system

Abstract

We provide the system. [Solution] Means of collecting project-related data, A means for cleaning the collected data and converting it into a format suitable for a generative artificial intelligence model, A method for proposing the optimal approach for each project using generative artificial intelligence models, A means of prioritizing the proposed approaches based on multiple evaluation metrics, Means for adjusting the selected approach according to the situation as the project progresses, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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 project management, it is difficult to select a flexible and effective approach while the environment and constraints are constantly changing. Conventional static project management methods cannot quickly respond to the unique rules and constraints of each company, which is one of the reasons for reducing the success rate of projects. In addition, finding an optimal management approach according to the characteristics of each project requires high skills and rich experience, which is a heavy burden for many companies.

Means for Solving the Problems

[0005] This invention provides a means for automatically collecting project-related data and cleaning it into a format suitable for a generative AI model, thereby enabling the deriving of the optimal approach for each project. Furthermore, it includes a means for generating diverse strategic proposals using the generative AI model and prioritizing them based on multiple evaluation indicators. This makes it possible to propose and adjust the optimal approach according to the situation even during project progress, significantly improving the flexibility and efficiency of project management.

[0006] "Project-related data" refers to information necessary for the progress, management, and evaluation of the project, and includes, for example, information on the project charter, tasks, resources, risks, and stakeholders.

[0007] "Cleaning methods" refer to techniques or processes that remove noise and inappropriate information from collected data and prepare it in a format suitable for analysis and processing.

[0008] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technologies such as machine learning and deep learning to generate the optimal solution under specific conditions based on input data.

[0009] "Approach" refers to the strategy, method, or plan taken to achieve a specific goal, and means the specific policies and procedures in the progress of a project.

[0010] "Evaluation indicators" are criteria or measures used to evaluate projects, strategies, etc., and include elements such as efficiency, effectiveness, cost, and risk.

[0011] "Methods for setting priorities" refer to methods and techniques for efficiently managing and executing tasks by determining their order based on their importance and urgency when multiple options or tasks exist. [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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0015] In the following embodiments, a tagged 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, a tagged 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, a tagged 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, and the like.

[0018] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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] This invention is a system that supports the selection of a flexible and efficient strategic approach in project management. The following specific processes are involved in its implementation.

[0034] First, the server automatically collects diverse data related to the project. This includes information from a database that integrates past project examples, internal company rules, PMI (Project Management Integration), and other best practices. Next, the server cleans this data and converts it into a format suitable for generative artificial intelligence models. This conversion process removes noise and redundant information and structures the data.

[0035] Next, the server utilizes a generative artificial intelligence model to generate strategic approaches suitable for each project. This AI model analyzes a wealth of data and proposes multiple possibilities. The server then prioritizes the generated approach proposals based on evaluation metrics to find the most suitable strategy.

[0036] Furthermore, the terminal functions as a means of providing information to the user, displaying the generated approach proposals as a visual dashboard. The user can then refer to this dashboard and select the approach that best suits the project's characteristics. The selected approach is tracked and adjusted in real time throughout the project's progress.

[0037] As a concrete example, let's consider a new product development project. The server uses an AI model to propose the optimal development method and marketing strategy based on past market data and competitor analysis information. The user then selects the method that best suits their current resources and goals and proceeds with the project.

[0038] Thus, this invention improves the efficiency and flexibility of project management and helps companies to quickly adapt to changing environments.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server automatically collects project-related data, including information on past project examples, company rules, and industry best practices. The collected data is retrieved through queries from specific databases or using external APIs.

[0042] Step 2:

[0043] The server cleans the data it has collected. The cleaning process removes noise from the data and standardizes its format. For example, it removes duplicate data, fills in missing data, and eliminates irrelevant data.

[0044] Step 3:

[0045] The server then converts the cleaned data into a format suitable for the generated AI model. Here, the data is structured so that the AI ​​model can properly analyze it, and the necessary variables and metrics are included.

[0046] Step 4:

[0047] The server uses a generated AI model to create the optimal approach for each project. The model analyzes the input data and outputs multiple strategic approach options. The AI ​​model then uses the trained data and algorithms to evaluate the proposed strategies.

[0048] Step 5:

[0049] The server prioritizes the generated approach proposals. Based on evaluation metrics for each approach, such as risk, resource consumption, and expected outcomes, it creates a ranking to select the optimal approach.

[0050] Step 6:

[0051] The device displays the generated approach proposals as a visual dashboard to provide information to the user. The dashboard makes it easier for the user to understand the details, benefits, and risks of each approach.

[0052] Step 7:

[0053] The user, via their device, selects the most suitable approach from the proposed options based on the project's characteristics and the company's goals. After selection, the project proceeds based on the chosen approach.

[0054] Step 8:

[0055] The server monitors project progress in real time and adjusts the strategy as needed. It evaluates the project's health based on progress data and suggests appropriate adjustments to the approach to the user.

[0056] (Example 1)

[0057] 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."

[0058] Project management requires the efficient collection of vast amounts of information and the rapid selection of a strategic approach appropriate to the project. However, traditional systems require considerable effort and time to collect and organize information, and to present and adjust appropriate strategies, making it particularly difficult to adapt to rapidly changing market environments. Therefore, to increase project success, a system that streamlines these processes and can respond flexibly is needed.

[0059] 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.

[0060] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative artificial intelligence model, and means for using the generative artificial intelligence model to generate the optimal strategic approach for each project. This enables efficient collection and organization of information in a project, as well as the rapid and appropriate selection and adjustment of strategic approaches.

[0061] "Information" is a general term for all data and knowledge related to the project, including past cases, rules, best practices, etc.

[0062] "Organization" is the process of removing noise and standardizing the format of collected information in order to make it suitable for a specific purpose.

[0063] "Generative AI models" are a general term for artificial intelligence methods and technologies that analyze large amounts of data and provide new insights and suggestions.

[0064] A "strategic approach" refers to the specific means and methodologies that should be taken to achieve the project's objectives.

[0065] "Evaluation criteria" are indicators used as a scale when selecting a generated strategy, and include factors such as probability of success, cost-effectiveness, and risk.

[0066] "Priority" refers to the order in which multiple options or processes should be prioritized.

[0067] A "display device" refers to hardware or software used to provide information to a user visually.

[0068] "Progress status" refers to information that shows the actual progress and degree of achievement of a project against its plan.

[0069] "Risk" refers to uncertain events that could potentially affect the achievement of a project's goals.

[0070] An "information processing system" refers to a computer-based system used to process, analyze, and provide results from project data.

[0071] In order to implement this invention, multiple components constituting the entire information processing system must function in coordination.

[0072] First, the server plays the role of information gathering. The server accesses various data sources and automatically retrieves a vast amount of information related to the project. This includes retrieving data from internal databases and external data sources, and extracting necessary data using, for example, SQL queries.

[0073] Next, the server organizes the collected information and converts it into a format optimized for generative artificial intelligence models. Here, the data is formatted as a DataFrame using the Python Pandas library, and then preprocessed using the Scikit-learn preprocessing module. This removes noise and redundancy from the data, ensuring it is structured as required.

[0074] Once the data is prepared, the server utilizes a generative AI model to derive the optimal strategic approach for each project. This process uses Hugging Face's Transformers library to perform data analysis using deep learning techniques with pre-trained models and propose multiple strategies.

[0075] The generated strategies are prioritized by the server based on evaluation criteria. The selected strategies are then dynamically adjusted according to the project's progress.

[0076] The terminal functions as an interface to the user. A dedicated display device (e.g., a dashboard using Tableau or Power BI) is used to show the generated strategies to the user in a visualized form. This visualization helps to understand the information and supports efficient decision-making.

[0077] Based on the information presented, the user selects the strategy best suited to the project's characteristics and current situation. During this process, the system records the user's selection and supports subsequent project progress.

[0078] As a concrete example, in a new product development project, the server collects and analyzes past market trends and competitor information, and uses an AI model to present the optimal development and sales strategy. Based on these results, the user can select a strategy that matches their current resources and goals, and proceed with the project.

[0079] An example of a prompt is, "Please list the optimal strategic proposals for launching a new product into the market, using historical data." In this way, the invention achieves increased efficiency and speed in project management by combining advanced information processing technologies.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects project-related information. Inputs include queries from internal corporate databases and external data sources. This retrieves data on past projects and industry best practices. The output is the collected raw dataset. Specifically, it retrieves data via an API and uses SQL queries to obtain the necessary information.

[0083] Step 2:

[0084] The server organizes the collected information and converts it into a format suitable for generative artificial intelligence models. Raw datasets are used as input, and pre-processed datasets suitable for AI models are output. Specifically, the server uses the Python Pandas library to format the dataframe, remove unnecessary data and noise, and standardize and encode the data. This results in a format that is easy to process.

[0085] Step 3:

[0086] The server analyzes pre-processed data using a generative AI model to generate the optimal strategic approach for each project. The input is a formatted dataset, and the output is multiple proposed strategies. Specifically, it uses the Hugging Face Transformers library to run a deep learning model and extract insights from the data.

[0087] Step 4:

[0088] The server analyzes the generated strategies against evaluation criteria and sets priorities. The inputs are the proposed strategies and evaluation criteria, and the output is a prioritized list of strategies. The specific operation involves statistical analysis using the Python SciPy library to calculate an evaluation score for each strategy.

[0089] Step 5:

[0090] The terminal visualizes and presents the generated strategies to the user. The input is a prioritized list of strategies, and the output is a visual dashboard displayed through the user interface. Specifically, it uses Tableau and Power BI to visualize data and present strategies in a way that is easy for the user to understand.

[0091] Step 6:

[0092] The user selects the most suitable strategy from the presented options and applies it to the project. The input is information from a visual dashboard, and the output is the selected strategy. Specifically, the user evaluates the strategies, chooses the one that best matches the project objectives and current situation, and incorporates it into the execution plan.

[0093] (Application Example 1)

[0094] 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."

[0095] In today's production environment, efficient and flexible project management is crucial. However, determining the optimal strategy based on diverse data is complex and requires timely adjustments. In addition, factory production projects require the presentation and adjustment of production strategies in real time, and the wide range of challenges presents obstacles.

[0096] 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.

[0097] In this invention, the server includes means for collecting project-related information, means for cleaning the collected information and converting it into a format suitable for a generative artificial intelligence model, means for proposing the optimal strategy for each project using the generative artificial intelligence model, and means for factory equipment to present operational strategies in real time via information terminals. This enables efficient real-time presentation and adjustment of operational strategies in production projects.

[0098] A "project" is a collection of activities that an organization or individual systematically undertakes to achieve a specific objective.

[0099] "Information" refers to a collection of various data and knowledge related to a project, and serves as a foundation for supporting decision-making.

[0100] "Cleaning" is the process of removing noise and redundant data from collected information and preparing it in a format suitable for analysis.

[0101] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and automatically generates optimal strategies and policies.

[0102] A "policy" refers to a specific action plan or strategy for carrying out a project.

[0103] An "evaluation indicator" is a standard or scale used to measure the effectiveness or importance of a proposed policy.

[0104] "Equipment" refers to machines and robots installed within a factory to perform production tasks.

[0105] An "information terminal" is a digital device that allows users to visually receive and operate information.

[0106] An "operational strategy" is a set of specific actions or plans that a device or system takes to achieve a particular objective.

[0107] "Real-time" refers to processing and responding in accordance with actual time, and is a state of immediate action.

[0108] The system for implementing this invention consists of a server, an information terminal, and equipment within the factory. The server collects project-related information through IoT devices and other means, and cleans that information. The cleaned data is converted into a format suitable for a generative AI model that runs on TENSORFLOW® using Python. This AI model generates optimal strategies based on the characteristics of the project and devises operational strategies within the factory.

[0109] The server transmits the generated policies to the information terminal in real time, and the user confirms them through the terminal's display. During this process, the user can select and apply multiple operational strategies provided by the generated AI model. This information is then reflected in the factory equipment, enabling efficient production activities.

[0110] A concrete example is the setup of a new product production line. Based on past data and market analysis, the AI ​​model calculates the optimal operation sequence for each production process, thereby improving factory efficiency. Furthermore, users can provide the AI ​​model with prompts via an information terminal, such as "We require an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," to obtain specific guidance.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server collects project-related information through IoT devices within the factory. This information includes historical production data, market trends, and current equipment operating status. The collected information is stored in a database on the server.

[0114] Step 2:

[0115] The server cleans the stored information, removing noise and redundant data. This process uses a specific algorithm to format the data into a format suitable for the generated AI model. The cleaned data is then prepared for further analysis.

[0116] Step 3:

[0117] The server runs a generative AI model using TensorFlow with clean data. This model analyzes historical data and real-time situations to calculate the optimal operating strategy. The results of this analysis are output as proposed strategies to be used in the next step.

