system

Abstract

We provide a system that allows for quick and accurate estimation of project duration and human resources based on project requirements and conditions. [Solution] A system including means for a user to input basic project information from a terminal, means for transmitting the input project requirements to a server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, updating it by comparing it with the estimation data, and re-running the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the construction industry, it is extremely important to quickly and accurately estimate the period and human resources based on the requirements and conditions of a project. However, in small and medium-sized construction companies, manual estimation is the mainstream, so it has been difficult to quickly respond to project changes and progress situations. As a result, compliance with regulations and the elimination of long working hours have been prone to delays, and efficient project management has been demanded.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for a user to input basic project information from a terminal, means for transmitting the input project requirements to a server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, updating it by comparing it with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal.

[0006] Furthermore, by providing a means to collect actual project data and feedback data after project completion and store it as training data for the generative AI model, the accuracy of the model can be improved, enabling more effective project management. In addition, by using a generative AI model to generate new estimates and resource allocation proposals based on real-time project progress, it becomes possible to respond flexibly to unpredictable fluctuations.

[0007] A "user" refers to a person who uses the system to manage a project.

[0008] "Terminal" refers to a device used by a user, such as a computer or smartphone.

[0009] A "server" refers to a central computer system that receives and processes data sent from terminals.

[0010] "Basic project information" refers to fundamental requirements such as the project name, construction area, materials to be used, and deadline.

[0011] "Project requirements" refer to the tasks and conditions necessary for the successful execution of a project.

[0012] "Database" refers to a storage place for data to store past project performance data and human resource information.

[0013] "Generative AI model" refers to an algorithm that uses machine learning and deep learning technologies to generate estimates from input data.

[0014] "Estimation result" refers to the estimation of the project period and required human resources output by the generative AI model.

[0015] "Structured data" refers to data organized in a specific format and is data in a format that can be easily analyzed and searched.

[0016] "Receiving progress data in real time" means immediately receiving the progress status data of a project.

[0017] "Updating" means replacing existing data with new data.

[0018] "Re-running the generative AI model" means running the generative AI model again based on the progress data to generate a new estimate.

[0019] "Resource allocation proposal" refers to a proposal for the optimal allocation method of human resources required for project execution.

[0020] "Feedback data" refers to data on the actual period and input resources obtained after project completion.

[0021] "Learning data" refers to data used to improve the accuracy of the generative AI model.

[0022] "Project progress status" refers to the progress degree and achievement status of the current project.

Brief Explanation of Drawings

[0023] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0024] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0025] First, let's explain the terminology used in the following explanation.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] 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).

[0030] 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."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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".

[0044] This invention provides a system for streamlining project management in the construction industry, where users input basic project information from a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources.

[0045] First, the user uses a terminal to enter basic project information. This information includes requirements such as the project name, construction area, materials to be used, and deadline. The terminal then sends this information to the server.

[0046] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. The server then inputs the preprocessed data and user input data into a generated AI model.

[0047] The generative AI model operates to estimate the project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[0048] The server sends the estimate results to the terminal, providing the data to the user. The user can then review the estimate results through the terminal and plan the project.

[0049] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the terminal. Users can review these and modify the project plan as needed.

[0050] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0051] As a concrete example, consider a small to medium-sized construction company that has received a contract for a new building construction project. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0052] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[0053] In this way, this system achieves efficiency and rationalization of project management in the construction industry and promotes legal and efficient work style reforms.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] The user uses a terminal to enter basic project information (e.g., project name, construction area, materials used, deadline, etc.).

[0057] Step 2:

[0058] The terminal sends the entered project requirements to the server.

[0059] Step 3:

[0060] The server retrieves past project performance data and human resource information from the database.

[0061] Step 4:

[0062] The server preprocesses the collected data, including imputing missing values ​​and formatting the data.

[0063] Step 5:

[0064] The server inputs pre-processed data and project requirements data from users into the generated AI model.

[0065] Step 6:

[0066] The generative AI model estimates the project duration and the required human resources.

[0067] Step 7:

[0068] The server stores the estimation results as structured data.

[0069] Step 8:

[0070] The server sends the estimate result to the terminal.

[0071] Step 9:

[0072] The terminal displays the estimate result to the user.

[0073] Step 10:

[0074] Users periodically input project progress into their terminals and send it to the server.

[0075] Step 11:

[0076] The server compares real-time progress data with estimated data and updates the progress status.

[0077] Step 12:

[0078] The server reruns the generated AI model and produces new estimation results.

[0079] Step 13:

[0080] The server generates a new resource allocation proposal and sends it to the terminal.

[0081] Step 14:

[0082] The terminal displays new quotes and resource allocation suggestions to the user.

[0083] Step 15:

[0084] After completing a project, the user inputs the actual project data and feedback data into their device and sends it to the server.

[0085] Step 16:

[0086] The server collects feedback data and stores it as training data for the generated AI model.

[0087] (Example 1)

[0088] 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."

[0089] Traditionally, project management in the construction industry has often been done manually, leading to inefficiencies in project progress tracking and human resource estimation. Furthermore, it has been difficult to respond quickly based on real-time progress or to make highly accurate estimates based on historical data. This has resulted in project delays and shortages or surpluses of human resources, ultimately leading to increased overall project costs and time.

[0090] 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.

[0091] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the inputted basic information to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting the basic project information and preprocessed data into a generating AI model to estimate the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient management and accurate human resource estimation during project progress.

[0092] A "user" is someone who operates the system, inputs basic project information, and provides progress data and feedback data.

[0093] A "terminal" is a device used by the user to input basic project information, progress data, and feedback data, and to communicate with the server.

[0094] A "server" is a central computer system that collects and preprocesses data from a database, performs estimations using a generated AI model, and stores and transmits the results.

[0095] "Basic project information" refers to information required in the initial stages of a project, such as the project name, construction area, materials to be used, and deadline.

[0096] A "database" is a system that stores and manages past project performance data and human resource information.

[0097] "Preprocessing" refers to the preparatory work involved in filling in missing values ​​and formatting data collected from a database, in order to input it into the generated AI model.

[0098] A "generative AI model" is a model trained using machine learning and deep learning technologies to accurately estimate project duration and required human resources.

[0099] "Structured data" refers to data in a systematically organized format when a server stores estimation results.

[0100] "Progress data" refers to data that shows the actual progress of an ongoing project.

[0101] A "resource allocation proposal" is a suggestion regarding the allocation of human resources to optimize project progress, based on the estimation results calculated by the generative AI model.

[0102] "Post-project feedback data" refers to actual project data and feedback information regarding areas for improvement collected after a project is completed.

[0103] This invention is a system for streamlining project management in the construction industry. This system optimizes project progress by allowing users to input basic project information via a terminal, and then having a server collect, process, and analyze that information. Specific embodiments are described below.

[0104] First, the user enters basic project information using a terminal. This basic information includes the project name, construction area, materials to be used, and deadline. This information is entered using dedicated software and sent from the terminal to the server.

[0105] Based on the received basic information, the server collects past project performance data and human resource information from the database. The collected data undergoes preprocessing, such as imputing missing values ​​and formatting the data. Data cleaning tools and ETL (Extract, Transform, Load) tools are often used for this purpose.

[0106] Based on the pre-processed data and user input data, the server runs a generative AI model. This generative AI model is trained on past project data and can estimate project duration and required human resources with high accuracy. Machine learning and deep learning techniques are used in the generative AI model.

[0107] During the estimation process, the following prompt statements are input to the generating AI model:

[0108] Project name: New building construction, Construction area: 2000m 2 Please estimate the necessary human resources and timeframe, given the materials used are concrete and the deadline is 12 months.

[0109] The generated estimate results are stored as structured data on the server. The server sends this data to the terminal, and the user checks the estimate results through the terminal.

[0110] During project progress, users periodically input progress data into their terminals and send it to the server. The server uses this progress data to compare it with estimation data and reruns the AI ​​model to generate new estimation results and resource allocation suggestions. For example, if the data indicates that "the current number of workers is 15 and the progress rate is 50%", a suggestion of "5 additional workers are needed" might be generated.

[0111] After project completion, users input actual project data and feedback data using their devices and send it to the server. The server collects this data and stores it as training data for the generative AI model. This improves the accuracy of the generative AI model, leading to even greater accuracy in future estimates.

[0112] In this way, this system streamlines and rationalizes project management in the construction industry, supporting accurate estimations and optimal resource allocation.

[0113] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0114] Step 1:

[0115] The user uses a terminal to enter basic project information (project name, construction area, materials used, deadline, etc.). The terminal has a dedicated input form, and the user enters the information according to this form. The entered basic information is sent from the terminal to the server. This operation completes the initial setup of the project.

[0116] Input: Basic project information (project name, construction area, materials used, deadline, etc.)

[0117] Output: Basic project information is sent to the server.

[0118] Step 2:

[0119] The server receives the entered basic information and retrieves past project performance data and human resource information from the database. It then performs preprocessing on the collected data, specifically including imputing missing values ​​and formatting the data. This process converts the data into an appropriate format for input into the generated AI model.

[0120] Input: Basic information, past project performance data, human resource information

[0121] Output: Preprocessed data

[0122] Step 3:

[0123] The server inputs pre-processed data and basic information entered by the user into the generating AI model. Prompts are used to instruct the generating AI model to estimate the project duration and required human resources. For example, "Project name: New building construction, construction area: 2000m²" 2 A prompt message such as "Materials used: concrete, deadline: 12 months, please estimate the necessary human resources and timeframe" is input to the generated AI model.

[0124] Input: Preprocessed data, basic information, prompt message

[0125] Output: Estimated project duration and required human resources.

[0126] Step 4:

[0127] The server saves the estimation results, which are the output of the generated AI model, as structured data. The estimation results are saved in a format such as "Construction of this building will take 6 months and require 20 workers." The saved data will be referenced and updated later.

[0128] Input: Estimate Result

[0129] Output: Saved as structured data

[0130] Step 5:

[0131] The server sends the saved estimate results to the terminal. The terminal displays the estimate results to the user. The user reviews these results and uses them to plan the project.

[0132] Input: Estimate results as structured data

[0133] Output: Estimated result displayed on the terminal

[0134] Step 6:

[0135] Users periodically input progress data into their terminals and send it to the server during project execution. For example, they might input data such as "Current number of workers: 15, progress rate: 50%." This allows for real-time monitoring of the project's status.

[0136] Input: Progress data (number of workers, progress rate, etc.)

[0137] Output: Progress data sent to the server

[0138] Step 7:

[0139] The server compares the received progress data with the estimated data and reruns the generated AI model as needed. This generates new estimated results and resource allocation suggestions. For example, it might generate a suggestion such as "5 additional workers are needed."

[0140] Input: Progress data, historical estimate data

[0141] Output: New estimate results and resource allocation proposals

[0142] Step 8:

[0143] The server sends the new estimate and resource allocation proposal to the terminal. The terminal displays this for the user to review. The user then modifies the project plan based on this proposal.

[0144] Input: New estimate results and resource allocation proposals

[0145] Output: New estimate results and resource allocation proposals displayed on the terminal.

[0146] Step 9:

[0147] After project completion, users input actual project data and feedback data into their devices and send it to the server. This includes detailed information about project progress and human resource utilization.

[0148] Input: Actual project data, feedback data

[0149] Output: Feedback data sent to the server

[0150] Step 10:

[0151] The server stores the received feedback data as training data for the generating AI model. This improves the model's accuracy, leading to even higher estimation accuracy in subsequent iterations.

[0152] Input: Feedback data

[0153] Output: Stored as training data

[0154] (Application Example 1)

[0155] 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."

[0156] Manufacturing projects in a factory environment require numerous processes and human resources, making their management extremely complex. In particular, understanding project progress, appropriately allocating resources, and adjusting plans according to progress are crucial and must be done efficiently. However, current systems often struggle to meet these requirements, resulting in inefficiencies. Therefore, this invention aims to solve these problems and improve the efficiency and accuracy of manufacturing project management in a factory environment.

[0157] 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.

[0158] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, and means for managing the progress of a manufacturing project in a factory environment in real time and estimating the necessary work processes and resource allocation. This enables more efficient project management and flexible resource management according to the progress status.

[0159] "Basic project information" refers to project requirements such as project name, area, materials used, and deadline, which are entered by the user via their device.

[0160] A "terminal" refers to a device that a user uses to input and verify information related to a project.

[0161] A "server" refers to a device that receives basic project information, collects necessary information from a database, and generates estimation results by executing a generated AI model.

[0162] A "database" refers to a data storage system that contains past project performance data and human resource information.

[0163] "Past project performance data" refers to data related to projects that have been carried out in the past, including project duration and resources used.

[0164] "Human resource information" refers to information about the number of workers required for a project and their skill sets.

[0165] "Preprocessing" refers to the process of preparing data before analysis, such as imputing missing values ​​and formatting the data.

[0166] A "generative AI model" refers to an algorithm that uses machine learning and deep learning techniques to estimate project duration and the necessary human resources.

[0167] "Project duration" refers to the period from the start to the end of a project.

[0168] "Required human resources" refers to the number of workers and their skill sets needed to complete the project.

[0169] "Estimate results" refer to data regarding the project duration and required human resources calculated by the generative AI model.

[0170] "Structured data" refers to data where estimation results are presented in an organized format, making it easy to process using computer systems.

[0171] "Progress data" refers to data related to the progress of a project during its operation.

[0172] "Resource allocation proposal" refers to a proposal for new human resources for project execution, generated as a result of re-running the generated AI model.

[0173] "Factory environment" refers to the physical location where work is carried out to manufacture products, as well as the surrounding conditions.

[0174] A "manufacturing project" refers to a series of tasks and their management required to produce a specific product.

[0175] This invention is a system for streamlining manufacturing project management in a factory environment. The following describes how to implement this system in detail.

[0176] The user first uses a terminal to enter basic project information. This information includes the project name, area, materials used, and deadline. This information is then sent from the terminal to the server. Common devices such as personal computers and tablets are used as terminals.

[0177] The server retrieves past project performance data and human resource information from the database based on the basic information of the received project, and performs preprocessing. Preprocessing includes imputing missing values ​​and formatting the data. Relational databases such as SQLite and MySQL (registered trademark) are used as the database.

[0178] Based on pre-processed data, the server supplies input data to the generative AI model. The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources with high accuracy. Specifically, machine learning frameworks such as scikit-learn's RandomForestRegressor and TENSORFLOW® are used.

[0179] The estimation results are stored on the server as structured data and sent to the terminal. Users can then review the estimation results and plan their projects through the terminal.

[0180] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. New resource allocation suggestions are also generated and sent to the terminal. Users review these and revise the project plan as needed.

[0181] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0182] As a concrete example, consider a project in which a factory is building a new product line. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "building this product line will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0183] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[0184] Through the above process, this system achieves increased efficiency and streamlining of manufacturing project management in a factory environment.

[0185] Examples of prompt statements are as follows:

[0186] Project Name: New Product Line Development

[0187] Construction area: 500

[0188] Materials used: Iron, plastic

[0189] Delivery date: 2024-12-31

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Step 1:

[0192] The user enters basic project information from their device. This basic information includes project name, area, materials used, and deadline. The entered data is temporarily stored on the device.

[0193] Step 2:

[0194] The terminal sends the entered project information to the server. Secure communication protocols such as HTTPS are used for data transmission. The transmitted data is received on the server side.

[0195] Step 3:

[0196] Based on the received project basic information, the server retrieves past project performance data and human resource information from the database. During this process, it uses SQL queries to extract the necessary data.

[0197] Step 4:

[0198] The server preprocesses the collected data. Specifically, it performs data imputation and formatting. The Python pandas library is used for preprocessing. The preprocessed data is then converted into a format suitable for estimation.

[0199] Step 5:

[0200] Based on pre-processed data and user-submitted project basic information, the server inputs data into a generated AI model. This model uses machine learning techniques to estimate project duration and required human resources. The software used includes scikit-learn's RandomForestRegressor and TensorFlow.

[0201] Step 6:

[0202] The generative AI model analyzes user-provided input data to predict project duration and required human resources. The prediction results are stored on the server as structured data.

[0203] Step 7:

[0204] The server sends the generated estimate results to the terminal. The user can then review the estimate results through the terminal and plan the project.

[0205] Step 8:

[0206] During project execution, users periodically input progress data into their terminals and send it to the server. The transmitted progress data is received by the server and stored in a database.

[0207] Step 9:

[0208] The server compares progress data with estimated data and reruns the generating AI model to produce new estimates. This enables real-time optimization of resource allocation.

[0209] Step 10:

[0210] The server sends the updated estimate and resource allocation proposal to the terminal. The user can review the new proposal and revise the project plan.

[0211] Step 11:

[0212] After the project is completed, the user inputs the actual project data and feedback data into their device and sends it to the server. This data is received by the server and stored in a database.

[0213] Step 12:

[0214] The server stores collected actual project data and feedback data as training data for the generated AI model. This allows for improved accuracy in future estimations.

[0215] 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.

[0216] This invention provides a system for streamlining project management in the construction industry. It allows users to input basic project information via a terminal, and a server uses this information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[0217] First, the user uses a terminal to enter basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. The user's emotional data is also obtained through an emotional engine. The terminal then sends this information to the server.

