs the project goals and market conditions into the server. Based on past successful product development examples, the server presents the optimal management method derived from an AI model. For risk management, agile methodologies are adopted to respond to technological changes during development and unexpected market changes, providing a concrete path to project success.

[0223] The following describes the processing flow.

[0224] Step 1:

[0225] The user uses a terminal to input the project's basic information, objectives, conditions, and constraints, and then sends them to the server.

[0226] Step 2:

[0227] The server analyzes the received project information based on its database. It searches past project data and company regulations to extract relevant information.

[0228] Step 3:

[0229] The server processes the analyzed data using a generative artificial intelligence model and generates a management methodology that best suits the project's characteristics. This generation process also takes into account resource allocation plans and risk management policies tailored to the project's specific conditions.

[0230] Step 4:

[0231] The generated project management methodology is sent from the server to the terminal and displayed to the user. The user reviews the presented methodology and confirms its contents.

[0232] Step 5:

[0233] Users send feedback to the server via their device, indicating their satisfaction level and areas for improvement for each element of the project proposal. This feedback may include suggestions for improvement or additional conditions.

[0234] Step 6:

[0235] The server readjusts the generated AI model based on user feedback and regenerates the project management methodology as needed. The improved suggestions are then sent back to the terminal and presented to the user. This cycle is repeated until the optimal management methodology is established.

[0236] (Example 1)

[0237] 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."

[0238] In projects operating in dynamic environments, selecting methods for quickly and appropriately managing resources and schedules is challenging. Furthermore, it's essential to effectively readjust management methods to flexibly respond to new conditions and constraints. This necessitates addressing project-related uncertainties and achieving optimal management.

[0239] 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.

[0240] In this invention, the server includes means for acquiring background information, objectives, limitations, and stakeholder requirements related to the project; means for searching a database containing data from previous similar cases, the organization's own guidelines, and optimal implementations of the technical domain; and means for designing the most suitable management method for the project using a machine learning algorithm. This enables efficient and flexible project management in a dynamic environment.

[0241] "Project-related background information" refers to basic information necessary to achieve the project's objectives and goals, including explanations of the project's needs, limitations, and stakeholder requirements.

[0242] "Data on similar cases" refers to data from past projects that have similar conditions and objectives to the current project.

[0243] "Organization-specific guidelines" refer to internal regulations established by a particular organization regarding its operation and management, and they indicate methods based on the organization's policies and rules.

[0244] "Optimal implementation of a technology" refers to generally recognized best practices in that field, and methods for achieving the highest levels of efficiency and effectiveness.

[0245] A "machine learning algorithm" is a set of mathematical models and procedures used to extract insights by analyzing large amounts of data and to automate specific tasks.

[0246] "Management methods" refer to methodologies and tools used to plan, implement, monitor, and control a project in order to achieve its objectives.

[0247] An "information display device" refers to a terminal or device used to visually present data and information to users, and includes computer monitors and smartphone screens.

[0248] This invention provides a system for effectively managing projects in a dynamic environment. This system consists of a server, terminals, and users, and utilizes a generative AI model to optimize project management methods.

[0249] The server receives project background information, objectives, limitations, and stakeholder requirements entered by the user through their terminal. The server searches a database to extract data from similar past cases, organization-specific guidelines, and best practices in the technical domain. Specific systems that can be used include cloud-based database management systems and generative artificial intelligence models such as the Google Cloud AI platform.

[0250] Based on the received and extracted data, the server uses an AI model to analyze it and generate an optimal project management method. This model utilizes machine learning libraries such as TensorFlow and PyTorch. The AI ​​model includes a variable structure, resource allocation method, and risk management measures for efficiently managing project progress.

[0251] The generated project management methodology is presented to the user via a terminal. The terminal has a display that can visually show the progress of the project and communicates the specific details of the management methodology to the user.

[0252] Users can evaluate the presented management methods and provide feedback back to the server via their device. The server then feeds this feedback information back into the AI ​​model and readjusts the generation method as needed. This enables project management that can flexibly adapt to new conditions and constraints.

[0253] As a concrete example, in a new product development project, the user inputs market conditions and development goals into a server. The server retrieves past successful development examples from a database, analyzes them using a generative AI model, and then presents a management method incorporating agile methodologies. This makes it possible to respond flexibly to technological changes and market fluctuations.

[0254] As an example of a prompt, the AI ​​model can be given input such as, "Generate the optimal project management methodology for achieving goals in a new product development project, paying particular attention to schedule management and risk management in an uncertain market environment," and a specific response can be obtained.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The user enters project background information, objectives, limitations, and stakeholder requirements into a terminal. This input is sent to the server as text data.

[0258] Step 2:

[0259] The server searches its internal database based on the received input data. The database contains data on similar past cases, organization-specific guidelines, and best practices in the technical domain. SQL queries are used to extract relevant data. The output consists of past project data and related information as search results.

[0260] Step 3:

[0261] The server inputs the extracted data into a generating AI model. This model, built using machine learning frameworks such as TensorFlow and PyTorch, analyzes the input data and generates the optimal management method for the project. Specific data processing includes feature extraction and analysis. The output is an optimized project management method.

[0262] Step 4:

[0263] The server sends the generated project management methodology to the terminal. Specifically, this involves converting the data so that the methodology is displayed on the terminal in a visualized format (e.g., a Gantt chart or a risk management list).

[0264] Step 5:

[0265] The terminal presents the user with project management methodologies sent from the server. The user reviews the details of the methodologies via the display. The presented information includes schedules, resource allocation, and risk management measures.

[0266] Step 6:

[0267] Users evaluate the presented management methods and send feedback to the server via their device. This feedback is entered as specific comments and requests for corrections.

[0268] Step 7:

[0269] The server receives feedback from the user and readjusts the generated AI model. Specifically, it inputs the feedback into the model and retrains it to regenerate project management methods. The model creates a new management method that reflects the feedback and sends it to the terminal.

[0270] (Application Example 1)

[0271] 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."

[0272] In modern manufacturing, factories are required to respond quickly to fluctuating production needs. However, traditional static work schedule management methods have limitations in terms of production line flexibility and resource allocation optimization, making efficient production operations difficult.

[0273] 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.

[0274] In this invention, the server includes means for receiving project information, means for searching a database of past project data, and means for generating an optimal project management method based on project conditions using a generative artificial intelligence model. This enables the optimization of work schedules in factories and the adjustment of dynamic resource allocation.

[0275] "Means for receiving project information" refers to a system that has the function of collecting information, including the project's background, goals, constraints, and stakeholder requirements, via a terminal.

[0276] A "database search method" refers to a function that allows for the rapid and effective extraction of information, including data from similar past projects, company-specific regulations, and industry best practices.

[0277] A "generative artificial intelligence model" is an algorithm that analyzes input project information and information obtained from a database to generate the optimal management method for a project.

[0278] "Means for optimizing factory work schedules" refers to a function that designs efficient work sequences and timings in production activities within a factory, thereby ensuring maximum productivity.

[0279] "Means for dynamically adjusting resource allocation" refers to a function that flexibly reallocates resources such as personnel, equipment, and materials within a factory according to the situation, in order to always utilize them in the most efficient manner.

[0280] "Means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback" refers to a function for receiving opinions and information provided by users, updating the generated AI model based on them, and improving the proposed project management method.

[0281] This invention provides a system for realizing dynamic project management in a factory. This system consists of three main components: a server, a terminal, and a user.

[0282] First, the server receives project information provided by the user via the terminal. This project information includes the work background, specific goals, constraints, and stakeholder requirements. Next, the server rapidly searches the database to extract data on similar past projects, company-specific norms, and industry best practices. Using this information, the server builds a generative AI model to generate optimal management methods tailored to the project's characteristics. This AI model uses Python as its programming language and utilizes the TensorFlow library for execution.

[0283] The generated project management methodology is presented to the user via a terminal. This methodology includes specific instructions regarding efficient work scheduling and dynamic resource allocation in the factory. The user can review this management methodology and decide whether to apply it to the field.

[0284] The feedback provided by the user is sent back to the server. Based on the received feedback, the server readjusts the generated AI model and regenerates the proposed management method if necessary. This process improves production efficiency in the factory and enables quick response to abnormal situations and troubles.

[0285] As a specific operation example, during the Christmas season, the production volume increases, so the server adjusts the resource allocation based on this information. Also, if there is a machine that requires maintenance, the server can receive this information in advance and reflect it in the work schedule.

[0286] As an example of a prompt sentence, "Please propose the optimal resource allocation for next week based on the current production schedule." is used. This prompt is input into the AI model to generate proposals for improving the efficiency of factory operations.

[0287] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0288] Step 1:

[0289] The server receives project information from the user through the terminal. As input, it includes the background, goals, constraints, and stakeholder requirements of the project. Based on this information, the server prepares for database search.

[0290] Step 2:

[0291] The server searches the database and extracts data on similar projects conducted in the past and related specification information. At this stage, the project information received from the user as input is used, and the server obtains data that meets the conditions as output.

