System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a progress report from a user using a generative artificial intelligence model and organizing information based on the progress report; means for storing the organized information; and means for reporting the stored information to interested parties.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Project management involves multiple members, and each member must be able to accurately grasp the progress and task status. Furthermore, when reporting progress to superiors and other stakeholders, the time and effort required to organize and report information, as well as the need to coordinate communication, can be challenging. Traditional methods involve a large amount of manual work, making it difficult to grasp the overall picture of the project, and further complicating project progress management and early problem detection. A means to efficiently resolve these project management challenges is needed. [Means for solving the problem]

[0005] This invention provides a project management system that processes progress reports using a generative artificial intelligence model. First, progress reports from users are received in text format, and the report content is analyzed and organized using a generative artificial intelligence model. The organized information is stored in memory and reported to relevant parties as needed. This system visualizes progress information in real time, enabling the overall progress of the project to be grasped. Furthermore, by storing organized information and reporting it to relevant parties at the appropriate time, communication efficiency can be improved. Furthermore, by evaluating the status of tasks and assigning statuses such as in progress or completed, incomplete tasks and delayed items can be identified early, contributing to the rapid resolution of problems.

[0006] A "generative artificial intelligence model" is an algorithm or system that uses natural language processing technology to analyze text data and generate and organize information.

[0007] "Progress Report" refers to information submitted by a user to report on the progress of a project or the status of a task.

[0008] A "user" is any person or entity that utilizes the system to create and submit progress reports.

[0009] "Means of organizing information" refers to the process of using a generative artificial intelligence model to extract necessary information from received progress reports and convert it into an easy-to-understand format.

[0010] The "means for storing information" is a mechanism for recording organized information as digital data in an appropriate memory space, making it possible to refer to it upon subsequent requests.

[0011] "Means for reporting to stakeholders" refers to the processes and systems for notifying other members and superiors involved in the project of the saved progress information in an appropriate time and format.

[0012] "Task status" is information indicating whether each task in a project is completed, in progress, or not yet started.

[0013] A "web interface" is a user interface that allows a user to access the system via a web browser and send progress reports or obtain progress information. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is a system for improving the efficiency of progress reports in project management by using a generative artificial intelligence model. This system includes a series of processes for receiving progress reports from users, organizing them using a generative artificial intelligence model, storing them, and reporting them to relevant parties.

[0036] System Overview

[0037] 1. Server

[0038] The server runs and provides a web interface to accept HTTP requests from front-end terminals and users.

[0039] The server receives the progress reports and analyzes and organizes them using a generative artificial intelligence model.

[0040] 2. Receiving and processing progress reports

[0041] A user creates a text file to report the progress of a project and sends it to the server. The progress report includes the user ID, task details, progress rate, and detailed information.

[0042] The server analyzes the received progress reports and organizes them using a generative artificial intelligence model. This organization process generates summaries from the reports, evaluates the progress of the tasks, and assigns appropriate statuses (e.g., in progress, completed).

[0043] 3. Storage of Information

[0044] The server stores organized progress reports in memory, including summary, status, and timestamp information.

[0045] 4. Reporting to relevant parties

[0046] The server reports the saved progress information to the relevant parties as needed. This reporting is done through a web interface, allowing the relevant parties to check the progress information as needed.

[0047] Specific examples

[0048] For example, suppose a user wants to report on the progress of a task called "Implementing Feature A." The user enters the following information:

[0049] User ID: 1

[0050] Task: Implement Feature A

[0051] Progress: 50%

[0052] Details: Basic functionality is complete. Test cases in progress.

[0053] When the user sends this information to the server, the server receives it, passes it to a generative AI model for analysis and organization, and generates the following organized information:

[0054] Summary: "Task: Feature A implementation is in progress."

[0055] Status: In progress

[0056] Timestamp: 2023-10-10 12:00:00

[0057] The server stores this information and allows stakeholders to view progress through a web interface, providing real-time visibility into project progress and enabling early identification of incomplete or delayed tasks.

[0058] The above is an example of an embodiment of the present invention. This system not only improves the efficiency of progress reports, but also significantly improves the overall project management and communication between the parties involved.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[0062] Step 2:

[0063] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[0064] json

[0065] {

[0066] "user_id": 1,

[0067] "task": "Implementation of feature A",

[0068] "progress": 50,

[0069] "details": "Basic functionality done. Test cases in progress."

[0070] }

[0071] Step 3:

[0072] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[0073] Step 4:

[0074] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[0075] Step 5:

[0076] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[0077] Summary: "Task: Feature A implementation is in progress."

[0078] Status: In progress (progress less than 100)

[0079] Timestamp: Current date and time

[0080] Step 6:

[0081] The server saves the generated and organized information by adding it to the progress_reports list in memory.

[0082] Step 7:

[0083] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[0084] json

[0085] {

[0086] "message": "Your report has been received."

[0087] }

[0088] Step 8:

[0089] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[0090] Step 9:

[0091] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[0092] Step 10:

[0093] The server returns the progress information it has obtained to the relevant parties in JSON format, including a summary of each progress report, its status, and a timestamp.

[0094] Through these steps, the project management system utilizing generative artificial intelligence functions efficiently, effectively organizing progress reports and sharing information with stakeholders.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In conventional project management, progress reporting is often done manually, resulting in inefficient information organization and reporting, and problems such as delays in communication and misunderstandings between stakeholders. These problems are particularly pronounced in large-scale projects, making it difficult to grasp the project's progress in real time. Therefore, the present invention aims to solve these problems and improve the efficiency of progress reporting and communication between stakeholders.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes: means for receiving progress reports and analyzing and organizing them using a generative artificial intelligence model; means for saving the organized information; means for reporting to relevant parties; means for the server to start up and accept HTTP requests from users and analyze and organize the progress reports; means for users to input progress reports through their terminals and send them to the server; means for the generative artificial intelligence model to analyze and organize the progress reports using prompt statements based on the progress reports; means for saving the generated summaries and statuses in memory; and means for reporting the saved progress information to relevant parties via a web interface so that the status can be checked in real time. This improves the efficiency of progress reports, enables the progress of the entire project to be grasped in real time, facilitates communication between relevant parties, and improves the accuracy of project management.

[0100] A "generative artificial intelligence model" is an artificial intelligence model that analyzes and organizes information based on data provided by the user, and automatically generates summaries and statuses.

[0101] "Progress report" is data such as task name, progress rate, detailed information, etc. that a user inputs to report the progress of a project.

[0102] The "server" is a computer system whose role is to receive requests from users, analyze and organize progress reports using a generative artificial intelligence model, store the information, and report it to relevant parties.

[0103] An "HTTP request" is a request for information sent by a user through a web interface to a server, whether for progress reporting or to perform other operations.

[0104] "Web Interface" means a web-based user interface that allows a user to enter progress reports and review stored information.

[0105] A "prompt sentence" is an instruction sentence that instructs a generative artificial intelligence model to perform a specific task, and is a sentence used when analyzing and organizing.

[0106] A "summary" is concise information extracted from a progress report by a generative artificial intelligence model that provides the core of the task.

[0107] "Status" is information that is evaluated by the generative artificial intelligence model based on progress reports and assigned to indicate the progress of a task, and represents a state such as "in progress" or "completed."

[0108] "Storage" refers to the server keeping organized progress information in memory or a database so that it can be accessed later.

[0109] A "stakeholder" is a person or organization that has an interest in the progress of the project and has the authority to review reported progress information.

[0110] "Real-time" refers to a state in which progress information is saved and can be accessed by relevant parties at the same time, and information is shared instantly.

[0111] The present invention is a system for improving the efficiency of progress reports in project management using a generative artificial intelligence model. This system is realized through cooperation between a server, terminals, and users.

[0112] The overall system configuration is as follows:

[0113] 1. Server

[0114] The server is run by web server software such as Apache (registered trademark) or Nginx.

[0115] The server is implemented using a programming language such as Python or Node.js and provides a REST API for accepting HTTP requests from users.

[0116] The server analyzes and organizes the progress reports using a generative artificial intelligence model (e.g., GPT-4 (registered trademark)).

[0117] 2. Terminal

[0118] The terminal uses a browser to display a web interface composed of HTML, CSS, and JavaScript (registered trademark).

[0119] The user inputs a progress report using a terminal and sends it to the server as an HTTP POST request.

[0120] Next, a series of processes performed by this system will be described in detail.

[0121] First, the user accesses the web interface on the terminal and enters the necessary information into the progress report form, specifically the task name, progress rate, detailed information, etc. Once the input is complete, the user presses the send button, and the terminal sends the information to the server.

[0122] The data received by the server is first parsed in JSON format and temporarily stored in internal memory. Next, the server generates a prompt for the generative AI model. This prompt contains the progress report entered by the user. For example, the prompt has the following format:

[0123] "Please summarize the progress information below and assign an appropriate status. Content: Feature A implemented. Progress: 50%. Details: Basic functionality completed. Test cases being created."

[0124] The generative AI model analyzes the prompt, summarizes the report, and returns the result with an appropriate status to the server. For example, the output might look something like this:

[0125] Summary: "Task: Feature A implementation is in progress."

[0126] Status: In progress

[0127] Timestamp: 2023-10-10 12:00:00

[0128] The server receives this information and stores it in a database (e.g., MySQL or PostgreSQL). The stored information includes a summary, status, and timestamp.

[0129] Finally, the server provides a web interface that allows stakeholders to view real-time progress information, for example, by accessing a dashboard on the web interface, allowing stakeholders to view the latest progress.

[0130] In this way, the system of the present invention realizes more efficient progress reporting and more accurate project management.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] The user accesses the web interface on the terminal and enters information into a progress report form.

[0134] Input: Task name, progress, and details.

[0135] Specific operation: A user opens a web page using a browser and enters the task name (e.g., Implementing Feature A), progress rate (e.g., 50%), and details (e.g., Basic functionality completed. Test cases being created.) into the progress report form. When the user presses the "Submit" button, the terminal formats this information and sends it to the server as an HTTP POST request.

[0136] Step 2:

[0137] The server receives the HTTP POST request and parses the data.

[0138] Input: Progress report data submitted by the user (task name, progress percentage, details).

[0139] Output: Data converted to JSON format.

[0140] What happens: The server receives an HTTP POST request, parses the data in the request body, converts it to JSON format, and temporarily stores it in internal memory.

[0141] Step 3:

[0142] The server sends a prompt to the generative artificial intelligence model, requesting it to analyze and organize the data.

[0143] Input: Progress report data in JSON format, generated prompt text.

[0144] Output: A summary and status returned by the generative AI model.

[0145] Specific operation: The server generates a prompt based on the progress report data. Example prompt: "Please summarize the following progress information and assign an appropriate status. Content: Implementing feature A. Progress rate: 50%. Details: Basic functionality is complete. Test cases are being created." The generated prompt is sent to the API of the generative AI model, and a summary and status are returned.

[0146] Step 4:

[0147] The server stores the output of the generative artificial intelligence model in a database.

[0148] Input: Summary and status generated by the model, timestamp of progress report.

[0149] Output: Progress information stored in a database.

[0150] What it does: The server saves the summary and status received from the generative AI model, along with the current timestamp, in a database (e.g., MySQL, PostgreSQL), by executing a SQL query to insert the information into the appropriate tables.

[0151] Step 5:

[0152] The server reports progress information to interested parties and provides a web interface.

[0153] Input: Progress information stored in the database.

[0154] Output: Latest progress information displayed on the web interface.

[0155] What it does: The server retrieves the latest progress information from the database and displays it on a dashboard on a web interface. Stakeholders can access the dashboard using a browser to check the latest progress information in real time. It can also send alerts via email or push notification when certain conditions are met.

[0156] As a result, users, terminals, and servers work together to improve the efficiency of progress reports and the accuracy of project management.

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] In modern production plants, efficient and real-time reporting and management of the work progress of automated equipment is required. However, manual reporting and management requires time and effort, and progress information often lacks accuracy and speed. Furthermore, if managers cannot grasp the work progress status of equipment within the facility in a timely manner, optimal production management becomes difficult. There is a need for a system to solve this situation.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0161] In this invention, the server includes means for receiving progress reports from automation equipment using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to a manager, means for saving the organized information in a database, and means for providing an interface for visualizing the organized information. This makes it possible to efficiently collect, organize, and report work progress information from automation equipment in real time, allowing managers to quickly and appropriately manage production.

[0162] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes data provided by users or devices and generates solutions or insights for specific problems.

[0163] "Automation equipment" refers to robots and automation devices used to automate work in production factories, etc.

[0164] A "progress report" is a report or data that organizes and provides information about the progress of a particular task or piece of work.

[0165] "Means for organizing information" refers to a method or apparatus that uses a generative artificial intelligence model to extract necessary information from received progress reports and organize it in a structured format.

[0166] "Means for storing information" refers to a method or device for storing organized information in a storage device such as a database or memory.

[0167] "Means for reporting information to an administrator" refers to a method or device for notifying an administrator of stored information as necessary so that the administrator can check it.

[0168] A "database" is a system that efficiently stores and manages organized progress information, allowing it to be quickly searched and accessed when needed.

[0169] "Interface" refers to a screen or web application that allows users or administrators to visually check and operate information.

[0170] "Work progress" is the indicator or data that shows how far a particular task or project has progressed.

[0171] The "task status" is information indicating the current status of the work, such as in progress, completed, or delayed.

[0172] "Status" is a label or tag used to express the progress of a task or project.

[0173] This invention provides a system for efficiently reporting and managing the work progress of automation equipment in a factory. The system includes a series of processes that use a generative artificial intelligence model to analyze the progress report and report it to a manager.

[0174] The system includes the following elements:

[0175] 1. Server

[0176] The server provides a web interface to accept HTTP requests from automation devices and administrator terminals.

[0177] The server receives progress reports from the automation equipment and uses a generative artificial intelligence model to analyze and organize the reports.

[0178] 2. Receiving and processing progress reports

[0179] The automation device describes its work progress in text format and sends the information to the server. The progress report includes the robot ID, task content, progress rate, and detailed information.

[0180] The server analyzes the received progress reports and organizes them using a generative AI model to generate summaries, evaluate the progress of tasks, and assign appropriate statuses (e.g., in progress, completed, etc.).

[0181] 3. Storage of Information

[0182] The server stores the organized progress report in a database (e.g., AWS® RDS). The stored information includes a summary, status, timestamp, etc.

[0183] 4. Reporting to the Administrator

[0184] The server reports the saved progress information to the administrator as needed via a web interface, allowing the administrator to view the progress information in real time.

[0185] Hardware and software used

[0186] Server: AWS EC2 instance

[0187] Database: AWS RDS (MySQL)

[0188] Generative AI model: OpenAI (registered trademark) GPT model

[0189] Smartphone application: React Native (front end), Node.js (back end)

[0190] Specific examples

[0191] For example, if an automation device is performing a "packaging" task, it will report the following:

[0192] Robot ID: R123

[0193] Task: Packing

[0194] Progress: 70%

[0195] Details: Item is 70% packed and ready for shipping.

[0196] The server analyzes this information and uses a generative artificial intelligence model to generate information organized as follows:

[0197] Summary: "Task: Packing is in progress."