[0118] Step 4:

[0119] The server transmits the generated operational strategy to the information terminal. The information terminal displays this visually and proposes it to the user. The user can compare multiple strategy options on the terminal screen and select the appropriate strategy.

[0120] Step 5:

[0121] The user reviews the selected operational strategy and provides prompts to the generating AI model as needed. For example, by giving instructions such as, "I need an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," the model can derive a more specific strategy.

[0122] Step 6:

[0123] The server issues final operational commands to the equipment based on the user's selection and provided prompts. These commands are transmitted to each piece of equipment in the factory and executed to ensure efficient operation of the production line.

[0124] 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.

[0125] This invention is a system that incorporates an emotion engine into the strategic approach selection process in project management. This enables a process that considers the user's emotional state and proposes the most suitable approach for the project's characteristics.

[0126] First, the server collects project-related data, removes noise, and cleans it into a format suitable for the AI ​​model. This data is then input into the AI ​​model, which generates optimal approach suggestions for each project. When combined with the emotion engine, the server also collects user emotion data and feeds this back into the approach suggestions output by the AI ​​model. For example, if a user is experiencing stress related to the project, the engine will suggest an approach that can alleviate that stress.

[0127] The device visually displays the results of an analysis of the user's emotional state along with the proposed approaches, making the information easy to understand. This allows the user to select an approach that is appropriate for the project's characteristics, taking their own emotional state into consideration. The emotion engine then adjusts the selected approach to optimize the user's job satisfaction and stress management.

[0128] As a concrete example, in a development project, if the server detects that a user is busy and under high stress, it will adjust task priorities and assignments based on emotional data, proposing a more efficient and less mentally taxing approach.

[0129] This invention aims to facilitate smoother corporate activities by providing a more human-centered approach that takes into account user emotions while maintaining efficiency in project management.

[0130] The following describes the processing flow.

[0131] Step 1:

[0132] The server automatically collects project-related data. This data includes past project examples, company rules, and industry best practice information. The server also uses APIs and databases to collect data from external resources.

[0133] Step 2:

[0134] The server cleans the collected data. This involves removing unnecessary information and noise and formatting the data into a standard format. The cleaning process removes duplicate data and fills in any incomplete data.

[0135] Step 3:

[0136] The server uses an emotion engine to collect user emotion data. This emotion data is obtained through user input, wearable devices, feedback forms, etc. The emotion engine includes measuring stress levels and satisfaction levels.

[0137] Step 4:

[0138] The server utilizes an AI model to generate the optimal approach for each project. Based on cleaned data and sentiment data, the AI ​​model proposes multiple strategic options. For example, it considers high-stress situations indicated by sentiment data and suggests task scheduling that reduces stress.

[0139] Step 5:

[0140] The server prioritizes the generated approach proposals based on evaluation metrics. At this stage, the benefits, risks, and impact on user emotions of each approach are considered to identify the most effective approach.

[0141] Step 6:

[0142] The device provides the user with a visual dashboard containing the results of an analysis of their emotional state, along with suggested approaches. Through this dashboard, the user can visually confirm the details of each approach and its impact on their emotions.

[0143] Step 7:

[0144] The user uses their device to select the approach that best suits their emotional state and project objectives from the proposed options. The selected approach is then incorporated into the project's progress plan.

[0145] Step 8:

[0146] The server monitors project progress in real time and continuously analyzes changes in sentiment data. If necessary, it dynamically adjusts strategies and provides feedback to users to support optimal project management.

[0147] (Example 2)

[0148] 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".

[0149] Selecting the appropriate approach is essential for improving efficiency in project management. However, existing systems only make objective judgments based on project data, making it difficult to adjust the approach while considering the emotional state of the users. As a result, user job satisfaction and stress reduction may not be sufficiently achieved, potentially leading to a decrease in overall project efficiency. This project aims to solve this problem.

[0150] 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.

[0151] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for an artificial intelligence model, means for proposing the optimal solution for each project using the artificial intelligence model, and means for collecting user sentiment information and feeding it back into the solutions generated by the artificial intelligence model. This makes it possible to adjust the approach to take into account the user's emotional state, enabling efficient and highly satisfying project management.

[0152] "Project-related information" refers to data necessary for the successful completion of a specific project, such as its progress, resources, schedule, and the roles of its members.

[0153] "Organization" refers to the process of converting data into an appropriate format and structure so that it can be effectively analyzed by artificial intelligence models.

[0154] An "artificial intelligence model" refers to machine learning algorithms and neural networks used to analyze collected information and propose the optimal approach for a project.

[0155] "Proposing countermeasures" refers to the artificial intelligence model presenting management policies and action plans for a specific project based on its analysis results.

[0156] "User emotional information" refers to data that indicates the emotional state and stress levels of individuals working on a project, and is gathered through chat tone and information from biosensors.

[0157] "Providing feedback" refers to incorporating acquired emotional information into the proposed solutions output by the artificial intelligence model and adjusting those solutions accordingly.

[0158] This invention constructs a system that combines an artificial intelligence model and an emotion data analysis engine to select effective strategies in project management. The system primarily relies on the collaboration of three parties: a server, a terminal, and a user.

[0159] The server collects project-related data from internal databases and external information sources. Data collection utilizes the Python Pandas library and leverages SQL queries. The collected data is then de-noised and converted into a format suitable for use with artificial intelligence models, such as JSON or CSV. Data processing tools like Pandas and NumPy are used for this conversion.

[0160] Next, the server inputs the collected data into a generative AI model. This model is built using frameworks such as TensorFlow or PyTorch and generates the optimal approach for a specific project based on a prompt. An example of a prompt used in this process is, "Please suggest a strategy to maximize the efficiency of the project."

[0161] The server further collects data from wearable devices and communication tools to obtain user emotional information. This emotional data includes the user's heart rate, chat content, and tone. Natural language processing tools such as NLTK and emotion analysis APIs are used for analysis. This data is fed back into the project's approach, which is then adjusted to reduce user stress.

[0162] The terminal visually displays the proposed approaches and emotional information analysis results received from the server. To achieve this, a dashboard is created using D3.js and Chart.js. Based on this information, users can select the most suitable approach, taking into account their own emotional state and the characteristics of the project. Specifically, it serves as a reference for users when readjusting task allocation or changing schedules.

[0163] This system aims to provide a human-centered strategic approach tailored to the characteristics of each project, thereby improving the efficiency of project management and maximizing user job satisfaction.

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server retrieves project-related information from internal databases and external information sources. Inputs include project progress, resource utilization, and task assignments. This information is imported as a dataframe using the Python Pandas library. The output is a dataset with unnecessary noise removed. Specifically, it extracts information from the database using SQL queries and imputes or removes missing values.

[0167] Step 2:

[0168] The server converts the collected data into a format that is easily analyzable by the generating AI model. The conversion targets the data format and structure. The input is the dataset cleaned in step 1. It is converted to CSV or JSON format using Pandas or NumPy. This data is processed into a shape suitable for the model, and the output is data in an analyzable format. Specifically, categorical data is encoded into numerical data, and data normalization is performed as needed.

[0169] Step 3:

[0170] The server uses the transformed data to input into a generating AI model and generate the optimal solution for the project. The prompt "Propose a strategy to maximize project efficiency" is used as input. The model is built with TensorFlow and PyTorch and outputs project-specific analysis results. Specifically, it calls the model, performs inference processing, and outputs the resulting artifacts (a series of proposed approaches).

[0171] Step 4:

[0172] The server collects user emotional information from wearable devices and communication tools. Input data includes heart rate, chat content, and tone of voice. The server analyzes this data using the natural language processing library NLTK and an emotion analysis API to quantify the user's emotional state. The output provides the user's stress level and emotional tone score. Specifically, the server periodically polls data from devices and tools to update the analysis results.

[0173] Step 5:

[0174] The server optimizes the proposed approaches generated using emotional data. Inputs include the proposed approaches generated in step 3 and the user's emotional score obtained in step 4. A feedback loop is constructed to prioritize approaches that reduce stress. The output is an optimized approach adapted to the user's emotions. Specifically, the server adjusts task priorities and assignments based on the user's emotional state.

[0175] Step 6:

[0176] The terminal visually displays the ultimately selected approach and the user's emotional state. It uses approach data and emotional analysis results from the server as input. Data is received via GraphQL or REST API, and a dashboard is created using D3.js or Chart.js. The output provides a graphical interface to facilitate user decision-making while considering their emotional state. Specific actions include providing intuitive displays and interactions using bar graphs and icons.

[0177] (Application Example 2)

[0178] 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".

[0179] Modern project management often prioritizes efficiency while neglecting the emotional aspects of stakeholders. This can lead to increased emotional stress during project execution, negatively impacting the quality and progress of deliverables. Furthermore, it can decrease the motivation of those involved in the project, posing a risk to overall work efficiency.

[0180] 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.

[0181] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative machine learning algorithm, means for proposing the optimal method for each project using a generative machine learning algorithm, means for acquiring user emotional information and making suggestions based on their emotional state, means for setting priorities for the proposed methods based on multiple evaluation criteria, and means for adjusting the selected methods according to the progress of the project. This makes it possible to select and implement the optimal method in project management while considering the emotional state of those involved.

[0182] "Project-related information" refers to all data and documents required for a particular project, including schedules, budgets, lists of stakeholders, and task details.

[0183] "Means of organizing collected information and converting it into a format suitable for generative machine learning algorithms" refers to the process of systematically compiling project-related information and making it available as structured data for input into machine learning algorithms.

[0184] "A method of proposing the optimal approach for each project using generative machine learning algorithms" refers to a process that automatically derives the optimal measures and strategies using AI technology based on the specific conditions and requirements of a project.

[0185] "Means for acquiring user emotional information and making suggestions based on emotional state" refers to a mechanism that measures and analyzes users' emotional reactions and states, and provides project guidelines and strategies tailored to them.

[0186] "A means of prioritizing proposed methods based on multiple evaluation criteria" refers to the process of evaluating proposed methods using various indicators of importance and impact, and listing them in order of effectiveness.

[0187] "Means for adjusting selected methods according to the project's progress" refers to a mechanism for changing and optimizing pre-selected methods according to the project's progress and external conditions.

[0188] This invention relates to a system for streamlining project management in smart cities, and the hardware includes a high-performance computer and a device that provides a user interface. Specifically, the computer (e.g., a server) collects and organizes project-related information from a database. The software used is Python and related libraries (Pandas, NumPy), which converts the data into a format suitable for generating machine learning algorithms (e.g., Azure® AI services). IBM Watson® is used for sentiment analysis.

[0189] The server inputs this formatted data into a machine learning algorithm to propose the optimal approach for each project. During this process, user sentiment information is also acquired in real time, and feedback based on the emotional state is reflected in the proposals. User sentiment information is collected through input from smartphones and tablets.

[0190] The proposed method is visually displayed to the user via their device. Users can view visualized information on project progress and emotional state on the dashboard. This allows for the selection of the most suitable method for the project and enables adjustments as the situation progresses.

[0191] As a concrete example, consider a scenario where a city official managing a traffic improvement project is experiencing stress associated with the project. In this case, the system analyzes traffic data and emotional data and executes a process to propose methods such as increasing public transport during peak hours. The prompt message used as an initial input to the system would be: "Please propose strategies to the AI ​​model to alleviate the stress currently felt by the city project manager. Specifically, we are looking for an approach that focuses on solutions to traffic congestion and reduces the burden while maintaining efficiency."

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The server collects project-related information from the database. Specifically, it extracts project schedules, budgets, task lists, and historical performance data from the database and lists them using a Python script. This prepares the collected information in a format that can be used in the next processing step.

[0195] Step 2:

[0196] The server formats the collected information and converts it into a format suitable for generative machine learning algorithms. It utilizes libraries such as Pandas and NumPy to clean the data, impute missing values, and convert it to a consistent format. The formatted data is then transformed into an appropriate structure for subsequent analysis by the AI ​​model.

[0197] Step 3:

[0198] The server inputs the formatted data into a machine learning algorithm to propose the optimal project approach. Using Azure's AI services, it analyzes patterns and trends derived from the input data to generate the most effective strategy for the project. The output is a concrete action plan for project management.

[0199] Step 4:

[0200] The device acquires and analyzes user emotional information in real time. It collects emotional data, such as user stress levels and satisfaction levels, via sensors and input devices on smartphones and tablets. The collected emotional data is analyzed using IBM Watson, and the results are fed back into the output of an AI model.

[0201] Step 5:

[0202] The device visualizes and presents project methodology proposals and sentiment analysis results to the user. Graphs and indicators showing project progress, predicted outcomes, and the user's emotional state are displayed on a specific dashboard screen. This enables users to make data-driven decisions. Adjustments that take emotional state into consideration are also suggested in parallel.