[0218] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. Furthermore, sentiment data is formatted into a format that can be applied to the model. The server then inputs the preprocessed data and user input data (including sentiment data) into the generated AI model.

[0219] The generative AI model operates to estimate project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[0220] The server sends the estimate results to the terminal, providing the data to the user. The terminal presents the user's sentiment data along with the estimate results, allowing the user to plan the project based on this information.

[0221] During project progress, users periodically input progress and sentiment data into their devices and send it to the server. The server compares this progress data with estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the device. The device displays resource allocation suggestions that take sentiment data into account to the user, who can then modify the project plan based on these suggestions.

[0222] After project completion, users input actual project data, feedback data, and sentiment data into their devices and send them to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0223] As a concrete example, consider a small to medium-sized construction company that has won a contract for a new building construction project. The user inputs basic project information from a terminal, and emotional data is also acquired through an emotion engine and sent to a server. The server collects data from similar past projects and performs preprocessing. Then, using a generative AI model and emotional data, it generates an estimate result stating, "Construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0224] During project progress, users input weekly progress and sentiment data from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. The terminal displays the new estimate and resource allocation suggestions, including sentiment data, to the user, who then modifies the plan based on this information.

[0225] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reforms. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user uses a device to input basic project information (e.g., project name, construction area, materials used, deadline, etc.). The emotion engine recognizes the user's emotions in real time as they input the information and collects that data as well.

[0229] Step 2:

[0230] The terminal sends the entered project requirements and sentiment data to the server.

[0231] Step 3:

[0232] The server retrieves past project performance data and human resource information from the database. Furthermore, it also retrieves collected sentiment data.

[0233] Step 4:

[0234] The server preprocesses the collected data, including imputing missing values ​​and formatting the data. Sentiment data is also converted into a format suitable for application to the model.

[0235] Step 5:

[0236] The server inputs pre-processed data and project requirements data from users (including sentiment data) into the generating AI model.

[0237] Step 6:

[0238] The generative AI model estimates the project duration and the required human resources. This estimation also takes emotional data into consideration.

[0239] Step 7:

[0240] The server stores the estimation results as structured data.

[0241] Step 8:

[0242] The server sends the estimation results and sentiment data to the terminal.

[0243] Step 9:

[0244] The device displays the estimate results and sentiment data to the user. The user then uses this information to plan the project.

[0245] Step 10:

[0246] During project progress, users periodically input progress data and emotional data into their devices. The emotional engine recognizes the user's emotional data in real time and sends it to the server as well.

[0247] Step 11:

[0248] The server updates the progress status by comparing real-time progress and sentiment data with estimated data.

[0249] Step 12:

[0250] The server reruns the generated AI model and produces new estimates and resource allocation suggestions, taking sentiment data into consideration.

[0251] Step 13:

[0252] The server sends the new estimate and resource allocation proposal to the terminal.

[0253] Step 14:

[0254] The device displays new estimate results and sentiment data to the user. The user then modifies the project plan based on this information.

[0255] Step 15:

[0256] After the project is completed, the user inputs actual project data, feedback data, and sentiment data into their device and sends it to the server. The sentiment engine also collects the final sentiment data.

[0257] Step 16:

[0258] The server collects feedback and sentiment data and stores it as training data for the generative AI model. This improves the model's accuracy and increases the accuracy of future estimates.

[0259] (Example 2)

[0260] 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".

[0261] In the construction industry, streamlining and improving the efficiency of project management is a critical challenge. In particular, there is a need for appropriate allocation of human resources and the ability to respond to real-time changes in the project's progress. Furthermore, there is a lack of project management methods that consider the stress and motivation of project managers, making flexible estimation and resource allocation based on human emotional data a difficult challenge.

[0262] 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.

[0263] In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements and sentiment data to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing such as imputing missing values ​​and formatting the data, means for inputting the preprocessed project requirements data and sentiment data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data and sentiment data in real time, updating them by comparing them with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient and flexible project management. Furthermore, by reflecting the user's sentiment data in project management, it becomes possible to achieve optimal resource allocation that takes stress and motivation into consideration.

[0264] A "terminal" is an electronic device used by users to input basic project information, progress data, and sentiment data, and to communicate with the server.

[0265] A "server" is a central management system that receives data sent from terminals, collects information from a database, performs preprocessing, calculates estimates using a generated AI model, and sends the results to the terminals.

[0266] "Project basic information" refers to key project requirements such as project name, construction area, materials used, and deadline, which are entered by the user via their device.

[0267] "Emotional data" refers to data that indicates the user's emotional state (e.g., stress level and motivation), and is acquired by the emotion engine.

[0268] A "generative AI model" is an artificial intelligence model trained using machine learning and deep learning techniques, and is used to estimate project duration and the human resources required.

[0269] "Preprocessing" refers to the process of imputing missing values ​​and formatting data collected from a database.

[0270] "Estimate" refers to the project duration and the predicted human resources required, calculated using a generative AI model.

[0271] "Structured data" refers to data, including estimation results, that has been formatted into a specified format and stored in a way that facilitates subsequent processing and analysis.

[0272] "Progress data" refers to data that shows the progress of a project, and users periodically input it from their devices.

[0273] "Feedback data" refers to data about actual project results and emotional states entered by users after project completion, and is used to improve the accuracy of the generative AI model.

[0274] A "resource allocation proposal" is a specific allocation plan for the necessary human resources calculated by a generative AI model.

[0275] A "database" is a system used to record and manage past project performance data and human resource information.

[0276] This invention is a system for streamlining project management in the construction industry. It provides a process where users input basic project information via a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[0277] First, the user uses a terminal to input basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. Furthermore, the terminal has an emotion engine built in that analyzes the user's facial expressions and tone of voice to obtain emotion data. This data is then sent from the terminal to the server.

[0278] The server collects past project performance data and human resource information from the database. This collected data is preprocessed using scripts such as Python. Specifically, missing values ​​are imputed and the data is formatted, and sentiment data is also formatted into a format that can be applied to the generative AI model. After that, the preprocessed data and user input data (including sentiment data) are input to the generative AI model as prompt messages.

[0279] The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources. It leverages historical project data to provide highly accurate estimates. This model utilizes GPT-4® and other advanced generative AI models. The generated estimate results are stored on a server as structured data.

[0280] The server sends this estimate result to the terminal, and the terminal provides the estimate result and emotion data to the user. Based on this, the user can formulate a project plan.

[0281] During the progress of the project, the user regularly inputs progress data and emotion data from the terminal and sends them to the server. Based on this data, the server compares it with the estimate data, re-executes the generation AI model to generate a new estimate result. Thereby, a resource allocation proposal corresponding to the situation change during the project progress is also generated and sent to the terminal.

[0282] After the project is completed, the user inputs the actual project data, feedback data, and emotion data from the terminal and sends them to the server. The server accumulates this feedback data as learning data for the generation AI model, thereby improving the accuracy of the model and making it possible to further enhance the estimate accuracy for subsequent times.

[0283] As a specific example, consider the case where a medium-sized construction company wins a project to build a new building. The user inputs the basic information of the project as follows:

[0284] Project name: New office building construction project

[0285] Construction area: 2,000 square meters

[0286] Materials used: Concrete, steel bars, glass

[0287] Delivery date: 12 months

[0288] The emotion engine determines that the user's stress level is "high." This information and emotion data are sent from the terminal to the server. The server collects and preprocesses data from similar past projects. Then, using the generative AI model and emotion data, it generates an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0289] During project progress, users input weekly progress and emotional data such as "Stress Level: Medium," and send it to the server. Based on this data, the server readjusts the estimate and generates new resource allocation suggestions, such as "5 additional workers are needed," and sends them to the terminal. The terminal displays this to the user, who then modifies the plan based on it.

[0290] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reform. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[0291] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0292] Step 1:

[0293] The user uses a terminal to input basic project information. This information includes the project name, construction area, materials used, and deadline. A specific example of input might be: "Project Name: New Company Building Construction Project," "Construction Area: 2000 square meters," "Materials Used: Concrete, rebar, glass," and "Deadline: 12 months." In addition, the emotion engine retrieves the user's stress level. Possible emotion data inputs might include "Stress Level: High." This data is sent to the terminal as input.

[0294] Step 2:

[0295] The terminal sends the project basic information and sentiment data entered by the user to the server. A secure communication protocol (e.g., HTTPS) is used for this transmission. As output after transmission, the project basic information and sentiment data are packetized and arrive at the server.

[0296] Step 3:

[0297] The server collects past project performance data and human resource information from the database. For example, data on "construction projects of 2000 square meters over the past five years" is collected. Database queries (SQL queries) are performed as input, and raw project data and human resource information are obtained as output.

[0298] Step 4:

[0299] The server begins preprocessing the collected data. This preprocessing includes imputing missing values ​​(e.g., imputing with the mean) and formatting the data (e.g., converting to numerical data). Furthermore, sentiment data is also formatted into a format that can be applied to the generative AI model. Specifically, preprocessing is performed using a Python script. The input is the raw data obtained in step 3, and the output is the preprocessed project data and sentiment data.

[0300] Step 5:

[0301] The server inputs pre-processed data and user input data (including sentiment data) as prompts into a generative AI model. The generative AI model (e.g., GPT-4) then runs machine learning algorithms to predict project duration and required human resources. For example, prompts like the following might be used:

[0302] Project Name: New Company Building Construction Project

[0303] Construction area: 2000 square meters

[0304] Materials used: Concrete, steel bars, glass

[0305] Delivery time: 12 months

[0306] User's stress level: High

[0307] Based on the input prompt sentence, the model performs calculations and generates an estimate result of "6 months, 20 workers" as the output.

[0308] Step 6:

[0309] The server stores the generated estimate result as structured data and sends it to the terminal. This transmitted data includes the estimate result of "6 months, 20 workers". After receiving it, the terminal displays the estimate result and emotion data to the user. As a result, the user can confirm the specific estimate result.

[0310] Step 7:

[0311] During the progress of the project, the user regularly inputs progress data and emotion data through the terminal and sends these data to the server. For example, data such as "Progress rate: 50%", "Stress level: Medium" are input. The terminal packets these data and sends them to the server.

[0312] Step 8:

[0313] The server re - executes the generated AI model to recalculate the estimate data based on the progress data and emotion data. A new estimate result and a resource allocation proposal are generated. For example, a proposal such as "An additional 5 workers are needed" is included. This new estimate result is held by the server and sent to the terminal. The terminal displays this new data to the user, and the user can modify the project plan based on this.

[0314] Step 9:

[0315] After the project is completed, the user inputs actual project results, feedback data, and sentiment data from their device and sends them to the server. For example, data such as the actual project duration being "7 months" or the worker's stress level being "ultimately low" might be input. The server stores this data as training data in the generating AI model to improve the accuracy of future estimates.

[0316] (Application Example 2)

[0317] 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".

[0318] Traditional project management systems made it cumbersome to input basic project information and progress data, making real-time updates and optimal resource allocation suggestions difficult. Furthermore, they failed to consider user emotions and motivations, hindering efficient project progress. This resulted in project delays and wasted resources.

[0319] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generation AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, updating it by comparing it with the estimation data, and re-executing the generation AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, means including an emotion engine that collects emotion data and reflects it in project management, and means for formatting the emotion data and applying it to the generation AI model. This enables real-time estimation and resource allocation proposals based on basic project information and progress data. Furthermore, flexible and efficient project management that takes user emotions into consideration can be realized.

[0320] "Basic project information" refers to data that forms the foundation for project progress, such as the project name, construction area, materials to be used, and deadline.

[0321] "Terminal" is a general term for devices used by users for input, and includes smartphones, tablets, and personal computers.

[0322] A "server" is a central computer system used to collect, process, store, and communicate with other devices.

[0323] A "database" is a digital storage device used to store past project performance data, human resource information, and other similar information.

[0324] "Preprocessing" is the process of shaping raw data into a format that can be input into a generating AI model, through methods such as imputing missing values ​​and normalization.

[0325] A "generative AI model" is an artificial intelligence model that learns from past data and uses new data to predict and estimate the duration and resources required for a project.

[0326] "Structured data" refers to data organized into a specific format, such as quotation results or resource allocation proposals.

[0327] A "resource allocation proposal" is a plan that proposes the optimal allocation of human resources based on the progress of the project.

[0328] "Emotional data" refers to data that shows psychological information such as a user's emotions, stress levels, and motivation.

[0329] An "emotion engine" is a system that collects and analyzes user emotional data and incorporates it into project management.

[0330] "Progress data" refers to data that shows the current progress of a project, and includes actual work progress and achievement levels.

[0331] This invention is a system for streamlining production process management in factories. This system allows users to input basic production information and progress data from a terminal, and processes this data on a server to automatically generate production schedule estimates and resource allocation suggestions. Furthermore, by collecting user sentiment data and incorporating it into a generated AI model, it achieves more efficient and flexible production management.

[0332] Specifically, users input basic production information and emotional data using devices such as smartphones, smart glasses, and head-mounted displays. This basic information includes the purpose of production, schedule, required resources, materials used, and deadline. Emotional data represents psychological information such as the user's emotional state, stress level, and motivation.

[0333] Input data is sent from the terminal to the server. The server collects past project performance data and human resource information from the database and performs preprocessing. Preprocessing includes imputing missing values ​​and normalizing the data, thereby formatting it into a format that can be applied to the generated AI model.

[0334] The server inputs pre-processed data and user input data into a generative AI model to estimate production time and required human resources. This generative AI model is trained using machine learning and deep learning techniques, and makes highly accurate estimates based on historical data. The estimation results are stored on the server as structured data and sent to the user's terminal.

[0335] Furthermore, the server receives progress data in real time and generates new estimates by re-running the AI ​​model based on this data. These new estimates and resource allocation suggestions are sent to the terminal, taking sentiment data into account, and the user can then modify the production plan based on them.

[0336] The hardware used includes smartphones (e.g., iOS, Android®), smart glasses (e.g., Google® Glass®), and head-mounted displays (e.g., HoloLens®). The software used includes Python, scikit-learn, Pandas, and Numpy. This system can provide highly accurate estimates and resource allocation suggestions based on generative AI models, and by considering user emotions, it enables more flexible and efficient production management.

[0337] As a concrete example, the user receives a prompt message stating, "Please enter the following basic production information: schedule of 5 weeks, resources of 10 people, and emotional data: joy 0.1, stress 0.4." Based on the data entered according to this prompt, the system automatically performs an estimate and provides a suggestion for the optimal resource allocation.

[0338] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0339] Step 1:

[0340] Users input basic production information and emotional data using a device (such as a smartphone, smart glasses, or head-mounted display). Specifically, users input the production objective, schedule, required resources, materials used, and emotional data (joy, stress, motivation, etc.). Based on this input information, the device sends the data to the server.

[0341] Input: Basic production information, emotion data

[0342] Output: Input data sent to the server

[0343] Step 2:

[0344] When data sent from a terminal arrives at the server, the server retrieves past project performance data and human resource information from the database. This collected data includes past production information, resource allocation, and progress data.

[0345] Input: Input data that arrived on the server

[0346] Output: Collected historical performance data and human resource information

[0347] Step 3:

[0348] The server preprocesses the collected data. Specifically, it imputes missing values ​​and normalizes the data. In this process, it also formats the sentiment data into a format that can be applied to the model.

[0349] Input: Collected historical performance data, human resource information, and sentiment data.

[0350] Output: Preprocessed data

[0351] Step 4:

[0352] Based on pre-processed data and user input data, the server inputs this data into a generative AI model. The generative AI model, having learned from historical data, predicts and estimates production time and required human resources from the new data.

[0353] Input: Pre-processed data, user-input data

[0354] Output: Estimate results (production period, required resources)

[0355] Step 5:

[0356] The quotation results are stored on the server as structured data and sent to the terminal. The terminal displays the received quotation results to the user, who then uses this information to plan production.

[0357] Input: Quotation result (production period, required resources)

[0358] Output: Estimated result displayed on the user's terminal

[0359] Step 6:

[0360] During project progress, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to understand the progress, compare it to the estimated data, and update it. The generative AI model is then rerun to generate new estimates and propose resource allocation.

[0361] Input: Progress data, sentiment data

[0362] Output: New estimate results, resource allocation proposals

[0363] Step 7:

[0364] The updated estimate results and resource allocation proposals are sent to the terminal. The terminal displays them to the user, who can modify the production plan as needed.

[0365] Input: New quote results, resource allocation proposals

[0366] Output: New estimate results and resource allocation proposals displayed on the terminal.

[0367] Example of a prompt:

[0368] "For basic production information, please enter a schedule of 5 weeks, 10 resources, and emotional data of joy 0.1 and stress 0.4."

[0369] 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.

[0370] 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.

[0371] 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.

[0372] [Second Embodiment]

[0373] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0374] 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.

[0375] 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).

[0376] 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.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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".

[0385] This invention provides a system for streamlining project management in the construction industry, where users input basic project information from a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources.