[0292] Step 3:

[0293] The server takes project information and data obtained from the database as input and processes it through a generative AI model. This AI model analyzes the data and generates the optimal project management method as output. The model is programmed in Python and uses the TensorFlow library.

[0294] Step 4:

[0295] The server presents the generated project management methodology to the user via the terminal. The user then reviews the outputted management methodology and decides whether to apply it. This process includes proposals for specific work schedules and resource allocations.

[0296] Step 5:

[0297] Users send feedback from their devices to the server as a result of the review. The feedback, as input, includes opinions and suggestions for improvement regarding management methods, and the output is used to adjust the AI ​​model.

[0298] Step 6:

[0299] The server readjusts the generated artificial intelligence model based on user feedback. This process allows the system to regenerate project management methods to accommodate new conditions and provide them to the user as output. For example, resource allocation adjustments are made to accommodate increased production volume.

[0300] 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.

[0301] This invention aims to effectively support the achievement of project objectives by combining an emotion engine with a project management system. This system consists of a server, terminals, and users, each functioning according to its respective role as follows:

[0302] The server receives project information from users via their terminals. This information includes the project's basic background, requirements, and stakeholder expectations. Next, the server searches past project databases and company regulations, extracts relevant information, and analyzes it to understand the project's current status.

[0303] Based on the extracted information, the server utilizes a generative artificial intelligence model to generate an optimal project management methodology. This generation process proposes a flexible framework that includes resource allocation and risk management policies tailored to project-specific conditions.

[0304] The generated project management methodology is presented to the user via a terminal. Here, an emotion engine is utilized to analyze the user's emotions. It recognizes how the user feels about the displayed methodology and adjusts the proposed content based on those emotions. This process proceeds by determining how interested or dissatisfied the user is with the presented methodology and analyzing the emotional information contained in the feedback for improvement on the server.

[0305] Based on user emotional feedback, the server readjusts the generated artificial intelligence model and regenerates the methodology as needed. This allows the project management methodology to evolve and optimize while reflecting user emotions.

[0306] As a specific example, assume a new product development project. In this project, the user provides the server with details of the target market and product functions. After analysis, the server generates an optimal development method and evaluates the user's initial reaction through the emotion engine. For example, if the user shows a positive reaction to the proposed agile development method, the project proceeds as is. On the other hand, if concerns are shown, the server re-proposes another method, such as a waterfall approach, to find an optimal solution based on the user's emotions.

[0307] The following describes the process flow.

[0308] Step 1:

[0309] The user uses the terminal to input the background information, goals, and stakeholder requirements of the project and sends them to the server.

[0310] Step 2:

[0311] [[ID=二十]]The server searches the database storing past project data and corporate regulation information based on the received project information, extracts relevant data, analyzes this information, and grasps the characteristics of the project.

[0312] Step 3:

[0313] The server uses the generated artificial intelligence model to generate an optimal project management method based on the extracted and analyzed data. For this generation, a framework including resource allocation, schedule management, and risk management is considered.

[0314] Step 4:

[0315] The generated project management method is presented to the user via the terminal. At the same time, the emotion engine starts the process of recognizing emotions from the user's expressions, voice tones, etc.

[0316] Step 5: It should be noted that in the above translation, the Chinese text "二十" in the description of "ステップ2" is an incorrect number in the original text. It is assumed that it should be "20" and is translated accordingly. If there are other specific requirements or corrections, please let me know.

[0317] Users input their feelings and feedback regarding the presented management methods via their device and send it to the server. This feedback includes specific opinions and requests.

[0318] Step 6:

[0319] Based on user feedback and sentiment analysis results, the server readjusts the generated artificial intelligence model and regenerates the project management methodology as needed. This regenerated methodology is then sent back to the terminal and presented to the user.

[0320] Step 7:

[0321] This process is repeated until the management method that best suits the user's emotions is found, helping to ensure the project runs smoothly.

[0322] (Example 2)

[0323] 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".

[0324] Traditional project management systems have struggled to efficiently generate methodologies optimized for project conditions and to adjust and revise them based on user feedback. Such systems require performance optimization that fully considers user satisfaction.

[0325] 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.

[0326] In this invention, the server includes means for receiving project information, means for searching storage areas for past similar data and specified information, means for generating an optimal management method based on conditions using a generative machine learning model, means for analyzing user emotions, and means for receiving feedback from users and readjusting the generative machine learning model based on said feedback. As a result, the project management method is optimized to take into account the emotional responses of users, enabling efficient project operation.

[0327] "Means for receiving project information" refers to a device or function for receiving information from users via a terminal, including the project's background, requirements, and stakeholder expectations.

[0328] "Means for searching past similar data and prescribed information storage areas" refers to a device or function for searching a database that stores data related to past projects and prescribed information of the organization, and for extracting highly relevant information.

[0329] "Means for generating optimal management methods based on conditions using generative machine learning models" refers to a device or function that uses machine learning to generate management methods optimized for specific project conditions.

[0330] "Means for analyzing user emotions" refers to a device or function that acquires and analyzes the emotions that users express in response to the management methods presented.

[0331] "Means for receiving feedback from users and readjusting the generated machine learning model based on said feedback" refers to a device or function for receiving feedback information obtained from users and readjusting the machine learning model taking that information into consideration.

[0332] This system is designed to streamline project management. Its specific implementation is described below.

[0333] The server receives project information provided by users from terminals via the network. This information includes the project's background, requirements, and stakeholder expectations, which are crucial elements for initial project setup.

[0334] Upon receiving the data, the server searches a database containing previously accumulated project data and specified information. For this purpose, SQL or NoSQL database technology is commonly used. The search results extract relevant information useful for understanding the project's current status, preparing it for subsequent analysis.

[0335] The server utilizes a pre-trained generative AI model to generate the optimal management method based on the specific conditions of the project. This AI model employs natural language processing technology and has the ability to automatically derive relevant management methods by inputting prompts.

[0336] The generated project management methodology is presented to the user via a terminal, where the emotion engine is utilized. Facial recognition and speech recognition technologies can be used for emotion analysis. The server obtains feedback by acquiring and analyzing the emotions the user shows in response to the presented content in real time.

[0337] Based on the feedback, the server readjusts the generated AI model as needed and regenerates the revised management methods. In this way, the system can leverage user sentiment information to evolve and optimize the optimal project management methods.

[0338] As a concrete example, in a new product development project, the user provides the server with detailed information about the target market and product features. The server analyzes this information and inputs a prompt into an AI model, such as, "The target market is Europe and the US; please propose an agile methodology for rapid market entry." The management methodology derived from this is then presented to the user, and based on the feedback, the methodology can be adjusted and improved as needed.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The user sends basic project information to the server via their terminal. This information includes the project's background, objectives, requirements, and stakeholder expectations. This information is stored in temporary storage for the server to use in subsequent analysis. Specifically, the user transfers the information by entering it into a form using their terminal and pressing the submit button.

[0342] Step 2:

[0343] The server searches a database containing historically similar data and company policy information based on the received project information. The input is project information, and a database query is executed to extract relevant information. The output is a list of relevant information, which is sent to the analysis module within the server. Specifically, SQL queries are executed to retrieve the necessary information from the database.

[0344] Step 3:

[0345] The server uses a generative AI model based on extracted relevant information to generate the optimal project management method. The input consists of data from similar past projects and current project information. The generative AI model receives these inputs, creates prompt statements, and calculates the optimal method. The output is a flexible set of management methods. Specifically, the AI ​​model performs natural language processing based on the prompt statements to generate a list of recommended management methods.

[0346] Step 4:

[0347] The server transfers the generated project management methodology to the terminal and presents it to the user. The input here is the generated management methodology, and the output is the visual information displayed on the user interface. Specifically, the generated methodology is displayed on the terminal screen as text and graphics, providing the user with detailed information.

[0348] Step 5:

[0349] The device analyzes the user's emotions using an emotion engine. Input is the user's visual or auditory responses, and an emotion recognition algorithm is executed as data processing. Output is a judgment of the emotional tendency (e.g., positive, negative, neutral). Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice characteristics in real time.

[0350] Step 6:

[0351] The server receives the sentiment analysis results and direct feedback from the user, and readjusts the generative AI model. The input is the sentiment analysis results and feedback, and the AI ​​model is retrained or adjusted based on this information. The output is a new set of improved project management techniques. Specifically, the feedback data is input to the AI, new prompt sentences are generated, and the techniques are recalculated based on these.

[0352] (Application Example 2)

[0353] 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."

[0354] In modern manufacturing, there is a demand for increased efficiency in production processes and improved quality. However, conventional production management systems struggle to respond flexibly to the specific circumstances of the factory floor. Furthermore, the lack of systems that provide optimal management methods that take into account the feelings of on-site personnel limits the potential for productivity improvement.

[0355] 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.

[0356] In this invention, the server includes means for receiving production information, means for searching a database of past production data and guideline information, means for generating an optimal production management method based on production conditions using a generative artificial intelligence model, means for presenting the generated production management method to the person in charge, means for evaluating the person in charge's emotions using an emotion engine, and means for receiving feedback from the person in charge and readjusting the generative artificial intelligence model based on the feedback. This enables flexible and optimal production management that reflects the emotions of the person in charge on site, and makes it possible to build an efficient and high-quality manufacturing process.