[0203] 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.

[0204] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] 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.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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".

[0219] This invention is a system that supports the selection of a flexible and efficient strategic approach in project management. The following specific processes are involved in its implementation.

[0220] First, the server automatically collects diverse data related to the project. This includes information from a database that integrates past project examples, internal company rules, PMI (Project Management Integration), and other best practices. Next, the server cleans this data and converts it into a format suitable for generative artificial intelligence models. This conversion process removes noise and redundant information and structures the data.

[0221] Next, the server utilizes a generative artificial intelligence model to generate strategic approaches suitable for each project. This AI model analyzes a wealth of data and proposes multiple possibilities. The server then prioritizes the generated approach proposals based on evaluation metrics to find the most suitable strategy.

[0222] Furthermore, the terminal functions as a means of providing information to the user, displaying the generated approach proposals as a visual dashboard. The user can then refer to this dashboard and select the approach that best suits the project's characteristics. The selected approach is tracked and adjusted in real time throughout the project's progress.

[0223] As a concrete example, let's consider a new product development project. The server uses an AI model to propose the optimal development method and marketing strategy based on past market data and competitor analysis information. The user then selects the method that best suits their current resources and goals and proceeds with the project.

[0224] Thus, this invention improves the efficiency and flexibility of project management and helps companies to quickly adapt to changing environments.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The server automatically collects project-related data, including information on past project examples, company rules, and industry best practices. The collected data is retrieved through queries from specific databases or using external APIs.

[0228] Step 2:

[0229] The server cleans the data it has collected. The cleaning process removes noise from the data and standardizes its format. For example, it removes duplicate data, fills in missing data, and eliminates irrelevant data.

[0230] Step 3:

[0231] The server then converts the cleaned data into a format suitable for the generated AI model. Here, the data is structured so that the AI ​​model can properly analyze it, and the necessary variables and metrics are included.

[0232] Step 4:

[0233] The server uses a generated AI model to create the optimal approach for each project. The model analyzes the input data and outputs multiple strategic approach options. The AI ​​model then uses the trained data and algorithms to evaluate the proposed strategies.

[0234] Step 5:

[0235] The server prioritizes the generated approach proposals. Based on evaluation metrics for each approach, such as risk, resource consumption, and expected outcomes, it creates a ranking to select the optimal approach.

[0236] Step 6:

[0237] The device displays the generated approach proposals as a visual dashboard to provide information to the user. The dashboard makes it easier for the user to understand the details, benefits, and risks of each approach.

[0238] Step 7:

[0239] The user, via their device, selects the most suitable approach from the proposed options based on the project's characteristics and the company's goals. After selection, the project proceeds based on the chosen approach.

[0240] Step 8:

[0241] The server monitors project progress in real time and adjusts the strategy as needed. It evaluates the project's health based on progress data and suggests appropriate adjustments to the approach to the user.

[0242] (Example 1)

[0243] 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."

[0244] Project management requires the efficient collection of vast amounts of information and the rapid selection of a strategic approach appropriate to the project. However, traditional systems require considerable effort and time to collect and organize information, and to present and adjust appropriate strategies, making it particularly difficult to adapt to rapidly changing market environments. Therefore, to increase project success, a system that streamlines these processes and can respond flexibly is needed.

[0245] 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.

[0246] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative artificial intelligence model, and means for using the generative artificial intelligence model to generate the optimal strategic approach for each project. This enables efficient collection and organization of information in a project, as well as the rapid and appropriate selection and adjustment of strategic approaches.

[0247] "Information" is a general term for all data and knowledge related to the project, including past cases, rules, best practices, etc.

[0248] "Organization" is the process of removing noise and standardizing the format of collected information in order to make it suitable for a specific purpose.

[0249] "Generative AI models" are a general term for artificial intelligence methods and technologies that analyze large amounts of data and provide new insights and suggestions.

[0250] A "strategic approach" refers to the specific means and methodologies that should be taken to achieve the project's objectives.

[0251] "Evaluation criteria" are indicators used as a scale when selecting a generated strategy, and include factors such as probability of success, cost-effectiveness, and risk.

[0252] "Priority" refers to the order in which multiple options or processes should be prioritized.

[0253] A "display device" refers to hardware or software used to provide information to a user visually.

[0254] "Progress status" refers to information that shows the actual progress and degree of achievement of a project against its plan.

[0255] "Risk" refers to uncertain events that could potentially affect the achievement of a project's goals.

[0256] An "information processing system" refers to a computer-based system used to process, analyze, and provide results from project data.

[0257] In order to implement this invention, multiple components constituting the entire information processing system must function in coordination.

[0258] First, the server plays the role of information gathering. The server accesses various data sources and automatically retrieves a vast amount of information related to the project. This includes retrieving data from internal databases and external data sources, and extracting necessary data using, for example, SQL queries.

[0259] Next, the server organizes the collected information and converts it into a format optimized for generative artificial intelligence models. Here, the data is formatted as a DataFrame using the Python Pandas library, and then preprocessed using the Scikit-learn preprocessing module. This removes noise and redundancy from the data, ensuring it is structured as required.

[0260] Once the data is prepared, the server utilizes a generative AI model to derive the optimal strategic approach for each project. This process uses Hugging Face's Transformers library to perform data analysis using deep learning techniques with pre-trained models and propose multiple strategies.

[0261] The generated strategies are prioritized by the server based on evaluation criteria. The selected strategies are then dynamically adjusted according to the project's progress.

[0262] The terminal functions as an interface to the user. A dedicated display device (e.g., a dashboard using Tableau or Power BI) is used to show the generated strategies to the user in a visualized form. This visualization helps to understand the information and supports efficient decision-making.

[0263] Based on the information presented, the user selects the strategy best suited to the project's characteristics and current situation. During this process, the system records the user's selection and supports subsequent project progress.

[0264] As a concrete example, in a new product development project, the server collects and analyzes past market trends and competitor information, and uses an AI model to present the optimal development and sales strategy. Based on these results, the user can select a strategy that matches their current resources and goals, and proceed with the project.

[0265] An example of a prompt is, "Please list the optimal strategic proposals for launching a new product into the market, using historical data." In this way, the invention achieves increased efficiency and speed in project management by combining advanced information processing technologies.

[0266] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0267] Step 1:

[0268] The server collects project-related information. Inputs include queries from internal corporate databases and external data sources. This retrieves data on past projects and industry best practices. The output is the collected raw dataset. Specifically, it retrieves data via an API and uses SQL queries to obtain the necessary information.

[0269] Step 2:

[0270] The server organizes the collected information and converts it into a format suitable for generative artificial intelligence models. Raw datasets are used as input, and pre-processed datasets suitable for AI models are output. Specifically, the server uses the Python Pandas library to format the dataframe, remove unnecessary data and noise, and standardize and encode the data. This results in a format that is easy to process.

[0271] Step 3:

[0272] The server analyzes pre-processed data using a generative AI model to generate the optimal strategic approach for each project. The input is a formatted dataset, and the output is multiple proposed strategies. Specifically, it uses the Hugging Face Transformers library to run a deep learning model and extract insights from the data.

[0273] Step 4:

[0274] The server analyzes the generated strategies against evaluation criteria and sets priorities. The inputs are the proposed strategies and evaluation criteria, and the output is a prioritized list of strategies. The specific operation involves statistical analysis using the Python SciPy library to calculate an evaluation score for each strategy.

[0275] Step 5:

[0276] The terminal visualizes and presents the generated strategies to the user. The input is a prioritized list of strategies, and the output is a visual dashboard displayed through the user interface. Specifically, it uses Tableau and Power BI to visualize data and present strategies in a way that is easy for the user to understand.

[0277] Step 6:

[0278] The user selects the most suitable strategy from the presented options and applies it to the project. The input is information from a visual dashboard, and the output is the selected strategy. Specifically, the user evaluates the strategies, chooses the one that best matches the project objectives and current situation, and incorporates it into the execution plan.

[0279] (Application Example 1)

[0280] 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."

[0281] In a modern production environment, it is very important to carry out project management efficiently and flexibly. However, making optimal strategic decisions based on diverse data is complex, and timely adjustments are required. In addition, in factory production projects, real-time presentation and adjustment of production strategies are demanded, and the wide variety of issues has become an obstacle.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0283] In this invention, the server includes means for collecting information related to a project, means for cleaning the collected information and converting it into a form suitable for a generated artificial intelligence model, means for using the generated artificial intelligence model to propose an optimal policy for each project, and means for the devices in the factory to present an operation strategy in real time via an information terminal. Thereby, real-time presentation and adjustment of an efficient operation strategy in a production project become possible.

[0284] A "project" is a collection of activities planned and carried out by an organization or an individual to achieve a specific goal.

[0285] "Information" is a collection of various data and knowledge related to a project and is a basis for supporting decision-making.

[0286] "Cleaning" is a process of removing noise and redundant data from the collected information and arranging it in a form suitable for analysis.

[0287] A "generated artificial intelligence model" is an algorithm or a system that learns from a large amount of data and automatically generates an optimal strategy or policy.

[0288] A "policy" indicates a specific action plan or strategy in project execution.

[0289] An "evaluation indicator" is a standard or scale used to measure the effectiveness or importance of a proposed policy.

[0290] "Equipment" refers to machines and robots installed within a factory to perform production tasks.

[0291] An "information terminal" is a digital device that allows users to visually receive and operate information.

[0292] An "operational strategy" is a set of specific actions or plans that a device or system takes to achieve a particular objective.

[0293] "Real-time" refers to processing and responding in accordance with actual time, and is a state of immediate action.

[0294] The system for implementing this invention consists of a server, an information terminal, and equipment within the factory. The server collects project-related information through IoT devices and other means, and cleans that information. The cleaned data is converted into a format suitable for a generative AI model that runs on TensorFlow using Python. This AI model generates optimal strategies based on the characteristics of the project and devises operational strategies within the factory.

[0295] The server transmits the generated policies to the information terminal in real time, and the user confirms them through the terminal's display. During this process, the user can select and apply multiple operational strategies provided by the generated AI model. This information is then reflected in the factory equipment, enabling efficient production activities.

[0296] A concrete example is the setup of a new product production line. Based on past data and market analysis, the AI ​​model calculates the optimal operation sequence for each production process, thereby improving factory efficiency. Furthermore, users can provide the AI ​​model with prompts via an information terminal, such as "We require an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," to obtain specific guidance.

[0297] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0298] Step 1:

[0299] The server collects project-related information through IoT devices within the factory. This information includes historical production data, market trends, and current equipment operating status. The collected information is stored in a database on the server.

[0300] Step 2:

[0301] The server cleans the stored information, removing noise and redundant data. This process uses a specific algorithm to format the data into a format suitable for the generated AI model. The cleaned data is then prepared for further analysis.

[0302] Step 3:

[0303] The server runs a generative AI model using TensorFlow with clean data. This model analyzes historical data and real-time situations to calculate the optimal operating strategy. The results of this analysis are output as proposed strategies to be used in the next step.

[0304] Step 4:

[0305] The server sends the generated operation strategy to the information terminal. The information terminal visually displays this and proposes it to the user. The user can compare multiple strategy plans on the terminal screen and select an appropriate strategy.

[0306] Step 5:

[0307] The user confirms the selected operation strategy and provides it to the prompt text generation AI model if necessary. For example, by giving an instruction such as "I am seeking an efficient robot strategy in the production line. Please present the optimal route from material handling to the inspection process.", more specific strategies can be derived from the model.

[0308] Step 6:

[0309] Based on the user's selection and the provided prompt text, the server issues a final operation command to the device. This command is sent to each device in the factory and is executed to achieve efficient operation in the production line.

[0310] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0311] The present invention is a system incorporating an emotion engine into the strategic approach selection process in project management. Thereby, a process of considering the user's emotional state and proposing the approach most suitable for the characteristics of the project is realized.

[0312] First, the server collects project-related data, removes noise, and cleans it into a format suitable for the AI ​​model. This data is then input into the AI ​​model, which generates optimal approach suggestions for each project. When combined with the emotion engine, the server also collects user emotion data and feeds this back into the approach suggestions output by the AI ​​model. For example, if a user is experiencing stress related to the project, the engine will suggest an approach that can alleviate that stress.

[0313] The device visually displays the results of an analysis of the user's emotional state along with the proposed approaches, making the information easy to understand. This allows the user to select an approach that is appropriate for the project's characteristics, taking their own emotional state into consideration. The emotion engine then adjusts the selected approach to optimize the user's job satisfaction and stress management.

[0314] As a concrete example, in a development project, if the server detects that a user is busy and under high stress, it will adjust task priorities and assignments based on emotional data, proposing a more efficient and less mentally taxing approach.