[0198] Status: In progress

[0199] Timestamp: 2023-10-10 15:00:00

[0200] Example prompt for a generative AI model:

[0201] "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[0202] In this way, factory managers can get a real-time view of the progress of their automation equipment through the Factory Insight application. The entire system enables efficient data processing and reporting, allowing managers to make appropriate decisions quickly.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The automation device generates work progress data. The inputs are work progress (robot ID, task, progress rate, detailed information). The output is the generated progress report data. Specifically, the automation device automatically measures the current work progress and summarizes it as a text-format progress report.

[0206] Step 2:

[0207] The automation device sends a progress report to the server. The input is the progress report data from step 1. The output is the progress report sent to the server. Specifically, the automation device sends the progress data using an HTTP POST request.

[0208] Step 3:

[0209] The server receives the progress reports and passes them to the generative AI model. The input is the progress reports received from the automation equipment. The output is the progress data passed to the generative AI model. Specifically, the server analyzes the progress reports, extracts the necessary data, and passes it to the generative AI model.

[0210] Step 4:

[0211] The generative AI model analyzes the progress report and organizes the information. The input is the progress data passed from the server. The output is an organized progress report (summary, status, timestamp). Specifically, the generative AI model generates a summary based on the received data, evaluates the progress of the task, and assigns an appropriate status.

[0212] Example prompt: "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[0213] Step 5:

[0214] The server stores the organized progress reports in a database. The input is the organized progress reports obtained from the generative AI model. The output is progress information stored in a database. Specifically, the server stores the organized data in a database, for example, AWS RDS.

[0215] Step 6:

[0216] The server sends the organized progress report to the administrator's terminal. The input is the progress information stored in the database. The output is the progress information displayed on the administrator's terminal. Specifically, the server allows the administrator to check the progress information in real time through a web interface.

[0217] Step 7:

[0218] The administrator's terminal visualizes the progress information. The input is organized progress information provided by the server. The output is progress data that can be visually confirmed by the administrator. Specifically, the web application on the terminal uses React Native to display the progress information in graph and list format.

[0219] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0220] This invention is a system that uses a generative AI model and an emotion engine to improve the efficiency of progress reports in project management and to report to stakeholders including the user's emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[0221] System Overview

[0222] 1. Server

[0223] The server is started using the Flask framework and accepts HTTP requests from front-end terminals and users. The server provides an endpoint / submit_report for receiving progress reports and an endpoint / get_reports for providing progress information.

[0224] 2. Receiving and processing progress reports

[0225] To report the progress of a project, a user creates information in text format and sends it to the server. This progress report includes the user ID, task details, progress rate, and detailed information.

[0226] The server receives the progress reports and uses a generative AI model to analyze and organize them. The analysis evaluates the progress and status of the task and generates a summary.

[0227] 3. Emotional Information Analysis

[0228] The server uses an emotion engine to analyze the user's emotion information from the progress report. The emotion engine analyzes emotional keywords and contexts in the text and evaluates the user's emotion (e.g., joy, anger, sadness, etc.).

[0229] The emotion information is analyzed, for example, as follows.

[0230] If a user reports, "Implementation of feature A is going well and is nearly complete," the emotion engine will identify "joy."

[0231] 4. Storage of Information

[0232] The server analyzes and organizes the progress and emotion information and stores it in a list in memory. This stored information includes a summary, status, emotion information, timestamp, etc.

[0233] 5. Reporting to relevant parties

[0234] The server provides a web interface for the participants to access the saved progress information, and the participants can check the progress information and emotion information in real time through this interface.

[0235] Specific examples

[0236] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[0237] User ID: 1

[0238] Task: Implement Feature A

[0239] Progress: 50%

[0240] Details: Basic functionality is complete. Test cases in progress.

[0241] When the user sends the above progress report to the server, the server performs the following process.

[0242] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[0243] Summary: "Task: Feature A implementation is in progress."

[0244] Status: In progress

[0245] Timestamp: 2023-10-10 12:00:00

[0246] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[0247] 3. Store organized progress and emotional information in memory.

[0248] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[0249] json

[0250] {

[0251] "summary": "Task: Feature A implementation is in progress.",

[0252] "status": "in progress",

[0253] "emotion": "joy",

[0254] "timestamp": "2023-10-10 12:00:00"

[0255] }

[0256] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[0260] Step 2:

[0261] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[0262] json

[0263] {

[0264] "user_id": 1,

[0265] "task": "Implementation of feature A",

[0266] "progress": 50,

[0267] "details": "Basic functionality done. Test cases in progress."

[0268] }

[0269] Step 3:

[0270] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[0271] Step 4:

[0272] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[0273] Step 5:

[0274] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[0275] Summary: "Task: Feature A implementation is in progress."

[0276] Status: In progress (progress less than 100)

[0277] Timestamp: Current date and time

[0278] Step 6:

[0279] The server passes the progress report text to the emotion engine, which analyzes the user's emotion information. For example, the emotion "joy" is identified from the report "Basic functionality is complete. Test cases are being created."

[0280] Step 7:

[0281] The server stores the generated summary, status, timestamp, and sentiment information in a progress_reports list in memory.

[0282] Step 8:

[0283] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[0284] json

[0285] {

[0286] "message": "Your report has been received."

[0287] }

[0288] Step 9:

[0289] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[0290] Step 10:

[0291] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[0292] Step 11:

[0293] The server returns the acquired progress and emotion information to the relevant parties in JSON format, including a summary of each progress report, its status, emotion information, and a timestamp.

[0294] Specific examples

[0295] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[0296] User ID: 1

[0297] Task: Implement Feature A

[0298] Progress: 50%

[0299] Details: Basic functionality is complete. Test cases in progress.

[0300] When the user sends the above progress report to the server, the server performs the following process.

[0301] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[0302] Summary: "Task: Feature A implementation is in progress."

[0303] Status: In progress

[0304] Timestamp: 2023-10-10 12:00:00

[0305] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[0306] 3. Store organized progress and emotional information in memory.

[0307] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[0308] json

[0309] {

[0310] "summary": "Task: Feature A implementation is in progress.",

[0311] "status": "in progress",

[0312] "emotion": "joy",

[0313] "timestamp": "2023-10-10 12:00:00"

[0314] }

[0315] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[0316] Example 2

[0317] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0318] In conventional project management, progress reporting systems often lack completeness and consideration of emotional aspects, making it difficult for stakeholders to accurately grasp the actual progress. Progress reports are often manually compiled, which is also problematic in terms of efficiency. This reduces the accuracy and effectiveness of project management and tends to hinder communication between stakeholders.

[0319] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0320] In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, emotion analysis means for analyzing user emotion information from the progress reports, and means for incorporating the emotion-analyzed information into the progress reports. This enables efficient organization of progress reports and integration of emotion information, allowing relevant parties to more accurately grasp the progress of the project.

[0321] A "generative artificial intelligence model" refers to an artificial intelligence technology that analyzes input data from users and organizes, converts, and summarizes the content.

[0322] "Progress Report" refers to documents or data that allow a user to provide information about the progress of a particular task or project.

[0323] "Means of organization" refers to the ability to analyze received progress reports and convert, summarize, or reconstruct them into an easily understandable format.

[0324] "Means for storage" refers to the function for temporarily or permanently storing analyzed and organized information in a database or memory.

[0325] "Means of reporting to interested parties" refers to functions, particularly web interfaces and APIs, that provide stored information in a way that makes it easily accessible to interested parties.

[0326] "Emotion analysis means" refers to a function for detecting emotional nuances from a user's progress report and evaluating and classifying specific emotions.

[0327] "Means for incorporating sentiment-analyzed information into progress reports" refers to a function for integrating the results of sentiment analysis with progress report information to provide more comprehensive report content.

[0328] This invention is a system that uses a generative AI model and an emotion analysis engine to improve the efficiency of progress reports in project management and to report to stakeholders including user emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion analysis engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[0329] Hardware and Software Configuration

[0330] 1. Server

[0331] The server is started using the Flask framework and accepts HTTP requests from front-end devices and users.

[0332] The server has an endpoint ( / submit_report) for receiving progress reports and an endpoint ( / get_reports) for providing progress information.

[0333] 2. Generative AI Models

[0334] Analyzes progress reports to assess the progress and status of tasks. Analysis results in summaries and statuses.

[0335] 3. Sentiment Analysis Engine

[0336] Analyze the user's emotional information from the progress report text. Analyze emotional keywords and context in the text to evaluate the user's emotions (joy, anger, sadness, etc.).

[0337] 4. Data Storage

[0338] The analyzed and organized progress and emotion information is stored in a list in memory, including a summary, status, emotion information, timestamp, etc.

[0339] 5. Submission of Reports

[0340] The server provides a web interface for participants to provide progress and sentiment information. Participants can check the progress information in real time through this interface or the endpoint ( / get_reports).

[0341] Specific examples

[0342] For example, when a user reports the progress of a task called "Implementing Function A," the following information is sent to the server:

[0343] User ID: 1

[0344] Task: Implement Feature A

[0345] Progress: 50%

[0346] Details: Basic functionality is complete. Test cases in progress.

[0347] Prompt Sentence Examples

[0348] "Task A is 50% complete. Basic functionality is complete and test cases are currently being written."

[0349] The server passes the received progress report to the generative AI model, which analyzes and organizes the content. For example, the following information is generated:

[0350] Summary: "Task: Feature A implementation is in progress."

[0351] Status: In progress

[0352] Timestamp: 2023-10-10 12:00:00

[0353] The server then uses an emotion analysis engine to analyze the detailed information and identify the emotion "joy." These analysis results are stored in memory, allowing interested parties to view progress and emotion information.

[0354] This system enables efficient organization of progress reports and integration of emotional information, allowing stakeholders to more accurately grasp the progress of the project. Furthermore, by taking into account the user's emotions, a more comprehensive understanding of the actual status of the project can be achieved.

[0355] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0356] Step 1:

[0357] Starting the Server

[0358] The server is started using the Flask framework. The server configures the / submit_report and / get_reports endpoints to accept HTTP requests. It is now ready to receive report data from devices and users. The server output indicates that the endpoints are up and running and ready to accept requests.

[0359] Step 2:

[0360] Receiving progress reports from users

[0361] The user creates project progress information in text format and sends it to the server. Specifically, JSON data containing the user ID, task content, progress rate, and detailed information is sent. The input to the server is this JSON data, and the server receives it. The output of the server is the received progress report data.

[0362] Step 3:

[0363] Analyzing and organizing progress reports using generative AI models

[0364] The server passes the received progress report data to the generative AI model for analysis and organization. The generative AI model evaluates the progress and status of the task and generates a summary and status. The input is the received progress report data, and the output is a summary and status information as the analysis result. Specific operations include analyzing the data and generating a summary.

[0365] Step 4:

[0366] Emotion analysis engine for emotional information analysis

[0367] After analysis by the generative AI model, the server passes the text details of the progress report to the sentiment analysis engine, which analyzes the emotional information. The sentiment analysis engine analyzes emotional keywords and context within the text to evaluate the user's emotions. The input is the text data of the detailed information, and the output is emotional information (joy, anger, sadness, etc.). Specific operations include text analysis and emotion classification.

[0368] Step 5:

[0369] Saving progress and emotion information

[0370] The server integrates the analysis results from the generative AI model with the emotional information from the emotion analysis engine and stores them in a list in memory. The stored data includes a summary, status, emotional information, timestamp, etc. The input is the analyzed progress information and emotional information, and the output is the integrated data stored in memory. Specific operations include data integration and storage.

[0371] Step 6:

[0372] Providing reports to stakeholders

[0373] The server provides a web interface for stakeholders to access the saved progress and emotion information. Stakeholders can check the progress in real time by accessing the / get_reports endpoint. The input is a request from the stakeholder, and the output is the saved progress and emotion information. Specific operations include retrieving data and displaying the web interface.

[0374] These are the specific processing steps of the program. This system improves the accuracy and efficiency of project management, allowing those involved to accurately grasp the progress status.

[0375] (Application example 2)

[0376] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0377] Conventional methods for measuring the effectiveness of advertising campaigns and reporting progress often only provide quantitative data, making it difficult for advertisers and other stakeholders to grasp the actual situation and user sentiment. Furthermore, the lack of a means to efficiently analyze user sentiment information and incorporate it into reports reduces the accuracy and effectiveness of project management. As a result, the effectiveness of advertising campaigns cannot be accurately evaluated, making it difficult to develop effective strategies.

[0378] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, means for generating emotional information using an emotion engine that analyzes emotional information from the content of the progress reports, and means for incorporating the generated emotional information into the content of the progress reports and notifying the relevant parties. This makes it possible to simultaneously report not only information about the progress of an advertising campaign but also user emotional information, enabling more detailed and accurate evaluations and effective strategy planning.

[0379] A "generative artificial intelligence model" is an artificial intelligence model that generates new content or summaries from given data or information.

[0380] A "progress report" is information used to report on the progress of a particular task or project.

[0381] "Information organization" refers to the process or method used to analyze and reconstruct received progress reports in an understandable format.

[0382] "Information storage" refers to the processes and systems used to store organized information and make it accessible at a later time.

[0383] "Means of reporting to stakeholders" refers to methods for providing organized data and information to stakeholders and sharing progress and status.

[0384] An "emotion engine" is a technology or model that analyzes emotions from text, voice, etc., and identifies the type and intensity of those emotions.

[0385] "Emotion information" is data such as the type and intensity of emotions obtained through analysis.

[0386] "Task progress" refers to the state of a task that indicates how far a particular task or operation has progressed.

[0387] An "advertising campaign" is a planned promotional activity to widely publicize a particular product or service and increase its awareness and sales.

[0388] "User emotion information" is emotional data obtained from the user's statements and actions, and indicates an emotional state such as joy, sadness, or anger.

[0389] The system for realizing this invention includes a server, a front-end terminal, and software components such as a generative artificial intelligence model and an emotion engine.

[0390] 1. Server configuration and processing

[0391] The server uses the Flask framework to handle HTTP requests and provides the following main endpoints:

[0392] / submit_report: Receive progress reports from users.

[0393] / get_reports: Provides organized progress and sentiment information.

[0394] The server has the following roles:

[0395] 1. Receive progress reports from users.

[0396] 2. Analyze the report content using a generative AI model and generate a summary.

[0397] 3. Analyze the emotional information of progress reports using an emotion engine.

[0398] 4. Store organized progress and emotional information.

[0399] 5. Report the stored information to the relevant parties.

[0400] 2. User behavior and device usage

[0401] The user enters the following information from a smartphone or other front-end device:

[0402] User ID

[0403] Campaign ID

[0404] Description (progress details)

[0405] Progress rate

[0406] This information is sent to the server in JSON format.

[0407] 3. Use of generative AI models and emotion engines

[0408] When the server receives a progress report, a generative AI model analyzes the report and generates a summary. An emotion engine analyzes the emotional information from the progress report text and identifies the emotion. The analyzed emotional information is incorporated into the report as a specific emotion (e.g., joy or sadness).

[0409] 4. Storage and reporting

[0410] The organized progress information and emotion information are stored in a server and provided to the participants in real time, who can check the progress information and emotion information in real time through a web interface.