[0357] "Production information" refers to data related to the production process in factories and manufacturing sites, including progress and resource usage.

[0358] "Guideline information" refers to guidelines and standards that have been predetermined for a company or industry.

[0359] A "generative artificial intelligence model" is an artificial intelligence structure that uses machine learning algorithms to analyze data and derive optimal solutions and strategies.

[0360] "Production management methods" refer to management techniques and processes for efficiently carrying out production processes and optimally allocating resources.

[0361] "Person in charge" refers to a person responsible for performing specific tasks or managing tasks within a production site or project.

[0362] An "emotion engine" is a system or program that analyzes data such as text, voice, and facial expressions to recognize human emotions.

[0363] "Feedback" refers to evaluations and opinions on a system or proposed method, and it provides valuable information for improvement.

[0364] A "flexible framework" refers to a work structure or framework that is flexible enough to adapt to various situations.

[0365] A "resource allocation strategy" refers to a strategy or plan for systematically allocating available resources.

[0366] This invention provides a system aimed at improving the efficiency and quality of production processes. The system consists of a server, terminals, and personnel.

[0367] The server is responsible for receiving production information, collecting data from sensors and terminals used on the production line. This production information includes data on product progress and resources used. The server also has the ability to search past production databases and company guidelines, and extract necessary information. Based on this information, it utilizes generative artificial intelligence models (e.g., TensorFlow) to generate optimal production management methods tailored to production conditions.

[0368] The generated production management methods are presented to on-site personnel via a terminal. The personnel's feelings towards the proposed methods are analyzed by an emotion engine installed on the terminal (e.g., Microsoft Azure Cognitive Services). It senses the personnel's facial expressions and voice to evaluate how satisfied they are with the proposal. Based on this emotion information, feedback is sent to a server, which readjusts the generated artificial intelligence model and regenerates the management methods as needed.

[0369] As a concrete example, if a production delay occurs at a factory, the server will analyze the cause of the delay and propose the optimal solution. For instance, it might devise methods to increase the speed of the production line or prioritize other processes, and present them to the person in charge. If the person in charge readily accepts, the solution will be implemented. An example of a prompt message would be, "Please propose the optimal management method to resolve the current production delay."

[0370] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0371] Step 1:

[0372] The server receives production information from sensors and terminals within the factory. The inputs include data on product progress and resource usage. Based on this data, the server processes it to understand the current state of the production process and formats it into an analyzable format.

[0373] Step 2:

[0374] The server searches historical production databases and guideline information. The input is the production information formatted in step 1, and the output is reference data based on similar past situations and standards. The data calculation performed here is a comparison of past results and current conditions on the production line.

[0375] Step 3:

[0376] The server uses a generative artificial intelligence model to generate an optimal production management method based on production conditions. The input is the reference data obtained in step 2, and the output is the proposed management method. Through the generative AI model, an optimal production management framework is constructed.

[0377] Step 4:

[0378] The terminal presents the generated production management method to the on-site staff. The input is the management method generated in step 3, and the output is information provided to the staff. The terminal conveys information through a visually easy-to-understand interface.

[0379] Step 5:

[0380] Using an emotion engine, the device evaluates the operator's emotions in response to the presented method. Input is reaction data such as the operator's facial expressions and voice, and output is the degree or tendency of those emotions. Sensors collect data in real time, and the emotion engine performs the analysis.

[0381] Step 6:

[0382] The system receives emotional feedback from the user (representative) via a terminal and sends it to the server. The input is the representative's feedback data, and the output is data transmission to the server. The terminal efficiently sends the feedback to the server using a data transmission protocol.

[0383] Step 7:

[0384] The server readjusts the generated artificial intelligence model based on the received feedback and regenerates the management method as needed. The input is the feedback data, and the output is the new management method. This readjustment generates the optimal method again, taking into account the emotions of the person in charge.

[0385] 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.

[0386] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[0387] 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.

[0388] [Third Embodiment]

[0389] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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".

[0401] The present invention provides a system aimed at effectively managing projects in a dynamic environment by applying a generated project management method. This system consists of a server, terminals, and users, and operates as follows.

[0402] The server receives project information entered by the user via a terminal at the start of the project. This includes the project background, goals, constraints, and stakeholder requirements. Based on the received information, the server searches its database to extract data from similar past projects, company-specific rules, and industry best practices.

[0403] Next, the server uses a generative artificial intelligence model to analyze and process the information received from the database. This model takes into account the project's characteristics and environmental factors to generate an optimal project management methodology. This methodology includes a flexible framework for efficiently managing project progress, resource allocation, schedule management, and risk management measures.

[0404] The generated project management methodology is presented to the user via a terminal. The user reviews this proposal and makes decisions regarding the implementation of the project. During this process, the user can provide feedback, which is then returned to the server.

[0405] The server improves the proposed method by readjusting the generated AI model based on user feedback, and regenerates it as needed. This regeneration process is designed to flexibly respond to new conditions and constraints that become apparent as the project progresses.

[0406] To give a concrete example, in a new product development project, the user inputs the project goals and market conditions into the server. Based on past successful product development examples, the server presents the optimal management method derived from an AI model. For risk management, agile methodologies are adopted to respond to technological changes during development and unexpected market changes, providing a concrete path to project success.

[0407] The following describes the processing flow.

[0408] Step 1:

[0409] The user uses a terminal to input the project's basic information, objectives, conditions, and constraints, and then sends them to the server.

[0410] Step 2:

[0411] The server analyzes the received project information based on its database. It searches past project data and company regulations to extract relevant information.

[0412] Step 3:

[0413] The server processes the analyzed data using a generative artificial intelligence model and generates a management methodology that best suits the project's characteristics. This generation process also takes into account resource allocation plans and risk management policies tailored to the project's specific conditions.

[0414] Step 4:

[0415] The generated project management methodology is sent from the server to the terminal and displayed to the user. The user reviews the presented methodology and confirms its contents.

[0416] Step 5:

[0417] Users send feedback to the server via their device, indicating their satisfaction level and areas for improvement for each element of the project proposal. This feedback may include suggestions for improvement or additional conditions.

[0418] Step 6:

[0419] The server readjusts the generated AI model based on user feedback and regenerates the project management methodology as needed. The improved suggestions are then sent back to the terminal and presented to the user. This cycle is repeated until the optimal management methodology is established.

[0420] (Example 1)

[0421] 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."

[0422] In projects operating in dynamic environments, selecting methods for quickly and appropriately managing resources and schedules is challenging. Furthermore, it's essential to effectively readjust management methods to flexibly respond to new conditions and constraints. This necessitates addressing project-related uncertainties and achieving optimal management.

[0423] 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.

[0424] In this invention, the server includes means for acquiring background information, objectives, limitations, and stakeholder requirements related to the project; means for searching a database containing data from previous similar cases, the organization's own guidelines, and optimal implementations of the technical domain; and means for designing the most suitable management method for the project using a machine learning algorithm. This enables efficient and flexible project management in a dynamic environment.

[0425] "Project-related background information" refers to basic information necessary to achieve the project's objectives and goals, including explanations of the project's needs, limitations, and stakeholder requirements.

[0426] "Data on similar cases" refers to data from past projects that have similar conditions and objectives to the current project.

[0427] "Organization-specific guidelines" refer to internal regulations established by a particular organization regarding its operation and management, and they indicate methods based on the organization's policies and rules.

[0428] "Optimal implementation of a technology" refers to generally recognized best practices in that field, and methods for achieving the highest levels of efficiency and effectiveness.

[0429] A "machine learning algorithm" is a set of mathematical models and procedures used to extract insights by analyzing large amounts of data and to automate specific tasks.

[0430] "Management methods" refer to methodologies and tools used to plan, implement, monitor, and control a project in order to achieve its objectives.

[0431] An "information display device" refers to a terminal or device used to visually present data and information to users, and includes computer monitors and smartphone screens.

[0432] This invention provides a system for effectively managing projects in a dynamic environment. This system consists of a server, terminals, and users, and utilizes a generative AI model to optimize project management methods.

[0433] The server receives project background information, objectives, limitations, and stakeholder requirements entered by the user through their terminal. The server searches a database to extract data from similar past cases, organization-specific guidelines, and best practices in the technical domain. Specific systems that can be used include cloud-based database management systems and generative artificial intelligence models such as the Google Cloud AI platform.

[0434] Based on the received and extracted data, the server uses an AI model to analyze it and generate an optimal project management method. This model utilizes machine learning libraries such as TensorFlow and PyTorch. The AI ​​model includes a variable structure, resource allocation method, and risk management measures for efficiently managing project progress.

[0435] The generated project management methodology is presented to the user via a terminal. The terminal has a display that can visually show the progress of the project and communicates the specific details of the management methodology to the user.

[0436] Users can evaluate the presented management methods and provide feedback back to the server via their device. The server then feeds this feedback information back into the AI ​​model and readjusts the generation method as needed. This enables project management that can flexibly adapt to new conditions and constraints.