[0315] This invention aims to facilitate smoother corporate activities by providing a more human-centered approach that takes into account user emotions while maintaining efficiency in project management.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] The server automatically collects project-related data. This data includes past project examples, company rules, and industry best practice information. The server also uses APIs and databases to collect data from external resources.

[0319] Step 2:

[0320] The server cleans the collected data. This involves removing unnecessary information and noise and formatting the data into a standard format. The cleaning process removes duplicate data and fills in any incomplete data.

[0321] Step 3:

[0322] The server uses an emotion engine to collect user emotion data. This emotion data is obtained through user input, wearable devices, feedback forms, etc. The emotion engine includes measuring stress levels and satisfaction levels.

[0323] Step 4:

[0324] The server utilizes an AI model to generate the optimal approach for each project. Based on cleaned data and sentiment data, the AI ​​model proposes multiple strategic options. For example, it considers high-stress situations indicated by sentiment data and suggests task scheduling that reduces stress.

[0325] Step 5:

[0326] The server prioritizes the generated approach proposals based on evaluation metrics. At this stage, the benefits, risks, and impact on user emotions of each approach are considered to identify the most effective approach.

[0327] Step 6:

[0328] The device provides the user with a visual dashboard containing the results of an analysis of their emotional state, along with suggested approaches. Through this dashboard, the user can visually confirm the details of each approach and its impact on their emotions.

[0329] Step 7:

[0330] The user uses their device to select the approach that best suits their emotional state and project objectives from the proposed options. The selected approach is then incorporated into the project's progress plan.

[0331] Step 8:

[0332] The server monitors project progress in real time and continuously analyzes changes in sentiment data. If necessary, it dynamically adjusts strategies and provides feedback to users to support optimal project management.

[0333] (Example 2)

[0334] 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".

[0335] Selecting the appropriate approach is essential for improving efficiency in project management. However, existing systems only make objective judgments based on project data, making it difficult to adjust the approach while considering the emotional state of the users. As a result, user job satisfaction and stress reduction may not be sufficiently achieved, potentially leading to a decrease in overall project efficiency. This project aims to solve this problem.

[0336] 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.

[0337] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for an artificial intelligence model, means for proposing the optimal solution for each project using the artificial intelligence model, and means for collecting user sentiment information and feeding it back into the solutions generated by the artificial intelligence model. This makes it possible to adjust the approach to take into account the user's emotional state, enabling efficient and highly satisfying project management.

[0338] "Project-related information" refers to data necessary for the successful completion of a specific project, such as its progress, resources, schedule, and the roles of its members.

[0339] "Organization" refers to the process of converting data into an appropriate format and structure so that it can be effectively analyzed by artificial intelligence models.

[0340] An "artificial intelligence model" refers to machine learning algorithms and neural networks used to analyze collected information and propose the optimal approach for a project.

[0341] "Proposing countermeasures" refers to the artificial intelligence model presenting management policies and action plans for a specific project based on its analysis results.

[0342] "User emotional information" refers to data that indicates the emotional state and stress levels of individuals working on a project, and is gathered through chat tone and information from biosensors.

[0343] "Providing feedback" refers to incorporating acquired emotional information into the proposed solutions output by the artificial intelligence model and adjusting those solutions accordingly.

[0344] This invention constructs a system that combines an artificial intelligence model and an emotion data analysis engine to select effective strategies in project management. The system primarily relies on the collaboration of three parties: a server, a terminal, and a user.

[0345] The server collects project-related data from internal databases and external information sources. Data collection utilizes the Python Pandas library and leverages SQL queries. The collected data is then de-noised and converted into a format suitable for use with artificial intelligence models, such as JSON or CSV. Data processing tools like Pandas and NumPy are used for this conversion.

[0346] Next, the server inputs the collected data into a generative AI model. This model is built using frameworks such as TensorFlow or PyTorch and generates the optimal approach for a specific project based on a prompt. An example of a prompt used in this process is, "Please suggest a strategy to maximize the efficiency of the project."

[0347] The server further collects data from wearable devices and communication tools to obtain user emotional information. This emotional data includes the user's heart rate, chat content, and tone. Natural language processing tools such as NLTK and emotion analysis APIs are used for analysis. This data is fed back into the project's approach, which is then adjusted to reduce user stress.

[0348] The terminal visually displays the proposed approaches and emotional information analysis results received from the server. To achieve this, a dashboard is created using D3.js and Chart.js. Based on this information, users can select the most suitable approach, taking into account their own emotional state and the characteristics of the project. Specifically, it serves as a reference for users when readjusting task allocation or changing schedules.

[0349] This system aims to provide a human-centered strategic approach tailored to the characteristics of each project, thereby improving the efficiency of project management and maximizing user job satisfaction.

[0350] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0351] Step 1:

[0352] The server retrieves project-related information from internal databases and external information sources. Inputs include project progress, resource utilization, and task assignments. This information is imported as a dataframe using the Python Pandas library. The output is a dataset with unnecessary noise removed. Specifically, it extracts information from the database using SQL queries and imputes or removes missing values.

[0353] Step 2:

[0354] The server converts the collected data into a format that is easily analyzable by the generating AI model. The conversion targets the data format and structure. The input is the dataset cleaned in step 1. It is converted to CSV or JSON format using Pandas or NumPy. This data is processed into a shape suitable for the model, and the output is data in an analyzable format. Specifically, categorical data is encoded into numerical data, and data normalization is performed as needed.

[0355] Step 3:

[0356] The server uses the transformed data to input into a generating AI model and generate the optimal solution for the project. The prompt "Propose a strategy to maximize project efficiency" is used as input. The model is built with TensorFlow and PyTorch and outputs project-specific analysis results. Specifically, it calls the model, performs inference processing, and outputs the resulting artifacts (a series of proposed approaches).

[0357] Step 4:

[0358] The server collects user emotional information from wearable devices and communication tools. Input data includes heart rate, chat content, and tone of voice. The server analyzes this data using the natural language processing library NLTK and an emotion analysis API to quantify the user's emotional state. The output provides the user's stress level and emotional tone score. Specifically, the server periodically polls data from devices and tools to update the analysis results.

[0359] Step 5:

[0360] The server optimizes the proposed approaches generated using emotional data. Inputs include the proposed approaches generated in step 3 and the user's emotional score obtained in step 4. A feedback loop is constructed to prioritize approaches that reduce stress. The output is an optimized approach adapted to the user's emotions. Specifically, the server adjusts task priorities and assignments based on the user's emotional state.

[0361] Step 6:

[0362] The terminal visually displays the ultimately selected approach and the user's emotional state. It uses approach data and emotional analysis results from the server as input. Data is received via GraphQL or REST API, and a dashboard is created using D3.js or Chart.js. The output provides a graphical interface to facilitate user decision-making while considering their emotional state. Specific actions include providing intuitive displays and interactions using bar graphs and icons.

[0363] (Application Example 2)

[0364] 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."

[0365] Modern project management often prioritizes efficiency while neglecting the emotional aspects of stakeholders. This can lead to increased emotional stress during project execution, negatively impacting the quality and progress of deliverables. Furthermore, it can decrease the motivation of those involved in the project, posing a risk to overall work efficiency.

[0366] 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.

[0367] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative machine learning algorithm, means for proposing the optimal method for each project using a generative machine learning algorithm, means for acquiring user emotional information and making suggestions based on their emotional state, means for setting priorities for the proposed methods based on multiple evaluation criteria, and means for adjusting the selected methods according to the progress of the project. This makes it possible to select and implement the optimal method in project management while considering the emotional state of those involved.

[0368] "Project-related information" refers to all data and documents required for a particular project, including schedules, budgets, lists of stakeholders, and task details.

[0369] "Means of organizing collected information and converting it into a format suitable for generative machine learning algorithms" refers to the process of systematically compiling project-related information and making it available as structured data for input into machine learning algorithms.

[0370] "A method of proposing the optimal approach for each project using generative machine learning algorithms" refers to a process that automatically derives the optimal measures and strategies using AI technology based on the specific conditions and requirements of a project.

[0371] "Means for acquiring user emotional information and making suggestions based on emotional state" refers to a mechanism that measures and analyzes users' emotional reactions and states, and provides project guidelines and strategies tailored to them.

[0372] "A means of prioritizing proposed methods based on multiple evaluation criteria" refers to the process of evaluating proposed methods using various indicators of importance and impact, and listing them in order of effectiveness.

[0373] "Means for adjusting selected methods according to the project's progress" refers to a mechanism for changing and optimizing pre-selected methods according to the project's progress and external conditions.

[0374] This invention relates to a system for streamlining project management in smart cities, and its hardware includes a high-performance computer and a device that provides a user interface. Specifically, the computer (e.g., a server) collects and organizes project-related information from a database. The software used is Python and related libraries (Pandas, NumPy), which converts the data into a format suitable for generating machine learning algorithms (e.g., Azure's AI service). IBM Watson is used for sentiment analysis.

[0375] The server inputs this formatted data into a machine learning algorithm to propose the optimal approach for each project. During this process, user sentiment information is also acquired in real time, and feedback based on the emotional state is reflected in the proposals. User sentiment information is collected through input from smartphones and tablets.

[0376] The proposed method is visually displayed to the user via their device. Users can view visualized information on project progress and emotional state on the dashboard. This allows for the selection of the most suitable method for the project and enables adjustments as the situation progresses.

[0377] As a concrete example, consider a scenario where a city official managing a traffic improvement project is experiencing stress associated with the project. In this case, the system analyzes traffic data and emotional data and executes a process to propose methods such as increasing public transport during peak hours. The prompt message used as an initial input to the system would be: "Please propose strategies to the AI ​​model to alleviate the stress currently felt by the city project manager. Specifically, we are looking for an approach that focuses on solutions to traffic congestion and reduces the burden while maintaining efficiency."

[0378] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0379] Step 1:

[0380] The server collects project-related information from the database. Specifically, it extracts project schedules, budgets, task lists, and historical performance data from the database and lists them using a Python script. This prepares the collected information in a format that can be used in the next processing step.

[0381] Step 2:

[0382] The server formats the collected information and converts it into a format suitable for generative machine learning algorithms. It utilizes libraries such as Pandas and NumPy to clean the data, impute missing values, and convert it to a consistent format. The formatted data is then transformed into an appropriate structure for subsequent analysis by the AI ​​model.

[0383] Step 3:

[0384] The server inputs the formatted data into a machine learning algorithm to propose the optimal project approach. Using Azure's AI services, it analyzes patterns and trends derived from the input data to generate the most effective strategy for the project. The output is a concrete action plan for project management.

[0385] Step 4:

[0386] The device acquires and analyzes user emotional information in real time. It collects emotional data, such as user stress levels and satisfaction levels, via sensors and input devices on smartphones and tablets. The collected emotional data is analyzed using IBM Watson, and the results are fed back into the output of an AI model.

[0387] Step 5:

[0388] The device visualizes and presents project methodology proposals and sentiment analysis results to the user. Graphs and indicators showing project progress, predicted outcomes, and the user's emotional state are displayed on a specific dashboard screen. This enables users to make data-driven decisions. Adjustments that take emotional state into consideration are also suggested in parallel.

[0389] 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.

[0390] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0391] 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.

[0392] [Third Embodiment]

[0393] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0394] 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.

[0395] 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).

[0396] 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.

[0397] 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.

[0398] 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).

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] 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".

[0405] This invention is a system that supports the selection of a flexible and efficient strategic approach in project management. The following specific processes are involved in its implementation.

[0406] First, the server automatically collects diverse data related to the project. This includes information from a database that integrates past project examples, internal company rules, PMI (Project Management Integration), and other best practices. Next, the server cleans this data and converts it into a format suitable for generative artificial intelligence models. This conversion process removes noise and redundant information and structures the data.

[0407] Next, the server utilizes a generative artificial intelligence model to generate strategic approaches suitable for each project. This AI model analyzes a wealth of data and proposes multiple possibilities. The server then prioritizes the generated approach proposals based on evaluation metrics to find the most suitable strategy.

[0408] Furthermore, the terminal functions as a means of providing information to the user, displaying the generated approach proposals as a visual dashboard. The user can then refer to this dashboard and select the approach that best suits the project's characteristics. The selected approach is tracked and adjusted in real time throughout the project's progress.

[0409] As a concrete example, let's consider a new product development project. The server uses an AI model to propose the optimal development method and marketing strategy based on past market data and competitor analysis information. The user then selects the method that best suits their current resources and goals and proceeds with the project.

[0410] Thus, this invention improves the efficiency and flexibility of project management and helps companies to quickly adapt to changing environments.

[0411] The following describes the processing flow.