[0411] Specific examples

[0412] For example, in an ad campaign progress report, a user submits the following:

[0413] User ID: 123

[0414] Campaign ID: 456

[0415] Explanation: Campaign A's webpage traffic is skyrocketing, and sales conversions are steadily increasing.

[0416] Progress: 75%

[0417] The server performs the following process.

[0418] 1. Pass the progress report to a generative AI model to generate a summary (e.g., "Campaign A is progressing well.").

[0419] 2. Use the emotion engine to analyze the emotion "joy" from the report content.

[0420] 3. Store organized information and emotional information and report it to the relevant parties.

[0421] Prompt Sentence Examples

[0422] An example of a prompt for the user to report progress is as follows:

[0423] Please send us your campaign progress report using the following information:

[0424] User ID: Enter your user ID

[0425] Campaign ID: Enter the campaign ID.

[0426] Description: Give specific details about the progress of your campaign

[0427] Progress rate: Enter the progress rate in %

[0428] Through the above process, the system can simultaneously report information about the progress of the advertising campaign and user sentiment information, helping stakeholders make more specific and accurate evaluations.

[0429] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0430] Step 1:

[0431] The user enters a progress report using a smartphone or front-end device. The input includes the user ID, campaign ID, detailed progress description, and progress rate. This information is sent to the server in JSON format. For example, enter the following:

[0432] {

[0433] "user_id": "123",

[0434] "campaign_id": "456",

[0435] "explanation": "Webpage traffic for Campaign A has skyrocketed, and sales conversions are steadily increasing.",

[0436] "progress": 75

[0437] }

[0438] Input: User ID, Campaign ID, Description, Progress Rate

[0439] Output: Progress report data in JSON format

[0440] Step 2:

[0441] The server processes the received progress report data. Specifically, it passes the progress report data to a generative AI model, which analyzes and summarizes the report content. The generative AI model analyzes the explanatory text and generates a summary such as "Campaign A is progressing smoothly."

[0442] Input: Progress report data in JSON format

[0443] Output: A summary of the analyzed progress report

[0444] Step 3:

[0445] The server uses an emotion engine to analyze the emotional information from the report content. Specifically, it extracts emotional keywords such as "rapid increase" and "steady rise" from the text and evaluates the emotion of "joy."

[0446] Input: Progress report description text

[0447] Output: Parsed emotion information (e.g., joy)

[0448] Step 4:

[0449] The server combines the generated summary with the analyzed emotion information to construct organized progress information, which includes progress report content, summary, emotion information, and timestamp.

[0450] Input: Summary, sentiment information, progress report details

[0451] Output: Organized progress information

[0452] Step 5:

[0453] The server stores organized progress information in memory, including summaries, emotion information, status, and timestamps.

[0454] Input: Organized progress information

[0455] Output: Saved progress information

[0456] Step 6:

[0457] The server reports the saved progress information to the participants through a web interface, which participants can access from a browser and view the progress information and emotion information in real time.

[0458] Input: Saved progress information

[0459] Output: Progress and sentiment information provided to stakeholders

[0460] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0461] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0462] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0463] [Second embodiment]

[0464] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0465] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0466] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0467] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0468] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0469] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0470] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0471] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0472] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0473] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0474] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0475] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0476] The present invention is a system for improving the efficiency of progress reports in project management by using a generative artificial intelligence model. This system includes a series of processes for receiving progress reports from users, organizing them using a generative artificial intelligence model, storing them, and reporting them to relevant parties.

[0477] System Overview

[0478] 1. Server

[0479] The server runs and provides a web interface to accept HTTP requests from front-end terminals and users.

[0480] The server receives the progress reports and analyzes and organizes them using a generative artificial intelligence model.

[0481] 2. Receiving and processing progress reports

[0482] A user creates a text file to report the progress of a project and sends it to the server. The progress report includes the user ID, task details, progress rate, and detailed information.

[0483] The server analyzes the received progress reports and organizes them using a generative artificial intelligence model. This organization process generates summaries from the reports, evaluates the progress of the tasks, and assigns appropriate statuses (e.g., in progress, completed).

[0484] 3. Storage of Information

[0485] The server stores organized progress reports in memory, including summary, status, and timestamp information.

[0486] 4. Reporting to relevant parties

[0487] The server reports the saved progress information to the relevant parties as needed. This reporting is done through a web interface, allowing the relevant parties to check the progress information as needed.

[0488] Specific examples

[0489] For example, suppose a user wants to report on the progress of a task called "Implementing Feature A." The user enters the following information:

[0490] User ID: 1

[0491] Task: Implement Feature A

[0492] Progress: 50%

[0493] Details: Basic functionality is complete. Test cases in progress.

[0494] When the user sends this information to the server, the server receives it, passes it to a generative AI model for analysis and organization, and generates the following organized information:

[0495] Summary: "Task: Feature A implementation is in progress."

[0496] Status: In progress

[0497] Timestamp: 2023-10-10 12:00:00

[0498] The server stores this information and allows stakeholders to view progress through a web interface, providing real-time visibility into project progress and enabling early identification of incomplete or delayed tasks.

[0499] The above is an example of an embodiment of the present invention. This system not only improves the efficiency of progress reports, but also significantly improves the overall project management and communication between the parties involved.

[0500] The processing flow will be explained below.

[0501] Step 1:

[0502] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[0503] Step 2:

[0504] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[0505] json

[0506] {

[0507] "user_id": 1,

[0508] "task": "Implementation of feature A",

[0509] "progress": 50,

[0510] "details": "Basic functionality done. Test cases in progress."

[0511] }

[0512] Step 3:

[0513] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[0514] Step 4:

[0515] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[0516] Step 5:

[0517] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[0518] Summary: "Task: Feature A implementation is in progress."

[0519] Status: In progress (progress less than 100)

[0520] Timestamp: Current date and time

[0521] Step 6:

[0522] The server saves the generated and organized information by adding it to the progress_reports list in memory.

[0523] Step 7:

[0524] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[0525] json

[0526] {

[0527] "message": "Your report has been received."

[0528] }

[0529] Step 8:

[0530] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[0531] Step 9:

[0532] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[0533] Step 10:

[0534] The server returns the progress information it has obtained to the relevant parties in JSON format, including a summary of each progress report, its status, and a timestamp.

[0535] Through these steps, the project management system utilizing generative artificial intelligence functions efficiently, effectively organizing progress reports and sharing information with stakeholders.

[0536] Example 1

[0537] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0538] In conventional project management, progress reporting is often done manually, resulting in inefficient information organization and reporting, and problems such as delays in communication and misunderstandings between stakeholders. These problems are particularly pronounced in large-scale projects, making it difficult to grasp the project's progress in real time. Therefore, the present invention aims to solve these problems and improve the efficiency of progress reporting and communication between stakeholders.

[0539] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0540] In this invention, the server includes: means for receiving progress reports and analyzing and organizing them using a generative artificial intelligence model; means for saving the organized information; means for reporting to relevant parties; means for the server to start up and accept HTTP requests from users and analyze and organize the progress reports; means for users to input progress reports through their terminals and send them to the server; means for the generative artificial intelligence model to analyze and organize the progress reports using prompt statements based on the progress reports; means for saving the generated summaries and statuses in memory; and means for reporting the saved progress information to relevant parties via a web interface so that the status can be checked in real time. This improves the efficiency of progress reports, enables the progress of the entire project to be grasped in real time, facilitates communication between relevant parties, and improves the accuracy of project management.

[0541] A "generative artificial intelligence model" is an artificial intelligence model that analyzes and organizes information based on data provided by the user, and automatically generates summaries and statuses.

[0542] "Progress report" is data such as task name, progress rate, detailed information, etc. that a user inputs to report the progress of a project.

[0543] The "server" is a computer system whose role is to receive requests from users, analyze and organize progress reports using a generative artificial intelligence model, store the information, and report it to relevant parties.

[0544] An "HTTP request" is a request for information sent by a user through a web interface to a server, whether for progress reporting or to perform other operations.

[0545] "Web Interface" means a web-based user interface that allows a user to enter progress reports and review stored information.

[0546] A "prompt sentence" is an instruction sentence that instructs a generative artificial intelligence model to perform a specific task, and is a sentence used when analyzing and organizing.

[0547] A "summary" is concise information extracted from a progress report by a generative artificial intelligence model that provides the core of the task.

[0548] "Status" is information that is evaluated by the generative artificial intelligence model based on progress reports and assigned to indicate the progress of a task, and represents a state such as "in progress" or "completed."

[0549] "Storage" refers to the server keeping organized progress information in memory or a database so that it can be accessed later.

[0550] A "stakeholder" is a person or organization that has an interest in the progress of the project and has the authority to review reported progress information.

[0551] "Real-time" refers to a state in which progress information is saved and can be accessed by relevant parties at the same time, and information is shared instantly.

[0552] The present invention is a system for improving the efficiency of progress reports in project management using a generative artificial intelligence model. This system is realized through cooperation between a server, terminals, and users.

[0553] The overall system configuration is as follows:

[0554] 1. Server

[0555] The server is run by web server software such as Apache or Nginx.

[0556] The server is implemented using a programming language such as Python or Node.js and provides a REST API for accepting HTTP requests from users.

[0557] The server analyzes and organizes the progress reports using a generative artificial intelligence model (e.g., GPT-4).

[0558] 2. Terminal

[0559] The device uses a browser to display a web interface composed of HTML, CSS, and JavaScript.

[0560] The user inputs a progress report using a terminal and sends it to the server as an HTTP POST request.

[0561] Next, a series of processes performed by this system will be described in detail.

[0562] First, the user accesses the web interface on the terminal and enters the necessary information into the progress report form, specifically the task name, progress rate, detailed information, etc. Once the input is complete, the user presses the send button, and the terminal sends the information to the server.

[0563] The data received by the server is first parsed in JSON format and temporarily stored in internal memory. Next, the server generates a prompt for the generative AI model. This prompt contains the progress report entered by the user. For example, the prompt has the following format:

[0564] "Please summarize the progress information below and assign an appropriate status. Content: Feature A implemented. Progress: 50%. Details: Basic functionality completed. Test cases being created."

[0565] The generative AI model analyzes the prompt, summarizes the report, and returns the result with an appropriate status to the server. For example, the output might look something like this:

[0566] Summary: "Task: Feature A implementation is in progress."

[0567] Status: In progress

[0568] Timestamp: 2023-10-10 12:00:00

[0569] The server receives this information and stores it in a database (e.g. MySQL, PostgreSQL), which contains a summary, status, and timestamp.

[0570] Finally, the server provides a web interface that allows stakeholders to view real-time progress information, for example, by accessing a dashboard on the web interface, allowing stakeholders to view the latest progress.

[0571] In this way, the system of the present invention realizes more efficient progress reporting and more accurate project management.

[0572] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0573] Step 1:

[0574] The user accesses the web interface on the terminal and enters information into a progress report form.

[0575] Input: Task name, progress, and details.

[0576] Specific operation: A user opens a web page using a browser and enters the task name (e.g., Implementing Feature A), progress rate (e.g., 50%), and details (e.g., Basic functionality completed. Test cases being created.) into the progress report form. When the user presses the "Submit" button, the terminal formats this information and sends it to the server as an HTTP POST request.

[0577] Step 2:

[0578] The server receives the HTTP POST request and parses the data.

[0579] Input: Progress report data submitted by the user (task name, progress percentage, details).

[0580] Output: Data converted to JSON format.

[0581] What happens: The server receives an HTTP POST request, parses the data in the request body, converts it to JSON format, and temporarily stores it in internal memory.

[0582] Step 3:

[0583] The server sends a prompt to the generative artificial intelligence model, requesting it to analyze and organize the data.

[0584] Input: Progress report data in JSON format, generated prompt text.

[0585] Output: A summary and status returned by the generative AI model.

[0586] Specific operation: The server generates a prompt based on the progress report data. Example prompt: "Please summarize the following progress information and assign an appropriate status. Content: Implementing feature A. Progress rate: 50%. Details: Basic functionality is complete. Test cases are being created." The generated prompt is sent to the API of the generative AI model, and a summary and status are returned.

[0587] Step 4:

[0588] The server stores the output of the generative artificial intelligence model in a database.

[0589] Input: Summary and status generated by the model, timestamp of progress report.

[0590] Output: Progress information stored in a database.

[0591] What it does: The server saves the summary and status received from the generative AI model, along with the current timestamp, in a database (e.g., MySQL, PostgreSQL), by executing a SQL query to insert the information into the appropriate tables.

[0592] Step 5:

[0593] The server reports progress information to interested parties and provides a web interface.

[0594] Input: Progress information stored in the database.

[0595] Output: Latest progress information displayed on the web interface.

[0596] What it does: The server retrieves the latest progress information from the database and displays it on a dashboard on a web interface. Stakeholders can access the dashboard using a browser to check the latest progress information in real time. It can also send alerts via email or push notification when certain conditions are met.

[0597] As a result, users, terminals, and servers work together to improve the efficiency of progress reports and the accuracy of project management.

[0598] (Application example 1)

[0599] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0600] In modern production plants, efficient and real-time reporting and management of the work progress of automated equipment is required. However, manual reporting and management requires time and effort, and progress information often lacks accuracy and speed. Furthermore, if managers cannot grasp the work progress status of equipment within the facility in a timely manner, optimal production management becomes difficult. There is a need for a system to solve this situation.

[0601] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0602] In this invention, the server includes means for receiving progress reports from automation equipment using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to a manager, means for saving the organized information in a database, and means for providing an interface for visualizing the organized information. This makes it possible to efficiently collect, organize, and report work progress information from automation equipment in real time, allowing managers to quickly and appropriately manage production.

[0603] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes data provided by users or devices and generates solutions or insights for specific problems.

[0604] "Automation equipment" refers to robots and automation devices used to automate work in production factories, etc.

[0605] A "progress report" is a report or data that organizes and provides information about the progress of a particular task or piece of work.

[0606] "Means for organizing information" refers to a method or apparatus that uses a generative artificial intelligence model to extract necessary information from received progress reports and organize it in a structured format.

[0607] "Means for storing information" refers to a method or device for storing organized information in a storage device such as a database or memory.

[0608] "Means for reporting information to an administrator" refers to a method or device for notifying an administrator of stored information as necessary so that the administrator can check it.

[0609] A "database" is a system that efficiently stores and manages organized progress information, allowing it to be quickly searched and accessed when needed.

[0610] "Interface" refers to a screen or web application that allows users or administrators to visually check and operate information.

[0611] "Work progress" is the indicator or data that shows how far a particular task or project has progressed.

[0612] The "task status" is information indicating the current status of the work, such as in progress, completed, or delayed.

[0613] "Status" is a label or tag used to express the progress of a task or project.

[0614] This invention provides a system for efficiently reporting and managing the work progress of automation equipment in a factory. The system includes a series of processes that use a generative artificial intelligence model to analyze the progress report and report it to a manager.

[0615] The system includes the following elements:

[0616] 1. Server

[0617] The server provides a web interface to accept HTTP requests from automation devices and administrator terminals.

[0618] The server receives progress reports from the automation equipment and uses a generative artificial intelligence model to analyze and organize the reports.

[0619] 2. Receiving and processing progress reports

[0620] The automation device describes its work progress in text format and sends the information to the server. The progress report includes the robot ID, task content, progress rate, and detailed information.