[0437] As a concrete example, in a new product development project, the user inputs market conditions and development goals into a server. The server retrieves past successful development examples from a database, analyzes them using a generative AI model, and then presents a management method incorporating agile methodologies. This makes it possible to respond flexibly to technological changes and market fluctuations.

[0438] As an example of a prompt, the AI ​​model can be given input such as, "Generate the optimal project management methodology for achieving goals in a new product development project, paying particular attention to schedule management and risk management in an uncertain market environment," and a specific response can be obtained.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The user enters project background information, objectives, limitations, and stakeholder requirements into a terminal. This input is sent to the server as text data.

[0442] Step 2:

[0443] The server searches its internal database based on the received input data. The database contains data on similar past cases, organization-specific guidelines, and best practices in the technical domain. SQL queries are used to extract relevant data. The output consists of past project data and related information as search results.

[0444] Step 3:

[0445] The server inputs the extracted data into a generating AI model. This model, built using machine learning frameworks such as TensorFlow and PyTorch, analyzes the input data and generates the optimal management method for the project. Specific data processing includes feature extraction and analysis. The output is an optimized project management method.

[0446] Step 4:

[0447] The server sends the generated project management methodology to the terminal. Specifically, this involves converting the data so that the methodology is displayed on the terminal in a visualized format (e.g., a Gantt chart or a risk management list).

[0448] Step 5:

[0449] The terminal presents the user with project management methodologies sent from the server. The user reviews the details of the methodologies via the display. The presented information includes schedules, resource allocation, and risk management measures.

[0450] Step 6:

[0451] Users evaluate the presented management methods and send feedback to the server via their device. This feedback is entered as specific comments and requests for corrections.

[0452] Step 7:

[0453] The server receives feedback from the user and readjusts the generated AI model. Specifically, it inputs the feedback into the model and retrains it to regenerate project management methods. The model creates a new management method that reflects the feedback and sends it to the terminal.

[0454] (Application Example 1)

[0455] 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."

[0456] In modern manufacturing, factories are required to respond quickly to fluctuating production needs. However, traditional static work schedule management methods have limitations in terms of production line flexibility and resource allocation optimization, making efficient production operations difficult.

[0457] 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.

[0458] In this invention, the server includes means for receiving project information, means for searching a database of past project data, and means for generating an optimal project management method based on project conditions using a generative artificial intelligence model. This enables the optimization of work schedules in factories and the adjustment of dynamic resource allocation.

[0459] "Means for receiving project information" refers to a system that has the function of collecting information, including the project's background, goals, constraints, and stakeholder requirements, via a terminal.

[0460] A "database search method" refers to a function that allows for the rapid and effective extraction of information, including data from similar past projects, company-specific regulations, and industry best practices.

[0461] A "generative artificial intelligence model" is an algorithm that analyzes input project information and information obtained from a database to generate the optimal management method for a project.

[0462] "Means for optimizing factory work schedules" refers to a function that designs efficient work sequences and timings in production activities within a factory, thereby ensuring maximum productivity.

[0463] "Means for dynamically adjusting resource allocation" refers to a function that flexibly reallocates resources such as personnel, equipment, and materials within a factory according to the situation, in order to always utilize them in the most efficient manner.

[0464] "Means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback" refers to a function for receiving opinions and information provided by users, updating the generated AI model based on them, and improving the proposed project management method.

[0465] This invention provides a system for realizing dynamic project management in a factory. This system consists of three main components: a server, a terminal, and a user.

[0466] First, the server receives project information provided by the user via the terminal. This project information includes the work background, specific goals, constraints, and stakeholder requirements. Next, the server rapidly searches the database to extract data on similar past projects, company-specific norms, and industry best practices. Using this information, the server builds a generative AI model to generate optimal management methods tailored to the project's characteristics. This AI model uses Python as its programming language and utilizes the TensorFlow library for execution.

[0467] The generated project management methodology is presented to the user via a terminal. This methodology includes specific instructions regarding efficient work scheduling and dynamic resource allocation in the factory. The user can review this management methodology and decide whether to apply it to the field.

[0468] The feedback provided by the user is sent back to the server. Based on the received feedback, the server readjusts the generated AI model and regenerates the suggested management methods as needed. This process improves production efficiency within the factory and enables rapid response to abnormal situations and problems.

[0469] As a concrete example of its operation, during the Christmas season, production volume increases, so the server adjusts resource allocation based on this information. Also, if there are machines requiring maintenance, the system can receive this information in advance and incorporate it into the work schedule.

[0470] As an example of a prompt, we will use the following: "Based on the current production schedule, please suggest the optimal resource allocation for next week." This prompt will be input into the AI ​​model, which will then generate suggestions to improve the efficiency of factory operations.

[0471] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0472] Step 1:

[0473] The server receives project information from the user via the terminal. This input includes the project's background, goals, constraints, and stakeholder requirements. Based on this information, the server prepares for database searches.

[0474] Step 2:

[0475] The server searches the database and extracts data and relevant normative information for similar projects that have been completed in the past. At this stage, project information received from the user is used as input, and the server obtains data that matches those criteria as output.

[0476] Step 3:

[0477] The server takes project information and data obtained from the database as input and processes it through a generative AI model. This AI model analyzes the data and generates the optimal project management method as output. The model is programmed in Python and uses the TensorFlow library.

[0478] Step 4:

[0479] The server presents the generated project management methodology to the user via the terminal. The user then reviews the outputted management methodology and decides whether to apply it. This process includes proposals for specific work schedules and resource allocations.

[0480] Step 5:

[0481] Users send feedback from their devices to the server as a result of the review. The feedback, as input, includes opinions and suggestions for improvement regarding management methods, and the output is used to adjust the AI ​​model.

[0482] Step 6:

[0483] The server readjusts the generated artificial intelligence model based on user feedback. This process allows the system to regenerate project management methods to accommodate new conditions and provide them to the user as output. For example, resource allocation adjustments are made to accommodate increased production volume.

[0484] 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.

[0485] This invention aims to effectively support the achievement of project objectives by combining an emotion engine with a project management system. This system consists of a server, terminals, and users, each functioning according to its respective role as follows:

[0486] The server receives project information from users via their terminals. This information includes the project's basic background, requirements, and stakeholder expectations. Next, the server searches past project databases and company regulations, extracts relevant information, and analyzes it to understand the project's current status.

[0487] Based on the extracted information, the server utilizes a generative artificial intelligence model to generate an optimal project management methodology. This generation process proposes a flexible framework that includes resource allocation and risk management policies tailored to project-specific conditions.

[0488] The generated project management methodology is presented to the user via a terminal. Here, an emotion engine is utilized to analyze the user's emotions. It recognizes how the user feels about the displayed methodology and adjusts the proposed content based on those emotions. This process proceeds by determining how interested or dissatisfied the user is with the presented methodology and analyzing the emotional information contained in the feedback for improvement on the server.

[0489] Based on user emotional feedback, the server readjusts the generated artificial intelligence model and regenerates the methodology as needed. This allows the project management methodology to evolve and optimize while reflecting user emotions.

[0490] As a concrete example, let's consider a new product development project. In this project, the user provides the server with details about the target market and product features. After analysis, the server generates the optimal development methodology and evaluates the user's initial reaction through the emotion engine. For example, if the user shows a positive reaction to the proposed agile development methodology, it proceeds as is. On the other hand, if concerns are expressed, the server proposes an alternative methodology, such as a waterfall approach, and finds the optimal solution based on the user's emotions.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] Users use their devices to input project background information, goals, and stakeholder requirements, and then send them to the server.

[0494] Step 2:

[0495] Based on the received project information, the server searches a database containing past project data and company regulations, and extracts relevant data. This information is then analyzed to understand the characteristics of the project.

[0496] Step 3:

[0497] The server uses a generative artificial intelligence model to generate an optimal project management method based on extracted and analyzed data. This generation considers a framework that includes resource allocation, schedule management, and risk management.

[0498] Step 4:

[0499] The generated project management methodology is presented to the user via the terminal. Simultaneously, the emotion engine begins the process of recognizing the user's emotions from their facial expressions, tone of voice, and other factors.

[0500] Step 5:

[0501] Users input their feelings and feedback regarding the presented management methods via their device and send it to the server. This feedback includes specific opinions and requests.

[0502] Step 6:

[0503] Based on user feedback and sentiment analysis results, the server readjusts the generated artificial intelligence model and regenerates the project management methodology as needed. This regenerated methodology is then sent back to the terminal and presented to the user.

[0504] Step 7:

[0505] This process is repeated until the management method that best suits the user's emotions is found, helping to ensure the project runs smoothly.

[0506] (Example 2)

[0507] 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."

[0508] Traditional project management systems have struggled to efficiently generate methodologies optimized for project conditions and to adjust and revise them based on user feedback. Such systems require performance optimization that fully considers user satisfaction.

[0509] 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.