[0412] Step 1:

[0413] The server automatically collects project-related data, including information on past project examples, company rules, and industry best practices. The collected data is retrieved through queries from specific databases or using external APIs.

[0414] Step 2:

[0415] The server cleans the data it has collected. The cleaning process removes noise from the data and standardizes its format. For example, it removes duplicate data, fills in missing data, and eliminates irrelevant data.

[0416] Step 3:

[0417] The server then converts the cleaned data into a format suitable for the generated AI model. Here, the data is structured so that the AI ​​model can properly analyze it, and the necessary variables and metrics are included.

[0418] Step 4:

[0419] The server uses a generated AI model to create the optimal approach for each project. The model analyzes the input data and outputs multiple strategic approach options. The AI ​​model then uses the trained data and algorithms to evaluate the proposed strategies.

[0420] Step 5:

[0421] The server prioritizes the generated approach proposals. Based on evaluation metrics for each approach, such as risk, resource consumption, and expected outcomes, it creates a ranking to select the optimal approach.

[0422] Step 6:

[0423] The device displays the generated approach proposals as a visual dashboard to provide information to the user. The dashboard makes it easier for the user to understand the details, benefits, and risks of each approach.

[0424] Step 7:

[0425] The user, via their device, selects the most suitable approach from the proposed options based on the project's characteristics and the company's goals. After selection, the project proceeds based on the chosen approach.

[0426] Step 8:

[0427] The server monitors project progress in real time and adjusts the strategy as needed. It evaluates the project's health based on progress data and suggests appropriate adjustments to the approach to the user.

[0428] (Example 1)

[0429] 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."

[0430] Project management requires the efficient collection of vast amounts of information and the rapid selection of a strategic approach appropriate to the project. However, traditional systems require considerable effort and time to collect and organize information, and to present and adjust appropriate strategies, making it particularly difficult to adapt to rapidly changing market environments. Therefore, to increase project success, a system that streamlines these processes and can respond flexibly is needed.

[0431] 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.

[0432] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative artificial intelligence model, and means for using the generative artificial intelligence model to generate the optimal strategic approach for each project. This enables efficient collection and organization of information in a project, as well as the rapid and appropriate selection and adjustment of strategic approaches.

[0433] "Information" is a general term for all data and knowledge related to the project, including past cases, rules, best practices, etc.

[0434] "Organization" is the process of removing noise and standardizing the format of collected information in order to make it suitable for a specific purpose.

[0435] "Generative AI models" are a general term for artificial intelligence methods and technologies that analyze large amounts of data and provide new insights and suggestions.

[0436] A "strategic approach" refers to the specific means and methodologies that should be taken to achieve the project's objectives.

[0437] "Evaluation criteria" are indicators used as a scale when selecting a generated strategy, and include factors such as probability of success, cost-effectiveness, and risk.

[0438] "Priority" refers to the order in which multiple options or processes should be prioritized.

[0439] A "display device" refers to hardware or software used to provide information to a user visually.

[0440] "Progress status" refers to information that shows the actual progress and degree of achievement of a project against its plan.

[0441] "Risk" refers to uncertain events that could potentially affect the achievement of a project's goals.

[0442] An "information processing system" refers to a computer-based system used to process, analyze, and provide results from project data.

[0443] In order to implement this invention, multiple components constituting the entire information processing system must function in coordination.

[0444] First, the server plays the role of information gathering. The server accesses various data sources and automatically retrieves a vast amount of information related to the project. This includes retrieving data from internal databases and external data sources, and extracting necessary data using, for example, SQL queries.

[0445] Next, the server organizes the collected information and converts it into a format optimized for generative artificial intelligence models. Here, the data is formatted as a DataFrame using the Python Pandas library, and then preprocessed using the Scikit-learn preprocessing module. This removes noise and redundancy from the data, ensuring it is structured as required.

[0446] Once the data is prepared, the server utilizes a generative AI model to derive the optimal strategic approach for each project. This process uses Hugging Face's Transformers library to perform data analysis using deep learning techniques with pre-trained models and propose multiple strategies.

[0447] The generated strategies are prioritized by the server based on evaluation criteria. The selected strategies are then dynamically adjusted according to the project's progress.

[0448] The terminal functions as an interface to the user. A dedicated display device (e.g., a dashboard using Tableau or Power BI) is used to show the generated strategies to the user in a visualized form. This visualization helps to understand the information and supports efficient decision-making.

[0449] Based on the information presented, the user selects the strategy best suited to the project's characteristics and current situation. During this process, the system records the user's selection and supports subsequent project progress.

[0450] As a concrete example, in a new product development project, the server collects and analyzes past market trends and competitor information, and uses an AI model to present the optimal development and sales strategy. Based on these results, the user can select a strategy that matches their current resources and goals, and proceed with the project.

[0451] An example of a prompt is, "Please list the optimal strategic proposals for launching a new product into the market, using historical data." In this way, the invention achieves increased efficiency and speed in project management by combining advanced information processing technologies.

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] The server collects project-related information. Inputs include queries from internal corporate databases and external data sources. This retrieves data on past projects and industry best practices. The output is the collected raw dataset. Specifically, it retrieves data via an API and uses SQL queries to obtain the necessary information.

[0455] Step 2:

[0456] The server organizes the collected information and converts it into a format suitable for generative artificial intelligence models. Raw datasets are used as input, and pre-processed datasets suitable for AI models are output. Specifically, the server uses the Python Pandas library to format the dataframe, remove unnecessary data and noise, and standardize and encode the data. This results in a format that is easy to process.

[0457] Step 3:

[0458] The server analyzes pre-processed data using a generative AI model to generate the optimal strategic approach for each project. The input is a formatted dataset, and the output is multiple proposed strategies. Specifically, it uses the Hugging Face Transformers library to run a deep learning model and extract insights from the data.

[0459] Step 4:

[0460] The server analyzes the generated strategies against evaluation criteria and sets priorities. The inputs are the proposed strategies and evaluation criteria, and the output is a prioritized list of strategies. The specific operation involves statistical analysis using the Python SciPy library to calculate an evaluation score for each strategy.

[0461] Step 5:

[0462] The terminal visualizes and presents the generated strategies to the user. The input is a prioritized list of strategies, and the output is a visual dashboard displayed through the user interface. Specifically, it uses Tableau and Power BI to visualize data and present strategies in a way that is easy for the user to understand.

[0463] Step 6:

[0464] The user selects the most suitable strategy from the presented options and applies it to the project. The input is information from a visual dashboard, and the output is the selected strategy. Specifically, the user evaluates the strategies, chooses the one that best matches the project objectives and current situation, and incorporates it into the execution plan.

[0465] (Application Example 1)

[0466] 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."

[0467] In today's production environment, efficient and flexible project management is crucial. However, determining the optimal strategy based on diverse data is complex and requires timely adjustments. In addition, factory production projects require the presentation and adjustment of production strategies in real time, and the wide range of challenges presents obstacles.

[0468] 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.

[0469] In this invention, the server includes means for collecting project-related information, means for cleaning the collected information and converting it into a format suitable for a generative artificial intelligence model, means for proposing the optimal strategy for each project using the generative artificial intelligence model, and means for factory equipment to present operational strategies in real time via information terminals. This enables efficient real-time presentation and adjustment of operational strategies in production projects.

[0470] A "project" is a collection of activities that an organization or individual systematically undertakes to achieve a specific objective.

[0471] "Information" refers to a collection of various data and knowledge related to a project, and serves as a foundation for supporting decision-making.

[0472] "Cleaning" is the process of removing noise and redundant data from collected information and preparing it in a format suitable for analysis.

[0473] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and automatically generates optimal strategies and policies.

[0474] A "policy" refers to a specific action plan or strategy for carrying out a project.

[0475] An "evaluation indicator" is a standard or scale used to measure the effectiveness or importance of a proposed policy.

[0476] "Equipment" refers to machines and robots installed within a factory to perform production tasks.

[0477] An "information terminal" is a digital device that allows users to visually receive and operate information.

[0478] An "operational strategy" is a set of specific actions or plans that a device or system takes to achieve a particular objective.

[0479] "Real-time" refers to processing and responding in accordance with actual time, and is a state of immediate action.

[0480] The system for implementing this invention consists of a server, an information terminal, and equipment within the factory. The server collects project-related information through IoT devices and other means, and cleans that information. The cleaned data is converted into a format suitable for a generative AI model that runs on TensorFlow using Python. This AI model generates optimal strategies based on the characteristics of the project and devises operational strategies within the factory.

[0481] The server transmits the generated policies to the information terminal in real time, and the user confirms them through the terminal's display. During this process, the user can select and apply multiple operational strategies provided by the generated AI model. This information is then reflected in the factory equipment, enabling efficient production activities.

[0482] A concrete example is the setup of a new product production line. Based on past data and market analysis, the AI ​​model calculates the optimal operation sequence for each production process, thereby improving factory efficiency. Furthermore, users can provide the AI ​​model with prompts via an information terminal, such as "We require an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," to obtain specific guidance.

[0483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0484] Step 1:

[0485] The server collects project-related information through IoT devices within the factory. This information includes historical production data, market trends, and current equipment operating status. The collected information is stored in a database on the server.

[0486] Step 2:

[0487] The server cleans the stored information, removing noise and redundant data. This process uses a specific algorithm to format the data into a format suitable for the generated AI model. The cleaned data is then prepared for further analysis.

[0488] Step 3:

[0489] The server runs a generative AI model using TensorFlow with clean data. This model analyzes historical data and real-time situations to calculate the optimal operating strategy. The results of this analysis are output as proposed strategies to be used in the next step.

[0490] Step 4:

[0491] The server transmits the generated operational strategy to the information terminal. The information terminal displays this visually and proposes it to the user. The user can compare multiple strategy options on the terminal screen and select the appropriate strategy.

[0492] Step 5:

[0493] The user reviews the selected operational strategy and provides prompts to the generating AI model as needed. For example, by giving instructions such as, "I need an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," the model can derive a more specific strategy.

[0494] Step 6:

[0495] The server issues final operational commands to the equipment based on the user's selection and provided prompts. These commands are transmitted to each piece of equipment in the factory and executed to ensure efficient operation of the production line.

[0496] 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.

[0497] This invention is a system that incorporates an emotion engine into the strategic approach selection process in project management. This enables a process that considers the user's emotional state and proposes the most suitable approach for the project's characteristics.

[0498] First, the server collects project-related data, removes noise, and cleans it into a format suitable for the AI ​​model. This data is then input into the AI ​​model, which generates optimal approach suggestions for each project. When combined with the emotion engine, the server also collects user emotion data and feeds this back into the approach suggestions output by the AI ​​model. For example, if a user is experiencing stress related to the project, the engine will suggest an approach that can alleviate that stress.

[0499] The device visually displays the results of an analysis of the user's emotional state along with the proposed approaches, making the information easy to understand. This allows the user to select an approach that is appropriate for the project's characteristics, taking their own emotional state into consideration. The emotion engine then adjusts the selected approach to optimize the user's job satisfaction and stress management.

[0500] As a concrete example, in a development project, if the server detects that a user is busy and under high stress, it will adjust task priorities and assignments based on emotional data, proposing a more efficient and less mentally taxing approach.

[0501] This invention aims to facilitate smoother corporate activities by providing a more human-centered approach that takes into account user emotions while maintaining efficiency in project management.

[0502] The following describes the processing flow.

[0503] Step 1:

[0504] The server automatically collects project-related data. This data includes past project examples, company rules, and industry best practice information. The server also uses APIs and databases to collect data from external resources.

[0505] Step 2:

[0506] The server cleans the collected data. This involves removing unnecessary information and noise and formatting the data into a standard format. The cleaning process removes duplicate data and fills in any incomplete data.

[0507] Step 3:

[0508] The server uses an emotion engine to collect user emotion data. This emotion data is obtained through user input, wearable devices, feedback forms, etc. The emotion engine includes measuring stress levels and satisfaction levels.

[0509] Step 4:

[0510] The server utilizes an AI model to generate the optimal approach for each project. Based on cleaned data and sentiment data, the AI ​​model proposes multiple strategic options. For example, it considers high-stress situations indicated by sentiment data and suggests task scheduling that reduces stress.

[0511] Step 5:

[0512] The server prioritizes the generated approach proposals based on evaluation metrics. At this stage, the benefits, risks, and impact on user emotions of each approach are considered to identify the most effective approach.

[0513] Step 6:

[0514] The device provides the user with a visual dashboard containing the results of an analysis of their emotional state, along with suggested approaches. Through this dashboard, the user can visually confirm the details of each approach and its impact on their emotions.

[0515] Step 7:

[0516] The user uses their device to select the approach that best suits their emotional state and project objectives from the proposed options. The selected approach is then incorporated into the project's progress plan.