[0621] The server analyzes the received progress reports and organizes them using a generative AI model to generate summaries, evaluate the progress of tasks, and assign appropriate statuses (e.g., in progress, completed, etc.).

[0622] 3. Storage of Information

[0623] The server stores the organized progress report in a database (e.g. AWS RDS), including summary, status, timestamp, etc.

[0624] 4. Reporting to the Administrator

[0625] The server reports the saved progress information to the administrator as needed via a web interface, allowing the administrator to view the progress information in real time.

[0626] Hardware and software used

[0627] Server: AWS EC2 instance

[0628] Database: AWS RDS (MySQL)

[0629] Generative AI model: OpenAI's GPT model

[0630] Smartphone application: React Native (front end), Node.js (back end)

[0631] Specific examples

[0632] For example, if an automation device is performing a "packaging" task, it will report the following:

[0633] Robot ID: R123

[0634] Task: Packing

[0635] Progress: 70%

[0636] Details: Item is 70% packed and ready for shipping.

[0637] The server analyzes this information and uses a generative artificial intelligence model to generate information organized as follows:

[0638] Summary: "Task: Packing is in progress."

[0639] Status: In progress

[0640] Timestamp: 2023-10-10 15:00:00

[0641] Example prompt for a generative AI model:

[0642] "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[0643] In this way, factory managers can get a real-time view of the progress of their automation equipment through the Factory Insight application. The entire system enables efficient data processing and reporting, allowing managers to make appropriate decisions quickly.

[0644] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0645] Step 1:

[0646] The automation device generates work progress data. The inputs are work progress (robot ID, task, progress rate, detailed information). The output is the generated progress report data. Specifically, the automation device automatically measures the current work progress and summarizes it as a text-format progress report.

[0647] Step 2:

[0648] The automation device sends a progress report to the server. The input is the progress report data from step 1. The output is the progress report sent to the server. Specifically, the automation device sends the progress data using an HTTP POST request.

[0649] Step 3:

[0650] The server receives the progress reports and passes them to the generative AI model. The input is the progress reports received from the automation equipment. The output is the progress data passed to the generative AI model. Specifically, the server analyzes the progress reports, extracts the necessary data, and passes it to the generative AI model.

[0651] Step 4:

[0652] The generative AI model analyzes the progress report and organizes the information. The input is the progress data passed from the server. The output is an organized progress report (summary, status, timestamp). Specifically, the generative AI model generates a summary based on the received data, evaluates the progress of the task, and assigns an appropriate status.

[0653] Example prompt: "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[0654] Step 5:

[0655] The server stores the organized progress reports in a database. The input is the organized progress reports obtained from the generative AI model. The output is progress information stored in a database. Specifically, the server stores the organized data in a database, for example, AWS RDS.

[0656] Step 6:

[0657] The server sends the organized progress report to the administrator's terminal. The input is the progress information stored in the database. The output is the progress information displayed on the administrator's terminal. Specifically, the server allows the administrator to check the progress information in real time through a web interface.

[0658] Step 7:

[0659] The administrator's terminal visualizes the progress information. The input is organized progress information provided by the server. The output is progress data that can be visually confirmed by the administrator. Specifically, the web application on the terminal uses React Native to display the progress information in graph and list format.

[0660] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0661] This invention is a system that uses a generative AI model and an emotion engine to improve the efficiency of progress reports in project management and to report to stakeholders including the user's emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[0662] System Overview

[0663] 1. Server

[0664] The server is started using the Flask framework and accepts HTTP requests from front-end terminals and users. The server provides an endpoint / submit_report for receiving progress reports and an endpoint / get_reports for providing progress information.

[0665] 2. Receiving and processing progress reports

[0666] To report the progress of a project, a user creates information in text format and sends it to the server. This progress report includes the user ID, task details, progress rate, and detailed information.

[0667] The server receives the progress reports and uses a generative AI model to analyze and organize them. The analysis evaluates the progress and status of the task and generates a summary.

[0668] 3. Emotional Information Analysis

[0669] The server uses an emotion engine to analyze the user's emotion information from the progress report. The emotion engine analyzes emotional keywords and contexts in the text and evaluates the user's emotion (e.g., joy, anger, sadness, etc.).

[0670] The emotion information is analyzed, for example, as follows.

[0671] If a user reports, "Implementation of feature A is going well and is nearly complete," the emotion engine will identify "joy."

[0672] 4. Storage of Information

[0673] The server analyzes and organizes the progress and emotion information and stores it in a list in memory. This stored information includes a summary, status, emotion information, timestamp, etc.

[0674] 5. Reporting to relevant parties

[0675] The server provides a web interface for the participants to access the saved progress information, and the participants can check the progress information and emotion information in real time through this interface.

[0676] Specific examples

[0677] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[0678] User ID: 1

[0679] Task: Implement Feature A

[0680] Progress: 50%

[0681] Details: Basic functionality is complete. Test cases in progress.

[0682] When the user sends the above progress report to the server, the server performs the following process.

[0683] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[0684] Summary: "Task: Feature A implementation is in progress."

[0685] Status: In progress

[0686] Timestamp: 2023-10-10 12:00:00

[0687] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[0688] 3. Store organized progress and emotional information in memory.

[0689] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[0690] json

[0691] {

[0692] "summary": "Task: Feature A implementation is in progress.",

[0693] "status": "in progress",

[0694] "emotion": "joy",

[0695] "timestamp": "2023-10-10 12:00:00"

[0696] }

[0697] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[0698] The processing flow will be explained below.

[0699] Step 1:

[0700] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[0701] Step 2:

[0702] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[0703] json

[0704] {

[0705] "user_id": 1,

[0706] "task": "Implementation of feature A",

[0707] "progress": 50,

[0708] "details": "Basic functionality done. Test cases in progress."

[0709] }

[0710] Step 3:

[0711] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[0712] Step 4:

[0713] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[0714] Step 5:

[0715] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[0716] Summary: "Task: Feature A implementation is in progress."

[0717] Status: In progress (progress less than 100)

[0718] Timestamp: Current date and time

[0719] Step 6:

[0720] The server passes the progress report text to the emotion engine, which analyzes the user's emotion information. For example, the emotion "joy" is identified from the report "Basic functionality is complete. Test cases are being created."

[0721] Step 7:

[0722] The server stores the generated summary, status, timestamp, and sentiment information in a progress_reports list in memory.

[0723] Step 8:

[0724] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[0725] json

[0726] {

[0727] "message": "Your report has been received."

[0728] }

[0729] Step 9:

[0730] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[0731] Step 10:

[0732] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[0733] Step 11:

[0734] The server returns the acquired progress and emotion information to the relevant parties in JSON format, including a summary of each progress report, its status, emotion information, and a timestamp.

[0735] Specific examples

[0736] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[0737] User ID: 1

[0738] Task: Implement Feature A

[0739] Progress: 50%

[0740] Details: Basic functionality is complete. Test cases in progress.

[0741] When the user sends the above progress report to the server, the server performs the following process.

[0742] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[0743] Summary: "Task: Feature A implementation is in progress."

[0744] Status: In progress

[0745] Timestamp: 2023-10-10 12:00:00

[0746] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[0747] 3. Store organized progress and emotional information in memory.

[0748] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[0749] json

[0750] {

[0751] "summary": "Task: Feature A implementation is in progress.",

[0752] "status": "in progress",

[0753] "emotion": "joy",

[0754] "timestamp": "2023-10-10 12:00:00"

[0755] }

[0756] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[0757] Example 2

[0758] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0759] In conventional project management, progress reporting systems often lack completeness and consideration of emotional aspects, making it difficult for stakeholders to accurately grasp the actual progress. Progress reports are often manually compiled, which is also problematic in terms of efficiency. This reduces the accuracy and effectiveness of project management and tends to hinder communication between stakeholders.

[0760] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0761] In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, emotion analysis means for analyzing user emotion information from the progress reports, and means for incorporating the emotion-analyzed information into the progress reports. This enables efficient organization of progress reports and integration of emotion information, allowing relevant parties to more accurately grasp the progress of the project.

[0762] A "generative artificial intelligence model" refers to an artificial intelligence technology that analyzes input data from users and organizes, converts, and summarizes the content.

[0763] "Progress Report" refers to documents or data that allow a user to provide information about the progress of a particular task or project.

[0764] "Means of organization" refers to the ability to analyze received progress reports and convert, summarize, or reconstruct them into an easily understandable format.

[0765] "Means for storage" refers to the function for temporarily or permanently storing analyzed and organized information in a database or memory.

[0766] "Means of reporting to interested parties" refers to functions, particularly web interfaces and APIs, that provide stored information in a way that makes it easily accessible to interested parties.

[0767] "Emotion analysis means" refers to a function for detecting emotional nuances from a user's progress report and evaluating and classifying specific emotions.

[0768] "Means for incorporating sentiment-analyzed information into progress reports" refers to a function for integrating the results of sentiment analysis with progress report information to provide more comprehensive report content.

[0769] This invention is a system that uses a generative AI model and an emotion analysis engine to improve the efficiency of progress reports in project management and to report to stakeholders including user emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion analysis engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[0770] Hardware and Software Configuration

[0771] 1. Server

[0772] The server is started using the Flask framework and accepts HTTP requests from front-end devices and users.

[0773] The server has an endpoint ( / submit_report) for receiving progress reports and an endpoint ( / get_reports) for providing progress information.

[0774] 2. Generative AI Models

[0775] Analyzes progress reports to assess the progress and status of tasks. Analysis results in summaries and statuses.

[0776] 3. Sentiment Analysis Engine

[0777] Analyze the user's emotional information from the progress report text. Analyze emotional keywords and context in the text to evaluate the user's emotions (joy, anger, sadness, etc.).

[0778] 4. Data Storage

[0779] The analyzed and organized progress and emotion information is stored in a list in memory, including a summary, status, emotion information, timestamp, etc.

[0780] 5. Submission of Reports

[0781] The server provides a web interface for participants to provide progress and sentiment information. Participants can check the progress information in real time through this interface or the endpoint ( / get_reports).

[0782] Specific examples

[0783] For example, when a user reports the progress of a task called "Implementing Function A," the following information is sent to the server:

[0784] User ID: 1

[0785] Task: Implement Feature A

[0786] Progress: 50%

[0787] Details: Basic functionality is complete. Test cases in progress.

[0788] Prompt Sentence Examples

[0789] "Task A is 50% complete. Basic functionality is complete and test cases are currently being written."

[0790] The server passes the received progress report to the generative AI model, which analyzes and organizes the content. For example, the following information is generated:

[0791] Summary: "Task: Feature A implementation is in progress."

[0792] Status: In progress

[0793] Timestamp: 2023-10-10 12:00:00

[0794] The server then uses an emotion analysis engine to analyze the detailed information and identify the emotion "joy." These analysis results are stored in memory, allowing interested parties to view progress and emotion information.

[0795] This system enables efficient organization of progress reports and integration of emotional information, allowing stakeholders to more accurately grasp the progress of the project. Furthermore, by taking into account the user's emotions, a more comprehensive understanding of the actual status of the project can be achieved.

[0796] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0797] Step 1:

[0798] Starting the Server

[0799] The server is started using the Flask framework. The server configures the / submit_report and / get_reports endpoints to accept HTTP requests. It is now ready to receive report data from devices and users. The server output indicates that the endpoints are up and running and ready to accept requests.

[0800] Step 2:

[0801] Receiving progress reports from users

[0802] The user creates project progress information in text format and sends it to the server. Specifically, JSON data containing the user ID, task content, progress rate, and detailed information is sent. The input to the server is this JSON data, and the server receives it. The output of the server is the received progress report data.

[0803] Step 3:

[0804] Analyzing and organizing progress reports using generative AI models

[0805] The server passes the received progress report data to the generative AI model for analysis and organization. The generative AI model evaluates the progress and status of the task and generates a summary and status. The input is the received progress report data, and the output is a summary and status information as the analysis result. Specific operations include analyzing the data and generating a summary.

[0806] Step 4:

[0807] Emotion analysis engine for emotional information analysis

[0808] After analysis by the generative AI model, the server passes the text details of the progress report to the sentiment analysis engine, which analyzes the emotional information. The sentiment analysis engine analyzes emotional keywords and context within the text to evaluate the user's emotions. The input is the text data of the detailed information, and the output is emotional information (joy, anger, sadness, etc.). Specific operations include text analysis and emotion classification.

[0809] Step 5:

[0810] Saving progress and emotion information

[0811] The server integrates the analysis results from the generative AI model with the emotional information from the emotion analysis engine and stores them in a list in memory. The stored data includes a summary, status, emotional information, timestamp, etc. The input is the analyzed progress information and emotional information, and the output is the integrated data stored in memory. Specific operations include data integration and storage.

[0812] Step 6:

[0813] Providing reports to stakeholders

[0814] The server provides a web interface for stakeholders to access the saved progress and emotion information. Stakeholders can check the progress in real time by accessing the / get_reports endpoint. The input is a request from the stakeholder, and the output is the saved progress and emotion information. Specific operations include retrieving data and displaying the web interface.

[0815] These are the specific processing steps of the program. This system improves the accuracy and efficiency of project management, allowing those involved to accurately grasp the progress status.

[0816] (Application example 2)

[0817] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0818] Conventional methods for measuring the effectiveness of advertising campaigns and reporting progress often only provide quantitative data, making it difficult for advertisers and other stakeholders to grasp the actual situation and user sentiment. Furthermore, the lack of a means to efficiently analyze user sentiment information and incorporate it into reports reduces the accuracy and effectiveness of project management. As a result, the effectiveness of advertising campaigns cannot be accurately evaluated, making it difficult to develop effective strategies.

[0819] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, means for generating emotional information using an emotion engine that analyzes emotional information from the content of the progress reports, and means for incorporating the generated emotional information into the content of the progress reports and notifying the relevant parties. This makes it possible to simultaneously report not only information about the progress of an advertising campaign but also user emotional information, enabling more detailed and accurate evaluations and effective strategy planning.

[0820] A "generative artificial intelligence model" is an artificial intelligence model that generates new content or summaries from given data or information.

[0821] A "progress report" is information used to report on the progress of a particular task or project.

[0822] "Information organization" refers to the process or method used to analyze and reconstruct received progress reports in an understandable format.

[0823] "Information storage" refers to the processes and systems used to store organized information and make it accessible at a later time.

[0824] "Means of reporting to stakeholders" refers to methods for providing organized data and information to stakeholders and sharing progress and status.

[0825] An "emotion engine" is a technology or model that analyzes emotions from text, voice, etc., and identifies the type and intensity of those emotions.

[0826] "Emotion information" is data such as the type and intensity of emotions obtained through analysis.

[0827] "Task progress" refers to the state of a task that indicates how far a particular task or operation has progressed.

[0828] An "advertising campaign" is a planned promotional activity to widely publicize a particular product or service and increase its awareness and sales.

[0829] "User emotion information" is emotional data obtained from the user's statements and actions, and indicates an emotional state such as joy, sadness, or anger.

[0830] The system for realizing this invention includes a server, a front-end terminal, and software components such as a generative artificial intelligence model and an emotion engine.