[0510] In this invention, the server includes means for receiving project information, means for searching storage areas for past similar data and specified information, means for generating an optimal management method based on conditions using a generative machine learning model, means for analyzing user emotions, and means for receiving feedback from users and readjusting the generative machine learning model based on said feedback. As a result, the project management method is optimized to take into account the emotional responses of users, enabling efficient project operation.

[0511] "Means for receiving project information" refers to a device or function for receiving information from users via a terminal, including the project's background, requirements, and stakeholder expectations.

[0512] "Means for searching past similar data and prescribed information storage areas" refers to a device or function for searching a database that stores data related to past projects and prescribed information of the organization, and for extracting highly relevant information.

[0513] "Means for generating optimal management methods based on conditions using generative machine learning models" refers to a device or function that uses machine learning to generate management methods optimized for specific project conditions.

[0514] "Means for analyzing user emotions" refers to a device or function that acquires and analyzes the emotions that users express in response to the management methods presented.

[0515] "Means for receiving feedback from users and readjusting the generated machine learning model based on said feedback" refers to a device or function for receiving feedback information obtained from users and readjusting the machine learning model taking that information into consideration.

[0516] This system is designed to streamline project management. Its specific implementation is described below.

[0517] The server receives project information provided by users from terminals via the network. This information includes the project's background, requirements, and stakeholder expectations, which are crucial elements for initial project setup.

[0518] Upon receiving the data, the server searches a database containing previously accumulated project data and specified information. For this purpose, SQL or NoSQL database technology is commonly used. The search results extract relevant information useful for understanding the project's current status, preparing it for subsequent analysis.

[0519] The server utilizes a pre-trained generative AI model to generate the optimal management method based on the specific conditions of the project. This AI model employs natural language processing technology and has the ability to automatically derive relevant management methods by inputting prompts.

[0520] The generated project management methodology is presented to the user via a terminal, where the emotion engine is utilized. Facial recognition and speech recognition technologies can be used for emotion analysis. The server obtains feedback by acquiring and analyzing the emotions the user shows in response to the presented content in real time.

[0521] Based on the feedback, the server readjusts the generated AI model as needed and regenerates the revised management methods. In this way, the system can leverage user sentiment information to evolve and optimize the optimal project management methods.

[0522] As a concrete example, in a new product development project, the user provides the server with detailed information about the target market and product features. The server analyzes this information and inputs a prompt into an AI model, such as, "The target market is Europe and the US; please propose an agile methodology for rapid market entry." The management methodology derived from this is then presented to the user, and based on the feedback, the methodology can be adjusted and improved as needed.

[0523] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0524] Step 1:

[0525] The user sends basic project information to the server via their terminal. This information includes the project's background, objectives, requirements, and stakeholder expectations. This information is stored in temporary storage for the server to use in subsequent analysis. Specifically, the user transfers the information by entering it into a form using their terminal and pressing the submit button.

[0526] Step 2:

[0527] The server searches a database containing historically similar data and company policy information based on the received project information. The input is project information, and a database query is executed to extract relevant information. The output is a list of relevant information, which is sent to the analysis module within the server. Specifically, SQL queries are executed to retrieve the necessary information from the database.

[0528] Step 3:

[0529] The server uses a generative AI model based on extracted relevant information to generate the optimal project management method. The input consists of data from similar past projects and current project information. The generative AI model receives these inputs, creates prompt statements, and calculates the optimal method. The output is a flexible set of management methods. Specifically, the AI ​​model performs natural language processing based on the prompt statements to generate a list of recommended management methods.

[0530] Step 4:

[0531] The server transfers the generated project management methodology to the terminal and presents it to the user. The input here is the generated management methodology, and the output is the visual information displayed on the user interface. Specifically, the generated methodology is displayed on the terminal screen as text and graphics, providing the user with detailed information.

[0532] Step 5:

[0533] The device analyzes the user's emotions using an emotion engine. Input is the user's visual or auditory responses, and an emotion recognition algorithm is executed as data processing. Output is a judgment of the emotional tendency (e.g., positive, negative, neutral). Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice characteristics in real time.

[0534] Step 6:

[0535] The server receives the sentiment analysis results and direct feedback from the user, and readjusts the generative AI model. The input is the sentiment analysis results and feedback, and the AI ​​model is retrained or adjusted based on this information. The output is a new set of improved project management techniques. Specifically, the feedback data is input to the AI, new prompt sentences are generated, and the techniques are recalculated based on these.

[0536] (Application Example 2)

[0537] 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."

[0538] In modern manufacturing, there is a demand for increased efficiency in production processes and improved quality. However, conventional production management systems struggle to respond flexibly to the specific circumstances of the factory floor. Furthermore, the lack of systems that provide optimal management methods that take into account the feelings of on-site personnel limits the potential for productivity improvement.

[0539] 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.

[0540] In this invention, the server includes means for receiving production information, means for searching a database of past production data and guideline information, means for generating an optimal production management method based on production conditions using a generative artificial intelligence model, means for presenting the generated production management method to the person in charge, means for evaluating the person in charge's emotions using an emotion engine, and means for receiving feedback from the person in charge and readjusting the generative artificial intelligence model based on the feedback. This enables flexible and optimal production management that reflects the emotions of the person in charge on site, and makes it possible to build an efficient and high-quality manufacturing process.

[0541] "Production information" refers to data related to the production process in factories and manufacturing sites, including progress and resource usage.

[0542] "Guideline information" refers to guidelines and standards that have been predetermined for a company or industry.

[0543] A "generative artificial intelligence model" is an artificial intelligence structure that uses machine learning algorithms to analyze data and derive optimal solutions and strategies.

[0544] "Production management methods" refer to management techniques and processes for efficiently carrying out production processes and optimally allocating resources.

[0545] "Person in charge" refers to a person responsible for performing specific tasks or managing tasks within a production site or project.

[0546] An "emotion engine" is a system or program that analyzes data such as text, voice, and facial expressions to recognize human emotions.

[0547] "Feedback" refers to evaluations and opinions on a system or proposed method, and it provides valuable information for improvement.

[0548] A "flexible framework" refers to a work structure or framework that is flexible enough to adapt to various situations.

[0549] A "resource allocation strategy" refers to a strategy or plan for systematically allocating available resources.

[0550] This invention provides a system aimed at improving the efficiency and quality of production processes. The system consists of a server, terminals, and personnel.

[0551] The server is responsible for receiving production information, collecting data from sensors and terminals used on the production line. This production information includes data on product progress and resources used. The server also has the ability to search past production databases and company guidelines, and extract necessary information. Based on this information, it utilizes generative artificial intelligence models (e.g., TensorFlow) to generate optimal production management methods tailored to production conditions.

[0552] The generated production management methods are presented to on-site personnel via a terminal. The personnel's feelings towards the proposed methods are analyzed by an emotion engine installed on the terminal (e.g., Microsoft Azure Cognitive Services). It senses the personnel's facial expressions and voice to evaluate how satisfied they are with the proposal. Based on this emotion information, feedback is sent to a server, which readjusts the generated artificial intelligence model and regenerates the management methods as needed.

[0553] As a concrete example, if a production delay occurs at a factory, the server will analyze the cause of the delay and propose the optimal solution. For instance, it might devise methods to increase the speed of the production line or prioritize other processes, and present them to the person in charge. If the person in charge readily accepts, the solution will be implemented. An example of a prompt message would be, "Please propose the optimal management method to resolve the current production delay."

[0554] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0555] Step 1:

[0556] The server receives production information from sensors and terminals within the factory. The inputs include data on product progress and resource usage. Based on this data, the server processes it to understand the current state of the production process and formats it into an analyzable format.

[0557] Step 2:

[0558] The server searches historical production databases and guideline information. The input is the production information formatted in step 1, and the output is reference data based on similar past situations and standards. The data calculation performed here is a comparison of past results and current conditions on the production line.

[0559] Step 3:

[0560] The server uses a generative artificial intelligence model to generate an optimal production management method based on production conditions. The input is the reference data obtained in step 2, and the output is the proposed management method. Through the generative AI model, an optimal production management framework is constructed.

[0561] Step 4:

[0562] The terminal presents the generated production management method to the on-site staff. The input is the management method generated in step 3, and the output is information provided to the staff. The terminal conveys information through a visually easy-to-understand interface.

[0563] Step 5:

[0564] Using an emotion engine, the device evaluates the operator's emotions in response to the presented method. Input is reaction data such as the operator's facial expressions and voice, and output is the degree or tendency of those emotions. Sensors collect data in real time, and the emotion engine performs the analysis.

[0565] Step 6:

[0566] The system receives emotional feedback from the user (representative) via a terminal and sends it to the server. The input is the representative's feedback data, and the output is data transmission to the server. The terminal efficiently sends the feedback to the server using a data transmission protocol.

[0567] Step 7:

[0568] The server readjusts the generated artificial intelligence model based on the received feedback and regenerates the management method as needed. The input is the feedback data, and the output is the new management method. This readjustment generates the optimal method again, taking into account the emotions of the person in charge.

[0569] 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.

[0570] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[0571] 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.

[0572] [Fourth Embodiment]

[0573] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0574] 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.