[0386] First, the user uses a terminal to enter basic project information. This information includes requirements such as the project name, construction area, materials to be used, and deadline. The terminal then sends this information to the server.

[0387] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. The server then inputs the preprocessed data and user input data into a generated AI model.

[0388] The generative AI model operates to estimate the project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[0389] The server sends the estimate results to the terminal, providing the data to the user. The user can then review the estimate results through the terminal and plan the project.

[0390] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the terminal. Users can review these and modify the project plan as needed.

[0391] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0392] As a concrete example, consider a small to medium-sized construction company that has received a contract for a new building construction project. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0393] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[0394] In this way, this system achieves efficiency and rationalization of project management in the construction industry and promotes legal and efficient work style reforms.

[0395] The following describes the processing flow.

[0396] Step 1:

[0397] The user uses a terminal to enter basic project information (e.g., project name, construction area, materials used, deadline, etc.).

[0398] Step 2:

[0399] The terminal sends the entered project requirements to the server.

[0400] Step 3:

[0401] The server retrieves past project performance data and human resource information from the database.

[0402] Step 4:

[0403] The server preprocesses the collected data, including imputing missing values ​​and formatting the data.

[0404] Step 5:

[0405] The server inputs pre-processed data and project requirements data from users into the generated AI model.

[0406] Step 6:

[0407] The generative AI model estimates the project duration and the required human resources.

[0408] Step 7:

[0409] The server stores the estimation results as structured data.

[0410] Step 8:

[0411] The server sends the estimate result to the terminal.

[0412] Step 9:

[0413] The terminal displays the estimate result to the user.

[0414] Step 10:

[0415] Users periodically input project progress into their terminals and send it to the server.

[0416] Step 11:

[0417] The server compares real-time progress data with estimated data and updates the progress status.

[0418] Step 12:

[0419] The server reruns the generated AI model and produces new estimation results.

[0420] Step 13:

[0421] The server generates a new resource allocation proposal and sends it to the terminal.

[0422] Step 14:

[0423] The terminal displays new quotes and resource allocation suggestions to the user.

[0424] Step 15:

[0425] After completing a project, the user inputs the actual project data and feedback data into their device and sends it to the server.

[0426] Step 16:

[0427] The server collects feedback data and stores it as training data for the generated AI model.

[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 smart glasses 214 will be referred to as the "terminal".

[0430] Traditionally, project management in the construction industry has often been done manually, leading to inefficiencies in project progress tracking and human resource estimation. Furthermore, it has been difficult to respond quickly based on real-time progress or to make highly accurate estimates based on historical data. This has resulted in project delays and shortages or surpluses of human resources, ultimately leading to increased overall project costs and time.

[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 a user to input basic project information from a terminal, means for transmitting the inputted basic information to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting the basic project information and preprocessed data into a generating AI model to estimate the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient management and accurate human resource estimation during project progress.

[0433] A "user" is someone who operates the system, inputs basic project information, and provides progress data and feedback data.

[0434] A "terminal" is a device used by the user to input basic project information, progress data, and feedback data, and to communicate with the server.

[0435] A "server" is a central computer system that collects and preprocesses data from a database, performs estimations using a generated AI model, and stores and transmits the results.

[0436] "Basic project information" refers to information required in the initial stages of a project, such as the project name, construction area, materials to be used, and deadline.

[0437] A "database" is a system that stores and manages past project performance data and human resource information.

[0438] "Preprocessing" refers to the preparatory work involved in filling in missing values ​​and formatting data collected from a database, in order to input it into the generated AI model.

[0439] A "generative AI model" is a model trained using machine learning and deep learning technologies to accurately estimate project duration and required human resources.

[0440] "Structured data" refers to data in a systematically organized format when a server stores estimation results.

[0441] "Progress data" refers to data that shows the actual progress of an ongoing project.

[0442] A "resource allocation proposal" is a suggestion regarding the allocation of human resources to optimize project progress, based on the estimation results calculated by the generative AI model.

[0443] "Post-project feedback data" refers to actual project data and feedback information regarding areas for improvement collected after a project is completed.

[0444] This invention is a system for streamlining project management in the construction industry. This system optimizes project progress by allowing users to input basic project information via a terminal, and then having a server collect, process, and analyze that information. Specific embodiments are described below.

[0445] First, the user enters basic project information using a terminal. This basic information includes the project name, construction area, materials to be used, and deadline. This information is entered using dedicated software and sent from the terminal to the server.

[0446] Based on the received basic information, the server collects past project performance data and human resource information from the database. The collected data undergoes preprocessing, such as imputing missing values ​​and formatting the data. Data cleaning tools and ETL (Extract, Transform, Load) tools are often used for this purpose.

[0447] Based on the pre-processed data and user input data, the server runs a generative AI model. This generative AI model is trained on past project data and can estimate project duration and required human resources with high accuracy. Machine learning and deep learning techniques are used in the generative AI model.

[0448] During the estimation process, the following prompt statements are input to the generating AI model:

[0449] Project name: New building construction, Construction area: 2000m 2 Please estimate the necessary human resources and timeframe, given the materials used are concrete and the deadline is 12 months.

[0450] The generated estimate results are stored as structured data on the server. The server sends this data to the terminal, and the user checks the estimate results through the terminal.

[0451] During project progress, users periodically input progress data into their terminals and send it to the server. The server uses this progress data to compare it with estimation data and reruns the AI ​​model to generate new estimation results and resource allocation suggestions. For example, if the data indicates that "the current number of workers is 15 and the progress rate is 50%", a suggestion of "5 additional workers are needed" might be generated.

[0452] After project completion, users input actual project data and feedback data using their devices and send it to the server. The server collects this data and stores it as training data for the generative AI model. This improves the accuracy of the generative AI model, leading to even greater accuracy in future estimates.

[0453] In this way, this system streamlines and rationalizes project management in the construction industry, supporting accurate estimations and optimal resource allocation.

[0454] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0455] Step 1:

[0456] The user uses a terminal to enter basic project information (project name, construction area, materials used, deadline, etc.). The terminal has a dedicated input form, and the user enters the information according to this form. The entered basic information is sent from the terminal to the server. This operation completes the initial setup of the project.

[0457] Input: Basic project information (project name, construction area, materials used, deadline, etc.)

[0458] Output: Basic project information is sent to the server.

[0459] Step 2:

[0460] The server receives the entered basic information and retrieves past project performance data and human resource information from the database. It then performs preprocessing on the collected data, specifically including imputing missing values ​​and formatting the data. This process converts the data into an appropriate format for input into the generated AI model.

[0461] Input: Basic information, past project performance data, human resource information

[0462] Output: Preprocessed data

[0463] Step 3:

[0464] The server inputs pre-processed data and basic information entered by the user into the generating AI model. Prompts are used to instruct the generating AI model to estimate the project duration and required human resources. For example, "Project name: New building construction, construction area: 2000m²" 2 A prompt message such as "Materials used: concrete, deadline: 12 months, please estimate the necessary human resources and timeframe" is input to the generated AI model.

[0465] Input: Preprocessed data, basic information, prompt message

[0466] Output: Estimated project duration and required human resources.

[0467] Step 4:

[0468] The server saves the estimation results, which are the output of the generated AI model, as structured data. The estimation results are saved in a format such as "Construction of this building will take 6 months and require 20 workers." The saved data will be referenced and updated later.

[0469] Input: Estimate Result

[0470] Output: Saved as structured data

[0471] Step 5:

[0472] The server sends the saved estimate results to the terminal. The terminal displays the estimate results to the user. The user reviews these results and uses them to plan the project.

[0473] Input: Estimate results as structured data

[0474] Output: Estimated result displayed on the terminal

[0475] Step 6:

[0476] Users periodically input progress data into their terminals and send it to the server during project execution. For example, they might input data such as "Current number of workers: 15, progress rate: 50%." This allows for real-time monitoring of the project's status.

[0477] Input: Progress data (number of workers, progress rate, etc.)

[0478] Output: Progress data sent to the server

[0479] Step 7:

[0480] The server compares the received progress data with the estimated data and reruns the generated AI model as needed. This generates new estimated results and resource allocation suggestions. For example, it might generate a suggestion such as "5 additional workers are needed."

[0481] Input: Progress data, historical estimate data

[0482] Output: New estimate results and resource allocation proposals

[0483] Step 8:

[0484] The server sends the new estimate and resource allocation proposal to the terminal. The terminal displays this for the user to review. The user then modifies the project plan based on this proposal.

[0485] Input: New estimate results and resource allocation proposals

[0486] Output: New estimate results and resource allocation proposals displayed on the terminal.

[0487] Step 9:

[0488] After project completion, users input actual project data and feedback data into their devices and send it to the server. This includes detailed information about project progress and human resource utilization.

[0489] Input: Actual project data, feedback data

[0490] Output: Feedback data sent to the server

[0491] Step 10:

[0492] The server stores the received feedback data as training data for the generating AI model. This improves the model's accuracy, leading to even higher estimation accuracy in subsequent iterations.

[0493] Input: Feedback data

[0494] Output: Stored as training data

[0495] (Application Example 1)

[0496] 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."

[0497] Manufacturing projects in a factory environment require numerous processes and human resources, making their management extremely complex. In particular, understanding project progress, appropriately allocating resources, and adjusting plans according to progress are crucial and must be done efficiently. However, current systems often struggle to meet these requirements, resulting in inefficiencies. Therefore, this invention aims to solve these problems and improve the efficiency and accuracy of manufacturing project management in a factory environment.

[0498] 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.

[0499] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, and means for managing the progress of a manufacturing project in a factory environment in real time and estimating the necessary work processes and resource allocation. This enables more efficient project management and flexible resource management according to the progress status.

[0500] "Basic project information" refers to project requirements such as project name, area, materials used, and deadline, which are entered by the user via their device.

[0501] A "terminal" refers to a device that a user uses to input and verify information related to a project.

[0502] A "server" refers to a device that receives basic project information, collects necessary information from a database, and generates estimation results by executing a generated AI model.

[0503] A "database" refers to a data storage system that contains past project performance data and human resource information.

[0504] "Past project performance data" refers to data related to projects that have been carried out in the past, including project duration and resources used.

[0505] "Human resource information" refers to information about the number of workers required for a project and their skill sets.

[0506] "Preprocessing" refers to the process of preparing data before analysis, such as imputing missing values ​​and formatting the data.

[0507] A "generative AI model" refers to an algorithm that uses machine learning and deep learning techniques to estimate project duration and the necessary human resources.

[0508] "Project duration" refers to the period from the start to the end of a project.

[0509] "Required human resources" refers to the number of workers and their skill sets needed to complete the project.

[0510] "Estimate results" refer to data regarding the project duration and required human resources calculated by the generative AI model.

[0511] "Structured data" refers to data where estimation results are presented in an organized format, making it easy to process using computer systems.

[0512] "Progress data" refers to data related to the progress of a project during its operation.

[0513] "Resource allocation proposal" refers to a proposal for new human resources for project execution, generated as a result of re-running the generated AI model.

[0514] "Factory environment" refers to the physical location where work is carried out to manufacture products, as well as the surrounding conditions.

[0515] A "manufacturing project" refers to a series of tasks and their management required to produce a specific product.

[0516] This invention is a system for streamlining manufacturing project management in a factory environment. The following describes how to implement this system in detail.

[0517] The user first uses a terminal to enter basic project information. This information includes the project name, area, materials used, and deadline. This information is then sent from the terminal to the server. Common devices such as personal computers and tablets are used as terminals.

[0518] The server retrieves past project performance data and human resource information from the database based on the basic information of the received project, and performs preprocessing. Preprocessing includes imputing missing values ​​and formatting the data. Relational databases such as SQLite and MySQL are used as the database.

[0519] Based on pre-processed data, the server supplies input data to the generative AI model. The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources with high accuracy. Specifically, machine learning frameworks such as scikit-learn's RandomForestRegressor and TensorFlow are used.

[0520] The estimation results are stored on the server as structured data and sent to the terminal. Users can then review the estimation results and plan their projects through the terminal.

[0521] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. New resource allocation suggestions are also generated and sent to the terminal. Users review these and revise the project plan as needed.

[0522] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0523] As a concrete example, consider a project in which a factory is building a new product line. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "building this product line will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0524] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[0525] Through the above process, this system achieves increased efficiency and streamlining of manufacturing project management in a factory environment.

[0526] Examples of prompt statements are as follows:

[0527] Project Name: New Product Line Development

[0528] Construction area: 500

[0529] Materials used: Iron, plastic

[0530] Delivery date: 2024-12-31

[0531] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0532] Step 1:

[0533] The user enters basic project information from their device. This basic information includes project name, area, materials used, and deadline. The entered data is temporarily stored on the device.

[0534] Step 2:

[0535] The terminal sends the entered project information to the server. Secure communication protocols such as HTTPS are used for data transmission. The transmitted data is received on the server side.

[0536] Step 3:

[0537] Based on the received project basic information, the server retrieves past project performance data and human resource information from the database. During this process, it uses SQL queries to extract the necessary data.

[0538] Step 4:

[0539] The server preprocesses the collected data. Specifically, it performs data imputation and formatting. The Python pandas library is used for preprocessing. The preprocessed data is then converted into a format suitable for estimation.

[0540] Step 5:

[0541] Based on pre-processed data and user-submitted project basic information, the server inputs data into a generated AI model. This model uses machine learning techniques to estimate project duration and required human resources. The software used includes scikit-learn's RandomForestRegressor and TensorFlow.

[0542] Step 6:

[0543] The generative AI model analyzes user-provided input data to predict project duration and required human resources. The prediction results are stored on the server as structured data.

[0544] Step 7:

[0545] The server sends the generated estimate results to the terminal. The user can then review the estimate results through the terminal and plan the project.

[0546] Step 8:

[0547] During project execution, users periodically input progress data into their terminals and send it to the server. The transmitted progress data is received by the server and stored in a database.

[0548] Step 9:

[0549] The server compares progress data with estimated data and reruns the generating AI model to produce new estimates. This enables real-time optimization of resource allocation.

[0550] Step 10:

[0551] The server sends the updated estimate and resource allocation proposal to the terminal. The user can review the new proposal and revise the project plan.

[0552] Step 11:

[0553] After the project is completed, the user inputs the actual project data and feedback data into their device and sends it to the server. This data is received by the server and stored in a database.

[0554] Step 12:

[0555] The server stores collected actual project data and feedback data as training data for the generated AI model. This allows for improved accuracy in future estimations.

[0556] 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.

[0557] This invention provides a system for streamlining project management in the construction industry. It allows users to input basic project information via a terminal, and a server uses this information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[0558] First, the user uses a terminal to enter basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. The user's emotional data is also obtained through an emotional engine. The terminal then sends this information to the server.

[0559] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. Furthermore, sentiment data is formatted into a format that can be applied to the model. The server then inputs the preprocessed data and user input data (including sentiment data) into the generated AI model.

[0560] The generative AI model operates to estimate project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[0561] The server sends the estimate results to the terminal, providing the data to the user. The terminal presents the user's sentiment data along with the estimate results, allowing the user to plan the project based on this information.

[0562] During project progress, users periodically input progress and sentiment data into their devices and send it to the server. The server compares this progress data with estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the device. The device displays resource allocation suggestions that take sentiment data into account to the user, who can then modify the project plan based on these suggestions.

[0563] After project completion, users input actual project data, feedback data, and sentiment data into their devices and send them to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0564] As a concrete example, consider a small to medium-sized construction company that has won a contract for a new building construction project. The user inputs basic project information from a terminal, and emotional data is also acquired through an emotion engine and sent to a server. The server collects data from similar past projects and performs preprocessing. Then, using a generative AI model and emotional data, it generates an estimate result stating, "Construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0565] During project progress, users input weekly progress and sentiment data from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. The terminal displays the new estimate and resource allocation suggestions, including sentiment data, to the user, who then modifies the plan based on this information.

[0566] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reforms. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The user uses a device to input basic project information (e.g., project name, construction area, materials used, deadline, etc.). The emotion engine recognizes the user's emotions in real time as they input the information and collects that data as well.

[0570] Step 2:

[0571] The terminal sends the entered project requirements and sentiment data to the server.

[0572] Step 3:

[0573] The server retrieves past project performance data and human resource information from the database. Furthermore, it also retrieves collected sentiment data.

[0574] Step 4:

[0575] The server preprocesses the collected data, including imputing missing values ​​and formatting the data. Sentiment data is also converted into a format suitable for application to the model.

[0576] Step 5:

[0577] The server inputs pre-processed data and project requirements data from users (including sentiment data) into the generating AI model.

[0578] Step 6:

[0579] The generative AI model estimates the project duration and the required human resources. This estimation also takes emotional data into consideration.

[0580] Step 7:

[0581] The server stores the estimation results as structured data.

[0582] Step 8:

[0583] The server sends the estimation results and sentiment data to the terminal.

[0584] Step 9:

[0585] The device displays the estimate results and sentiment data to the user. The user then uses this information to plan the project.

[0586] Step 10:

[0587] During project progress, users periodically input progress data and emotional data into their devices. The emotional engine recognizes the user's emotional data in real time and sends it to the server as well.