[0831] 1. Server configuration and processing

[0832] The server uses the Flask framework to handle HTTP requests and provides the following main endpoints:

[0833] / submit_report: Receive progress reports from users.

[0834] / get_reports: Provides organized progress and sentiment information.

[0835] The server has the following roles:

[0836] 1. Receive progress reports from users.

[0837] 2. Analyze the report content using a generative AI model and generate a summary.

[0838] 3. Analyze the emotional information of progress reports using an emotion engine.

[0839] 4. Store organized progress and emotional information.

[0840] 5. Report the stored information to the relevant parties.

[0841] 2. User behavior and device usage

[0842] The user enters the following information from a smartphone or other front-end device:

[0843] User ID

[0844] Campaign ID

[0845] Description (progress details)

[0846] Progress rate

[0847] This information is sent to the server in JSON format.

[0848] 3. Use of generative AI models and emotion engines

[0849] When the server receives a progress report, a generative AI model analyzes the report and generates a summary. An emotion engine analyzes the emotional information from the progress report text and identifies the emotion. The analyzed emotional information is incorporated into the report as a specific emotion (e.g., joy or sadness).

[0850] 4. Storage and reporting

[0851] The organized progress information and emotion information are stored in a server and provided to the participants in real time, who can check the progress information and emotion information in real time through a web interface.

[0852] Specific examples

[0853] For example, in an ad campaign progress report, a user submits the following:

[0854] User ID: 123

[0855] Campaign ID: 456

[0856] Explanation: Campaign A's webpage traffic is skyrocketing, and sales conversions are steadily increasing.

[0857] Progress: 75%

[0858] The server performs the following process.

[0859] 1. Pass the progress report to a generative AI model to generate a summary (e.g., "Campaign A is progressing well.").

[0860] 2. Use the emotion engine to analyze the emotion "joy" from the report content.

[0861] 3. Store organized information and emotional information and report it to the relevant parties.

[0862] Prompt Sentence Examples

[0863] An example of a prompt for the user to report progress is as follows:

[0864] Please send us your campaign progress report using the following information:

[0865] User ID: Enter your user ID

[0866] Campaign ID: Enter the campaign ID.

[0867] Description: Give specific details about the progress of your campaign

[0868] Progress rate: Enter the progress rate in %

[0869] Through the above process, the system can simultaneously report information about the progress of the advertising campaign and user sentiment information, helping stakeholders make more specific and accurate evaluations.

[0870] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0871] Step 1:

[0872] The user enters a progress report using a smartphone or front-end device. The input includes the user ID, campaign ID, detailed progress description, and progress rate. This information is sent to the server in JSON format. For example, enter the following:

[0873] {

[0874] "user_id": "123",

[0875] "campaign_id": "456",

[0876] "explanation": "Webpage traffic for Campaign A has skyrocketed, and sales conversions are steadily increasing.",

[0877] "progress": 75

[0878] }

[0879] Input: User ID, Campaign ID, Description, Progress Rate

[0880] Output: Progress report data in JSON format

[0881] Step 2:

[0882] The server processes the received progress report data. Specifically, it passes the progress report data to a generative AI model, which analyzes and summarizes the report content. The generative AI model analyzes the explanatory text and generates a summary such as "Campaign A is progressing smoothly."

[0883] Input: Progress report data in JSON format

[0884] Output: A summary of the analyzed progress report

[0885] Step 3:

[0886] The server uses an emotion engine to analyze the emotional information from the report content. Specifically, it extracts emotional keywords such as "rapid increase" and "steady rise" from the text and evaluates the emotion of "joy."

[0887] Input: Progress report description text

[0888] Output: Parsed emotion information (e.g., joy)

[0889] Step 4:

[0890] The server combines the generated summary with the analyzed emotion information to construct organized progress information, which includes progress report content, summary, emotion information, and timestamp.

[0891] Input: Summary, sentiment information, progress report details

[0892] Output: Organized progress information

[0893] Step 5:

[0894] The server stores organized progress information in memory, including summaries, emotion information, status, and timestamps.

[0895] Input: Organized progress information

[0896] Output: Saved progress information

[0897] Step 6:

[0898] The server reports the saved progress information to the participants through a web interface, which participants can access from a browser and view the progress information and emotion information in real time.

[0899] Input: Saved progress information

[0900] Output: Progress and sentiment information provided to stakeholders

[0901] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0902] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0903] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0904] [Third embodiment]

[0905] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0906] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0907] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0908] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0909] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0910] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0911] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0912] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0913] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0914] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0915] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0916] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0917] The present invention is a system for improving the efficiency of progress reports in project management by using a generative artificial intelligence model. This system includes a series of processes for receiving progress reports from users, organizing them using a generative artificial intelligence model, storing them, and reporting them to relevant parties.

[0918] System Overview

[0919] 1. Server

[0920] The server runs and provides a web interface to accept HTTP requests from front-end terminals and users.

[0921] The server receives the progress reports and analyzes and organizes them using a generative artificial intelligence model.

[0922] 2. Receiving and processing progress reports

[0923] A user creates a text file to report the progress of a project and sends it to the server. The progress report includes the user ID, task details, progress rate, and detailed information.

[0924] The server analyzes the received progress reports and organizes them using a generative artificial intelligence model. This organization process generates summaries from the reports, evaluates the progress of the tasks, and assigns appropriate statuses (e.g., in progress, completed).

[0925] 3. Storage of Information

[0926] The server stores organized progress reports in memory, including summary, status, and timestamp information.

[0927] 4. Reporting to relevant parties

[0928] The server reports the saved progress information to the relevant parties as needed. This reporting is done through a web interface, allowing the relevant parties to check the progress information as needed.

[0929] Specific examples

[0930] For example, suppose a user wants to report on the progress of a task called "Implementing Feature A." The user enters the following information:

[0931] User ID: 1

[0932] Task: Implement Feature A

[0933] Progress: 50%

[0934] Details: Basic functionality is complete. Test cases in progress.

[0935] When the user sends this information to the server, the server receives it, passes it to a generative AI model for analysis and organization, and generates the following organized information:

[0936] Summary: "Task: Feature A implementation is in progress."

[0937] Status: In progress

[0938] Timestamp: 2023-10-10 12:00:00

[0939] The server stores this information and allows stakeholders to view progress through a web interface, providing real-time visibility into project progress and enabling early identification of incomplete or delayed tasks.

[0940] The above is an example of an embodiment of the present invention. This system not only improves the efficiency of progress reports, but also significantly improves the overall project management and communication between the parties involved.

[0941] The processing flow will be explained below.

[0942] Step 1:

[0943] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[0944] Step 2:

[0945] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[0946] json

[0947] {

[0948] "user_id": 1,

[0949] "task": "Implementation of feature A",

[0950] "progress": 50,

[0951] "details": "Basic functionality done. Test cases in progress."

[0952] }

[0953] Step 3:

[0954] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[0955] Step 4:

[0956] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[0957] Step 5:

[0958] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[0959] Summary: "Task: Feature A implementation is in progress."

[0960] Status: In progress (progress less than 100)

[0961] Timestamp: Current date and time

[0962] Step 6:

[0963] The server saves the generated and organized information by adding it to the progress_reports list in memory.

[0964] Step 7:

[0965] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[0966] json

[0967] {

[0968] "message": "Your report has been received."

[0969] }

[0970] Step 8:

[0971] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[0972] Step 9:

[0973] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[0974] Step 10:

[0975] The server returns the progress information it has obtained to the relevant parties in JSON format, including a summary of each progress report, its status, and a timestamp.

[0976] Through these steps, the project management system utilizing generative artificial intelligence functions efficiently, effectively organizing progress reports and sharing information with stakeholders.

[0977] Example 1

[0978] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0979] In conventional project management, progress reporting is often done manually, resulting in inefficient information organization and reporting, and problems such as delays in communication and misunderstandings between stakeholders. These problems are particularly pronounced in large-scale projects, making it difficult to grasp the project's progress in real time. Therefore, the present invention aims to solve these problems and improve the efficiency of progress reporting and communication between stakeholders.

[0980] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0981] In this invention, the server includes: means for receiving progress reports and analyzing and organizing them using a generative artificial intelligence model; means for saving the organized information; means for reporting to relevant parties; means for the server to start up and accept HTTP requests from users and analyze and organize the progress reports; means for users to input progress reports through their terminals and send them to the server; means for the generative artificial intelligence model to analyze and organize the progress reports using prompt statements based on the progress reports; means for saving the generated summaries and statuses in memory; and means for reporting the saved progress information to relevant parties via a web interface so that the status can be checked in real time. This improves the efficiency of progress reports, enables the progress of the entire project to be grasped in real time, facilitates communication between relevant parties, and improves the accuracy of project management.

[0982] A "generative artificial intelligence model" is an artificial intelligence model that analyzes and organizes information based on data provided by the user, and automatically generates summaries and statuses.

[0983] "Progress report" is data such as task name, progress rate, detailed information, etc. that a user inputs to report the progress of a project.

[0984] The "server" is a computer system whose role is to receive requests from users, analyze and organize progress reports using a generative artificial intelligence model, store the information, and report it to relevant parties.

[0985] An "HTTP request" is a request for information sent by a user through a web interface to a server, whether for progress reporting or to perform other operations.

[0986] "Web Interface" means a web-based user interface that allows a user to enter progress reports and review stored information.

[0987] A "prompt sentence" is an instruction sentence that instructs a generative artificial intelligence model to perform a specific task, and is a sentence used when analyzing and organizing.

[0988] A "summary" is concise information extracted from a progress report by a generative artificial intelligence model that provides the core of the task.

[0989] "Status" is information that is evaluated by the generative artificial intelligence model based on progress reports and assigned to indicate the progress of a task, and represents a state such as "in progress" or "completed."

[0990] "Storage" refers to the server keeping organized progress information in memory or a database so that it can be accessed later.

[0991] A "stakeholder" is a person or organization that has an interest in the progress of the project and has the authority to review reported progress information.

[0992] "Real-time" refers to a state in which progress information is saved and can be accessed by relevant parties at the same time, and information is shared instantly.

[0993] The present invention is a system for improving the efficiency of progress reports in project management using a generative artificial intelligence model. This system is realized through cooperation between a server, terminals, and users.

[0994] The overall system configuration is as follows:

[0995] 1. Server

[0996] The server is run by web server software such as Apache or Nginx.

[0997] The server is implemented using a programming language such as Python or Node.js and provides a REST API for accepting HTTP requests from users.

[0998] The server analyzes and organizes the progress reports using a generative artificial intelligence model (e.g., GPT-4).

[0999] 2. Terminal

[1000] The device uses a browser to display a web interface composed of HTML, CSS, and JavaScript.

[1001] The user inputs a progress report using a terminal and sends it to the server as an HTTP POST request.

[1002] Next, a series of processes performed by this system will be described in detail.

[1003] First, the user accesses the web interface on the terminal and enters the necessary information into the progress report form, specifically the task name, progress rate, detailed information, etc. Once the input is complete, the user presses the send button, and the terminal sends the information to the server.

[1004] The data received by the server is first parsed in JSON format and temporarily stored in internal memory. Next, the server generates a prompt for the generative AI model. This prompt contains the progress report entered by the user. For example, the prompt has the following format:

[1005] "Please summarize the progress information below and assign an appropriate status. Content: Feature A implemented. Progress: 50%. Details: Basic functionality completed. Test cases being created."

[1006] The generative AI model analyzes the prompt, summarizes the report, and returns the result with an appropriate status to the server. For example, the output might look something like this:

[1007] Summary: "Task: Feature A implementation is in progress."

[1008] Status: In progress

[1009] Timestamp: 2023-10-10 12:00:00

[1010] The server receives this information and stores it in a database (e.g. MySQL, PostgreSQL), which contains a summary, status, and timestamp.

[1011] Finally, the server provides a web interface that allows stakeholders to view real-time progress information, for example, by accessing a dashboard on the web interface, allowing stakeholders to view the latest progress.

[1012] In this way, the system of the present invention realizes more efficient progress reporting and more accurate project management.

[1013] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1014] Step 1:

[1015] The user accesses the web interface on the terminal and enters information into a progress report form.

[1016] Input: Task name, progress, and details.

[1017] Specific operation: A user opens a web page using a browser and enters the task name (e.g., Implementing Feature A), progress rate (e.g., 50%), and details (e.g., Basic functionality completed. Test cases being created.) into the progress report form. When the user presses the "Submit" button, the terminal formats this information and sends it to the server as an HTTP POST request.

[1018] Step 2:

[1019] The server receives the HTTP POST request and parses the data.

[1020] Input: Progress report data submitted by the user (task name, progress percentage, details).

[1021] Output: Data converted to JSON format.

[1022] What happens: The server receives an HTTP POST request, parses the data in the request body, converts it to JSON format, and temporarily stores it in internal memory.

[1023] Step 3:

[1024] The server sends a prompt to the generative artificial intelligence model, requesting it to analyze and organize the data.

[1025] Input: Progress report data in JSON format, generated prompt text.

[1026] Output: A summary and status returned by the generative AI model.

[1027] Specific operation: The server generates a prompt based on the progress report data. Example prompt: "Please summarize the following progress information and assign an appropriate status. Content: Implementing feature A. Progress rate: 50%. Details: Basic functionality is complete. Test cases are being created." The generated prompt is sent to the API of the generative AI model, and a summary and status are returned.

[1028] Step 4:

[1029] The server stores the output of the generative artificial intelligence model in a database.

[1030] Input: Summary and status generated by the model, timestamp of progress report.

[1031] Output: Progress information stored in a database.

[1032] What it does: The server saves the summary and status received from the generative AI model, along with the current timestamp, in a database (e.g., MySQL, PostgreSQL), by executing a SQL query to insert the information into the appropriate tables.

[1033] Step 5:

[1034] The server reports progress information to interested parties and provides a web interface.

[1035] Input: Progress information stored in the database.

[1036] Output: Latest progress information displayed on the web interface.

[1037] What it does: The server retrieves the latest progress information from the database and displays it on a dashboard on a web interface. Stakeholders can access the dashboard using a browser to check the latest progress information in real time. It can also send alerts via email or push notification when certain conditions are met.

[1038] As a result, users, terminals, and servers work together to improve the efficiency of progress reports and the accuracy of project management.

[1039] (Application example 1)

[1040] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1041] In modern production plants, efficient and real-time reporting and management of the work progress of automated equipment is required. However, manual reporting and management requires time and effort, and progress information often lacks accuracy and speed. Furthermore, if managers cannot grasp the work progress status of equipment within the facility in a timely manner, optimal production management becomes difficult. There is a need for a system to solve this situation.

[1042] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1043] In this invention, the server includes means for receiving progress reports from automation equipment using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to a manager, means for saving the organized information in a database, and means for providing an interface for visualizing the organized information. This makes it possible to efficiently collect, organize, and report work progress information from automation equipment in real time, allowing managers to quickly and appropriately manage production.

[1044] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes data provided by users or devices and generates solutions or insights for specific problems.

[1045] "Automation equipment" refers to robots and automation devices used to automate work in production factories, etc.

[1046] A "progress report" is a report or data that organizes and provides information about the progress of a particular task or piece of work.