[0517] Step 8:

[0518] The server monitors project progress in real time and continuously analyzes changes in sentiment data. If necessary, it dynamically adjusts strategies and provides feedback to users to support optimal project management.

[0519] (Example 2)

[0520] 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."

[0521] Selecting the appropriate approach is essential for improving efficiency in project management. However, existing systems only make objective judgments based on project data, making it difficult to adjust the approach while considering the emotional state of the users. As a result, user job satisfaction and stress reduction may not be sufficiently achieved, potentially leading to a decrease in overall project efficiency. This project aims to solve this problem.

[0522] 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.

[0523] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for an artificial intelligence model, means for proposing the optimal solution for each project using the artificial intelligence model, and means for collecting user sentiment information and feeding it back into the solutions generated by the artificial intelligence model. This makes it possible to adjust the approach to take into account the user's emotional state, enabling efficient and highly satisfying project management.

[0524] "Project-related information" refers to data necessary for the successful completion of a specific project, such as its progress, resources, schedule, and the roles of its members.

[0525] "Organization" refers to the process of converting data into an appropriate format and structure so that it can be effectively analyzed by artificial intelligence models.

[0526] An "artificial intelligence model" refers to machine learning algorithms and neural networks used to analyze collected information and propose the optimal approach for a project.

[0527] "Proposing countermeasures" refers to the artificial intelligence model presenting management policies and action plans for a specific project based on its analysis results.

[0528] "User emotional information" refers to data that indicates the emotional state and stress levels of individuals working on a project, and is gathered through chat tone and information from biosensors.

[0529] "Providing feedback" refers to incorporating acquired emotional information into the proposed solutions output by the artificial intelligence model and adjusting those solutions accordingly.

[0530] This invention constructs a system that combines an artificial intelligence model and an emotion data analysis engine to select effective strategies in project management. The system primarily relies on the collaboration of three parties: a server, a terminal, and a user.

[0531] The server collects project-related data from internal databases and external information sources. Data collection utilizes the Python Pandas library and leverages SQL queries. The collected data is then de-noised and converted into a format suitable for use with artificial intelligence models, such as JSON or CSV. Data processing tools like Pandas and NumPy are used for this conversion.

[0532] Next, the server inputs the collected data into a generative AI model. This model is built using frameworks such as TensorFlow or PyTorch and generates the optimal approach for a specific project based on a prompt. An example of a prompt used in this process is, "Please suggest a strategy to maximize the efficiency of the project."

[0533] The server further collects data from wearable devices and communication tools to obtain user emotional information. This emotional data includes the user's heart rate, chat content, and tone. Natural language processing tools such as NLTK and emotion analysis APIs are used for analysis. This data is fed back into the project's approach, which is then adjusted to reduce user stress.

[0534] The terminal visually displays the proposed approaches and emotional information analysis results received from the server. To achieve this, a dashboard is created using D3.js and Chart.js. Based on this information, users can select the most suitable approach, taking into account their own emotional state and the characteristics of the project. Specifically, it serves as a reference for users when readjusting task allocation or changing schedules.

[0535] This system aims to provide a human-centered strategic approach tailored to the characteristics of each project, thereby improving the efficiency of project management and maximizing user job satisfaction.

[0536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0537] Step 1:

[0538] The server retrieves project-related information from internal databases and external information sources. Inputs include project progress, resource utilization, and task assignments. This information is imported as a dataframe using the Python Pandas library. The output is a dataset with unnecessary noise removed. Specifically, it extracts information from the database using SQL queries and imputes or removes missing values.

[0539] Step 2:

[0540] The server converts the collected data into a format that is easily analyzable by the generating AI model. The conversion targets the data format and structure. The input is the dataset cleaned in step 1. It is converted to CSV or JSON format using Pandas or NumPy. This data is processed into a shape suitable for the model, and the output is data in an analyzable format. Specifically, categorical data is encoded into numerical data, and data normalization is performed as needed.

[0541] Step 3:

[0542] The server uses the transformed data to input into a generating AI model and generate the optimal solution for the project. The prompt "Propose a strategy to maximize project efficiency" is used as input. The model is built with TensorFlow and PyTorch and outputs project-specific analysis results. Specifically, it calls the model, performs inference processing, and outputs the resulting artifacts (a series of proposed approaches).

[0543] Step 4:

[0544] The server collects user emotional information from wearable devices and communication tools. Input data includes heart rate, chat content, and tone of voice. The server analyzes this data using the natural language processing library NLTK and an emotion analysis API to quantify the user's emotional state. The output provides the user's stress level and emotional tone score. Specifically, the server periodically polls data from devices and tools to update the analysis results.

[0545] Step 5:

[0546] The server optimizes the proposed approaches generated using emotional data. Inputs include the proposed approaches generated in step 3 and the user's emotional score obtained in step 4. A feedback loop is constructed to prioritize approaches that reduce stress. The output is an optimized approach adapted to the user's emotions. Specifically, the server adjusts task priorities and assignments based on the user's emotional state.

[0547] Step 6:

[0548] The terminal visually displays the ultimately selected approach and the user's emotional state. It uses approach data and emotional analysis results from the server as input. Data is received via GraphQL or REST API, and a dashboard is created using D3.js or Chart.js. The output provides a graphical interface to facilitate user decision-making while considering their emotional state. Specific actions include providing intuitive displays and interactions using bar graphs and icons.

[0549] (Application Example 2)

[0550] 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."

[0551] Modern project management often prioritizes efficiency while neglecting the emotional aspects of stakeholders. This can lead to increased emotional stress during project execution, negatively impacting the quality and progress of deliverables. Furthermore, it can decrease the motivation of those involved in the project, posing a risk to overall work efficiency.

[0552] 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.

[0553] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative machine learning algorithm, means for proposing the optimal method for each project using a generative machine learning algorithm, means for acquiring user emotional information and making suggestions based on their emotional state, means for setting priorities for the proposed methods based on multiple evaluation criteria, and means for adjusting the selected methods according to the progress of the project. This makes it possible to select and implement the optimal method in project management while considering the emotional state of those involved.

[0554] "Project-related information" refers to all data and documents required for a particular project, including schedules, budgets, lists of stakeholders, and task details.

[0555] "Means of organizing collected information and converting it into a format suitable for generative machine learning algorithms" refers to the process of systematically compiling project-related information and making it available as structured data for input into machine learning algorithms.

[0556] "A method of proposing the optimal approach for each project using generative machine learning algorithms" refers to a process that automatically derives the optimal measures and strategies using AI technology based on the specific conditions and requirements of a project.

[0557] "Means for acquiring user emotional information and making suggestions based on emotional state" refers to a mechanism that measures and analyzes users' emotional reactions and states, and provides project guidelines and strategies tailored to them.

[0558] "A means of prioritizing proposed methods based on multiple evaluation criteria" refers to the process of evaluating proposed methods using various indicators of importance and impact, and listing them in order of effectiveness.

[0559] "Means for adjusting selected methods according to the project's progress" refers to a mechanism for changing and optimizing pre-selected methods according to the project's progress and external conditions.

[0560] This invention relates to a system for streamlining project management in smart cities, and its hardware includes a high-performance computer and a device that provides a user interface. Specifically, the computer (e.g., a server) collects and organizes project-related information from a database. The software used is Python and related libraries (Pandas, NumPy), which converts the data into a format suitable for generating machine learning algorithms (e.g., Azure's AI service). IBM Watson is used for sentiment analysis.

[0561] The server inputs this formatted data into a machine learning algorithm to propose the optimal approach for each project. During this process, user sentiment information is also acquired in real time, and feedback based on the emotional state is reflected in the proposals. User sentiment information is collected through input from smartphones and tablets.

[0562] The proposed method is visually displayed to the user via their device. Users can view visualized information on project progress and emotional state on the dashboard. This allows for the selection of the most suitable method for the project and enables adjustments as the situation progresses.

[0563] As a concrete example, consider a scenario where a city official managing a traffic improvement project is experiencing stress associated with the project. In this case, the system analyzes traffic data and emotional data and executes a process to propose methods such as increasing public transport during peak hours. The prompt message used as an initial input to the system would be: "Please propose strategies to the AI ​​model to alleviate the stress currently felt by the city project manager. Specifically, we are looking for an approach that focuses on solutions to traffic congestion and reduces the burden while maintaining efficiency."

[0564] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0565] Step 1:

[0566] The server collects project-related information from the database. Specifically, it extracts project schedules, budgets, task lists, and historical performance data from the database and lists them using a Python script. This prepares the collected information in a format that can be used in the next processing step.

[0567] Step 2:

[0568] The server formats the collected information and converts it into a format suitable for generative machine learning algorithms. It utilizes libraries such as Pandas and NumPy to clean the data, impute missing values, and convert it to a consistent format. The formatted data is then transformed into an appropriate structure for subsequent analysis by the AI ​​model.

[0569] Step 3:

[0570] The server inputs the formatted data into a machine learning algorithm to propose the optimal project approach. Using Azure's AI services, it analyzes patterns and trends derived from the input data to generate the most effective strategy for the project. The output is a concrete action plan for project management.

[0571] Step 4:

[0572] The device acquires and analyzes user emotional information in real time. It collects emotional data, such as user stress levels and satisfaction levels, via sensors and input devices on smartphones and tablets. The collected emotional data is analyzed using IBM Watson, and the results are fed back into the output of an AI model.

[0573] Step 5:

[0574] The device visualizes and presents project methodology proposals and sentiment analysis results to the user. Graphs and indicators showing project progress, predicted outcomes, and the user's emotional state are displayed on a specific dashboard screen. This enables users to make data-driven decisions. Adjustments that take emotional state into consideration are also suggested in parallel.

[0575] 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.

[0576] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0577] 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.

[0578] [Fourth Embodiment]

[0579] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0580] 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.

[0581] 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).

[0582] 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.

[0583] 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.

[0584] 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).

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] 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.

[0591] 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".

[0592] This invention is a system that supports the selection of a flexible and efficient strategic approach in project management. The following specific processes are involved in its implementation.

[0593] First, the server automatically collects diverse data related to the project. This includes information from a database that integrates past project examples, internal company rules, PMI (Project Management Integration), and other best practices. Next, the server cleans this data and converts it into a format suitable for generative artificial intelligence models. This conversion process removes noise and redundant information and structures the data.

[0594] Next, the server utilizes a generative artificial intelligence model to generate strategic approaches suitable for each project. This AI model analyzes a wealth of data and proposes multiple possibilities. The server then prioritizes the generated approach proposals based on evaluation metrics to find the most suitable strategy.

[0595] Furthermore, the terminal functions as a means of providing information to the user, displaying the generated approach proposals as a visual dashboard. The user can then refer to this dashboard and select the approach that best suits the project's characteristics. The selected approach is tracked and adjusted in real time throughout the project's progress.

[0596] As a concrete example, let's consider a new product development project. The server uses an AI model to propose the optimal development method and marketing strategy based on past market data and competitor analysis information. The user then selects the method that best suits their current resources and goals and proceeds with the project.

[0597] Thus, this invention improves the efficiency and flexibility of project management and helps companies to quickly adapt to changing environments.

[0598] The following describes the processing flow.

[0599] Step 1:

[0600] The server automatically collects project-related data, including information on past project examples, company rules, and industry best practices. The collected data is retrieved through queries from specific databases or using external APIs.

[0601] Step 2:

[0602] The server cleans the data it has collected. The cleaning process removes noise from the data and standardizes its format. For example, it removes duplicate data, fills in missing data, and eliminates irrelevant data.

[0603] Step 3:

[0604] The server then converts the cleaned data into a format suitable for the generated AI model. Here, the data is structured so that the AI ​​model can properly analyze it, and the necessary variables and metrics are included.

[0605] Step 4:

[0606] The server uses a generated AI model to create the optimal approach for each project. The model analyzes the input data and outputs multiple strategic approach options. The AI ​​model then uses the trained data and algorithms to evaluate the proposed strategies.

[0607] Step 5:

[0608] The server prioritizes the generated approach proposals. Based on evaluation metrics for each approach, such as risk, resource consumption, and expected outcomes, it creates a ranking to select the optimal approach.

[0609] Step 6:

[0610] The device displays the generated approach proposals as a visual dashboard to provide information to the user. The dashboard makes it easier for the user to understand the details, benefits, and risks of each approach.

[0611] Step 7:

[0612] The user, via their device, selects the most suitable approach from the proposed options based on the project's characteristics and the company's goals. After selection, the project proceeds based on the chosen approach.

[0613] Step 8:

[0614] The server monitors project progress in real time and adjusts the strategy as needed. It evaluates the project's health based on progress data and suggests appropriate adjustments to the approach to the user.

[0615] (Example 1)

[0616] 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".