[0588] Step 11:

[0589] The server updates the progress status by comparing real-time progress and sentiment data with estimated data.

[0590] Step 12:

[0591] The server reruns the generated AI model and produces new estimates and resource allocation suggestions, taking sentiment data into consideration.

[0592] Step 13:

[0593] The server sends the new estimate and resource allocation proposal to the terminal.

[0594] Step 14:

[0595] The device displays new estimate results and sentiment data to the user. The user then modifies the project plan based on this information.

[0596] Step 15:

[0597] After the project is completed, the user inputs actual project data, feedback data, and sentiment data into their device and sends it to the server. The sentiment engine also collects the final sentiment data.

[0598] Step 16:

[0599] The server collects feedback and sentiment data and stores it as training data for the generative AI model. This improves the model's accuracy and increases the accuracy of future estimates.

[0600] (Example 2)

[0601] 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".

[0602] In the construction industry, streamlining and improving the efficiency of project management is a critical challenge. In particular, there is a need for appropriate allocation of human resources and the ability to respond to real-time changes in the project's progress. Furthermore, there is a lack of project management methods that consider the stress and motivation of project managers, making flexible estimation and resource allocation based on human emotional data a difficult challenge.

[0603] 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.

[0604] In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements and sentiment data to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing such as imputing missing values ​​and formatting the data, means for inputting the preprocessed project requirements data and sentiment data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data and sentiment data in real time, updating them by comparing them with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient and flexible project management. Furthermore, by reflecting the user's sentiment data in project management, it becomes possible to achieve optimal resource allocation that takes stress and motivation into consideration.

[0605] A "terminal" is an electronic device used by users to input basic project information, progress data, and sentiment data, and to communicate with the server.

[0606] A "server" is a central management system that receives data sent from terminals, collects information from a database, performs preprocessing, calculates estimates using a generated AI model, and sends the results to the terminals.

[0607] "Project basic information" refers to key project requirements such as project name, construction area, materials used, and deadline, which are entered by the user via their device.

[0608] "Emotional data" refers to data that indicates the user's emotional state (e.g., stress level and motivation), and is acquired by the emotion engine.

[0609] A "generative AI model" is an artificial intelligence model trained using machine learning and deep learning techniques, and is used to estimate project duration and the human resources required.

[0610] "Preprocessing" refers to the process of imputing missing values ​​and formatting data collected from a database.

[0611] "Estimate" refers to the project duration and the predicted human resources required, calculated using a generative AI model.

[0612] "Structured data" refers to data, including estimation results, that has been formatted into a specified format and stored in a way that facilitates subsequent processing and analysis.

[0613] "Progress data" refers to data that shows the progress of a project, and users periodically input it from their devices.

[0614] "Feedback data" refers to data about actual project results and emotional states entered by users after project completion, and is used to improve the accuracy of the generative AI model.

[0615] A "resource allocation proposal" is a specific allocation plan for the necessary human resources calculated by a generative AI model.

[0616] A "database" is a system used to record and manage past project performance data and human resource information.

[0617] This invention is a system for streamlining project management in the construction industry. It provides a process where users input basic project information via a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[0618] First, the user uses a terminal to input basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. Furthermore, the terminal has an emotion engine built in that analyzes the user's facial expressions and tone of voice to obtain emotion data. This data is then sent from the terminal to the server.

[0619] The server collects past project performance data and human resource information from the database. This collected data is preprocessed using scripts such as Python. Specifically, missing values ​​are imputed and the data is formatted, and sentiment data is also formatted into a format that can be applied to the generative AI model. After that, the preprocessed data and user input data (including sentiment data) are input to the generative AI model as prompt messages.

[0620] The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources. It leverages historical project data to provide highly accurate estimates. GPT-4 and other advanced generative AI models are used for this purpose. The generated estimate results are stored on a server as structured data.

[0621] The server sends the estimate result to the terminal, which then provides the user with the estimate result and sentiment data. The user can then use this information to plan their project.

[0622] As the project progresses, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to compare with the estimated data, reruns the AI ​​model, and generates new estimates. This also generates resource allocation suggestions that adapt to changes in the project's progress and sends them to the device.

[0623] After project completion, users input actual project data, feedback data, and sentiment data from their devices and send them to the server. The server stores this feedback data as training data for the generating AI model, thereby improving the model's accuracy and further enhancing the accuracy of future estimates.

[0624] As a concrete example, consider a case where a small to medium-sized construction company receives a contract for a new building construction project. The user enters the basic project information as follows:

[0625] Project Name: New Company Building Construction Project

[0626] Construction area: 2000 square meters

[0627] Materials used: Concrete, rebar, glass

[0628] Delivery time: 12 months

[0629] The emotion engine determines that the user's stress level is "high." This information and emotion data are sent from the terminal to the server. The server collects and preprocesses data from similar past projects. Then, using the generative AI model and emotion data, it generates an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0630] During project progress, users input weekly progress and emotional data such as "Stress Level: Medium," and send it to the server. Based on this data, the server readjusts the estimate and generates new resource allocation suggestions, such as "5 additional workers are needed," and sends them to the terminal. The terminal displays this to the user, who then modifies the plan based on it.

[0631] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reform. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[0632] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0633] Step 1:

[0634] The user uses a terminal to input basic project information. This information includes the project name, construction area, materials used, and deadline. A specific example of input might be: "Project Name: New Company Building Construction Project," "Construction Area: 2000 square meters," "Materials Used: Concrete, rebar, glass," and "Deadline: 12 months." In addition, the emotion engine retrieves the user's stress level. Possible emotion data inputs might include "Stress Level: High." This data is sent to the terminal as input.

[0635] Step 2:

[0636] The terminal sends the project basic information and sentiment data entered by the user to the server. A secure communication protocol (e.g., HTTPS) is used for this transmission. As output after transmission, the project basic information and sentiment data are packetized and arrive at the server.

[0637] Step 3:

[0638] The server collects past project performance data and human resource information from the database. For example, data on "construction projects of 2000 square meters over the past five years" is collected. Database queries (SQL queries) are performed as input, and raw project data and human resource information are obtained as output.

[0639] Step 4:

[0640] The server begins preprocessing the collected data. This preprocessing includes imputing missing values ​​(e.g., imputing with the mean) and formatting the data (e.g., converting to numerical data). Furthermore, sentiment data is also formatted into a format that can be applied to the generative AI model. Specifically, preprocessing is performed using a Python script. The input is the raw data obtained in step 3, and the output is the preprocessed project data and sentiment data.

[0641] Step 5:

[0642] The server inputs pre-processed data and user input data (including sentiment data) as prompts into a generative AI model. The generative AI model (e.g., GPT-4) then runs machine learning algorithms to predict project duration and required human resources. For example, prompts like the following might be used:

[0643] Project Name: New Company Building Construction Project

[0644] Construction area: 2000 square meters

[0645] Materials used: Concrete, rebar, glass

[0646] Delivery time: 12 months

[0647] User stress level: High

[0648] Based on the input prompt, the model performs calculations and generates an estimated result of "6 months, 20 workers" as output.

[0649] Step 6:

[0650] The server stores the generated estimate results as structured data and sends it to the terminal. This transmitted data includes an estimate result such as "6 months, 20 workers." After receiving it, the terminal displays the estimate result and sentiment data to the user. This allows the user to see the specific estimate result.

[0651] Step 7:

[0652] While the project is underway, users periodically input progress and emotional data through their devices and send this data to the server. For example, data such as "Progress Rate: 50%" and "Stress Level: Medium" might be entered. The device packets this data and sends it to the server.

[0653] Step 8:

[0654] The server reruns the generating AI model to recalculate the estimation data based on progress and sentiment data. New estimation results and resource allocation suggestions are generated, such as a suggestion that "five additional workers are needed." These new estimation results are stored on the server and sent to the terminal. The terminal displays this new data to the user, who can then modify the project plan based on it.

[0655] Step 9:

[0656] After the project is completed, the user inputs actual project results, feedback data, and sentiment data from their device and sends them to the server. For example, data such as the actual project duration being "7 months" or the worker's stress level being "ultimately low" might be input. The server stores this data as training data in the generating AI model to improve the accuracy of future estimates.

[0657] (Application Example 2)

[0658] 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."

[0659] Traditional project management systems made it cumbersome to input basic project information and progress data, making real-time updates and optimal resource allocation suggestions difficult. Furthermore, they failed to consider user emotions and motivations, hindering efficient project progress. This resulted in project delays and wasted resources.

[0660] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generation AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, updating it by comparing it with the estimation data, and re-executing the generation AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, means including an emotion engine that collects emotion data and reflects it in project management, and means for formatting the emotion data and applying it to the generation AI model. This enables real-time estimation and resource allocation proposals based on basic project information and progress data. Furthermore, flexible and efficient project management that takes user emotions into consideration can be realized.

[0661] "Basic project information" refers to data that forms the foundation for project progress, such as the project name, construction area, materials to be used, and deadline.

[0662] "Terminal" is a general term for devices used by users for input, and includes smartphones, tablets, and personal computers.

[0663] A "server" is a central computer system used to collect, process, store, and communicate with other devices.

[0664] A "database" is a digital storage device used to store past project performance data, human resource information, and other similar information.

[0665] "Preprocessing" is the process of shaping raw data into a format that can be input into a generating AI model, through methods such as imputing missing values ​​and normalization.

[0666] A "generative AI model" is an artificial intelligence model that learns from past data and uses new data to predict and estimate the duration and resources required for a project.

[0667] "Structured data" refers to data organized into a specific format, such as quotation results or resource allocation proposals.

[0668] A "resource allocation proposal" is a plan that proposes the optimal allocation of human resources based on the progress of the project.

[0669] "Emotional data" refers to data that shows psychological information such as a user's emotions, stress levels, and motivation.

[0670] An "emotion engine" is a system that collects and analyzes user emotional data and incorporates it into project management.

[0671] "Progress data" refers to data that shows the current progress of a project, and includes actual work progress and achievement levels.

[0672] This invention is a system for streamlining production process management in factories. This system allows users to input basic production information and progress data from a terminal, and processes this data on a server to automatically generate production schedule estimates and resource allocation suggestions. Furthermore, by collecting user sentiment data and incorporating it into a generated AI model, it achieves more efficient and flexible production management.

[0673] Specifically, users input basic production information and emotional data using devices such as smartphones, smart glasses, and head-mounted displays. This basic information includes the purpose of production, schedule, required resources, materials used, and deadline. Emotional data represents psychological information such as the user's emotional state, stress level, and motivation.

[0674] Input data is sent from the terminal to the server. The server collects past project performance data and human resource information from the database and performs preprocessing. Preprocessing includes imputing missing values ​​and normalizing the data, thereby formatting it into a format that can be applied to the generated AI model.

[0675] The server inputs pre-processed data and user input data into a generative AI model to estimate production time and required human resources. This generative AI model is trained using machine learning and deep learning techniques, and makes highly accurate estimates based on historical data. The estimation results are stored on the server as structured data and sent to the user's terminal.

[0676] Furthermore, the server receives progress data in real time and generates new estimates by re-running the AI ​​model based on this data. These new estimates and resource allocation suggestions are sent to the terminal, taking sentiment data into account, and the user can then modify the production plan based on them.

[0677] The hardware used includes smartphones (e.g., iOS, Android), smart glasses (e.g., Google Glass), and head-mounted displays (e.g., HoloLens). The software used includes Python, scikit-learn, Pandas, and Numpy. This system can provide highly accurate estimates and resource allocation suggestions based on generative AI models, and by considering user sentiment, it enables more flexible and efficient production management.

[0678] As a concrete example, the user receives a prompt message stating, "Please enter the following basic production information: schedule of 5 weeks, resources of 10 people, and emotional data: joy 0.1, stress 0.4." Based on the data entered according to this prompt, the system automatically performs an estimate and provides a suggestion for the optimal resource allocation.

[0679] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0680] Step 1:

[0681] Users input basic production information and emotional data using a device (such as a smartphone, smart glasses, or head-mounted display). Specifically, users input the production objective, schedule, required resources, materials used, and emotional data (joy, stress, motivation, etc.). Based on this input information, the device sends the data to the server.

[0682] Input: Basic production information, emotion data

[0683] Output: Input data sent to the server

[0684] Step 2:

[0685] When data sent from a terminal arrives at the server, the server retrieves past project performance data and human resource information from the database. This collected data includes past production information, resource allocation, and progress data.

[0686] Input: Input data that arrived on the server

[0687] Output: Collected historical performance data and human resource information

[0688] Step 3:

[0689] The server preprocesses the collected data. Specifically, it imputes missing values ​​and normalizes the data. In this process, it also formats the sentiment data into a format that can be applied to the model.

[0690] Input: Collected historical performance data, human resource information, and sentiment data.

[0691] Output: Preprocessed data

[0692] Step 4:

[0693] Based on pre-processed data and user input data, the server inputs this data into a generative AI model. The generative AI model, having learned from historical data, predicts and estimates production time and required human resources from the new data.

[0694] Input: Pre-processed data, user-input data

[0695] Output: Estimate results (production period, required resources)

[0696] Step 5:

[0697] The quotation results are stored on the server as structured data and sent to the terminal. The terminal displays the received quotation results to the user, who then uses this information to plan production.

[0698] Input: Quotation result (production period, required resources)

[0699] Output: Estimated result displayed on the user's terminal

[0700] Step 6:

[0701] During project progress, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to understand the progress, compare it to the estimated data, and update it. The generative AI model is then rerun to generate new estimates and propose resource allocation.

[0702] Input: Progress data, sentiment data

[0703] Output: New estimate results, resource allocation proposals

[0704] Step 7:

[0705] The updated estimate results and resource allocation proposals are sent to the terminal. The terminal displays them to the user, who can modify the production plan as needed.

[0706] Input: New quote results, resource allocation proposals

[0707] Output: New estimate results and resource allocation proposals displayed on the terminal.

[0708] Example of a prompt:

[0709] "For basic production information, please enter a schedule of 5 weeks, 10 resources, and emotional data of joy 0.1 and stress 0.4."

[0710] 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.

[0711] 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.

[0712] 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.

[0713] [Third Embodiment]

[0714] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0715] 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.

[0716] 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).

[0717] 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.

[0718] 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.

[0719] 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).

[0720] 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.

[0721] 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.

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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".

[0726] This invention provides a system for streamlining project management in the construction industry, where users input basic project information from a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources.

[0727] First, the user uses a terminal to enter basic project information. This information includes requirements such as the project name, construction area, materials to be used, and deadline. The terminal then sends this information to the server.

[0728] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. The server then inputs the preprocessed data and user input data into a generated AI model.

[0729] The generative AI model operates to estimate the project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[0730] The server sends the estimate results to the terminal, providing the data to the user. The user can then review the estimate results through the terminal and plan the project.

[0731] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the terminal. Users can review these and modify the project plan as needed.

[0732] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0733] As a concrete example, consider a small to medium-sized construction company that has received a contract for a new building construction project. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0734] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[0735] In this way, this system achieves efficiency and rationalization of project management in the construction industry and promotes legal and efficient work style reforms.

[0736] The following describes the processing flow.

[0737] Step 1:

[0738] The user uses a terminal to enter basic project information (e.g., project name, construction area, materials used, deadline, etc.).

[0739] Step 2:

[0740] The terminal sends the entered project requirements to the server.

[0741] Step 3:

[0742] The server retrieves past project performance data and human resource information from the database.

[0743] Step 4:

[0744] The server preprocesses the collected data, including imputing missing values ​​and formatting the data.

[0745] Step 5:

[0746] The server inputs pre-processed data and project requirements data from users into the generated AI model.

[0747] Step 6:

[0748] The generative AI model estimates the project duration and the required human resources.

[0749] Step 7:

[0750] The server stores the estimation results as structured data.

[0751] Step 8:

[0752] The server sends the estimate result to the terminal.

[0753] Step 9:

[0754] The terminal displays the estimate result to the user.

[0755] Step 10:

[0756] Users periodically input project progress into their terminals and send it to the server.

[0757] Step 11:

[0758] The server compares real-time progress data with estimated data and updates the progress status.

[0759] Step 12:

[0760] The server reruns the generated AI model and produces new estimation results.

[0761] Step 13:

[0762] The server generates a new resource allocation proposal and sends it to the terminal.

[0763] Step 14:

[0764] The terminal displays new quotes and resource allocation suggestions to the user.

[0765] Step 15:

[0766] After completing a project, the user inputs the actual project data and feedback data into their device and sends it to the server.

[0767] Step 16:

[0768] The server collects feedback data and stores it as training data for the generated AI model.

[0769] (Example 1)

[0770] 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."

[0771] Traditionally, project management in the construction industry has often been done manually, leading to inefficiencies in project progress tracking and human resource estimation. Furthermore, it has been difficult to respond quickly based on real-time progress or to make highly accurate estimates based on historical data. This has resulted in project delays and shortages or surpluses of human resources, ultimately leading to increased overall project costs and time.

[0772] 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.

[0773] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the inputted basic information to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting the basic project information and preprocessed data into a generating AI model to estimate the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient management and accurate human resource estimation during project progress.