[0575] 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).

[0576] 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.

[0577] 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.

[0578] 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).

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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".

[0586] The present invention provides a system aimed at effectively managing projects in a dynamic environment by applying a generated project management method. This system consists of a server, terminals, and users, and operates as follows.

[0587] The server receives project information entered by the user via a terminal at the start of the project. This includes the project background, goals, constraints, and stakeholder requirements. Based on the received information, the server searches its database to extract data from similar past projects, company-specific rules, and industry best practices.

[0588] Next, the server uses a generative artificial intelligence model to analyze and process the information received from the database. This model takes into account the project's characteristics and environmental factors to generate an optimal project management methodology. This methodology includes a flexible framework for efficiently managing project progress, resource allocation, schedule management, and risk management measures.

[0589] The generated project management methodology is presented to the user via a terminal. The user reviews this proposal and makes decisions regarding the implementation of the project. During this process, the user can provide feedback, which is then returned to the server.

[0590] The server improves the proposed method by readjusting the generated AI model based on user feedback, and regenerates it as needed. This regeneration process is designed to flexibly respond to new conditions and constraints that become apparent as the project progresses.

[0591] To give a concrete example, in a new product development project, the user inputs the project goals and market conditions into the server. Based on past successful product development examples, the server presents the optimal management method derived from an AI model. For risk management, agile methodologies are adopted to respond to technological changes during development and unexpected market changes, providing a concrete path to project success.

[0592] The following describes the processing flow.

[0593] Step 1:

[0594] The user uses a terminal to input the project's basic information, objectives, conditions, and constraints, and then sends them to the server.

[0595] Step 2:

[0596] The server analyzes the received project information based on its database. It searches past project data and company regulations to extract relevant information.

[0597] Step 3:

[0598] The server processes the analyzed data using a generative artificial intelligence model and generates a management methodology that best suits the project's characteristics. This generation process also takes into account resource allocation plans and risk management policies tailored to the project's specific conditions.

[0599] Step 4:

[0600] The generated project management methodology is sent from the server to the terminal and displayed to the user. The user reviews the presented methodology and confirms its contents.

[0601] Step 5:

[0602] Users send feedback to the server via their device, indicating their satisfaction level and areas for improvement for each element of the project proposal. This feedback may include suggestions for improvement or additional conditions.

[0603] Step 6:

[0604] The server readjusts the generated AI model based on user feedback and regenerates the project management methodology as needed. The improved suggestions are then sent back to the terminal and presented to the user. This cycle is repeated until the optimal management methodology is established.

[0605] (Example 1)

[0606] 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".

[0607] In projects operating in dynamic environments, selecting methods for quickly and appropriately managing resources and schedules is challenging. Furthermore, it's essential to effectively readjust management methods to flexibly respond to new conditions and constraints. This necessitates addressing project-related uncertainties and achieving optimal management.

[0608] 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.

[0609] In this invention, the server includes means for acquiring background information, objectives, limitations, and stakeholder requirements related to the project; means for searching a database containing data from previous similar cases, the organization's own guidelines, and optimal implementations of the technical domain; and means for designing the most suitable management method for the project using a machine learning algorithm. This enables efficient and flexible project management in a dynamic environment.

[0610] "Project-related background information" refers to basic information necessary to achieve the project's objectives and goals, including explanations of the project's needs, limitations, and stakeholder requirements.

[0611] "Data on similar cases" refers to data from past projects that have similar conditions and objectives to the current project.

[0612] "Organization-specific guidelines" refer to internal regulations established by a particular organization regarding its operation and management, and they indicate methods based on the organization's policies and rules.

[0613] "Optimal implementation of a technology" refers to generally recognized best practices in that field, and methods for achieving the highest levels of efficiency and effectiveness.

[0614] A "machine learning algorithm" is a set of mathematical models and procedures used to extract insights by analyzing large amounts of data and to automate specific tasks.

[0615] "Management methods" refer to methodologies and tools used to plan, implement, monitor, and control a project in order to achieve its objectives.

[0616] An "information display device" refers to a terminal or device used to visually present data and information to users, and includes computer monitors and smartphone screens.

[0617] This invention provides a system for effectively managing projects in a dynamic environment. This system consists of a server, terminals, and users, and utilizes a generative AI model to optimize project management methods.

[0618] The server receives project background information, objectives, limitations, and stakeholder requirements entered by the user through their terminal. The server searches a database to extract data from similar past cases, organization-specific guidelines, and best practices in the technical domain. Specific systems that can be used include cloud-based database management systems and generative artificial intelligence models such as the Google Cloud AI platform.

[0619] Based on the received and extracted data, the server uses an AI model to analyze it and generate an optimal project management method. This model utilizes machine learning libraries such as TensorFlow and PyTorch. The AI ​​model includes a variable structure, resource allocation method, and risk management measures for efficiently managing project progress.

[0620] The generated project management methodology is presented to the user via a terminal. The terminal has a display that can visually show the progress of the project and communicates the specific details of the management methodology to the user.

[0621] Users can evaluate the presented management methods and provide feedback back to the server via their device. The server then feeds this feedback information back into the AI ​​model and readjusts the generation method as needed. This enables project management that can flexibly adapt to new conditions and constraints.

[0622] As a concrete example, in a new product development project, the user inputs market conditions and development goals into a server. The server retrieves past successful development examples from a database, analyzes them using a generative AI model, and then presents a management method incorporating agile methodologies. This makes it possible to respond flexibly to technological changes and market fluctuations.

[0623] As an example of a prompt, the AI ​​model can be given input such as, "Generate the optimal project management methodology for achieving goals in a new product development project, paying particular attention to schedule management and risk management in an uncertain market environment," and a specific response can be obtained.

[0624] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0625] Step 1:

[0626] The user enters project background information, objectives, limitations, and stakeholder requirements into a terminal. This input is sent to the server as text data.

[0627] Step 2:

[0628] The server searches its internal database based on the received input data. The database contains data on similar past cases, organization-specific guidelines, and best practices in the technical domain. SQL queries are used to extract relevant data. The output consists of past project data and related information as search results.

[0629] Step 3:

[0630] The server inputs the extracted data into a generating AI model. This model, built using machine learning frameworks such as TensorFlow and PyTorch, analyzes the input data and generates the optimal management method for the project. Specific data processing includes feature extraction and analysis. The output is an optimized project management method.

[0631] Step 4:

[0632] The server sends the generated project management methodology to the terminal. Specifically, this involves converting the data so that the methodology is displayed on the terminal in a visualized format (e.g., a Gantt chart or a risk management list).

[0633] Step 5:

[0634] The terminal presents the user with project management methodologies sent from the server. The user reviews the details of the methodologies via the display. The presented information includes schedules, resource allocation, and risk management measures.

[0635] Step 6:

[0636] Users evaluate the presented management methods and send feedback to the server via their device. This feedback is entered as specific comments and requests for corrections.

[0637] Step 7:

[0638] The server receives feedback from the user and readjusts the generated AI model. Specifically, it inputs the feedback into the model and retrains it to regenerate project management methods. The model creates a new management method that reflects the feedback and sends it to the terminal.

[0639] (Application Example 1)

[0640] 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".

[0641] In modern manufacturing, factories are required to respond quickly to fluctuating production needs. However, traditional static work schedule management methods have limitations in terms of production line flexibility and resource allocation optimization, making efficient production operations difficult.

[0642] 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.

[0643] In this invention, the server includes means for receiving project information, means for searching a database of past project data, and means for generating an optimal project management method based on project conditions using a generative artificial intelligence model. This enables the optimization of work schedules in factories and the adjustment of dynamic resource allocation.

[0644] "Means for receiving project information" refers to a system that has the function of collecting information, including the project's background, goals, constraints, and stakeholder requirements, via a terminal.

[0645] A "database search method" refers to a function that allows for the rapid and effective extraction of information, including data from similar past projects, company-specific regulations, and industry best practices.

[0646] A "generative artificial intelligence model" is an algorithm that analyzes input project information and information obtained from a database to generate the optimal management method for a project.

[0647] "Means for optimizing factory work schedules" refers to a function that designs efficient work sequences and timings in production activities within a factory, thereby ensuring maximum productivity.

[0648] "Means for dynamically adjusting resource allocation" refers to a function that flexibly reallocates resources such as personnel, equipment, and materials within a factory according to the situation, in order to always utilize them in the most efficient manner.

[0649] "Means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback" refers to a function for receiving opinions and information provided by users, updating the generated AI model based on them, and improving the proposed project management method.

[0650] This invention provides a system for realizing dynamic project management in a factory. This system consists of three main components: a server, a terminal, and a user.

[0651] First, the server receives project information provided by the user via the terminal. This project information includes the work background, specific goals, constraints, and stakeholder requirements. Next, the server rapidly searches the database to extract data on similar past projects, company-specific norms, and industry best practices. Using this information, the server builds a generative AI model to generate optimal management methods tailored to the project's characteristics. This AI model uses Python as its programming language and utilizes the TensorFlow library for execution.