[1047] "Means for organizing information" refers to a method or apparatus that uses a generative artificial intelligence model to extract necessary information from received progress reports and organize it in a structured format.

[1048] "Means for storing information" refers to a method or device for storing organized information in a storage device such as a database or memory.

[1049] "Means for reporting information to an administrator" refers to a method or device for notifying an administrator of stored information as necessary so that the administrator can check it.

[1050] A "database" is a system that efficiently stores and manages organized progress information, allowing it to be quickly searched and accessed when needed.

[1051] "Interface" refers to a screen or web application that allows users or administrators to visually check and operate information.

[1052] "Work progress" is the indicator or data that shows how far a particular task or project has progressed.

[1053] The "task status" is information indicating the current status of the work, such as in progress, completed, or delayed.

[1054] "Status" is a label or tag used to express the progress of a task or project.

[1055] This invention provides a system for efficiently reporting and managing the work progress of automation equipment in a factory. The system includes a series of processes that use a generative artificial intelligence model to analyze the progress report and report it to a manager.

[1056] The system includes the following elements:

[1057] 1. Server

[1058] The server provides a web interface to accept HTTP requests from automation devices and administrator terminals.

[1059] The server receives progress reports from the automation equipment and uses a generative artificial intelligence model to analyze and organize the reports.

[1060] 2. Receiving and processing progress reports

[1061] The automation device describes its work progress in text format and sends the information to the server. The progress report includes the robot ID, task content, progress rate, and detailed information.

[1062] The server analyzes the received progress reports and organizes them using a generative AI model to generate summaries, evaluate the progress of tasks, and assign appropriate statuses (e.g., in progress, completed, etc.).

[1063] 3. Storage of Information

[1064] The server stores the organized progress report in a database (e.g. AWS RDS), including summary, status, timestamp, etc.

[1065] 4. Reporting to the Administrator

[1066] The server reports the saved progress information to the administrator as needed via a web interface, allowing the administrator to view the progress information in real time.

[1067] Hardware and software used

[1068] Server: AWS EC2 instance

[1069] Database: AWS RDS (MySQL)

[1070] Generative AI model: OpenAI's GPT model

[1071] Smartphone application: React Native (front end), Node.js (back end)

[1072] Specific examples

[1073] For example, if an automation device is performing a "packaging" task, it will report the following:

[1074] Robot ID: R123

[1075] Task: Packing

[1076] Progress: 70%

[1077] Details: Item is 70% packed and ready for shipping.

[1078] The server analyzes this information and uses a generative artificial intelligence model to generate information organized as follows:

[1079] Summary: "Task: Packing is in progress."

[1080] Status: In progress

[1081] Timestamp: 2023-10-10 15:00:00

[1082] Example prompt for a generative AI model:

[1083] "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[1084] In this way, factory managers can get a real-time view of the progress of their automation equipment through the Factory Insight application. The entire system enables efficient data processing and reporting, allowing managers to make appropriate decisions quickly.

[1085] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1086] Step 1:

[1087] The automation device generates work progress data. The inputs are work progress (robot ID, task, progress rate, detailed information). The output is the generated progress report data. Specifically, the automation device automatically measures the current work progress and summarizes it as a text-format progress report.

[1088] Step 2:

[1089] The automation device sends a progress report to the server. The input is the progress report data from step 1. The output is the progress report sent to the server. Specifically, the automation device sends the progress data using an HTTP POST request.

[1090] Step 3:

[1091] The server receives the progress reports and passes them to the generative AI model. The input is the progress reports received from the automation equipment. The output is the progress data passed to the generative AI model. Specifically, the server analyzes the progress reports, extracts the necessary data, and passes it to the generative AI model.

[1092] Step 4:

[1093] The generative AI model analyzes the progress report and organizes the information. The input is the progress data passed from the server. The output is an organized progress report (summary, status, timestamp). Specifically, the generative AI model generates a summary based on the received data, evaluates the progress of the task, and assigns an appropriate status.

[1094] Example prompt: "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[1095] Step 5:

[1096] The server stores the organized progress reports in a database. The input is the organized progress reports obtained from the generative AI model. The output is progress information stored in a database. Specifically, the server stores the organized data in a database, for example, AWS RDS.

[1097] Step 6:

[1098] The server sends the organized progress report to the administrator's terminal. The input is the progress information stored in the database. The output is the progress information displayed on the administrator's terminal. Specifically, the server allows the administrator to check the progress information in real time through a web interface.

[1099] Step 7:

[1100] The administrator's terminal visualizes the progress information. The input is organized progress information provided by the server. The output is progress data that can be visually confirmed by the administrator. Specifically, the web application on the terminal uses React Native to display the progress information in graph and list format.

[1101] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1102] This invention is a system that uses a generative AI model and an emotion engine to improve the efficiency of progress reports in project management and to report to stakeholders including the user's emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[1103] System Overview

[1104] 1. Server

[1105] The server is started using the Flask framework and accepts HTTP requests from front-end terminals and users. The server provides an endpoint / submit_report for receiving progress reports and an endpoint / get_reports for providing progress information.

[1106] 2. Receiving and processing progress reports

[1107] To report the progress of a project, a user creates information in text format and sends it to the server. This progress report includes the user ID, task details, progress rate, and detailed information.

[1108] The server receives the progress reports and uses a generative AI model to analyze and organize them. The analysis evaluates the progress and status of the task and generates a summary.

[1109] 3. Emotional Information Analysis

[1110] The server uses an emotion engine to analyze the user's emotion information from the progress report. The emotion engine analyzes emotional keywords and contexts in the text and evaluates the user's emotion (e.g., joy, anger, sadness, etc.).

[1111] The emotion information is analyzed, for example, as follows.

[1112] If a user reports, "Implementation of feature A is going well and is nearly complete," the emotion engine will identify "joy."

[1113] 4. Storage of Information

[1114] The server analyzes and organizes the progress and emotion information and stores it in a list in memory. This stored information includes a summary, status, emotion information, timestamp, etc.

[1115] 5. Reporting to relevant parties

[1116] The server provides a web interface for the participants to access the saved progress information, and the participants can check the progress information and emotion information in real time through this interface.

[1117] Specific examples

[1118] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[1119] User ID: 1

[1120] Task: Implement Feature A

[1121] Progress: 50%

[1122] Details: Basic functionality is complete. Test cases in progress.

[1123] When the user sends the above progress report to the server, the server performs the following process.

[1124] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[1125] Summary: "Task: Feature A implementation is in progress."

[1126] Status: In progress

[1127] Timestamp: 2023-10-10 12:00:00

[1128] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[1129] 3. Store organized progress and emotional information in memory.

[1130] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[1131] json

[1132] {

[1133] "summary": "Task: Feature A implementation is in progress.",

[1134] "status": "in progress",

[1135] "emotion": "joy",

[1136] "timestamp": "2023-10-10 12:00:00"

[1137] }

[1138] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[1139] The processing flow will be explained below.

[1140] Step 1:

[1141] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[1142] Step 2:

[1143] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[1144] json

[1145] {

[1146] "user_id": 1,

[1147] "task": "Implementation of feature A",

[1148] "progress": 50,

[1149] "details": "Basic functionality done. Test cases in progress."

[1150] }

[1151] Step 3:

[1152] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[1153] Step 4:

[1154] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[1155] Step 5:

[1156] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[1157] Summary: "Task: Feature A implementation is in progress."

[1158] Status: In progress (progress less than 100)

[1159] Timestamp: Current date and time

[1160] Step 6:

[1161] The server passes the progress report text to the emotion engine, which analyzes the user's emotion information. For example, the emotion "joy" is identified from the report "Basic functionality is complete. Test cases are being created."

[1162] Step 7:

[1163] The server stores the generated summary, status, timestamp, and sentiment information in a progress_reports list in memory.

[1164] Step 8:

[1165] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[1166] json

[1167] {

[1168] "message": "Your report has been received."

[1169] }

[1170] Step 9:

[1171] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[1172] Step 10:

[1173] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[1174] Step 11:

[1175] The server returns the acquired progress and emotion information to the relevant parties in JSON format, including a summary of each progress report, its status, emotion information, and a timestamp.

[1176] Specific examples

[1177] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[1178] User ID: 1

[1179] Task: Implement Feature A

[1180] Progress: 50%

[1181] Details: Basic functionality is complete. Test cases in progress.

[1182] When the user sends the above progress report to the server, the server performs the following process.

[1183] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[1184] Summary: "Task: Feature A implementation is in progress."

[1185] Status: In progress

[1186] Timestamp: 2023-10-10 12:00:00

[1187] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[1188] 3. Store organized progress and emotional information in memory.

[1189] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[1190] json

[1191] {

[1192] "summary": "Task: Feature A implementation is in progress.",

[1193] "status": "in progress",

[1194] "emotion": "joy",

[1195] "timestamp": "2023-10-10 12:00:00"

[1196] }

[1197] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[1198] Example 2

[1199] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1200] In conventional project management, progress reporting systems often lack completeness and consideration of emotional aspects, making it difficult for stakeholders to accurately grasp the actual progress. Progress reports are often manually compiled, which is also problematic in terms of efficiency. This reduces the accuracy and effectiveness of project management and tends to hinder communication between stakeholders.

[1201] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1202] In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, emotion analysis means for analyzing user emotion information from the progress reports, and means for incorporating the emotion-analyzed information into the progress reports. This enables efficient organization of progress reports and integration of emotion information, allowing relevant parties to more accurately grasp the progress of the project.

[1203] A "generative artificial intelligence model" refers to an artificial intelligence technology that analyzes input data from users and organizes, converts, and summarizes the content.

[1204] "Progress Report" refers to documents or data that allow a user to provide information about the progress of a particular task or project.

[1205] "Means of organization" refers to the ability to analyze received progress reports and convert, summarize, or reconstruct them into an easily understandable format.

[1206] "Means for storage" refers to the function for temporarily or permanently storing analyzed and organized information in a database or memory.

[1207] "Means of reporting to interested parties" refers to functions, particularly web interfaces and APIs, that provide stored information in a way that makes it easily accessible to interested parties.

[1208] "Emotion analysis means" refers to a function for detecting emotional nuances from a user's progress report and evaluating and classifying specific emotions.

[1209] "Means for incorporating sentiment-analyzed information into progress reports" refers to a function for integrating the results of sentiment analysis with progress report information to provide more comprehensive report content.

[1210] This invention is a system that uses a generative AI model and an emotion analysis engine to improve the efficiency of progress reports in project management and to report to stakeholders including user emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion analysis engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[1211] Hardware and Software Configuration

[1212] 1. Server

[1213] The server is started using the Flask framework and accepts HTTP requests from front-end devices and users.

[1214] The server has an endpoint ( / submit_report) for receiving progress reports and an endpoint ( / get_reports) for providing progress information.

[1215] 2. Generative AI Models

[1216] Analyzes progress reports to assess the progress and status of tasks. Analysis results in summaries and statuses.

[1217] 3. Sentiment Analysis Engine

[1218] Analyze the user's emotional information from the progress report text. Analyze emotional keywords and context in the text to evaluate the user's emotions (joy, anger, sadness, etc.).

[1219] 4. Data Storage

[1220] The analyzed and organized progress and emotion information is stored in a list in memory, including a summary, status, emotion information, timestamp, etc.

[1221] 5. Submission of Reports

[1222] The server provides a web interface for participants to provide progress and sentiment information. Participants can check the progress information in real time through this interface or the endpoint ( / get_reports).

[1223] Specific examples

[1224] For example, when a user reports the progress of a task called "Implementing Function A," the following information is sent to the server:

[1225] User ID: 1

[1226] Task: Implement Feature A

[1227] Progress: 50%

[1228] Details: Basic functionality is complete. Test cases in progress.

[1229] Prompt Sentence Examples

[1230] "Task A is 50% complete. Basic functionality is complete and test cases are currently being written."

[1231] The server passes the received progress report to the generative AI model, which analyzes and organizes the content. For example, the following information is generated:

[1232] Summary: "Task: Feature A implementation is in progress."

[1233] Status: In progress

[1234] Timestamp: 2023-10-10 12:00:00

[1235] The server then uses an emotion analysis engine to analyze the detailed information and identify the emotion "joy." These analysis results are stored in memory, allowing interested parties to view progress and emotion information.

[1236] This system enables efficient organization of progress reports and integration of emotional information, allowing stakeholders to more accurately grasp the progress of the project. Furthermore, by taking into account the user's emotions, a more comprehensive understanding of the actual status of the project can be achieved.

[1237] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1238] Step 1:

[1239] Starting the Server

[1240] The server is started using the Flask framework. The server configures the / submit_report and / get_reports endpoints to accept HTTP requests. It is now ready to receive report data from devices and users. The server output indicates that the endpoints are up and running and ready to accept requests.

[1241] Step 2:

[1242] Receiving progress reports from users

[1243] The user creates project progress information in text format and sends it to the server. Specifically, JSON data containing the user ID, task content, progress rate, and detailed information is sent. The input to the server is this JSON data, and the server receives it. The output of the server is the received progress report data.

[1244] Step 3:

[1245] Analyzing and organizing progress reports using generative AI models

[1246] The server passes the received progress report data to the generative AI model for analysis and organization. The generative AI model evaluates the progress and status of the task and generates a summary and status. The input is the received progress report data, and the output is a summary and status information as the analysis result. Specific operations include analyzing the data and generating a summary.

[1247] Step 4:

[1248] Emotion analysis engine for emotional information analysis

[1249] After analysis by the generative AI model, the server passes the text details of the progress report to the sentiment analysis engine, which analyzes the emotional information. The sentiment analysis engine analyzes emotional keywords and context within the text to evaluate the user's emotions. The input is the text data of the detailed information, and the output is emotional information (joy, anger, sadness, etc.). Specific operations include text analysis and emotion classification.

[1250] Step 5:

[1251] Saving progress and emotion information

[1252] The server integrates the analysis results from the generative AI model with the emotional information from the emotion analysis engine and stores them in a list in memory. The stored data includes a summary, status, emotional information, timestamp, etc. The input is the analyzed progress information and emotional information, and the output is the integrated data stored in memory. Specific operations include data integration and storage.

[1253] Step 6:

[1254] Providing reports to stakeholders

[1255] The server provides a web interface for stakeholders to access the saved progress and emotion information. Stakeholders can check the progress in real time by accessing the / get_reports endpoint. The input is a request from the stakeholder, and the output is the saved progress and emotion information. Specific operations include retrieving data and displaying the web interface.

[1256] These are the specific processing steps of the program. This system improves the accuracy and efficiency of project management, allowing those involved to accurately grasp the progress status.

[1257] (Application example 2)

[1258] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1259] Conventional methods for measuring the effectiveness of advertising campaigns and reporting progress often only provide quantitative data, making it difficult for advertisers and other stakeholders to grasp the actual situation and user sentiment. Furthermore, the lack of a means to efficiently analyze user sentiment information and incorporate it into reports reduces the accuracy and effectiveness of project management. As a result, the effectiveness of advertising campaigns cannot be accurately evaluated, making it difficult to develop effective strategies.

[1260] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, means for generating emotional information using an emotion engine that analyzes emotional information from the content of the progress reports, and means for incorporating the generated emotional information into the content of the progress reports and notifying the relevant parties. This makes it possible to simultaneously report not only information about the progress of an advertising campaign but also user emotional information, enabling more detailed and accurate evaluations and effective strategy planning.