[0774] A "user" is someone who operates the system, inputs basic project information, and provides progress data and feedback data.

[0775] A "terminal" is a device used by the user to input basic project information, progress data, and feedback data, and to communicate with the server.

[0776] A "server" is a central computer system that collects and preprocesses data from a database, performs estimations using a generated AI model, and stores and transmits the results.

[0777] "Basic project information" refers to information required in the initial stages of a project, such as the project name, construction area, materials to be used, and deadline.

[0778] A "database" is a system that stores and manages past project performance data and human resource information.

[0779] "Preprocessing" refers to the preparatory work involved in filling in missing values ​​and formatting data collected from a database, in order to input it into the generated AI model.

[0780] A "generative AI model" is a model trained using machine learning and deep learning technologies to accurately estimate project duration and required human resources.

[0781] "Structured data" refers to data in a systematically organized format when a server stores estimation results.

[0782] "Progress data" refers to data that shows the actual progress of an ongoing project.

[0783] A "resource allocation proposal" is a suggestion regarding the allocation of human resources to optimize project progress, based on the estimation results calculated by the generative AI model.

[0784] "Post-project feedback data" refers to actual project data and feedback information regarding areas for improvement collected after a project is completed.

[0785] This invention is a system for streamlining project management in the construction industry. This system optimizes project progress by allowing users to input basic project information via a terminal, and then having a server collect, process, and analyze that information. Specific embodiments are described below.

[0786] First, the user enters basic project information using a terminal. This basic information includes the project name, construction area, materials to be used, and deadline. This information is entered using dedicated software and sent from the terminal to the server.

[0787] Based on the received basic information, the server collects past project performance data and human resource information from the database. The collected data undergoes preprocessing, such as imputing missing values ​​and formatting the data. Data cleaning tools and ETL (Extract, Transform, Load) tools are often used for this purpose.

[0788] Based on the pre-processed data and user input data, the server runs a generative AI model. This generative AI model is trained on past project data and can estimate project duration and required human resources with high accuracy. Machine learning and deep learning techniques are used in the generative AI model.

[0789] During the estimation process, the following prompt statements are input to the generating AI model:

[0790] Project name: New building construction, Construction area: 2000m 2 Please estimate the necessary human resources and timeframe, given the materials used are concrete and the deadline is 12 months.

[0791] The generated estimate results are stored as structured data on the server. The server sends this data to the terminal, and the user checks the estimate results through the terminal.

[0792] During project progress, users periodically input progress data into their terminals and send it to the server. The server uses this progress data to compare it with estimation data and reruns the AI ​​model to generate new estimation results and resource allocation suggestions. For example, if the data indicates that "the current number of workers is 15 and the progress rate is 50%", a suggestion of "5 additional workers are needed" might be generated.

[0793] After project completion, users input actual project data and feedback data using their devices and send it to the server. The server collects this data and stores it as training data for the generative AI model. This improves the accuracy of the generative AI model, leading to even greater accuracy in future estimates.

[0794] In this way, this system streamlines and rationalizes project management in the construction industry, supporting accurate estimations and optimal resource allocation.

[0795] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0796] Step 1:

[0797] The user uses a terminal to enter basic project information (project name, construction area, materials used, deadline, etc.). The terminal has a dedicated input form, and the user enters the information according to this form. The entered basic information is sent from the terminal to the server. This operation completes the initial setup of the project.

[0798] Input: Basic project information (project name, construction area, materials used, deadline, etc.)

[0799] Output: Basic project information is sent to the server.

[0800] Step 2:

[0801] The server receives the entered basic information and retrieves past project performance data and human resource information from the database. It then performs preprocessing on the collected data, specifically including imputing missing values ​​and formatting the data. This process converts the data into an appropriate format for input into the generated AI model.

[0802] Input: Basic information, past project performance data, human resource information

[0803] Output: Preprocessed data

[0804] Step 3:

[0805] The server inputs pre-processed data and basic information entered by the user into the generating AI model. Prompts are used to instruct the generating AI model to estimate the project duration and required human resources. For example, "Project name: New building construction, construction area: 2000m²" 2 A prompt message such as "Materials used: concrete, deadline: 12 months, please estimate the necessary human resources and timeframe" is input to the generated AI model.

[0806] Input: Preprocessed data, basic information, prompt message

[0807] Output: Estimated project duration and required human resources.

[0808] Step 4:

[0809] The server saves the estimation results, which are the output of the generated AI model, as structured data. The estimation results are saved in a format such as "Construction of this building will take 6 months and require 20 workers." The saved data will be referenced and updated later.

[0810] Input: Estimate Result

[0811] Output: Saved as structured data

[0812] Step 5:

[0813] The server sends the saved estimate results to the terminal. The terminal displays the estimate results to the user. The user reviews these results and uses them to plan the project.

[0814] Input: Estimate results as structured data

[0815] Output: Estimated result displayed on the terminal

[0816] Step 6:

[0817] Users periodically input progress data into their terminals and send it to the server during project execution. For example, they might input data such as "Current number of workers: 15, progress rate: 50%." This allows for real-time monitoring of the project's status.

[0818] Input: Progress data (number of workers, progress rate, etc.)

[0819] Output: Progress data sent to the server

[0820] Step 7:

[0821] The server compares the received progress data with the estimated data and reruns the generated AI model as needed. This generates new estimated results and resource allocation suggestions. For example, it might generate a suggestion such as "5 additional workers are needed."

[0822] Input: Progress data, historical estimate data

[0823] Output: New estimate results and resource allocation proposals

[0824] Step 8:

[0825] The server sends the new estimate and resource allocation proposal to the terminal. The terminal displays this for the user to review. The user then modifies the project plan based on this proposal.

[0826] Input: New estimate results and resource allocation proposals

[0827] Output: New estimate results and resource allocation proposals displayed on the terminal.

[0828] Step 9:

[0829] After project completion, users input actual project data and feedback data into their devices and send it to the server. This includes detailed information about project progress and human resource utilization.

[0830] Input: Actual project data, feedback data

[0831] Output: Feedback data sent to the server

[0832] Step 10:

[0833] The server stores the received feedback data as training data for the generating AI model. This improves the model's accuracy, leading to even higher estimation accuracy in subsequent iterations.

[0834] Input: Feedback data

[0835] Output: Stored as training data

[0836] (Application Example 1)

[0837] 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."

[0838] Manufacturing projects in a factory environment require numerous processes and human resources, making their management extremely complex. In particular, understanding project progress, appropriately allocating resources, and adjusting plans according to progress are crucial and must be done efficiently. However, current systems often struggle to meet these requirements, resulting in inefficiencies. Therefore, this invention aims to solve these problems and improve the efficiency and accuracy of manufacturing project management in a factory environment.

[0839] 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.

[0840] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, and means for managing the progress of a manufacturing project in a factory environment in real time and estimating the necessary work processes and resource allocation. This enables more efficient project management and flexible resource management according to the progress status.

[0841] "Basic project information" refers to project requirements such as project name, area, materials used, and deadline, which are entered by the user via their device.

[0842] A "terminal" refers to a device that a user uses to input and verify information related to a project.

[0843] A "server" refers to a device that receives basic project information, collects necessary information from a database, and generates estimation results by executing a generated AI model.

[0844] A "database" refers to a data storage system that contains past project performance data and human resource information.

[0845] "Past project performance data" refers to data related to projects that have been carried out in the past, including project duration and resources used.

[0846] "Human resource information" refers to information about the number of workers required for a project and their skill sets.

[0847] "Preprocessing" refers to the process of preparing data before analysis, such as imputing missing values ​​and formatting the data.

[0848] A "generative AI model" refers to an algorithm that uses machine learning and deep learning techniques to estimate project duration and the necessary human resources.

[0849] "Project duration" refers to the period from the start to the end of a project.

[0850] "Required human resources" refers to the number of workers and their skill sets needed to complete the project.

[0851] "Estimate results" refer to data regarding the project duration and required human resources calculated by the generative AI model.

[0852] "Structured data" refers to data where estimation results are presented in an organized format, making it easy to process using computer systems.

[0853] "Progress data" refers to data related to the progress of a project during its operation.

[0854] "Resource allocation proposal" refers to a proposal for new human resources for project execution, generated as a result of re-running the generated AI model.

[0855] "Factory environment" refers to the physical location where work is carried out to manufacture products, as well as the surrounding conditions.

[0856] A "manufacturing project" refers to a series of tasks and their management required to produce a specific product.

[0857] This invention is a system for streamlining manufacturing project management in a factory environment. The following describes how to implement this system in detail.

[0858] The user first uses a terminal to enter basic project information. This information includes the project name, area, materials used, and deadline. This information is then sent from the terminal to the server. Common devices such as personal computers and tablets are used as terminals.

[0859] The server retrieves past project performance data and human resource information from the database based on the basic information of the received project, and performs preprocessing. Preprocessing includes imputing missing values ​​and formatting the data. Relational databases such as SQLite and MySQL are used as the database.

[0860] Based on pre-processed data, the server supplies input data to the generative AI model. The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources with high accuracy. Specifically, machine learning frameworks such as scikit-learn's RandomForestRegressor and TensorFlow are used.

[0861] The estimation results are stored on the server as structured data and sent to the terminal. Users can then review the estimation results and plan their projects through the terminal.

[0862] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. New resource allocation suggestions are also generated and sent to the terminal. Users review these and revise the project plan as needed.

[0863] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0864] As a concrete example, consider a project in which a factory is building a new product line. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "building this product line will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0865] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[0866] Through the above process, this system achieves increased efficiency and streamlining of manufacturing project management in a factory environment.

[0867] Examples of prompt statements are as follows:

[0868] Project Name: New Product Line Development

[0869] Construction area: 500

[0870] Materials used: Iron, plastic

[0871] Delivery date: 2024-12-31

[0872] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0873] Step 1:

[0874] The user enters basic project information from their device. This basic information includes project name, area, materials used, and deadline. The entered data is temporarily stored on the device.

[0875] Step 2:

[0876] The terminal sends the entered project information to the server. Secure communication protocols such as HTTPS are used for data transmission. The transmitted data is received on the server side.

[0877] Step 3:

[0878] Based on the received project basic information, the server retrieves past project performance data and human resource information from the database. During this process, it uses SQL queries to extract the necessary data.

[0879] Step 4:

[0880] The server preprocesses the collected data. Specifically, it performs data imputation and formatting. The Python pandas library is used for preprocessing. The preprocessed data is then converted into a format suitable for estimation.

[0881] Step 5:

[0882] Based on pre-processed data and user-submitted project basic information, the server inputs data into a generated AI model. This model uses machine learning techniques to estimate project duration and required human resources. The software used includes scikit-learn's RandomForestRegressor and TensorFlow.

[0883] Step 6:

[0884] The generative AI model analyzes user-provided input data to predict project duration and required human resources. The prediction results are stored on the server as structured data.

[0885] Step 7:

[0886] The server sends the generated estimate results to the terminal. The user can then review the estimate results through the terminal and plan the project.

[0887] Step 8:

[0888] During project execution, users periodically input progress data into their terminals and send it to the server. The transmitted progress data is received by the server and stored in a database.

[0889] Step 9:

[0890] The server compares progress data with estimated data and reruns the generating AI model to produce new estimates. This enables real-time optimization of resource allocation.

[0891] Step 10:

[0892] The server sends the updated estimate and resource allocation proposal to the terminal. The user can review the new proposal and revise the project plan.

[0893] Step 11:

[0894] After the project is completed, the user inputs the actual project data and feedback data into their device and sends it to the server. This data is received by the server and stored in a database.

[0895] Step 12:

[0896] The server stores collected actual project data and feedback data as training data for the generated AI model. This allows for improved accuracy in future estimations.

[0897] 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.

[0898] This invention provides a system for streamlining project management in the construction industry. It allows users to input basic project information via a terminal, and a server uses this information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[0899] First, the user uses a terminal to enter basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. The user's emotional data is also obtained through an emotional engine. The terminal then sends this information to the server.

[0900] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. Furthermore, sentiment data is formatted into a format that can be applied to the model. The server then inputs the preprocessed data and user input data (including sentiment data) into the generated AI model.

[0901] The generative AI model operates to estimate project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[0902] The server sends the estimate results to the terminal, providing the data to the user. The terminal presents the user's sentiment data along with the estimate results, allowing the user to plan the project based on this information.

[0903] During project progress, users periodically input progress and sentiment data into their devices and send it to the server. The server compares this progress data with estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the device. The device displays resource allocation suggestions that take sentiment data into account to the user, who can then modify the project plan based on these suggestions.

[0904] After project completion, users input actual project data, feedback data, and sentiment data into their devices and send them to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[0905] As a concrete example, consider a small to medium-sized construction company that has won a contract for a new building construction project. The user inputs basic project information from a terminal, and emotional data is also acquired through an emotion engine and sent to a server. The server collects data from similar past projects and performs preprocessing. Then, using a generative AI model and emotional data, it generates an estimate result stating, "Construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0906] During project progress, users input weekly progress and sentiment data from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. The terminal displays the new estimate and resource allocation suggestions, including sentiment data, to the user, who then modifies the plan based on this information.

[0907] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reforms. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[0908] The following describes the processing flow.

[0909] Step 1:

[0910] The user uses a device to input basic project information (e.g., project name, construction area, materials used, deadline, etc.). The emotion engine recognizes the user's emotions in real time as they input the information and collects that data as well.

[0911] Step 2:

[0912] The terminal sends the entered project requirements and sentiment data to the server.

[0913] Step 3:

[0914] The server retrieves past project performance data and human resource information from the database. Furthermore, it also retrieves collected sentiment data.

[0915] Step 4:

[0916] The server preprocesses the collected data, including imputing missing values ​​and formatting the data. Sentiment data is also converted into a format suitable for application to the model.

[0917] Step 5:

[0918] The server inputs pre-processed data and project requirements data from users (including sentiment data) into the generating AI model.

[0919] Step 6:

[0920] The generative AI model estimates the project duration and the required human resources. This estimation also takes emotional data into consideration.

[0921] Step 7:

[0922] The server stores the estimation results as structured data.

[0923] Step 8:

[0924] The server sends the estimation results and sentiment data to the terminal.

[0925] Step 9:

[0926] The device displays the estimate results and sentiment data to the user. The user then uses this information to plan the project.

[0927] Step 10:

[0928] During project progress, users periodically input progress data and emotional data into their devices. The emotional engine recognizes the user's emotional data in real time and sends it to the server as well.

[0929] Step 11:

[0930] The server updates the progress status by comparing real-time progress and sentiment data with estimated data.

[0931] Step 12:

[0932] The server reruns the generated AI model and produces new estimates and resource allocation suggestions, taking sentiment data into consideration.

[0933] Step 13:

[0934] The server sends the new estimate and resource allocation proposal to the terminal.

[0935] Step 14:

[0936] The device displays new estimate results and sentiment data to the user. The user then modifies the project plan based on this information.

[0937] Step 15:

[0938] After the project is completed, the user inputs actual project data, feedback data, and sentiment data into their device and sends it to the server. The sentiment engine also collects the final sentiment data.

[0939] Step 16:

[0940] The server collects feedback and sentiment data and stores it as training data for the generative AI model. This improves the model's accuracy and increases the accuracy of future estimates.

[0941] (Example 2)

[0942] 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."

[0943] In the construction industry, streamlining and improving the efficiency of project management is a critical challenge. In particular, there is a need for appropriate allocation of human resources and the ability to respond to real-time changes in the project's progress. Furthermore, there is a lack of project management methods that consider the stress and motivation of project managers, making flexible estimation and resource allocation based on human emotional data a difficult challenge.

[0944] 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.

[0945] In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements and sentiment data to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing such as imputing missing values ​​and formatting the data, means for inputting the preprocessed project requirements data and sentiment data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data and sentiment data in real time, updating them by comparing them with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient and flexible project management. Furthermore, by reflecting the user's sentiment data in project management, it becomes possible to achieve optimal resource allocation that takes stress and motivation into consideration.

[0946] A "terminal" is an electronic device used by users to input basic project information, progress data, and sentiment data, and to communicate with the server.

[0947] A "server" is a central management system that receives data sent from terminals, collects information from a database, performs preprocessing, calculates estimates using a generated AI model, and sends the results to the terminals.

[0948] "Project basic information" refers to key project requirements such as project name, construction area, materials used, and deadline, which are entered by the user via their device.

[0949] "Emotional data" refers to data that indicates the user's emotional state (e.g., stress level and motivation), and is acquired by the emotion engine.

[0950] A "generative AI model" is an artificial intelligence model trained using machine learning and deep learning techniques, and is used to estimate project duration and the human resources required.

[0951] "Preprocessing" refers to the process of imputing missing values ​​and formatting data collected from a database.

[0952] "Estimate" refers to the project duration and the predicted human resources required, calculated using a generative AI model.

[0953] "Structured data" refers to data, including estimation results, that has been formatted into a specified format and stored in a way that facilitates subsequent processing and analysis.

[0954] "Progress data" refers to data that shows the progress of a project, and users periodically input it from their devices.

[0955] "Feedback data" refers to data about actual project results and emotional states entered by users after project completion, and is used to improve the accuracy of the generative AI model.