[0652] The generated project management methodology is presented to the user via a terminal. This methodology includes specific instructions regarding efficient work scheduling and dynamic resource allocation in the factory. The user can review this management methodology and decide whether to apply it to the field.

[0653] The feedback provided by the user is sent back to the server. Based on the received feedback, the server readjusts the generated AI model and regenerates the suggested management methods as needed. This process improves production efficiency within the factory and enables rapid response to abnormal situations and problems.

[0654] As a concrete example of its operation, during the Christmas season, production volume increases, so the server adjusts resource allocation based on this information. Also, if there are machines requiring maintenance, the system can receive this information in advance and incorporate it into the work schedule.

[0655] As an example of a prompt, we will use the following: "Based on the current production schedule, please suggest the optimal resource allocation for next week." This prompt will be input into the AI ​​model, which will then generate suggestions to improve the efficiency of factory operations.

[0656] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0657] Step 1:

[0658] The server receives project information from the user via the terminal. This input includes the project's background, goals, constraints, and stakeholder requirements. Based on this information, the server prepares for database searches.

[0659] Step 2:

[0660] The server searches the database and extracts data and relevant normative information for similar projects that have been completed in the past. At this stage, project information received from the user is used as input, and the server obtains data that matches those criteria as output.

[0661] Step 3:

[0662] The server takes project information and data obtained from the database as input and processes it through a generative AI model. This AI model analyzes the data and generates the optimal project management method as output. The model is programmed in Python and uses the TensorFlow library.

[0663] Step 4:

[0664] The server presents the generated project management methodology to the user via the terminal. The user then reviews the outputted management methodology and decides whether to apply it. This process includes proposals for specific work schedules and resource allocations.

[0665] Step 5:

[0666] Users send feedback from their devices to the server as a result of the review. The feedback, as input, includes opinions and suggestions for improvement regarding management methods, and the output is used to adjust the AI ​​model.

[0667] Step 6:

[0668] The server readjusts the generated artificial intelligence model based on user feedback. This process allows the system to regenerate project management methods to accommodate new conditions and provide them to the user as output. For example, resource allocation adjustments are made to accommodate increased production volume.

[0669] 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.

[0670] This invention aims to effectively support the achievement of project objectives by combining an emotion engine with a project management system. This system consists of a server, terminals, and users, each functioning according to its respective role as follows:

[0671] The server receives project information from users via their terminals. This information includes the project's basic background, requirements, and stakeholder expectations. Next, the server searches past project databases and company regulations, extracts relevant information, and analyzes it to understand the project's current status.

[0672] Based on the extracted information, the server utilizes a generative artificial intelligence model to generate an optimal project management methodology. This generation process proposes a flexible framework that includes resource allocation and risk management policies tailored to project-specific conditions.

[0673] The generated project management methodology is presented to the user via a terminal. Here, an emotion engine is utilized to analyze the user's emotions. It recognizes how the user feels about the displayed methodology and adjusts the proposed content based on those emotions. This process proceeds by determining how interested or dissatisfied the user is with the presented methodology and analyzing the emotional information contained in the feedback for improvement on the server.

[0674] Based on user emotional feedback, the server readjusts the generated artificial intelligence model and regenerates the methodology as needed. This allows the project management methodology to evolve and optimize while reflecting user emotions.

[0675] As a concrete example, let's consider a new product development project. In this project, the user provides the server with details about the target market and product features. After analysis, the server generates the optimal development methodology and evaluates the user's initial reaction through the emotion engine. For example, if the user shows a positive reaction to the proposed agile development methodology, it proceeds as is. On the other hand, if concerns are expressed, the server proposes an alternative methodology, such as a waterfall approach, and finds the optimal solution based on the user's emotions.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] Users use their devices to input project background information, goals, and stakeholder requirements, and then send them to the server.

[0679] Step 2:

[0680] Based on the received project information, the server searches a database containing past project data and company regulations, and extracts relevant data. This information is then analyzed to understand the characteristics of the project.

[0681] Step 3:

[0682] The server uses a generative artificial intelligence model to generate an optimal project management method based on extracted and analyzed data. This generation considers a framework that includes resource allocation, schedule management, and risk management.

[0683] Step 4:

[0684] The generated project management methodology is presented to the user via the terminal. Simultaneously, the emotion engine begins the process of recognizing the user's emotions from their facial expressions, tone of voice, and other factors.

[0685] Step 5:

[0686] Users input their feelings and feedback regarding the presented management methods via their device and send it to the server. This feedback includes specific opinions and requests.

[0687] Step 6:

[0688] Based on user feedback and sentiment analysis results, the server readjusts the generated artificial intelligence model and regenerates the project management methodology as needed. This regenerated methodology is then sent back to the terminal and presented to the user.

[0689] Step 7:

[0690] This process is repeated until the management method that best suits the user's emotions is found, helping to ensure the project runs smoothly.

[0691] (Example 2)

[0692] 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".

[0693] Traditional project management systems have struggled to efficiently generate methodologies optimized for project conditions and to adjust and revise them based on user feedback. Such systems require performance optimization that fully considers user satisfaction.

[0694] 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.

[0695] In this invention, the server includes means for receiving project information, means for searching storage areas for past similar data and specified information, means for generating an optimal management method based on conditions using a generative machine learning model, means for analyzing user emotions, and means for receiving feedback from users and readjusting the generative machine learning model based on said feedback. As a result, the project management method is optimized to take into account the emotional responses of users, enabling efficient project operation.

[0696] "Means for receiving project information" refers to a device or function for receiving information from users via a terminal, including the project's background, requirements, and stakeholder expectations.

[0697] "Means for searching past similar data and prescribed information storage areas" refers to a device or function for searching a database that stores data related to past projects and prescribed information of the organization, and for extracting highly relevant information.

[0698] "Means for generating optimal management methods based on conditions using generative machine learning models" refers to a device or function that uses machine learning to generate management methods optimized for specific project conditions.

[0699] "Means for analyzing user emotions" refers to a device or function that acquires and analyzes the emotions that users express in response to the management methods presented.

[0700] "Means for receiving feedback from users and readjusting the generated machine learning model based on said feedback" refers to a device or function for receiving feedback information obtained from users and readjusting the machine learning model taking that information into consideration.

[0701] This system is designed to streamline project management. Its specific implementation is described below.

[0702] The server receives project information provided by users from terminals via the network. This information includes the project's background, requirements, and stakeholder expectations, which are crucial elements for initial project setup.

[0703] Upon receiving the data, the server searches a database containing previously accumulated project data and specified information. For this purpose, SQL or NoSQL database technology is commonly used. The search results extract relevant information useful for understanding the project's current status, preparing it for subsequent analysis.

[0704] The server utilizes a pre-trained generative AI model to generate the optimal management method based on the specific conditions of the project. This AI model employs natural language processing technology and has the ability to automatically derive relevant management methods by inputting prompts.

[0705] The generated project management methodology is presented to the user via a terminal, where the emotion engine is utilized. Facial recognition and speech recognition technologies can be used for emotion analysis. The server obtains feedback by acquiring and analyzing the emotions the user shows in response to the presented content in real time.

[0706] Based on the feedback, the server readjusts the generated AI model as needed and regenerates the revised management methods. In this way, the system can leverage user sentiment information to evolve and optimize the optimal project management methods.

[0707] As a concrete example, in a new product development project, the user provides the server with detailed information about the target market and product features. The server analyzes this information and inputs a prompt into an AI model, such as, "The target market is Europe and the US; please propose an agile methodology for rapid market entry." The management methodology derived from this is then presented to the user, and based on the feedback, the methodology can be adjusted and improved as needed.

[0708] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0709] Step 1:

[0710] The user sends basic project information to the server via their terminal. This information includes the project's background, objectives, requirements, and stakeholder expectations. This information is stored in temporary storage for the server to use in subsequent analysis. Specifically, the user transfers the information by entering it into a form using their terminal and pressing the submit button.

[0711] Step 2:

[0712] The server searches a database containing historically similar data and company policy information based on the received project information. The input is project information, and a database query is executed to extract relevant information. The output is a list of relevant information, which is sent to the analysis module within the server. Specifically, SQL queries are executed to retrieve the necessary information from the database.

[0713] Step 3:

[0714] The server uses a generative AI model based on extracted relevant information to generate the optimal project management method. The input consists of data from similar past projects and current project information. The generative AI model receives these inputs, creates prompt statements, and calculates the optimal method. The output is a flexible set of management methods. Specifically, the AI ​​model performs natural language processing based on the prompt statements to generate a list of recommended management methods.

[0715] Step 4:

[0716] The server transfers the generated project management methodology to the terminal and presents it to the user. The input here is the generated management methodology, and the output is the visual information displayed on the user interface. Specifically, the generated methodology is displayed on the terminal screen as text and graphics, providing the user with detailed information.

[0717] Step 5:

[0718] The device analyzes the user's emotions using an emotion engine. Input is the user's visual or auditory responses, and an emotion recognition algorithm is executed as data processing. Output is a judgment of the emotional tendency (e.g., positive, negative, neutral). Specifically, the device uses a camera and microphone to analyze the user's facial expressions and voice characteristics in real time.