[0617] Project management requires the efficient collection of vast amounts of information and the rapid selection of a strategic approach appropriate to the project. However, traditional systems require considerable effort and time to collect and organize information, and to present and adjust appropriate strategies, making it particularly difficult to adapt to rapidly changing market environments. Therefore, to increase project success, a system that streamlines these processes and can respond flexibly is needed.

[0618] 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.

[0619] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative artificial intelligence model, and means for using the generative artificial intelligence model to generate the optimal strategic approach for each project. This enables efficient collection and organization of information in a project, as well as the rapid and appropriate selection and adjustment of strategic approaches.

[0620] "Information" is a general term for all data and knowledge related to the project, including past cases, rules, best practices, etc.

[0621] "Organization" is the process of removing noise and standardizing the format of collected information in order to make it suitable for a specific purpose.

[0622] "Generative AI models" are a general term for artificial intelligence methods and technologies that analyze large amounts of data and provide new insights and suggestions.

[0623] A "strategic approach" refers to the specific means and methodologies that should be taken to achieve the project's objectives.

[0624] "Evaluation criteria" are indicators used as a scale when selecting a generated strategy, and include factors such as probability of success, cost-effectiveness, and risk.

[0625] "Priority" refers to the order in which multiple options or processes should be prioritized.

[0626] A "display device" refers to hardware or software used to provide information to a user visually.

[0627] "Progress status" refers to information that shows the actual progress and degree of achievement of a project against its plan.

[0628] "Risk" refers to uncertain events that could potentially affect the achievement of a project's goals.

[0629] An "information processing system" refers to a computer-based system used to process, analyze, and provide results from project data.

[0630] In order to implement this invention, multiple components constituting the entire information processing system must function in coordination.

[0631] First, the server plays the role of information gathering. The server accesses various data sources and automatically retrieves a vast amount of information related to the project. This includes retrieving data from internal databases and external data sources, and extracting necessary data using, for example, SQL queries.

[0632] Next, the server organizes the collected information and converts it into a format optimized for generative artificial intelligence models. Here, the data is formatted as a DataFrame using the Python Pandas library, and then preprocessed using the Scikit-learn preprocessing module. This removes noise and redundancy from the data, ensuring it is structured as required.

[0633] Once the data is prepared, the server utilizes a generative AI model to derive the optimal strategic approach for each project. This process uses Hugging Face's Transformers library to perform data analysis using deep learning techniques with pre-trained models and propose multiple strategies.

[0634] The generated strategies are prioritized by the server based on evaluation criteria. The selected strategies are then dynamically adjusted according to the project's progress.

[0635] The terminal functions as an interface to the user. A dedicated display device (e.g., a dashboard using Tableau or Power BI) is used to show the generated strategies to the user in a visualized form. This visualization helps to understand the information and supports efficient decision-making.

[0636] Based on the information presented, the user selects the strategy best suited to the project's characteristics and current situation. During this process, the system records the user's selection and supports subsequent project progress.

[0637] As a concrete example, in a new product development project, the server collects and analyzes past market trends and competitor information, and uses an AI model to present the optimal development and sales strategy. Based on these results, the user can select a strategy that matches their current resources and goals, and proceed with the project.

[0638] An example of a prompt is, "Please list the optimal strategic proposals for launching a new product into the market, using historical data." In this way, the invention achieves increased efficiency and speed in project management by combining advanced information processing technologies.

[0639] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0640] Step 1:

[0641] The server collects project-related information. Inputs include queries from internal corporate databases and external data sources. This retrieves data on past projects and industry best practices. The output is the collected raw dataset. Specifically, it retrieves data via an API and uses SQL queries to obtain the necessary information.

[0642] Step 2:

[0643] The server organizes the collected information and converts it into a format suitable for generative artificial intelligence models. Raw datasets are used as input, and pre-processed datasets suitable for AI models are output. Specifically, the server uses the Python Pandas library to format the dataframe, remove unnecessary data and noise, and standardize and encode the data. This results in a format that is easy to process.

[0644] Step 3:

[0645] The server analyzes pre-processed data using a generative AI model to generate the optimal strategic approach for each project. The input is a formatted dataset, and the output is multiple proposed strategies. Specifically, it uses the Hugging Face Transformers library to run a deep learning model and extract insights from the data.

[0646] Step 4:

[0647] The server analyzes the generated strategies against evaluation criteria and sets priorities. The inputs are the proposed strategies and evaluation criteria, and the output is a prioritized list of strategies. The specific operation involves statistical analysis using the Python SciPy library to calculate an evaluation score for each strategy.

[0648] Step 5:

[0649] The terminal visualizes and presents the generated strategies to the user. The input is a prioritized list of strategies, and the output is a visual dashboard displayed through the user interface. Specifically, it uses Tableau and Power BI to visualize data and present strategies in a way that is easy for the user to understand.

[0650] Step 6:

[0651] The user selects the most suitable strategy from the presented options and applies it to the project. The input is information from a visual dashboard, and the output is the selected strategy. Specifically, the user evaluates the strategies, chooses the one that best matches the project objectives and current situation, and incorporates it into the execution plan.

[0652] (Application Example 1)

[0653] 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".

[0654] In today's production environment, efficient and flexible project management is crucial. However, determining the optimal strategy based on diverse data is complex and requires timely adjustments. In addition, factory production projects require the presentation and adjustment of production strategies in real time, and the wide range of challenges presents obstacles.

[0655] 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.

[0656] In this invention, the server includes means for collecting project-related information, means for cleaning the collected information and converting it into a format suitable for a generative artificial intelligence model, means for proposing the optimal strategy for each project using the generative artificial intelligence model, and means for factory equipment to present operational strategies in real time via information terminals. This enables efficient real-time presentation and adjustment of operational strategies in production projects.

[0657] A "project" is a collection of activities that an organization or individual systematically undertakes to achieve a specific objective.

[0658] "Information" refers to a collection of various data and knowledge related to a project, and serves as a foundation for supporting decision-making.

[0659] "Cleaning" is the process of removing noise and redundant data from collected information and preparing it in a format suitable for analysis.

[0660] A "generative artificial intelligence model" is an algorithm or system that learns from large amounts of data and automatically generates optimal strategies and policies.

[0661] A "policy" refers to a specific action plan or strategy for carrying out a project.

[0662] An "evaluation indicator" is a standard or scale used to measure the effectiveness or importance of a proposed policy.

[0663] "Equipment" refers to machines and robots installed within a factory to perform production tasks.

[0664] An "information terminal" is a digital device that allows users to visually receive and operate information.

[0665] An "operational strategy" is a set of specific actions or plans that a device or system takes to achieve a particular objective.

[0666] "Real-time" refers to processing and responding in accordance with actual time, and is a state of immediate action.

[0667] The system for implementing this invention consists of a server, an information terminal, and equipment within the factory. The server collects project-related information through IoT devices and other means, and cleans that information. The cleaned data is converted into a format suitable for a generative AI model that runs on TensorFlow using Python. This AI model generates optimal strategies based on the characteristics of the project and devises operational strategies within the factory.

[0668] The server transmits the generated policies to the information terminal in real time, and the user confirms them through the terminal's display. During this process, the user can select and apply multiple operational strategies provided by the generated AI model. This information is then reflected in the factory equipment, enabling efficient production activities.

[0669] A concrete example is the setup of a new product production line. Based on past data and market analysis, the AI ​​model calculates the optimal operation sequence for each production process, thereby improving factory efficiency. Furthermore, users can provide the AI ​​model with prompts via an information terminal, such as "We require an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," to obtain specific guidance.

[0670] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0671] Step 1:

[0672] The server collects project-related information through IoT devices within the factory. This information includes historical production data, market trends, and current equipment operating status. The collected information is stored in a database on the server.

[0673] Step 2:

[0674] The server cleans the stored information, removing noise and redundant data. This process uses a specific algorithm to format the data into a format suitable for the generated AI model. The cleaned data is then prepared for further analysis.

[0675] Step 3:

[0676] The server runs a generative AI model using TensorFlow with clean data. This model analyzes historical data and real-time situations to calculate the optimal operating strategy. The results of this analysis are output as proposed strategies to be used in the next step.

[0677] Step 4:

[0678] The server transmits the generated operational strategy to the information terminal. The information terminal displays this visually and proposes it to the user. The user can compare multiple strategy options on the terminal screen and select the appropriate strategy.

[0679] Step 5:

[0680] The user reviews the selected operational strategy and provides prompts to the generating AI model as needed. For example, by giving instructions such as, "I need an efficient robot strategy for the production line. Please provide the optimal route from material handling to the inspection process," the model can derive a more specific strategy.

[0681] Step 6:

[0682] The server issues final operational commands to the equipment based on the user's selection and provided prompts. These commands are transmitted to each piece of equipment in the factory and executed to ensure efficient operation of the production line.

[0683] 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.

[0684] This invention is a system that incorporates an emotion engine into the strategic approach selection process in project management. This enables a process that considers the user's emotional state and proposes the most suitable approach for the project's characteristics.

[0685] First, the server collects project-related data, removes noise, and cleans it into a format suitable for the AI ​​model. This data is then input into the AI ​​model, which generates optimal approach suggestions for each project. When combined with the emotion engine, the server also collects user emotion data and feeds this back into the approach suggestions output by the AI ​​model. For example, if a user is experiencing stress related to the project, the engine will suggest an approach that can alleviate that stress.

[0686] The device visually displays the results of an analysis of the user's emotional state along with the proposed approaches, making the information easy to understand. This allows the user to select an approach that is appropriate for the project's characteristics, taking their own emotional state into consideration. The emotion engine then adjusts the selected approach to optimize the user's job satisfaction and stress management.

[0687] As a concrete example, in a development project, if the server detects that a user is busy and under high stress, it will adjust task priorities and assignments based on emotional data, proposing a more efficient and less mentally taxing approach.

[0688] This invention aims to facilitate smoother corporate activities by providing a more human-centered approach that takes into account user emotions while maintaining efficiency in project management.

[0689] The following describes the processing flow.

[0690] Step 1:

[0691] The server automatically collects project-related data. This data includes past project examples, company rules, and industry best practice information. The server also uses APIs and databases to collect data from external resources.

[0692] Step 2:

[0693] The server cleans the collected data. This involves removing unnecessary information and noise and formatting the data into a standard format. The cleaning process removes duplicate data and fills in any incomplete data.

[0694] Step 3:

[0695] The server uses an emotion engine to collect user emotion data. This emotion data is obtained through user input, wearable devices, feedback forms, etc. The emotion engine includes measuring stress levels and satisfaction levels.

[0696] Step 4:

[0697] The server utilizes an AI model to generate the optimal approach for each project. Based on cleaned data and sentiment data, the AI ​​model proposes multiple strategic options. For example, it considers high-stress situations indicated by sentiment data and suggests task scheduling that reduces stress.

[0698] Step 5:

[0699] The server prioritizes the generated approach proposals based on evaluation metrics. At this stage, the benefits, risks, and impact on user emotions of each approach are considered to identify the most effective approach.

[0700] Step 6:

[0701] The device provides the user with a visual dashboard containing the results of an analysis of their emotional state, along with suggested approaches. Through this dashboard, the user can visually confirm the details of each approach and its impact on their emotions.

[0702] Step 7:

[0703] The user uses their device to select the approach that best suits their emotional state and project objectives from the proposed options. The selected approach is then incorporated into the project's progress plan.

[0704] Step 8:

[0705] The server monitors project progress in real time and continuously analyzes changes in sentiment data. If necessary, it dynamically adjusts strategies and provides feedback to users to support optimal project management.

[0706] (Example 2)

[0707] 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".

[0708] Selecting the appropriate approach is essential for improving efficiency in project management. However, existing systems only make objective judgments based on project data, making it difficult to adjust the approach while considering the emotional state of the users. As a result, user job satisfaction and stress reduction may not be sufficiently achieved, potentially leading to a decrease in overall project efficiency. This project aims to solve this problem.

[0709] 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.

[0710] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for an artificial intelligence model, means for proposing the optimal solution for each project using the artificial intelligence model, and means for collecting user sentiment information and feeding it back into the solutions generated by the artificial intelligence model. This makes it possible to adjust the approach to take into account the user's emotional state, enabling efficient and highly satisfying project management.

[0711] "Project-related information" refers to data necessary for the successful completion of a specific project, such as its progress, resources, schedule, and the roles of its members.

[0712] "Organization" refers to the process of converting data into an appropriate format and structure so that it can be effectively analyzed by artificial intelligence models.

[0713] An "artificial intelligence model" refers to machine learning algorithms and neural networks used to analyze collected information and propose the optimal approach for a project.