[0956] A "resource allocation proposal" is a specific allocation plan for the necessary human resources calculated by a generative AI model.

[0957] A "database" is a system used to record and manage past project performance data and human resource information.

[0958] This invention is a system for streamlining project management in the construction industry. It provides a process where users input basic project information via a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[0959] First, the user uses a terminal to input basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. Furthermore, the terminal has an emotion engine built in that analyzes the user's facial expressions and tone of voice to obtain emotion data. This data is then sent from the terminal to the server.

[0960] The server collects past project performance data and human resource information from the database. This collected data is preprocessed using scripts such as Python. Specifically, missing values ​​are imputed and the data is formatted, and sentiment data is also formatted into a format that can be applied to the generative AI model. After that, the preprocessed data and user input data (including sentiment data) are input to the generative AI model as prompt messages.

[0961] The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources. It leverages historical project data to provide highly accurate estimates. GPT-4 and other advanced generative AI models are used for this purpose. The generated estimate results are stored on a server as structured data.

[0962] The server sends the estimate result to the terminal, which then provides the user with the estimate result and sentiment data. The user can then use this information to plan their project.

[0963] As the project progresses, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to compare with the estimated data, reruns the AI ​​model, and generates new estimates. This also generates resource allocation suggestions that adapt to changes in the project's progress and sends them to the device.

[0964] After project completion, users input actual project data, feedback data, and sentiment data from their devices and send them to the server. The server stores this feedback data as training data for the generating AI model, thereby improving the model's accuracy and further enhancing the accuracy of future estimates.

[0965] As a concrete example, consider a case where a small to medium-sized construction company receives a contract for a new building construction project. The user enters the basic project information as follows:

[0966] Project Name: New Company Building Construction Project

[0967] Construction area: 2000 square meters

[0968] Materials used: Concrete, rebar, glass

[0969] Delivery time: 12 months

[0970] The emotion engine determines that the user's stress level is "high." This information and emotion data are sent from the terminal to the server. The server collects and preprocesses data from similar past projects. Then, using the generative AI model and emotion data, it generates an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[0971] During project progress, users input weekly progress and emotional data such as "Stress Level: Medium," and send it to the server. Based on this data, the server readjusts the estimate and generates new resource allocation suggestions, such as "5 additional workers are needed," and sends them to the terminal. The terminal displays this to the user, who then modifies the plan based on it.

[0972] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reform. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[0973] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0974] Step 1:

[0975] The user uses a terminal to input basic project information. This information includes the project name, construction area, materials used, and deadline. A specific example of input might be: "Project Name: New Company Building Construction Project," "Construction Area: 2000 square meters," "Materials Used: Concrete, rebar, glass," and "Deadline: 12 months." In addition, the emotion engine retrieves the user's stress level. Possible emotion data inputs might include "Stress Level: High." This data is sent to the terminal as input.

[0976] Step 2:

[0977] The terminal sends the project basic information and sentiment data entered by the user to the server. A secure communication protocol (e.g., HTTPS) is used for this transmission. As output after transmission, the project basic information and sentiment data are packetized and arrive at the server.

[0978] Step 3:

[0979] The server collects past project performance data and human resource information from the database. For example, data on "construction projects of 2000 square meters over the past five years" is collected. Database queries (SQL queries) are performed as input, and raw project data and human resource information are obtained as output.

[0980] Step 4:

[0981] The server begins preprocessing the collected data. This preprocessing includes imputing missing values ​​(e.g., imputing with the mean) and formatting the data (e.g., converting to numerical data). Furthermore, sentiment data is also formatted into a format that can be applied to the generative AI model. Specifically, preprocessing is performed using a Python script. The input is the raw data obtained in step 3, and the output is the preprocessed project data and sentiment data.

[0982] Step 5:

[0983] The server inputs pre-processed data and user input data (including sentiment data) as prompts into a generative AI model. The generative AI model (e.g., GPT-4) then runs machine learning algorithms to predict project duration and required human resources. For example, prompts like the following might be used:

[0984] Project Name: New Company Building Construction Project

[0985] Construction area: 2000 square meters

[0986] Materials used: Concrete, rebar, glass

[0987] Delivery time: 12 months

[0988] User stress level: High

[0989] Based on the input prompt, the model performs calculations and generates an estimated result of "6 months, 20 workers" as output.

[0990] Step 6:

[0991] The server stores the generated estimate results as structured data and sends it to the terminal. This transmitted data includes an estimate result such as "6 months, 20 workers." After receiving it, the terminal displays the estimate result and sentiment data to the user. This allows the user to see the specific estimate result.

[0992] Step 7:

[0993] While the project is underway, users periodically input progress and emotional data through their devices and send this data to the server. For example, data such as "Progress Rate: 50%" and "Stress Level: Medium" might be entered. The device packets this data and sends it to the server.

[0994] Step 8:

[0995] The server reruns the generating AI model to recalculate the estimation data based on progress and sentiment data. New estimation results and resource allocation suggestions are generated, such as a suggestion that "five additional workers are needed." These new estimation results are stored on the server and sent to the terminal. The terminal displays this new data to the user, who can then modify the project plan based on it.

[0996] Step 9:

[0997] After the project is completed, the user inputs actual project results, feedback data, and sentiment data from their device and sends them to the server. For example, data such as the actual project duration being "7 months" or the worker's stress level being "ultimately low" might be input. The server stores this data as training data in the generating AI model to improve the accuracy of future estimates.

[0998] (Application Example 2)

[0999] 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."

[1000] Traditional project management systems made it cumbersome to input basic project information and progress data, making real-time updates and optimal resource allocation suggestions difficult. Furthermore, they failed to consider user emotions and motivations, hindering efficient project progress. This resulted in project delays and wasted resources.

[1001] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generation AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, updating it by comparing it with the estimation data, and re-executing the generation AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, means including an emotion engine that collects emotion data and reflects it in project management, and means for formatting the emotion data and applying it to the generation AI model. This enables real-time estimation and resource allocation proposals based on basic project information and progress data. Furthermore, flexible and efficient project management that takes user emotions into consideration can be realized.

[1002] "Basic project information" refers to data that forms the foundation for project progress, such as the project name, construction area, materials to be used, and deadline.

[1003] "Terminal" is a general term for devices used by users for input, and includes smartphones, tablets, and personal computers.

[1004] A "server" is a central computer system used to collect, process, store, and communicate with other devices.

[1005] A "database" is a digital storage device used to store past project performance data, human resource information, and other similar information.

[1006] "Preprocessing" is the process of shaping raw data into a format that can be input into a generating AI model, through methods such as imputing missing values ​​and normalization.

[1007] A "generative AI model" is an artificial intelligence model that learns from past data and uses new data to predict and estimate the duration and resources required for a project.

[1008] "Structured data" refers to data organized into a specific format, such as quotation results or resource allocation proposals.

[1009] A "resource allocation proposal" is a plan that proposes the optimal allocation of human resources based on the progress of the project.

[1010] "Emotional data" refers to data that shows psychological information such as a user's emotions, stress levels, and motivation.

[1011] An "emotion engine" is a system that collects and analyzes user emotional data and incorporates it into project management.

[1012] "Progress data" refers to data that shows the current progress of a project, and includes actual work progress and achievement levels.

[1013] This invention is a system for streamlining production process management in factories. This system allows users to input basic production information and progress data from a terminal, and processes this data on a server to automatically generate production schedule estimates and resource allocation suggestions. Furthermore, by collecting user sentiment data and incorporating it into a generated AI model, it achieves more efficient and flexible production management.

[1014] Specifically, users input basic production information and emotional data using devices such as smartphones, smart glasses, and head-mounted displays. This basic information includes the purpose of production, schedule, required resources, materials used, and deadline. Emotional data represents psychological information such as the user's emotional state, stress level, and motivation.

[1015] Input data is sent from the terminal to the server. The server collects past project performance data and human resource information from the database and performs preprocessing. Preprocessing includes imputing missing values ​​and normalizing the data, thereby formatting it into a format that can be applied to the generated AI model.

[1016] The server inputs pre-processed data and user input data into a generative AI model to estimate production time and required human resources. This generative AI model is trained using machine learning and deep learning techniques, and makes highly accurate estimates based on historical data. The estimation results are stored on the server as structured data and sent to the user's terminal.

[1017] Furthermore, the server receives progress data in real time and generates new estimates by re-running the AI ​​model based on this data. These new estimates and resource allocation suggestions are sent to the terminal, taking sentiment data into account, and the user can then modify the production plan based on them.

[1018] The hardware used includes smartphones (e.g., iOS, Android), smart glasses (e.g., Google Glass), and head-mounted displays (e.g., HoloLens). The software used includes Python, scikit-learn, Pandas, and Numpy. This system can provide highly accurate estimates and resource allocation suggestions based on generative AI models, and by considering user sentiment, it enables more flexible and efficient production management.

[1019] As a concrete example, the user receives a prompt message stating, "Please enter the following basic production information: schedule of 5 weeks, resources of 10 people, and emotional data: joy 0.1, stress 0.4." Based on the data entered according to this prompt, the system automatically performs an estimate and provides a suggestion for the optimal resource allocation.

[1020] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1021] Step 1:

[1022] Users input basic production information and emotional data using a device (such as a smartphone, smart glasses, or head-mounted display). Specifically, users input the production objective, schedule, required resources, materials used, and emotional data (joy, stress, motivation, etc.). Based on this input information, the device sends the data to the server.

[1023] Input: Basic production information, emotion data

[1024] Output: Input data sent to the server

[1025] Step 2:

[1026] When data sent from a terminal arrives at the server, the server retrieves past project performance data and human resource information from the database. This collected data includes past production information, resource allocation, and progress data.

[1027] Input: Input data that arrived on the server

[1028] Output: Collected historical performance data and human resource information

[1029] Step 3:

[1030] The server preprocesses the collected data. Specifically, it imputes missing values ​​and normalizes the data. In this process, it also formats the sentiment data into a format that can be applied to the model.

[1031] Input: Collected historical performance data, human resource information, and sentiment data.

[1032] Output: Preprocessed data

[1033] Step 4:

[1034] Based on pre-processed data and user input data, the server inputs this data into a generative AI model. The generative AI model, having learned from historical data, predicts and estimates production time and required human resources from the new data.

[1035] Input: Pre-processed data, user-input data

[1036] Output: Estimate results (production period, required resources)

[1037] Step 5:

[1038] The quotation results are stored on the server as structured data and sent to the terminal. The terminal displays the received quotation results to the user, who then uses this information to plan production.

[1039] Input: Quotation result (production period, required resources)

[1040] Output: Estimated result displayed on the user's terminal

[1041] Step 6:

[1042] During project progress, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to understand the progress, compare it to the estimated data, and update it. The generative AI model is then rerun to generate new estimates and propose resource allocation.

[1043] Input: Progress data, sentiment data

[1044] Output: New estimate results, resource allocation proposals

[1045] Step 7:

[1046] The updated estimate results and resource allocation proposals are sent to the terminal. The terminal displays them to the user, who can modify the production plan as needed.

[1047] Input: New quote results, resource allocation proposals

[1048] Output: New estimate results and resource allocation proposals displayed on the terminal.

[1049] Example of a prompt:

[1050] "For basic production information, please enter a schedule of 5 weeks, 10 resources, and emotional data of joy 0.1 and stress 0.4."

[1051] 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.

[1052] 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.

[1053] 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.

[1054] [Fourth Embodiment]

[1055] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1056] 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.

[1057] 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).

[1058] 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.

[1059] 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.

[1060] 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).

[1061] 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.

[1062] 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.

[1063] 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.

[1064] 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.

[1065] 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.

[1066] 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.

[1067] 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".

[1068] This invention provides a system for streamlining project management in the construction industry, where users input basic project information from a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources.

[1069] First, the user uses a terminal to enter basic project information. This information includes requirements such as the project name, construction area, materials to be used, and deadline. The terminal then sends this information to the server.

[1070] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. The server then inputs the preprocessed data and user input data into a generated AI model.

[1071] The generative AI model operates to estimate the project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[1072] The server sends the estimate results to the terminal, providing the data to the user. The user can then review the estimate results through the terminal and plan the project.

[1073] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the terminal. Users can review these and modify the project plan as needed.

[1074] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[1075] As a concrete example, consider a small to medium-sized construction company that has received a contract for a new building construction project. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[1076] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[1077] In this way, this system achieves efficiency and rationalization of project management in the construction industry and promotes legal and efficient work style reforms.

[1078] The following describes the processing flow.

[1079] Step 1:

[1080] The user uses a terminal to enter basic project information (e.g., project name, construction area, materials used, deadline, etc.).

[1081] Step 2:

[1082] The terminal sends the entered project requirements to the server.

[1083] Step 3:

[1084] The server retrieves past project performance data and human resource information from the database.

[1085] Step 4:

[1086] The server preprocesses the collected data, including imputing missing values ​​and formatting the data.

[1087] Step 5:

[1088] The server inputs pre-processed data and project requirements data from users into the generated AI model.

[1089] Step 6:

[1090] The generative AI model estimates the project duration and the required human resources.

[1091] Step 7:

[1092] The server stores the estimation results as structured data.

[1093] Step 8:

[1094] The server sends the estimate result to the terminal.

[1095] Step 9:

[1096] The terminal displays the estimate result to the user.

[1097] Step 10:

[1098] Users periodically input project progress into their terminals and send it to the server.

[1099] Step 11:

[1100] The server compares real-time progress data with estimated data and updates the progress status.

[1101] Step 12:

[1102] The server reruns the generated AI model and produces new estimation results.

[1103] Step 13:

[1104] The server generates a new resource allocation proposal and sends it to the terminal.

[1105] Step 14:

[1106] The terminal displays new quotes and resource allocation suggestions to the user.

[1107] Step 15:

[1108] After completing a project, the user inputs the actual project data and feedback data into their device and sends it to the server.

[1109] Step 16:

[1110] The server collects feedback data and stores it as training data for the generated AI model.

[1111] (Example 1)

[1112] 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".

[1113] Traditionally, project management in the construction industry has often been done manually, leading to inefficiencies in project progress tracking and human resource estimation. Furthermore, it has been difficult to respond quickly based on real-time progress or to make highly accurate estimates based on historical data. This has resulted in project delays and shortages or surpluses of human resources, ultimately leading to increased overall project costs and time.

[1114] 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.

[1115] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the inputted basic information to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting the basic project information and preprocessed data into a generating AI model to estimate the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient management and accurate human resource estimation during project progress.

[1116] A "user" is someone who operates the system, inputs basic project information, and provides progress data and feedback data.

[1117] A "terminal" is a device used by the user to input basic project information, progress data, and feedback data, and to communicate with the server.

[1118] A "server" is a central computer system that collects and preprocesses data from a database, performs estimations using a generated AI model, and stores and transmits the results.

[1119] "Basic project information" refers to information required in the initial stages of a project, such as the project name, construction area, materials to be used, and deadline.

[1120] A "database" is a system that stores and manages past project performance data and human resource information.

[1121] "Preprocessing" refers to the preparatory work involved in filling in missing values ​​and formatting data collected from a database, in order to input it into the generated AI model.

[1122] A "generative AI model" is a model trained using machine learning and deep learning technologies to accurately estimate project duration and required human resources.

[1123] "Structured data" refers to data in a systematically organized format when a server stores estimation results.

[1124] "Progress data" refers to data that shows the actual progress of an ongoing project.

[1125] A "resource allocation proposal" is a suggestion regarding the allocation of human resources to optimize project progress, based on the estimation results calculated by the generative AI model.

[1126] "Post-project feedback data" refers to actual project data and feedback information regarding areas for improvement collected after a project is completed.

[1127] This invention is a system for streamlining project management in the construction industry. This system optimizes project progress by allowing users to input basic project information via a terminal, and then having a server collect, process, and analyze that information. Specific embodiments are described below.

[1128] First, the user enters basic project information using a terminal. This basic information includes the project name, construction area, materials to be used, and deadline. This information is entered using dedicated software and sent from the terminal to the server.

[1129] Based on the received basic information, the server collects past project performance data and human resource information from the database. The collected data undergoes preprocessing, such as imputing missing values ​​and formatting the data. Data cleaning tools and ETL (Extract, Transform, Load) tools are often used for this purpose.

[1130] Based on the pre-processed data and user input data, the server runs a generative AI model. This generative AI model is trained on past project data and can estimate project duration and required human resources with high accuracy. Machine learning and deep learning techniques are used in the generative AI model.

[1131] During the estimation process, the following prompt statements are input to the generating AI model:

[1132] Project name: New building construction, Construction area: 2000m 2 Please estimate the necessary human resources and timeframe, given the materials used are concrete and the deadline is 12 months.

[1133] The generated estimate results are stored as structured data on the server. The server sends this data to the terminal, and the user checks the estimate results through the terminal.

[1134] During project progress, users periodically input progress data into their terminals and send it to the server. The server uses this progress data to compare it with estimation data and reruns the AI ​​model to generate new estimation results and resource allocation suggestions. For example, if the data indicates that "the current number of workers is 15 and the progress rate is 50%", a suggestion of "5 additional workers are needed" might be generated.