[0719] Step 6:

[0720] The server receives the sentiment analysis results and direct feedback from the user, and readjusts the generative AI model. The input is the sentiment analysis results and feedback, and the AI ​​model is retrained or adjusted based on this information. The output is a new set of improved project management techniques. Specifically, the feedback data is input to the AI, new prompt sentences are generated, and the techniques are recalculated based on these.

[0721] (Application Example 2)

[0722] 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".

[0723] In modern manufacturing, there is a demand for increased efficiency in production processes and improved quality. However, conventional production management systems struggle to respond flexibly to the specific circumstances of the factory floor. Furthermore, the lack of systems that provide optimal management methods that take into account the feelings of on-site personnel limits the potential for productivity improvement.

[0724] 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.

[0725] In this invention, the server includes means for receiving production information, means for searching a database of past production data and guideline information, means for generating an optimal production management method based on production conditions using a generative artificial intelligence model, means for presenting the generated production management method to the person in charge, means for evaluating the person in charge's emotions using an emotion engine, and means for receiving feedback from the person in charge and readjusting the generative artificial intelligence model based on the feedback. This enables flexible and optimal production management that reflects the emotions of the person in charge on site, and makes it possible to build an efficient and high-quality manufacturing process.

[0726] "Production information" refers to data related to the production process in factories and manufacturing sites, including progress and resource usage.

[0727] "Guideline information" refers to guidelines and standards that have been predetermined for a company or industry.

[0728] A "generative artificial intelligence model" is an artificial intelligence structure that uses machine learning algorithms to analyze data and derive optimal solutions and strategies.

[0729] "Production management methods" refer to management techniques and processes for efficiently carrying out production processes and optimally allocating resources.

[0730] "Person in charge" refers to a person responsible for performing specific tasks or managing tasks within a production site or project.

[0731] An "emotion engine" is a system or program that analyzes data such as text, voice, and facial expressions to recognize human emotions.

[0732] "Feedback" refers to evaluations and opinions on a system or proposed method, and it provides valuable information for improvement.

[0733] A "flexible framework" refers to a work structure or framework that is flexible enough to adapt to various situations.

[0734] A "resource allocation strategy" refers to a strategy or plan for systematically allocating available resources.

[0735] This invention provides a system aimed at improving the efficiency and quality of production processes. The system consists of a server, terminals, and personnel.

[0736] The server is responsible for receiving production information, collecting data from sensors and terminals used on the production line. This production information includes data on product progress and resources used. The server also has the ability to search past production databases and company guidelines, and extract necessary information. Based on this information, it utilizes generative artificial intelligence models (e.g., TensorFlow) to generate optimal production management methods tailored to production conditions.

[0737] The generated production management methods are presented to on-site personnel via a terminal. The personnel's feelings towards the proposed methods are analyzed by an emotion engine installed on the terminal (e.g., Microsoft Azure Cognitive Services). It senses the personnel's facial expressions and voice to evaluate how satisfied they are with the proposal. Based on this emotion information, feedback is sent to a server, which readjusts the generated artificial intelligence model and regenerates the management methods as needed.

[0738] As a concrete example, if a production delay occurs at a factory, the server will analyze the cause of the delay and propose the optimal solution. For instance, it might devise methods to increase the speed of the production line or prioritize other processes, and present them to the person in charge. If the person in charge readily accepts, the solution will be implemented. An example of a prompt message would be, "Please propose the optimal management method to resolve the current production delay."

[0739] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0740] Step 1:

[0741] The server receives production information from sensors and terminals within the factory. The inputs include data on product progress and resource usage. Based on this data, the server processes it to understand the current state of the production process and formats it into an analyzable format.

[0742] Step 2:

[0743] The server searches historical production databases and guideline information. The input is the production information formatted in step 1, and the output is reference data based on similar past situations and standards. The data calculation performed here is a comparison of past results and current conditions on the production line.

[0744] Step 3:

[0745] The server uses a generative artificial intelligence model to generate an optimal production management method based on production conditions. The input is the reference data obtained in step 2, and the output is the proposed management method. Through the generative AI model, an optimal production management framework is constructed.

[0746] Step 4:

[0747] The terminal presents the generated production management method to the on-site staff. The input is the management method generated in step 3, and the output is information provided to the staff. The terminal conveys information through a visually easy-to-understand interface.

[0748] Step 5:

[0749] Using an emotion engine, the device evaluates the operator's emotions in response to the presented method. Input is reaction data such as the operator's facial expressions and voice, and output is the degree or tendency of those emotions. Sensors collect data in real time, and the emotion engine performs the analysis.

[0750] Step 6:

[0751] The system receives emotional feedback from the user (representative) via a terminal and sends it to the server. The input is the representative's feedback data, and the output is data transmission to the server. The terminal efficiently sends the feedback to the server using a data transmission protocol.

[0752] Step 7:

[0753] The server readjusts the generated artificial intelligence model based on the received feedback and regenerates the management method as needed. The input is the feedback data, and the output is the new management method. This readjustment generates the optimal method again, taking into account the emotions of the person in charge.

[0754] 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.

[0755] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include those described above. 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 shown 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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."

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] The following is further disclosed regarding the embodiments described above.

[0776] (Claim 1)

[0777] A means of receiving project information,

[0778] A means of searching a database of past project data and regulations,

[0779] A means of generating the optimal project management method based on project conditions using a generative artificial intelligence model,

[0780] A means of presenting the generated project management method to the user,

[0781] A means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, which has the ability to combine a flexible framework and a resource allocation strategy as a project management method.

[0785] (Claim 3)

[0786] The system according to claim 1, comprising a function to regenerate and re-present proposed project management methods based on user feedback.

[0787] "Example 1"

[0788] (Claim 1)

[0789] Means for obtaining background information, objectives, limitations, and stakeholder requirements related to the project,

[0790] A means for searching a database containing data from similar previous cases, as well as the organization's own guidelines and optimal implementations in its technical domain,

[0791] A means of designing the most suitable management method for a project using machine learning algorithms,

[0792] A means of showing the designed management method to human users via an information display device,

[0793] A means of receiving evaluation information from human users and adjusting machine learning algorithms based on that evaluation information,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, which combines a variable structure and a method of resource allocation as a designed project management method.

[0797] (Claim 3)

[0798] The system according to claim 1, further comprising a function to redesign the proposed project management method based on evaluation information from human users and present it again via an information display device.

[0799] "Application Example 1"

[0800] (Claim 1)

[0801] A means of receiving project information,

[0802] A means of searching a database of past project data and regulations,

[0803] A means of generating the optimal project management method based on project conditions using a generative artificial intelligence model,

[0804] A means of presenting the generated project management method to the user,

[0805] A means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback,

[0806] A means to optimize factory work schedules and dynamically adjust resource allocation,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, which has the ability to combine a flexible framework and a resource allocation strategy as a project management method.

[0810] (Claim 3)

[0811] The system according to claim 1, comprising the function of regenerating proposed project management methods based on user feedback and improving work efficiency within the factory.

[0812] "Example 2 of combining an emotion engine"

[0813] (Claim 1)

[0814] A means of receiving project information,

[0815] A means for searching a storage area of ​​past similar data and specified information,

[0816] A means of generating the optimal management method based on conditions using a generative machine learning model,

[0817] A means of presenting the generated management method to the user,

[0818] A means of analyzing user emotions,

[0819] A means for receiving feedback from users and readjusting the generative machine learning model based on that feedback,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, which has the function of combining a flexible framework and resource allocation strategy as a management method.

[0823] (Claim 3)

[0824] The system according to claim 1, comprising a function to regenerate and re-present proposed management methods based on user feedback.

[0825] "Application example 2 when combining with an emotional engine"

[0826] (Claim 1)

[0827] Means for receiving production information,

[0828] A means of searching a database of past production data and guideline information,

[0829] A means for generating an optimal production management method based on production conditions using a generative artificial intelligence model,

[0830] A means of presenting the generated production management method to the person in charge,

[0831] A means of evaluating the emotions of the person in charge using an emotion engine,

[0832] A means for receiving feedback from the person in charge and readjusting the generated artificial intelligence model based on said feedback,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, comprising a flexible framework and resource allocation strategy, and the ability to regenerate methods while taking emotional feedback into consideration.

[0836] (Claim 3)

[0837] The system according to claim 1, comprising a function to optimize and re-present a proposed production management method based on emotional feedback from the person in charge. [Explanation of symbols]

[0838] 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 project information, A means of searching a database of past project data and regulations, A means of generating the optimal project management method based on project conditions using a generative artificial intelligence model, A means of presenting the generated project management method to the user, A means for receiving feedback from users and readjusting the generated artificial intelligence model based on said feedback, A means to optimize factory work schedules and dynamically adjust resource allocation, A system that includes this.

2. The system according to claim 1, which has the function of combining a flexible framework and a resource allocation strategy as a project management method.

3. The system according to claim 1, comprising a function to regenerate proposed project management methods based on user feedback and improve work efficiency within the factory.

Images