[1261] A "generative artificial intelligence model" is an artificial intelligence model that generates new content or summaries from given data or information.

[1262] A "progress report" is information used to report on the progress of a particular task or project.

[1263] "Information organization" refers to the process or method used to analyze and reconstruct received progress reports in an understandable format.

[1264] "Information storage" refers to the processes and systems used to store organized information and make it accessible at a later time.

[1265] "Means of reporting to stakeholders" refers to methods for providing organized data and information to stakeholders and sharing progress and status.

[1266] An "emotion engine" is a technology or model that analyzes emotions from text, voice, etc., and identifies the type and intensity of those emotions.

[1267] "Emotion information" is data such as the type and intensity of emotions obtained through analysis.

[1268] "Task progress" refers to the state of a task that indicates how far a particular task or operation has progressed.

[1269] An "advertising campaign" is a planned promotional activity to widely publicize a particular product or service and increase its awareness and sales.

[1270] "User emotion information" is emotional data obtained from the user's statements and actions, and indicates an emotional state such as joy, sadness, or anger.

[1271] The system for realizing this invention includes a server, a front-end terminal, and software components such as a generative artificial intelligence model and an emotion engine.

[1272] 1. Server configuration and processing

[1273] The server uses the Flask framework to handle HTTP requests and provides the following main endpoints:

[1274] / submit_report: Receive progress reports from users.

[1275] / get_reports: Provides organized progress and sentiment information.

[1276] The server has the following roles:

[1277] 1. Receive progress reports from users.

[1278] 2. Analyze the report content using a generative AI model and generate a summary.

[1279] 3. Analyze the emotional information of progress reports using an emotion engine.

[1280] 4. Store organized progress and emotional information.

[1281] 5. Report the stored information to the relevant parties.

[1282] 2. User behavior and device usage

[1283] The user enters the following information from a smartphone or other front-end device:

[1284] User ID

[1285] Campaign ID

[1286] Description (progress details)

[1287] Progress rate

[1288] This information is sent to the server in JSON format.

[1289] 3. Use of generative AI models and emotion engines

[1290] When the server receives a progress report, a generative AI model analyzes the report and generates a summary. An emotion engine analyzes the emotional information from the progress report text and identifies the emotion. The analyzed emotional information is incorporated into the report as a specific emotion (e.g., joy or sadness).

[1291] 4. Storage and reporting

[1292] The organized progress information and emotion information are stored in a server and provided to the participants in real time, who can check the progress information and emotion information in real time through a web interface.

[1293] Specific examples

[1294] For example, in an ad campaign progress report, a user submits the following:

[1295] User ID: 123

[1296] Campaign ID: 456

[1297] Explanation: Campaign A's webpage traffic is skyrocketing, and sales conversions are steadily increasing.

[1298] Progress: 75%

[1299] The server performs the following process.

[1300] 1. Pass the progress report to a generative AI model to generate a summary (e.g., "Campaign A is progressing well.").

[1301] 2. Use the emotion engine to analyze the emotion "joy" from the report content.

[1302] 3. Store organized information and emotional information and report it to the relevant parties.

[1303] Prompt Sentence Examples

[1304] An example of a prompt for the user to report progress is as follows:

[1305] Please send us your campaign progress report using the following information:

[1306] User ID: Enter your user ID

[1307] Campaign ID: Enter the campaign ID.

[1308] Description: Give specific details about the progress of your campaign

[1309] Progress rate: Enter the progress rate in %

[1310] Through the above process, the system can simultaneously report information about the progress of the advertising campaign and user sentiment information, helping stakeholders make more specific and accurate evaluations.

[1311] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1312] Step 1:

[1313] The user enters a progress report using a smartphone or front-end device. The input includes the user ID, campaign ID, detailed progress description, and progress rate. This information is sent to the server in JSON format. For example, enter the following:

[1314] {

[1315] "user_id": "123",

[1316] "campaign_id": "456",

[1317] "explanation": "Webpage traffic for Campaign A has skyrocketed, and sales conversions are steadily increasing.",

[1318] "progress": 75

[1319] }

[1320] Input: User ID, Campaign ID, Description, Progress Rate

[1321] Output: Progress report data in JSON format

[1322] Step 2:

[1323] The server processes the received progress report data. Specifically, it passes the progress report data to a generative AI model, which analyzes and summarizes the report content. The generative AI model analyzes the explanatory text and generates a summary such as "Campaign A is progressing smoothly."

[1324] Input: Progress report data in JSON format

[1325] Output: A summary of the analyzed progress report

[1326] Step 3:

[1327] The server uses an emotion engine to analyze the emotional information from the report content. Specifically, it extracts emotional keywords such as "rapid increase" and "steady rise" from the text and evaluates the emotion of "joy."

[1328] Input: Progress report description text

[1329] Output: Parsed emotion information (e.g., joy)

[1330] Step 4:

[1331] The server combines the generated summary with the analyzed emotion information to construct organized progress information, which includes progress report content, summary, emotion information, and timestamp.

[1332] Input: Summary, sentiment information, progress report details

[1333] Output: Organized progress information

[1334] Step 5:

[1335] The server stores organized progress information in memory, including summaries, emotion information, status, and timestamps.

[1336] Input: Organized progress information

[1337] Output: Saved progress information

[1338] Step 6:

[1339] The server reports the saved progress information to the participants through a web interface, which participants can access from a browser and view the progress information and emotion information in real time.

[1340] Input: Saved progress information

[1341] Output: Progress and sentiment information provided to stakeholders

[1342] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1343] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1344] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1345] [Fourth embodiment]

[1346] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1347] 7, a 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.

[1348] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1349] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1350] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1351] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1352] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1353] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1354] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1355] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1356] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1357] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1358] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1359] The present invention is a system for improving the efficiency of progress reports in project management by using a generative artificial intelligence model. This system includes a series of processes for receiving progress reports from users, organizing them using a generative artificial intelligence model, storing them, and reporting them to relevant parties.

[1360] System Overview

[1361] 1. Server

[1362] The server runs and provides a web interface to accept HTTP requests from front-end terminals and users.

[1363] The server receives the progress reports and analyzes and organizes them using a generative artificial intelligence model.

[1364] 2. Receiving and processing progress reports

[1365] A user creates a text file to report the progress of a project and sends it to the server. The progress report includes the user ID, task details, progress rate, and detailed information.

[1366] The server analyzes the received progress reports and organizes them using a generative artificial intelligence model. This organization process generates summaries from the reports, evaluates the progress of the tasks, and assigns appropriate statuses (e.g., in progress, completed).

[1367] 3. Storage of Information

[1368] The server stores organized progress reports in memory, including summary, status, and timestamp information.

[1369] 4. Reporting to relevant parties

[1370] The server reports the saved progress information to the relevant parties as needed. This reporting is done through a web interface, allowing the relevant parties to check the progress information as needed.

[1371] Specific examples

[1372] For example, suppose a user wants to report on the progress of a task called "Implementing Feature A." The user enters the following information:

[1373] User ID: 1

[1374] Task: Implement Feature A

[1375] Progress: 50%

[1376] Details: Basic functionality is complete. Test cases in progress.

[1377] When the user sends this information to the server, the server receives it, passes it to a generative AI model for analysis and organization, and generates the following organized information:

[1378] Summary: "Task: Feature A implementation is in progress."

[1379] Status: In progress

[1380] Timestamp: 2023-10-10 12:00:00

[1381] The server stores this information and allows stakeholders to view progress through a web interface, providing real-time visibility into project progress and enabling early identification of incomplete or delayed tasks.

[1382] The above is an example of an embodiment of the present invention. This system not only improves the efficiency of progress reports, but also significantly improves the overall project management and communication between the parties involved.

[1383] The processing flow will be explained below.

[1384] Step 1:

[1385] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[1386] Step 2:

[1387] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[1388] json

[1389] {

[1390] "user_id": 1,

[1391] "task": "Implementation of feature A",

[1392] "progress": 50,

[1393] "details": "Basic functionality done. Test cases in progress."

[1394] }

[1395] Step 3:

[1396] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[1397] Step 4:

[1398] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[1399] Step 5:

[1400] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[1401] Summary: "Task: Feature A implementation is in progress."

[1402] Status: In progress (progress less than 100)

[1403] Timestamp: Current date and time

[1404] Step 6:

[1405] The server saves the generated and organized information by adding it to the progress_reports list in memory.

[1406] Step 7:

[1407] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[1408] json

[1409] {

[1410] "message": "Your report has been received."

[1411] }

[1412] Step 8:

[1413] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[1414] Step 9:

[1415] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[1416] Step 10:

[1417] The server returns the progress information it has obtained to the relevant parties in JSON format, including a summary of each progress report, its status, and a timestamp.

[1418] Through these steps, the project management system utilizing generative artificial intelligence functions efficiently, effectively organizing progress reports and sharing information with stakeholders.

[1419] Example 1

[1420] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1421] In conventional project management, progress reporting is often done manually, resulting in inefficient information organization and reporting, and problems such as delays in communication and misunderstandings between stakeholders. These problems are particularly pronounced in large-scale projects, making it difficult to grasp the project's progress in real time. Therefore, the present invention aims to solve these problems and improve the efficiency of progress reporting and communication between stakeholders.

[1422] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1423] In this invention, the server includes: means for receiving progress reports and analyzing and organizing them using a generative artificial intelligence model; means for saving the organized information; means for reporting to relevant parties; means for the server to start up and accept HTTP requests from users and analyze and organize the progress reports; means for users to input progress reports through their terminals and send them to the server; means for the generative artificial intelligence model to analyze and organize the progress reports using prompt statements based on the progress reports; means for saving the generated summaries and statuses in memory; and means for reporting the saved progress information to relevant parties via a web interface so that the status can be checked in real time. This improves the efficiency of progress reports, enables the progress of the entire project to be grasped in real time, facilitates communication between relevant parties, and improves the accuracy of project management.

[1424] A "generative artificial intelligence model" is an artificial intelligence model that analyzes and organizes information based on data provided by the user, and automatically generates summaries and statuses.

[1425] "Progress report" is data such as task name, progress rate, detailed information, etc. that a user inputs to report the progress of a project.

[1426] The "server" is a computer system whose role is to receive requests from users, analyze and organize progress reports using a generative artificial intelligence model, store the information, and report it to relevant parties.

[1427] An "HTTP request" is a request for information sent by a user through a web interface to a server, whether for progress reporting or to perform other operations.

[1428] "Web Interface" means a web-based user interface that allows a user to enter progress reports and review stored information.

[1429] A "prompt sentence" is an instruction sentence that instructs a generative artificial intelligence model to perform a specific task, and is a sentence used when analyzing and organizing.

[1430] A "summary" is concise information extracted from a progress report by a generative artificial intelligence model that provides the core of the task.

[1431] "Status" is information that is evaluated by the generative artificial intelligence model based on progress reports and assigned to indicate the progress of a task, and represents a state such as "in progress" or "completed."

[1432] "Storage" refers to the server keeping organized progress information in memory or a database so that it can be accessed later.

[1433] A "stakeholder" is a person or organization that has an interest in the progress of the project and has the authority to review reported progress information.

[1434] "Real-time" refers to a state in which progress information is saved and can be accessed by relevant parties at the same time, and information is shared instantly.

[1435] The present invention is a system for improving the efficiency of progress reports in project management using a generative artificial intelligence model. This system is realized through cooperation between a server, terminals, and users.

[1436] The overall system configuration is as follows:

[1437] 1. Server

[1438] The server is run by web server software such as Apache or Nginx.

[1439] The server is implemented using a programming language such as Python or Node.js and provides a REST API for accepting HTTP requests from users.

[1440] The server analyzes and organizes the progress reports using a generative artificial intelligence model (e.g., GPT-4).

[1441] 2. Terminal

[1442] The device uses a browser to display a web interface composed of HTML, CSS, and JavaScript.

[1443] The user inputs a progress report using a terminal and sends it to the server as an HTTP POST request.

[1444] Next, a series of processes performed by this system will be described in detail.

[1445] First, the user accesses the web interface on the terminal and enters the necessary information into the progress report form, specifically the task name, progress rate, detailed information, etc. Once the input is complete, the user presses the send button, and the terminal sends the information to the server.

[1446] The data received by the server is first parsed in JSON format and temporarily stored in internal memory. Next, the server generates a prompt for the generative AI model. This prompt contains the progress report entered by the user. For example, the prompt has the following format:

[1447] "Please summarize the progress information below and assign an appropriate status. Content: Feature A implemented. Progress: 50%. Details: Basic functionality completed. Test cases being created."

[1448] The generative AI model analyzes the prompt, summarizes the report, and returns the result with an appropriate status to the server. For example, the output might look something like this:

[1449] Summary: "Task: Feature A implementation is in progress."

[1450] Status: In progress

[1451] Timestamp: 2023-10-10 12:00:00

[1452] The server receives this information and stores it in a database (e.g. MySQL, PostgreSQL), which contains a summary, status, and timestamp.

[1453] Finally, the server provides a web interface that allows stakeholders to view real-time progress information, for example, by accessing a dashboard on the web interface, allowing stakeholders to view the latest progress.

[1454] In this way, the system of the present invention realizes more efficient progress reporting and more accurate project management.

[1455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1456] Step 1:

[1457] The user accesses the web interface on the terminal and enters information into a progress report form.

[1458] Input: Task name, progress, and details.

[1459] Specific operation: A user opens a web page using a browser and enters the task name (e.g., Implementing Feature A), progress rate (e.g., 50%), and details (e.g., Basic functionality completed. Test cases being created.) into the progress report form. When the user presses the "Submit" button, the terminal formats this information and sends it to the server as an HTTP POST request.

[1460] Step 2:

[1461] The server receives the HTTP POST request and parses the data.

[1462] Input: Progress report data submitted by the user (task name, progress percentage, details).

[1463] Output: Data converted to JSON format.

[1464] What happens: The server receives an HTTP POST request, parses the data in the request body, converts it to JSON format, and temporarily stores it in internal memory.

[1465] Step 3:

[1466] The server sends a prompt to the generative artificial intelligence model, requesting it to analyze and organize the data.

[1467] Input: Progress report data in JSON format, generated prompt text.

[1468] Output: A summary and status returned by the generative AI model.

[1469] Specific operation: The server generates a prompt based on the progress report data. Example prompt: "Please summarize the following progress information and assign an appropriate status. Content: Implementing feature A. Progress rate: 50%. Details: Basic functionality is complete. Test cases are being created." The generated prompt is sent to the API of the generative AI model, and a summary and status are returned.

[1470] Step 4:

[1471] The server stores the output of the generative artificial intelligence model in a database.

[1472] Input: Summary and status generated by the model, timestamp of progress report.

[1473] Output: Progress information stored in a database.

[1474] What it does: The server saves the summary and status received from the generative AI model, along with the current timestamp, in a database (e.g., MySQL, PostgreSQL), by executing a SQL query to insert the information into the appropriate tables.

[1475] Step 5:

[1476] The server reports progress information to interested parties and provides a web interface.

[1477] Input: Progress information stored in the database.