[1135] After project completion, users input actual project data and feedback data using their devices and send it to the server. The server collects this data and stores it as training data for the generative AI model. This improves the accuracy of the generative AI model, leading to even greater accuracy in future estimates.

[1136] In this way, this system streamlines and rationalizes project management in the construction industry, supporting accurate estimations and optimal resource allocation.

[1137] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1138] Step 1:

[1139] The user uses a terminal to enter basic project information (project name, construction area, materials used, deadline, etc.). The terminal has a dedicated input form, and the user enters the information according to this form. The entered basic information is sent from the terminal to the server. This operation completes the initial setup of the project.

[1140] Input: Basic project information (project name, construction area, materials used, deadline, etc.)

[1141] Output: Basic project information is sent to the server.

[1142] Step 2:

[1143] The server receives the entered basic information and retrieves past project performance data and human resource information from the database. It then performs preprocessing on the collected data, specifically including imputing missing values ​​and formatting the data. This process converts the data into an appropriate format for input into the generated AI model.

[1144] Input: Basic information, past project performance data, human resource information

[1145] Output: Preprocessed data

[1146] Step 3:

[1147] The server inputs pre-processed data and basic information entered by the user into the generating AI model. Prompts are used to instruct the generating AI model to estimate the project duration and required human resources. For example, "Project name: New building construction, construction area: 2000m²" 2 A prompt message such as "Materials used: concrete, deadline: 12 months, please estimate the necessary human resources and timeframe" is input to the generated AI model.

[1148] Input: Preprocessed data, basic information, prompt message

[1149] Output: Estimated project duration and required human resources.

[1150] Step 4:

[1151] The server saves the estimation results, which are the output of the generated AI model, as structured data. The estimation results are saved in a format such as "Construction of this building will take 6 months and require 20 workers." The saved data will be referenced and updated later.

[1152] Input: Estimate Result

[1153] Output: Saved as structured data

[1154] Step 5:

[1155] The server sends the saved estimate results to the terminal. The terminal displays the estimate results to the user. The user reviews these results and uses them to plan the project.

[1156] Input: Estimate results as structured data

[1157] Output: Estimated result displayed on the terminal

[1158] Step 6:

[1159] Users periodically input progress data into their terminals and send it to the server during project execution. For example, they might input data such as "Current number of workers: 15, progress rate: 50%." This allows for real-time monitoring of the project's status.

[1160] Input: Progress data (number of workers, progress rate, etc.)

[1161] Output: Progress data sent to the server

[1162] Step 7:

[1163] The server compares the received progress data with the estimated data and reruns the generated AI model as needed. This generates new estimated results and resource allocation suggestions. For example, it might generate a suggestion such as "5 additional workers are needed."

[1164] Input: Progress data, historical estimate data

[1165] Output: New estimate results and resource allocation proposals

[1166] Step 8:

[1167] The server sends the new estimate and resource allocation proposal to the terminal. The terminal displays this for the user to review. The user then modifies the project plan based on this proposal.

[1168] Input: New estimate results and resource allocation proposals

[1169] Output: New estimate results and resource allocation proposals displayed on the terminal.

[1170] Step 9:

[1171] After project completion, users input actual project data and feedback data into their devices and send it to the server. This includes detailed information about project progress and human resource utilization.

[1172] Input: Actual project data, feedback data

[1173] Output: Feedback data sent to the server

[1174] Step 10:

[1175] The server stores the received feedback data as training data for the generating AI model. This improves the model's accuracy, leading to even higher estimation accuracy in subsequent iterations.

[1176] Input: Feedback data

[1177] Output: Stored as training data

[1178] (Application Example 1)

[1179] 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".

[1180] Manufacturing projects in a factory environment require numerous processes and human resources, making their management extremely complex. In particular, understanding project progress, appropriately allocating resources, and adjusting plans according to progress are crucial and must be done efficiently. However, current systems often struggle to meet these requirements, resulting in inefficiencies. Therefore, this invention aims to solve these problems and improve the efficiency and accuracy of manufacturing project management in a factory environment.

[1181] 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.

[1182] In this invention, the server includes means for a user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, comparing and updating it with the estimation data, and re-executing the generating AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, and means for managing the progress of a manufacturing project in a factory environment in real time and estimating the necessary work processes and resource allocation. This enables more efficient project management and flexible resource management according to the progress status.

[1183] "Basic project information" refers to project requirements such as project name, area, materials used, and deadline, which are entered by the user via their device.

[1184] A "terminal" refers to a device that a user uses to input and verify information related to a project.

[1185] A "server" refers to a device that receives basic project information, collects necessary information from a database, and generates estimation results by executing a generated AI model.

[1186] A "database" refers to a data storage system that contains past project performance data and human resource information.

[1187] "Past project performance data" refers to data related to projects that have been carried out in the past, including project duration and resources used.

[1188] "Human resource information" refers to information about the number of workers required for a project and their skill sets.

[1189] "Preprocessing" refers to the process of preparing data before analysis, such as imputing missing values ​​and formatting the data.

[1190] A "generative AI model" refers to an algorithm that uses machine learning and deep learning techniques to estimate project duration and the necessary human resources.

[1191] "Project duration" refers to the period from the start to the end of a project.

[1192] "Required human resources" refers to the number of workers and their skill sets needed to complete the project.

[1193] "Estimate results" refer to data regarding the project duration and required human resources calculated by the generative AI model.

[1194] "Structured data" refers to data where estimation results are presented in an organized format, making it easy to process using computer systems.

[1195] "Progress data" refers to data related to the progress of a project during its operation.

[1196] "Resource allocation proposal" refers to a proposal for new human resources for project execution, generated as a result of re-running the generated AI model.

[1197] "Factory environment" refers to the physical location where work is carried out to manufacture products, as well as the surrounding conditions.

[1198] A "manufacturing project" refers to a series of tasks and their management required to produce a specific product.

[1199] This invention is a system for streamlining manufacturing project management in a factory environment. The following describes how to implement this system in detail.

[1200] The user first uses a terminal to enter basic project information. This information includes the project name, area, materials used, and deadline. This information is then sent from the terminal to the server. Common devices such as personal computers and tablets are used as terminals.

[1201] The server retrieves past project performance data and human resource information from the database based on the basic information of the received project, and performs preprocessing. Preprocessing includes imputing missing values ​​and formatting the data. Relational databases such as SQLite and MySQL are used as the database.

[1202] Based on pre-processed data, the server supplies input data to the generative AI model. The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources with high accuracy. Specifically, machine learning frameworks such as scikit-learn's RandomForestRegressor and TensorFlow are used.

[1203] The estimation results are stored on the server as structured data and sent to the terminal. Users can then review the estimation results and plan their projects through the terminal.

[1204] During project progress, users periodically input progress data into their terminals and send it to the server. The server compares this progress data with the estimated data, reruns the AI ​​model, and generates new estimates. New resource allocation suggestions are also generated and sent to the terminal. Users review these and revise the project plan as needed.

[1205] After project completion, users input actual project data and feedback data into their devices and send it to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[1206] As a concrete example, consider a project in which a factory is building a new product line. The user inputs basic project information from a terminal and sends it to the server. The server collects data from similar past projects and performs preprocessing. Then, it runs a generative AI model to generate an estimate that "building this product line will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[1207] During project progress, users input weekly progress reports from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. Users can review and implement these suggestions to prevent project delays.

[1208] Through the above process, this system achieves increased efficiency and streamlining of manufacturing project management in a factory environment.

[1209] Examples of prompt statements are as follows:

[1210] Project Name: New Product Line Development

[1211] Construction area: 500

[1212] Materials used: Iron, plastic

[1213] Delivery date: 2024-12-31

[1214] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1215] Step 1:

[1216] The user enters basic project information from their device. This basic information includes project name, area, materials used, and deadline. The entered data is temporarily stored on the device.

[1217] Step 2:

[1218] The terminal sends the entered project information to the server. Secure communication protocols such as HTTPS are used for data transmission. The transmitted data is received on the server side.

[1219] Step 3:

[1220] Based on the received project basic information, the server retrieves past project performance data and human resource information from the database. During this process, it uses SQL queries to extract the necessary data.

[1221] Step 4:

[1222] The server preprocesses the collected data. Specifically, it performs data imputation and formatting. The Python pandas library is used for preprocessing. The preprocessed data is then converted into a format suitable for estimation.

[1223] Step 5:

[1224] Based on pre-processed data and user-submitted project basic information, the server inputs data into a generated AI model. This model uses machine learning techniques to estimate project duration and required human resources. The software used includes scikit-learn's RandomForestRegressor and TensorFlow.

[1225] Step 6:

[1226] The generative AI model analyzes user-provided input data to predict project duration and required human resources. The prediction results are stored on the server as structured data.

[1227] Step 7:

[1228] The server sends the generated estimate results to the terminal. The user can then review the estimate results through the terminal and plan the project.

[1229] Step 8:

[1230] During project execution, users periodically input progress data into their terminals and send it to the server. The transmitted progress data is received by the server and stored in a database.

[1231] Step 9:

[1232] The server compares progress data with estimated data and reruns the generating AI model to produce new estimates. This enables real-time optimization of resource allocation.

[1233] Step 10:

[1234] The server sends the updated estimate and resource allocation proposal to the terminal. The user can review the new proposal and revise the project plan.

[1235] Step 11:

[1236] After the project is completed, the user inputs the actual project data and feedback data into their device and sends it to the server. This data is received by the server and stored in a database.

[1237] Step 12:

[1238] The server stores collected actual project data and feedback data as training data for the generated AI model. This allows for improved accuracy in future estimations.

[1239] 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.

[1240] This invention provides a system for streamlining project management in the construction industry. It allows users to input basic project information via a terminal, and a server uses this information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[1241] First, the user uses a terminal to enter basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. The user's emotional data is also obtained through an emotional engine. The terminal then sends this information to the server.

[1242] The server collects past project performance data and human resource information from the database. This collected data is preprocessed, including imputing missing values ​​and formatting the data. Furthermore, sentiment data is formatted into a format that can be applied to the model. The server then inputs the preprocessed data and user input data (including sentiment data) into the generated AI model.

[1243] The generative AI model operates to estimate project duration and required human resources. This model is trained using machine learning and deep learning techniques and provides highly accurate estimates based on past project data. The generated estimates are stored on the server as structured data.

[1244] The server sends the estimate results to the terminal, providing the data to the user. The terminal presents the user's sentiment data along with the estimate results, allowing the user to plan the project based on this information.

[1245] During project progress, users periodically input progress and sentiment data into their devices and send it to the server. The server compares this progress data with estimated data, reruns the AI ​​model, and generates new estimates. As a result, new resource allocation suggestions are also generated and sent to the device. The device displays resource allocation suggestions that take sentiment data into account to the user, who can then modify the project plan based on these suggestions.

[1246] After project completion, users input actual project data, feedback data, and sentiment data into their devices and send them to the server. The server collects this feedback data and stores it as training data for the generated AI model. This improves the model's accuracy and makes it possible to further enhance the accuracy of future estimates.

[1247] As a concrete example, consider a small to medium-sized construction company that has won a contract for a new building construction project. The user inputs basic project information from a terminal, and emotional data is also acquired through an emotion engine and sent to a server. The server collects data from similar past projects and performs preprocessing. Then, using a generative AI model and emotional data, it generates an estimate result stating, "Construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[1248] During project progress, users input weekly progress and sentiment data from their terminals and send them to the server. The server uses this data to readjust estimates and generates new resource allocation suggestions, such as "We need to add 5 more workers," which are then sent to the terminal. The terminal displays the new estimate and resource allocation suggestions, including sentiment data, to the user, who then modifies the plan based on this information.

[1249] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reforms. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[1250] The following describes the processing flow.

[1251] Step 1:

[1252] The user uses a device to input basic project information (e.g., project name, construction area, materials used, deadline, etc.). The emotion engine recognizes the user's emotions in real time as they input the information and collects that data as well.

[1253] Step 2:

[1254] The terminal sends the entered project requirements and sentiment data to the server.

[1255] Step 3:

[1256] The server retrieves past project performance data and human resource information from the database. Furthermore, it also retrieves collected sentiment data.

[1257] Step 4:

[1258] The server preprocesses the collected data, including imputing missing values ​​and formatting the data. Sentiment data is also converted into a format suitable for application to the model.

[1259] Step 5:

[1260] The server inputs pre-processed data and project requirements data from users (including sentiment data) into the generating AI model.

[1261] Step 6:

[1262] The generative AI model estimates the project duration and the required human resources. This estimation also takes emotional data into consideration.

[1263] Step 7:

[1264] The server stores the estimation results as structured data.

[1265] Step 8:

[1266] The server sends the estimation results and sentiment data to the terminal.

[1267] Step 9:

[1268] The device displays the estimate results and sentiment data to the user. The user then uses this information to plan the project.

[1269] Step 10:

[1270] During project progress, users periodically input progress data and emotional data into their devices. The emotional engine recognizes the user's emotional data in real time and sends it to the server as well.

[1271] Step 11:

[1272] The server updates the progress status by comparing real-time progress and sentiment data with estimated data.

[1273] Step 12:

[1274] The server reruns the generated AI model and produces new estimates and resource allocation suggestions, taking sentiment data into consideration.

[1275] Step 13:

[1276] The server sends the new estimate and resource allocation proposal to the terminal.

[1277] Step 14:

[1278] The device displays new estimate results and sentiment data to the user. The user then modifies the project plan based on this information.

[1279] Step 15:

[1280] After the project is completed, the user inputs actual project data, feedback data, and sentiment data into their device and sends it to the server. The sentiment engine also collects the final sentiment data.

[1281] Step 16:

[1282] The server collects feedback and sentiment data and stores it as training data for the generative AI model. This improves the model's accuracy and increases the accuracy of future estimates.

[1283] (Example 2)

[1284] 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".

[1285] In the construction industry, streamlining and improving the efficiency of project management is a critical challenge. In particular, there is a need for appropriate allocation of human resources and the ability to respond to real-time changes in the project's progress. Furthermore, there is a lack of project management methods that consider the stress and motivation of project managers, making flexible estimation and resource allocation based on human emotional data a difficult challenge.

[1286] 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.

[1287] In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements and sentiment data to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing such as imputing missing values ​​and formatting the data, means for inputting the preprocessed project requirements data and sentiment data into a generating AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data and sentiment data in real time, updating them by comparing them with the estimation data, and re-executing the generating AI model, and means for transmitting the updated estimate and resource allocation proposal to the terminal. This enables efficient and flexible project management. Furthermore, by reflecting the user's sentiment data in project management, it becomes possible to achieve optimal resource allocation that takes stress and motivation into consideration.

[1288] A "terminal" is an electronic device used by users to input basic project information, progress data, and sentiment data, and to communicate with the server.

[1289] A "server" is a central management system that receives data sent from terminals, collects information from a database, performs preprocessing, calculates estimates using a generated AI model, and sends the results to the terminals.

[1290] "Project basic information" refers to key project requirements such as project name, construction area, materials used, and deadline, which are entered by the user via their device.

[1291] "Emotional data" refers to data that indicates the user's emotional state (e.g., stress level and motivation), and is acquired by the emotion engine.

[1292] A "generative AI model" is an artificial intelligence model trained using machine learning and deep learning techniques, and is used to estimate project duration and the human resources required.

[1293] "Preprocessing" refers to the process of imputing missing values ​​and formatting data collected from a database.

[1294] "Estimate" refers to the project duration and the predicted human resources required, calculated using a generative AI model.

[1295] "Structured data" refers to data, including estimation results, that has been formatted into a specified format and stored in a way that facilitates subsequent processing and analysis.

[1296] "Progress data" refers to data that shows the progress of a project, and users periodically input it from their devices.

[1297] "Feedback data" refers to data about actual project results and emotional states entered by users after project completion, and is used to improve the accuracy of the generative AI model.

[1298] A "resource allocation proposal" is a specific allocation plan for the necessary human resources calculated by a generative AI model.

[1299] A "database" is a system used to record and manage past project performance data and human resource information.

[1300] This invention is a system for streamlining project management in the construction industry. It provides a process where users input basic project information via a terminal, and a server uses that information to generate estimates and automatically create the necessary human resources. Furthermore, the system incorporates an emotion engine that recognizes user emotions, and by reflecting this information in the AI ​​model, it achieves more flexible and efficient project management.

[1301] First, the user uses a terminal to input basic project information. This information includes requirements such as project name, construction area, materials to be used, and deadline. Furthermore, the terminal has an emotion engine built in that analyzes the user's facial expressions and tone of voice to obtain emotion data. This data is then sent from the terminal to the server.

[1302] The server collects past project performance data and human resource information from the database. This collected data is preprocessed using scripts such as Python. Specifically, missing values ​​are imputed and the data is formatted, and sentiment data is also formatted into a format that can be applied to the generative AI model. After that, the preprocessed data and user input data (including sentiment data) are input to the generative AI model as prompt messages.