[0714] "Proposing countermeasures" refers to the artificial intelligence model presenting management policies and action plans for a specific project based on its analysis results.

[0715] "User emotional information" refers to data that indicates the emotional state and stress levels of individuals working on a project, and is gathered through chat tone and information from biosensors.

[0716] "Providing feedback" refers to incorporating acquired emotional information into the proposed solutions output by the artificial intelligence model and adjusting those solutions accordingly.

[0717] This invention constructs a system that combines an artificial intelligence model and an emotion data analysis engine to select effective strategies in project management. The system primarily relies on the collaboration of three parties: a server, a terminal, and a user.

[0718] The server collects project-related data from internal databases and external information sources. Data collection utilizes the Python Pandas library and leverages SQL queries. The collected data is then de-noised and converted into a format suitable for use with artificial intelligence models, such as JSON or CSV. Data processing tools like Pandas and NumPy are used for this conversion.

[0719] Next, the server inputs the collected data into a generative AI model. This model is built using frameworks such as TensorFlow or PyTorch and generates the optimal approach for a specific project based on a prompt. An example of a prompt used in this process is, "Please suggest a strategy to maximize the efficiency of the project."

[0720] The server further collects data from wearable devices and communication tools to obtain user emotional information. This emotional data includes the user's heart rate, chat content, and tone. Natural language processing tools such as NLTK and emotion analysis APIs are used for analysis. This data is fed back into the project's approach, which is then adjusted to reduce user stress.

[0721] The terminal visually displays the proposed approaches and emotional information analysis results received from the server. To achieve this, a dashboard is created using D3.js and Chart.js. Based on this information, users can select the most suitable approach, taking into account their own emotional state and the characteristics of the project. Specifically, it serves as a reference for users when readjusting task allocation or changing schedules.

[0722] This system aims to provide a human-centered strategic approach tailored to the characteristics of each project, thereby improving the efficiency of project management and maximizing user job satisfaction.

[0723] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0724] Step 1:

[0725] The server retrieves project-related information from internal databases and external information sources. Inputs include project progress, resource utilization, and task assignments. This information is imported as a dataframe using the Python Pandas library. The output is a dataset with unnecessary noise removed. Specifically, it extracts information from the database using SQL queries and imputes or removes missing values.

[0726] Step 2:

[0727] The server converts the collected data into a format that is easily analyzable by the generating AI model. The conversion targets the data format and structure. The input is the dataset cleaned in step 1. It is converted to CSV or JSON format using Pandas or NumPy. This data is processed into a shape suitable for the model, and the output is data in an analyzable format. Specifically, categorical data is encoded into numerical data, and data normalization is performed as needed.

[0728] Step 3:

[0729] The server uses the transformed data to input into a generating AI model and generate the optimal solution for the project. The prompt "Propose a strategy to maximize project efficiency" is used as input. The model is built with TensorFlow and PyTorch and outputs project-specific analysis results. Specifically, it calls the model, performs inference processing, and outputs the resulting artifacts (a series of proposed approaches).

[0730] Step 4:

[0731] The server collects user emotional information from wearable devices and communication tools. Input data includes heart rate, chat content, and tone of voice. The server analyzes this data using the natural language processing library NLTK and an emotion analysis API to quantify the user's emotional state. The output provides the user's stress level and emotional tone score. Specifically, the server periodically polls data from devices and tools to update the analysis results.

[0732] Step 5:

[0733] The server optimizes the proposed approaches generated using emotional data. Inputs include the proposed approaches generated in step 3 and the user's emotional score obtained in step 4. A feedback loop is constructed to prioritize approaches that reduce stress. The output is an optimized approach adapted to the user's emotions. Specifically, the server adjusts task priorities and assignments based on the user's emotional state.

[0734] Step 6:

[0735] The terminal visually displays the ultimately selected approach and the user's emotional state. It uses approach data and emotional analysis results from the server as input. Data is received via GraphQL or REST API, and a dashboard is created using D3.js or Chart.js. The output provides a graphical interface to facilitate user decision-making while considering their emotional state. Specific actions include providing intuitive displays and interactions using bar graphs and icons.

[0736] (Application Example 2)

[0737] 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".

[0738] Modern project management often prioritizes efficiency while neglecting the emotional aspects of stakeholders. This can lead to increased emotional stress during project execution, negatively impacting the quality and progress of deliverables. Furthermore, it can decrease the motivation of those involved in the project, posing a risk to overall work efficiency.

[0739] 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.

[0740] In this invention, the server includes means for collecting project-related information, means for organizing the collected information and converting it into a format suitable for a generative machine learning algorithm, means for proposing the optimal method for each project using a generative machine learning algorithm, means for acquiring user emotional information and making suggestions based on their emotional state, means for setting priorities for the proposed methods based on multiple evaluation criteria, and means for adjusting the selected methods according to the progress of the project. This makes it possible to select and implement the optimal method in project management while considering the emotional state of those involved.

[0741] "Project-related information" refers to all data and documents required for a particular project, including schedules, budgets, lists of stakeholders, and task details.

[0742] "Means of organizing collected information and converting it into a format suitable for generative machine learning algorithms" refers to the process of systematically compiling project-related information and making it available as structured data for input into machine learning algorithms.

[0743] "A method of proposing the optimal approach for each project using generative machine learning algorithms" refers to a process that automatically derives the optimal measures and strategies using AI technology based on the specific conditions and requirements of a project.

[0744] "Means for acquiring user emotional information and making suggestions based on emotional state" refers to a mechanism that measures and analyzes users' emotional reactions and states, and provides project guidelines and strategies tailored to them.

[0745] "A means of prioritizing proposed methods based on multiple evaluation criteria" refers to the process of evaluating proposed methods using various indicators of importance and impact, and listing them in order of effectiveness.

[0746] "Means for adjusting selected methods according to the project's progress" refers to a mechanism for changing and optimizing pre-selected methods according to the project's progress and external conditions.

[0747] This invention relates to a system for streamlining project management in smart cities, and its hardware includes a high-performance computer and a device that provides a user interface. Specifically, the computer (e.g., a server) collects and organizes project-related information from a database. The software used is Python and related libraries (Pandas, NumPy), which converts the data into a format suitable for generating machine learning algorithms (e.g., Azure's AI service). IBM Watson is used for sentiment analysis.

[0748] The server inputs this formatted data into a machine learning algorithm to propose the optimal approach for each project. During this process, user sentiment information is also acquired in real time, and feedback based on the emotional state is reflected in the proposals. User sentiment information is collected through input from smartphones and tablets.

[0749] The proposed method is visually displayed to the user via their device. Users can view visualized information on project progress and emotional state on the dashboard. This allows for the selection of the most suitable method for the project and enables adjustments as the situation progresses.

[0750] As a concrete example, consider a scenario where a city official managing a traffic improvement project is experiencing stress associated with the project. In this case, the system analyzes traffic data and emotional data and executes a process to propose methods such as increasing public transport during peak hours. The prompt message used as an initial input to the system would be: "Please propose strategies to the AI ​​model to alleviate the stress currently felt by the city project manager. Specifically, we are looking for an approach that focuses on solutions to traffic congestion and reduces the burden while maintaining efficiency."

[0751] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0752] Step 1:

[0753] The server collects project-related information from the database. Specifically, it extracts project schedules, budgets, task lists, and historical performance data from the database and lists them using a Python script. This prepares the collected information in a format that can be used in the next processing step.

[0754] Step 2:

[0755] The server formats the collected information and converts it into a format suitable for generative machine learning algorithms. It utilizes libraries such as Pandas and NumPy to clean the data, impute missing values, and convert it to a consistent format. The formatted data is then transformed into an appropriate structure for subsequent analysis by the AI ​​model.

[0756] Step 3:

[0757] The server inputs the formatted data into a machine learning algorithm to propose the optimal project approach. Using Azure's AI services, it analyzes patterns and trends derived from the input data to generate the most effective strategy for the project. The output is a concrete action plan for project management.

[0758] Step 4:

[0759] The device acquires and analyzes user emotional information in real time. It collects emotional data, such as user stress levels and satisfaction levels, via sensors and input devices on smartphones and tablets. The collected emotional data is analyzed using IBM Watson, and the results are fed back into the output of an AI model.

[0760] Step 5:

[0761] The device visualizes and presents project methodology proposals and sentiment analysis results to the user. Graphs and indicators showing project progress, predicted outcomes, and the user's emotional state are displayed on a specific dashboard screen. This enables users to make data-driven decisions. Adjustments that take emotional state into consideration are also suggested in parallel.

[0762] 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.

[0763] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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.

[0768] 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.

[0769] 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.

[0770] 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."

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] The following is further disclosed regarding the embodiments described above.

[0784] (Claim 1)

[0785] Means of collecting project-related data,

[0786] A means for cleaning the collected data and converting it into a format suitable for a generative artificial intelligence model,

[0787] A method for proposing the optimal approach for each project using generative artificial intelligence models,

[0788] A means of prioritizing the proposed approaches based on multiple evaluation metrics,

[0789] Means for adjusting the selected approach according to the situation as the project progresses,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, comprising a dashboard that visually presents the proposed approach to the user.

[0793] (Claim 3)

[0794] The system according to claim 1, comprising means for analyzing project progress data in real time and identifying risks and problems.

[0795] "Example 1"

[0796] (Claim 1)

[0797] Means of collecting information related to the project,

[0798] A means for organizing the collected information and converting it into a format suitable for a generative artificial intelligence model,

[0799] A means of generating the optimal strategic approach for each project using a generative artificial intelligence model,

[0800] A means of prioritizing the generated strategies based on multiple evaluation criteria,

[0801] A means of adjusting the established strategy according to the project's progress,

[0802] An information processing system that includes this.

[0803] (Claim 2)

[0804] The information processing system according to claim 1, comprising a display device that provides the generated strategy to the user in a visualized form.

[0805] (Claim 3)

[0806] The information processing system according to claim 1, comprising means for analyzing the progress of a project in real time and identifying potential risks and issues.

[0807] "Application Example 1"

[0808] (Claim 1)

[0809] Means of collecting information related to the project,

[0810] A means for cleaning the collected information and converting it into a format suitable for a generative artificial intelligence model,

[0811] A means of proposing the optimal strategy for each project using a generative artificial intelligence model,

[0812] A means of prioritizing the proposed policies based on multiple evaluation indicators,

[0813] A means of adjusting the selected policy according to the situation as the project progresses,

[0814] A means by which equipment within a factory presents its operational strategy in real time via an information terminal,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, comprising a display device that visually provides the proposed policy to the user.

[0818] (Claim 3)

[0819] The system according to claim 1, comprising means for analyzing project progress data in real time and identifying risks and problems.

[0820] "Example 2 of combining an emotion engine"

[0821] (Claim 1)

[0822] Means of collecting information related to the project,

[0823] A means of organizing the collected information and converting it into a format suitable for artificial intelligence models,

[0824] A method of proposing the optimal solution for each project using an artificial intelligence model,

[0825] A means of prioritizing the proposed measures based on multiple evaluation criteria,

[0826] A means of collecting user sentiment information and feeding it back into countermeasures generated by an artificial intelligence model,

[0827] A means of adjusting the selected measures according to the project's progress and the users' emotional state,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, comprising a display device that visually provides the proposed countermeasures and the results of the analysis of the user's emotional state.

[0831] (Claim 3)

[0832] The system according to claim 1, comprising means for analyzing the progress of a project in real time and identifying issues and problems.

[0833] "Application example 2 when combining with an emotional engine"

[0834] (Claim 1)

[0835] Means of collecting information related to the project,

[0836] A means of organizing the collected information and converting it into a format suitable for generative machine learning algorithms,

[0837] A method for proposing the optimal approach for each project using generative machine learning algorithms,

[0838] A means of acquiring user emotional information and making suggestions based on their emotional state,

[0839] A means of prioritizing the proposed methods based on multiple evaluation criteria,

[0840] A means of adjusting the selected method according to the situation during the project,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, comprising a display device that visually presents the proposed method to the user and also displays the results of the emotional state analysis.

[0844] (Claim 3)

[0845] The system according to claim 1, comprising means for analyzing project progress information in real time and identifying risks and problems, and means for proposing risk mitigation measures that take emotional data into consideration. [Explanation of symbols]

[0846] 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. Means of collecting project-related data, A means for cleaning the collected data and converting it into a format suitable for a generative artificial intelligence model, A method for proposing the optimal approach for each project using generative artificial intelligence models, A means of prioritizing the proposed approaches based on multiple evaluation metrics, Means for adjusting the selected approach according to the situation as the project progresses, A system that includes this.

2. The system according to claim 1, comprising a dashboard that visually provides the user with the proposed approach.

3. The system according to claim 1, comprising means for analyzing project progress data in real time and identifying risks and problems.

Images