[1303] The generative AI model is trained using machine learning and deep learning techniques to estimate project duration and required human resources. It leverages historical project data to provide highly accurate estimates. GPT-4 and other advanced generative AI models are used for this purpose. The generated estimate results are stored on a server as structured data.

[1304] The server sends the estimate result to the terminal, which then provides the user with the estimate result and sentiment data. The user can then use this information to plan their project.

[1305] As the project progresses, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to compare with the estimated data, reruns the AI ​​model, and generates new estimates. This also generates resource allocation suggestions that adapt to changes in the project's progress and sends them to the device.

[1306] After project completion, users input actual project data, feedback data, and sentiment data from their devices and send them to the server. The server stores this feedback data as training data for the generating AI model, thereby improving the model's accuracy and further enhancing the accuracy of future estimates.

[1307] As a concrete example, consider a case where a small to medium-sized construction company receives a contract for a new building construction project. The user enters the basic project information as follows:

[1308] Project Name: New Company Building Construction Project

[1309] Construction area: 2000 square meters

[1310] Materials used: Concrete, rebar, glass

[1311] Delivery time: 12 months

[1312] The emotion engine determines that the user's stress level is "high." This information and emotion data are sent from the terminal to the server. The server collects and preprocesses data from similar past projects. Then, using the generative AI model and emotion data, it generates an estimate that "the construction of this building will take 6 months and require 20 workers." This result is sent to the terminal for the user to review.

[1313] During project progress, users input weekly progress and emotional data such as "Stress Level: Medium," and send it to the server. Based on this data, the server readjusts the estimate and generates new resource allocation suggestions, such as "5 additional workers are needed," and sends them to the terminal. The terminal displays this to the user, who then modifies the plan based on it.

[1314] In this way, this system achieves efficiency and rationalization of project management in the construction industry, promoting legal and efficient work style reform. Furthermore, by combining it with an emotion engine, it realizes optimal project management that takes into account user stress and motivation.

[1315] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1316] Step 1:

[1317] The user uses a terminal to input basic project information. This information includes the project name, construction area, materials used, and deadline. A specific example of input might be: "Project Name: New Company Building Construction Project," "Construction Area: 2000 square meters," "Materials Used: Concrete, rebar, glass," and "Deadline: 12 months." In addition, the emotion engine retrieves the user's stress level. Possible emotion data inputs might include "Stress Level: High." This data is sent to the terminal as input.

[1318] Step 2:

[1319] The terminal sends the project basic information and sentiment data entered by the user to the server. A secure communication protocol (e.g., HTTPS) is used for this transmission. As output after transmission, the project basic information and sentiment data are packetized and arrive at the server.

[1320] Step 3:

[1321] The server collects past project performance data and human resource information from the database. For example, data on "construction projects of 2000 square meters over the past five years" is collected. Database queries (SQL queries) are performed as input, and raw project data and human resource information are obtained as output.

[1322] Step 4:

[1323] The server begins preprocessing the collected data. This preprocessing includes imputing missing values ​​(e.g., imputing with the mean) and formatting the data (e.g., converting to numerical data). Furthermore, sentiment data is also formatted into a format that can be applied to the generative AI model. Specifically, preprocessing is performed using a Python script. The input is the raw data obtained in step 3, and the output is the preprocessed project data and sentiment data.

[1324] Step 5:

[1325] The server inputs pre-processed data and user input data (including sentiment data) as prompts into a generative AI model. The generative AI model (e.g., GPT-4) then runs machine learning algorithms to predict project duration and required human resources. For example, prompts like the following might be used:

[1326] Project Name: New Company Building Construction Project

[1327] Construction area: 2000 square meters

[1328] Materials used: Concrete, rebar, glass

[1329] Delivery time: 12 months

[1330] User stress level: High

[1331] Based on the input prompt, the model performs calculations and generates an estimated result of "6 months, 20 workers" as output.

[1332] Step 6:

[1333] The server stores the generated estimate results as structured data and sends it to the terminal. This transmitted data includes an estimate result such as "6 months, 20 workers." After receiving it, the terminal displays the estimate result and sentiment data to the user. This allows the user to see the specific estimate result.

[1334] Step 7:

[1335] While the project is underway, users periodically input progress and emotional data through their devices and send this data to the server. For example, data such as "Progress Rate: 50%" and "Stress Level: Medium" might be entered. The device packets this data and sends it to the server.

[1336] Step 8:

[1337] The server reruns the generating AI model to recalculate the estimation data based on progress and sentiment data. New estimation results and resource allocation suggestions are generated, such as a suggestion that "five additional workers are needed." These new estimation results are stored on the server and sent to the terminal. The terminal displays this new data to the user, who can then modify the project plan based on it.

[1338] Step 9:

[1339] After the project is completed, the user inputs actual project results, feedback data, and sentiment data from their device and sends them to the server. For example, data such as the actual project duration being "7 months" or the worker's stress level being "ultimately low" might be input. The server stores this data as training data in the generating AI model to improve the accuracy of future estimates.

[1340] (Application Example 2)

[1341] 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".

[1342] Traditional project management systems made it cumbersome to input basic project information and progress data, making real-time updates and optimal resource allocation suggestions difficult. Furthermore, they failed to consider user emotions and motivations, hindering efficient project progress. This resulted in project delays and wasted resources.

[1343] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input basic project information from a terminal, means for transmitting the input project requirements to the server, means for collecting past project performance data and human resource information from a database and performing preprocessing, means for inputting project requirement data into a generation AI model and estimating the project period and required human resources, means for storing the estimation results as structured data and transmitting them to the terminal, means for receiving progress data in real time, updating it by comparing it with the estimation data, and re-executing the generation AI model, means for transmitting the updated estimate and resource allocation proposal to the terminal, means including an emotion engine that collects emotion data and reflects it in project management, and means for formatting the emotion data and applying it to the generation AI model. This enables real-time estimation and resource allocation proposals based on basic project information and progress data. Furthermore, flexible and efficient project management that takes user emotions into consideration can be realized.

[1344] "Basic project information" refers to data that forms the foundation for project progress, such as the project name, construction area, materials to be used, and deadline.

[1345] "Terminal" is a general term for devices used by users for input, and includes smartphones, tablets, and personal computers.

[1346] A "server" is a central computer system used to collect, process, store, and communicate with other devices.

[1347] A "database" is a digital storage device used to store past project performance data, human resource information, and other similar information.

[1348] "Preprocessing" is the process of shaping raw data into a format that can be input into a generating AI model, through methods such as imputing missing values ​​and normalization.

[1349] A "generative AI model" is an artificial intelligence model that learns from past data and uses new data to predict and estimate the duration and resources required for a project.

[1350] "Structured data" refers to data organized into a specific format, such as quotation results or resource allocation proposals.

[1351] A "resource allocation proposal" is a plan that proposes the optimal allocation of human resources based on the progress of the project.

[1352] "Emotional data" refers to data that shows psychological information such as a user's emotions, stress levels, and motivation.

[1353] An "emotion engine" is a system that collects and analyzes user emotional data and incorporates it into project management.

[1354] "Progress data" refers to data that shows the current progress of a project, and includes actual work progress and achievement levels.

[1355] This invention is a system for streamlining production process management in factories. This system allows users to input basic production information and progress data from a terminal, and processes this data on a server to automatically generate production schedule estimates and resource allocation suggestions. Furthermore, by collecting user sentiment data and incorporating it into a generated AI model, it achieves more efficient and flexible production management.

[1356] Specifically, users input basic production information and emotional data using devices such as smartphones, smart glasses, and head-mounted displays. This basic information includes the purpose of production, schedule, required resources, materials used, and deadline. Emotional data represents psychological information such as the user's emotional state, stress level, and motivation.

[1357] Input data is sent from the terminal to the server. The server collects past project performance data and human resource information from the database and performs preprocessing. Preprocessing includes imputing missing values ​​and normalizing the data, thereby formatting it into a format that can be applied to the generated AI model.

[1358] The server inputs pre-processed data and user input data into a generative AI model to estimate production time and required human resources. This generative AI model is trained using machine learning and deep learning techniques, and makes highly accurate estimates based on historical data. The estimation results are stored on the server as structured data and sent to the user's terminal.

[1359] Furthermore, the server receives progress data in real time and generates new estimates by re-running the AI ​​model based on this data. These new estimates and resource allocation suggestions are sent to the terminal, taking sentiment data into account, and the user can then modify the production plan based on them.

[1360] The hardware used includes smartphones (e.g., iOS, Android), smart glasses (e.g., Google Glass), and head-mounted displays (e.g., HoloLens). The software used includes Python, scikit-learn, Pandas, and Numpy. This system can provide highly accurate estimates and resource allocation suggestions based on generative AI models, and by considering user sentiment, it enables more flexible and efficient production management.

[1361] As a concrete example, the user receives a prompt message stating, "Please enter the following basic production information: schedule of 5 weeks, resources of 10 people, and emotional data: joy 0.1, stress 0.4." Based on the data entered according to this prompt, the system automatically performs an estimate and provides a suggestion for the optimal resource allocation.

[1362] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1363] Step 1:

[1364] Users input basic production information and emotional data using a device (such as a smartphone, smart glasses, or head-mounted display). Specifically, users input the production objective, schedule, required resources, materials used, and emotional data (joy, stress, motivation, etc.). Based on this input information, the device sends the data to the server.

[1365] Input: Basic production information, emotion data

[1366] Output: Input data sent to the server

[1367] Step 2:

[1368] When data sent from a terminal arrives at the server, the server retrieves past project performance data and human resource information from the database. This collected data includes past production information, resource allocation, and progress data.

[1369] Input: Input data that arrived on the server

[1370] Output: Collected historical performance data and human resource information

[1371] Step 3:

[1372] The server preprocesses the collected data. Specifically, it imputes missing values ​​and normalizes the data. In this process, it also formats the sentiment data into a format that can be applied to the model.

[1373] Input: Collected historical performance data, human resource information, and sentiment data.

[1374] Output: Preprocessed data

[1375] Step 4:

[1376] Based on pre-processed data and user input data, the server inputs this data into a generative AI model. The generative AI model, having learned from historical data, predicts and estimates production time and required human resources from the new data.

[1377] Input: Pre-processed data, user-input data

[1378] Output: Estimate results (production period, required resources)

[1379] Step 5:

[1380] The quotation results are stored on the server as structured data and sent to the terminal. The terminal displays the received quotation results to the user, who then uses this information to plan production.

[1381] Input: Quotation result (production period, required resources)

[1382] Output: Estimated result displayed on the user's terminal

[1383] Step 6:

[1384] During project progress, users periodically input progress and sentiment data from their devices and send it to the server. The server uses this data to understand the progress, compare it to the estimated data, and update it. The generative AI model is then rerun to generate new estimates and propose resource allocation.

[1385] Input: Progress data, sentiment data

[1386] Output: New estimate results, resource allocation proposals

[1387] Step 7:

[1388] The updated estimate results and resource allocation proposals are sent to the terminal. The terminal displays them to the user, who can modify the production plan as needed.

[1389] Input: New quote results, resource allocation proposals

[1390] Output: New estimate results and resource allocation proposals displayed on the terminal.

[1391] Example of a prompt:

[1392] "For basic production information, please enter a schedule of 5 weeks, 10 resources, and emotional data of joy 0.1 and stress 0.4."

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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."

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] 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.

[1412] 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.

[1413] 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.

[1414] The following is further disclosed regarding the embodiments described above.

[1415] (Claim 1)

[1416] A means for users to input basic project information from their devices,

[1417] A means for sending the input project requirements to the server,

[1418] A means for collecting past project performance data and human resource information from a database and performing preprocessing,

[1419] A method for inputting project requirements data into an AI model to estimate the project duration and required human resources,

[1420] A means for storing the aforementioned estimation results as structured data and transmitting them to a terminal,

[1421] A means of receiving progress data in real time, comparing it with estimated data and updating it, and rerunning the generated AI model,

[1422] A means to send updated quotes and resource allocation proposals to the terminal.

[1423] Includes system.

[1424] (Claim 2)

[1425] This further includes means for collecting actual project data and feedback data after project completion and storing them as training data for the generated AI model.

[1426] The system according to claim 1.

[1427] (Claim 3)

[1428] We use a generative AI model to generate new estimates and resource allocation proposals based on real-time project progress.

[1429] The system according to claim 1.

[1430] "Example 1"

[1431] (Claim 1)

[1432] A means for users to input basic project information from their devices,

[1433] Means for transmitting the input basic information to the server,

[1434] A means for collecting past project performance data and human resource information from a database and performing preprocessing,

[1435] A means of inputting basic project information and pre-processed data into a generating AI model to estimate the project duration and required human resources,

[1436] A means for storing the aforementioned estimation results as structured data and transmitting them to a terminal,

[1437] A means of receiving progress data in real time, comparing and updating it with estimated data, and rerunning the generated AI model,

[1438] A means to send updated quotes and resource allocation proposals to the terminal.

[1439] Includes system.

[1440] (Claim 2)

[1441] This further includes means for collecting actual project data and feedback data after project completion and storing them as training data for the generated AI model.

[1442] The system according to claim 1.

[1443] (Claim 3)

[1444] During project progress, a generative AI model is used to generate new estimates and resource allocation proposals based on the project's progress.

[1445] The system according to claim 1.

[1446] "Application Example 1"

[1447] (Claim 1)

[1448] A means for users to input basic project information from their devices,

[1449] A means for sending the input project requirements to the server,

[1450] A means for collecting past project performance data and human resource information from a database and performing preprocessing,

[1451] A method for inputting project requirements data into an AI model to estimate the project duration and required human resources,

[1452] A means for storing the aforementioned estimation results as structured data and transmitting them to a terminal,

[1453] A means of receiving progress data in real time, comparing it with estimated data and updating it, and rerunning the generated AI model,

[1454] A means of sending updated quotes and resource allocation proposals to a terminal,

[1455] A means to manage the progress of manufacturing projects in a factory environment in real time and to estimate the necessary work processes and resource allocation.

[1456] Includes system.

[1457] (Claim 2)

[1458] This further includes means for collecting actual project data and feedback data after project completion and storing them as training data for the generated AI model.

[1459] The system according to claim 1.

[1460] (Claim 3)

[1461] We use a generative AI model to generate new estimates and resource allocation proposals based on real-time project progress.

[1462] The system according to claim 1.

[1463] "Example 2 of combining an emotion engine"

[1464] (Claim 1)

[1465] A means for users to input basic project information from their device,

[1466] Means for transmitting the input project requirements and sentiment data to a server,

[1467] A preprocessing means that collects past project performance data and human resource information from a database, and performs data preprocessing such as imputing missing values ​​and formatting the data,

[1468] A method for estimating project duration and required human resources by inputting pre-processed project requirements data and sentiment data into a generating AI model,

[1469] A means for storing the aforementioned estimation results as structured data and transmitting them to a terminal,

[1470] A means of receiving progress and sentiment data in real time, updating it by comparing it with estimated data, and rerunning the generative AI model,

[1471] A means to send updated quotes and resource allocation proposals to the terminal.

[1472] Includes system.

[1473] (Claim 2)

[1474] This further includes means for collecting actual project data, feedback data, and sentiment data after project completion and storing them as training data for generative AI models.

[1475] The system according to claim 1.

[1476] (Claim 3)

[1477] We use generative AI models to generate new estimates and resource allocation suggestions based on real-time project progress and sentiment data.

[1478] The system according to claim 1.

[1479] "Application example 2 when combining with an emotional engine"

[1480] (Claim 1)

[1481] A means for users to input basic project information from their devices,

[1482] A means for sending the input project requirements to the server,

[1483] A means for collecting past project performance data and human resource information from a database and performing preprocessing,

[1484] A method for inputting project requirements data into an AI model to estimate the project duration and required human resources,

[1485] A means for storing the aforementioned estimation results as structured data and transmitting them to a terminal,

[1486] A means of receiving progress data in real time, comparing it with estimated data and updating it, and rerunning the generated AI model,

[1487] A means of sending updated quotes and resource allocation proposals to a terminal,

[1488] A means including an emotion engine that collects emotional data and incorporates it into project management,

[1489] A system that includes means for formatting emotional data and applying it to a generative AI model.

[1490] (Claim 2)

[1491] The system according to claim 1, further comprising means for collecting actual project data and feedback data after the completion of the project and storing them as training data for the generated AI model.

[1492] (Claim 3)

[1493] The system according to claim 1, which uses a generative AI model to generate new estimates and resource allocation proposals based on real-time project progress. [Explanation of Symbols]

[1494] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input basic project information from their devices, A means for sending the input project requirements to the server, A means for collecting past project performance data and human resource information from a database and performing preprocessing, A method for inputting project requirements data into an AI model to estimate the project duration and required human resources, A means for storing the aforementioned estimation results as structured data and transmitting them to a terminal, A means of receiving progress data in real time, comparing it with estimated data and updating it, and rerunning the generated AI model, A means to send updated quotes and resource allocation proposals to the terminal. Includes system.

2. This further includes means for collecting actual project data and feedback data after project completion and storing them as training data for the generated AI model. The system according to claim 1.

3. We use a generative AI model to generate new estimates and resource allocation proposals based on real-time project progress. The system according to claim 1.

Images