[1478] Output: Latest progress information displayed on the web interface.

[1479] What it does: The server retrieves the latest progress information from the database and displays it on a dashboard on a web interface. Stakeholders can access the dashboard using a browser to check the latest progress information in real time. It can also send alerts via email or push notification when certain conditions are met.

[1480] As a result, users, terminals, and servers work together to improve the efficiency of progress reports and the accuracy of project management.

[1481] (Application example 1)

[1482] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1483] In modern production plants, efficient and real-time reporting and management of the work progress of automated equipment is required. However, manual reporting and management requires time and effort, and progress information often lacks accuracy and speed. Furthermore, if managers cannot grasp the work progress status of equipment within the facility in a timely manner, optimal production management becomes difficult. There is a need for a system to solve this situation.

[1484] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1485] In this invention, the server includes means for receiving progress reports from automation equipment using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to a manager, means for saving the organized information in a database, and means for providing an interface for visualizing the organized information. This makes it possible to efficiently collect, organize, and report work progress information from automation equipment in real time, allowing managers to quickly and appropriately manage production.

[1486] A "generative artificial intelligence model" is an artificial intelligence algorithm that analyzes data provided by users or devices and generates solutions or insights for specific problems.

[1487] "Automation equipment" refers to robots and automation devices used to automate work in production factories, etc.

[1488] A "progress report" is a report or data that organizes and provides information about the progress of a particular task or piece of work.

[1489] "Means for organizing information" refers to a method or apparatus that uses a generative artificial intelligence model to extract necessary information from received progress reports and organize it in a structured format.

[1490] "Means for storing information" refers to a method or device for storing organized information in a storage device such as a database or memory.

[1491] "Means for reporting information to an administrator" refers to a method or device for notifying an administrator of stored information as necessary so that the administrator can check it.

[1492] A "database" is a system that efficiently stores and manages organized progress information, allowing it to be quickly searched and accessed when needed.

[1493] "Interface" refers to a screen or web application that allows users or administrators to visually check and operate information.

[1494] "Work progress" is the indicator or data that shows how far a particular task or project has progressed.

[1495] The "task status" is information indicating the current status of the work, such as in progress, completed, or delayed.

[1496] "Status" is a label or tag used to express the progress of a task or project.

[1497] This invention provides a system for efficiently reporting and managing the work progress of automation equipment in a factory. The system includes a series of processes that use a generative artificial intelligence model to analyze the progress report and report it to a manager.

[1498] The system includes the following elements:

[1499] 1. Server

[1500] The server provides a web interface to accept HTTP requests from automation devices and administrator terminals.

[1501] The server receives progress reports from the automation equipment and uses a generative artificial intelligence model to analyze and organize the reports.

[1502] 2. Receiving and processing progress reports

[1503] The automation device describes its work progress in text format and sends the information to the server. The progress report includes the robot ID, task content, progress rate, and detailed information.

[1504] The server analyzes the received progress reports and organizes them using a generative AI model to generate summaries, evaluate the progress of tasks, and assign appropriate statuses (e.g., in progress, completed, etc.).

[1505] 3. Storage of Information

[1506] The server stores the organized progress report in a database (e.g. AWS RDS), including summary, status, timestamp, etc.

[1507] 4. Reporting to the Administrator

[1508] The server reports the saved progress information to the administrator as needed via a web interface, allowing the administrator to view the progress information in real time.

[1509] Hardware and software used

[1510] Server: AWS EC2 instance

[1511] Database: AWS RDS (MySQL)

[1512] Generative AI model: OpenAI's GPT model

[1513] Smartphone application: React Native (front end), Node.js (back end)

[1514] Specific examples

[1515] For example, if an automation device is performing a "packaging" task, it will report the following:

[1516] Robot ID: R123

[1517] Task: Packing

[1518] Progress: 70%

[1519] Details: Item is 70% packed and ready for shipping.

[1520] The server analyzes this information and uses a generative artificial intelligence model to generate information organized as follows:

[1521] Summary: "Task: Packing is in progress."

[1522] Status: In progress

[1523] Timestamp: 2023-10-10 15:00:00

[1524] Example prompt for a generative AI model:

[1525] "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[1526] In this way, factory managers can get a real-time view of the progress of their automation equipment through the Factory Insight application. The entire system enables efficient data processing and reporting, allowing managers to make appropriate decisions quickly.

[1527] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1528] Step 1:

[1529] The automation device generates work progress data. The inputs are work progress (robot ID, task, progress rate, detailed information). The output is the generated progress report data. Specifically, the automation device automatically measures the current work progress and summarizes it as a text-format progress report.

[1530] Step 2:

[1531] The automation device sends a progress report to the server. The input is the progress report data from step 1. The output is the progress report sent to the server. Specifically, the automation device sends the progress data using an HTTP POST request.

[1532] Step 3:

[1533] The server receives the progress reports and passes them to the generative AI model. The input is the progress reports received from the automation equipment. The output is the progress data passed to the generative AI model. Specifically, the server analyzes the progress reports, extracts the necessary data, and passes it to the generative AI model.

[1534] Step 4:

[1535] The generative AI model analyzes the progress report and organizes the information. The input is the progress data passed from the server. The output is an organized progress report (summary, status, timestamp). Specifically, the generative AI model generates a summary based on the received data, evaluates the progress of the task, and assigns an appropriate status.

[1536] Example prompt: "Generate a summary and determine the status based on the following progress report: Robot ID: R123, Task: Packing, Progress: 70%, Details: 70% of the product has been packed. Preparing for delivery."

[1537] Step 5:

[1538] The server stores the organized progress reports in a database. The input is the organized progress reports obtained from the generative AI model. The output is progress information stored in a database. Specifically, the server stores the organized data in a database, for example, AWS RDS.

[1539] Step 6:

[1540] The server sends the organized progress report to the administrator's terminal. The input is the progress information stored in the database. The output is the progress information displayed on the administrator's terminal. Specifically, the server allows the administrator to check the progress information in real time through a web interface.

[1541] Step 7:

[1542] The administrator's terminal visualizes the progress information. The input is organized progress information provided by the server. The output is progress data that can be visually confirmed by the administrator. Specifically, the web application on the terminal uses React Native to display the progress information in graph and list format.

[1543] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1544] This invention is a system that uses a generative AI model and an emotion engine to improve the efficiency of progress reports in project management and to report to stakeholders including the user's emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[1545] System Overview

[1546] 1. Server

[1547] The server is started using the Flask framework and accepts HTTP requests from front-end terminals and users. The server provides an endpoint / submit_report for receiving progress reports and an endpoint / get_reports for providing progress information.

[1548] 2. Receiving and processing progress reports

[1549] To report the progress of a project, a user creates information in text format and sends it to the server. This progress report includes the user ID, task details, progress rate, and detailed information.

[1550] The server receives the progress reports and uses a generative AI model to analyze and organize them. The analysis evaluates the progress and status of the task and generates a summary.

[1551] 3. Emotional Information Analysis

[1552] The server uses an emotion engine to analyze the user's emotion information from the progress report. The emotion engine analyzes emotional keywords and contexts in the text and evaluates the user's emotion (e.g., joy, anger, sadness, etc.).

[1553] The emotion information is analyzed, for example, as follows.

[1554] If a user reports, "Implementation of feature A is going well and is nearly complete," the emotion engine will identify "joy."

[1555] 4. Storage of Information

[1556] The server analyzes and organizes the progress and emotion information and stores it in a list in memory. This stored information includes a summary, status, emotion information, timestamp, etc.

[1557] 5. Reporting to relevant parties

[1558] The server provides a web interface for the participants to access the saved progress information, and the participants can check the progress information and emotion information in real time through this interface.

[1559] Specific examples

[1560] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[1561] User ID: 1

[1562] Task: Implement Feature A

[1563] Progress: 50%

[1564] Details: Basic functionality is complete. Test cases in progress.

[1565] When the user sends the above progress report to the server, the server performs the following process.

[1566] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[1567] Summary: "Task: Feature A implementation is in progress."

[1568] Status: In progress

[1569] Timestamp: 2023-10-10 12:00:00

[1570] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[1571] 3. Store organized progress and emotional information in memory.

[1572] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[1573] json

[1574] {

[1575] "summary": "Task: Feature A implementation is in progress.",

[1576] "status": "in progress",

[1577] "emotion": "joy",

[1578] "timestamp": "2023-10-10 12:00:00"

[1579] }

[1580] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[1581] The processing flow will be explained below.

[1582] Step 1:

[1583] The server is started using the Flask framework. The server is running on localhost with app.run(debug=True) and is ready to accept HTTP requests.

[1584] Step 2:

[1585] A user creates a project progress report. The progress report includes the user ID, task name, progress rate, and detailed information. For example, the data is constructed in the following JSON format.

[1586] json

[1587] {

[1588] "user_id": 1,

[1589] "task": "Implementation of feature A",

[1590] "progress": 50,

[1591] "details": "Basic functionality done. Test cases in progress."

[1592] }

[1593] Step 3:

[1594] The user submits the above JSON-formatted progress report via a POST request to the server's / submit_report endpoint.

[1595] Step 4:

[1596] The server receives a POST request at the submit_report endpoint and retrieves the JSON data from request.json, which is stored in the variable report.

[1597] Step 5:

[1598] The server passes the acquired report data to a generative AI model for analysis and organization. In this example, the process_report function is responsible for this, generating the following information:

[1599] Summary: "Task: Feature A implementation is in progress."

[1600] Status: In progress (progress less than 100)

[1601] Timestamp: Current date and time

[1602] Step 6:

[1603] The server passes the progress report text to the emotion engine, which analyzes the user's emotion information. For example, the emotion "joy" is identified from the report "Basic functionality is complete. Test cases are being created."

[1604] Step 7:

[1605] The server stores the generated summary, status, timestamp, and sentiment information in a progress_reports list in memory.

[1606] Step 8:

[1607] The server will return a confirmation to the user that it has received the progress report. The response will be in JSON format and will contain the following:

[1608] json

[1609] {

[1610] "message": "Your report has been received."

[1611] }

[1612] Step 9:

[1613] A stakeholder sends a GET request to the server's / get_reports endpoint to view project progress information.

[1614] Step 10:

[1615] The server receives a GET request on the get_reports endpoint to retrieve the contents of the progress_reports list.

[1616] Step 11:

[1617] The server returns the acquired progress and emotion information to the relevant parties in JSON format, including a summary of each progress report, its status, emotion information, and a timestamp.

[1618] Specific examples

[1619] For example, suppose a user reports on the progress of a task called "Implementing Feature A." The user sends the following information:

[1620] User ID: 1

[1621] Task: Implement Feature A

[1622] Progress: 50%

[1623] Details: Basic functionality is complete. Test cases in progress.

[1624] When the user sends the above progress report to the server, the server performs the following process.

[1625] 1. Progress reports are received and passed to a generative AI model for analysis and organization. As a result, the following information is generated:

[1626] Summary: "Task: Feature A implementation is in progress."

[1627] Status: In progress

[1628] Timestamp: 2023-10-10 12:00:00

[1629] 2. The emotion engine is used to analyze the progress report content, and as a result, "joy" is identified as the emotional information.

[1630] 3. Store organized progress and emotional information in memory.

[1631] 4. Allow stakeholders to check progress and sentiment information through a web interface. By accessing the / get_reports endpoint, stakeholders can obtain the following information:

[1632] json

[1633] {

[1634] "summary": "Task: Feature A implementation is in progress.",

[1635] "status": "in progress",

[1636] "emotion": "joy",

[1637] "timestamp": "2023-10-10 12:00:00"

[1638] }

[1639] In this way, the system of the present invention efficiently organizes progress reports and analyzes emotional information, improving the quality of project management. Furthermore, by taking into account users' emotions, the system enables stakeholders to more accurately grasp the actual status of the project.

[1640] Example 2

[1641] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1642] In conventional project management, progress reporting systems often lack completeness and consideration of emotional aspects, making it difficult for stakeholders to accurately grasp the actual progress. Progress reports are often manually compiled, which is also problematic in terms of efficiency. This reduces the accuracy and effectiveness of project management and tends to hinder communication between stakeholders.

[1643] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1644] In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, emotion analysis means for analyzing user emotion information from the progress reports, and means for incorporating the emotion-analyzed information into the progress reports. This enables efficient organization of progress reports and integration of emotion information, allowing relevant parties to more accurately grasp the progress of the project.

[1645] A "generative artificial intelligence model" refers to an artificial intelligence technology that analyzes input data from users and organizes, converts, and summarizes the content.

[1646] "Progress Report" refers to documents or data that allow a user to provide information about the progress of a particular task or project.

[1647] "Means of organization" refers to the ability to analyze received progress reports and convert, summarize, or reconstruct them into an easily understandable format.

[1648] "Means for storage" refers to the function for temporarily or permanently storing analyzed and organized information in a database or memory.

[1649] "Means of reporting to interested parties" refers to functions, particularly web interfaces and APIs, that provide stored information in a way that makes it easily accessible to interested parties.

[1650] "Emotion analysis means" refers to a function for detecting emotional nuances from a user's progress report and evaluating and classifying specific emotions.

[1651] "Means for incorporating sentiment-analyzed information into progress reports" refers to a function for integrating the results of sentiment analysis with progress report information to provide more comprehensive report content.

[1652] This invention is a system that uses a generative AI model and an emotion analysis engine to improve the efficiency of progress reports in project management and to report to stakeholders including user emotional information. This system not only receives progress reports from users and organizes them using a generative AI model, but also uses the emotion analysis engine to analyze the user's emotional information and incorporate it into the report content, thereby improving the accuracy and effectiveness of project management.

[1653] Hardware and Software Configuration

[1654] 1. Server

[1655] The server is started using the Flask framework and accepts HTTP requests from front-end devices and users.

[1656] The server has an endpoint ( / submit_report) for receiving progress reports and an endpoint ( / get_reports) for providing progress information.

[1657] 2. Generative AI Models

[1658] Analyzes progress reports to assess the progress and status of tasks. Analysis results in summaries and statuses.

[1659] 3. Sentiment Analysis Engine

[1660] Analyze the user's emotional information from the progress report text. Analyze emotional keywords and context in the text to evaluate the user's emotions (joy, anger, sadness, etc.).

[1661] 4. Data Storage

[1662] The analyzed and organized progress and emotion information is stored in a list in memory, including a summary, status, emotion information, timestamp, etc.

[1663] 5. Submission of Reports

[1664] The server provides a web interface for participants to provide progress and sentiment information. Participants can check the progress information in real time through this interface or the endpoint ( / get_reports).

[1665] Specific examples

[1666] For example, when a user reports the progress of a task called "Implementing Function A," the following information is sent to the server:

[1667] User ID: 1

[1668] Task: Implement Feature A

[1669] Progress: 50%

[1670] Details: Basic functionality is complete. Test cases in progress.

[1671] Prompt Sentence Examples

[1672] "Task A is 50% complete. Basic functionality is complete and test cases are currently being written."

[1673] The server passes the received progress report to the generative AI model, which analyzes and organizes the content. For example, the following information is generated:

[1674] Summary: "Task: Feature A implementation is in progress."

[1675] Status: In progress

[1676] Timestamp: 2023-10-10 12:00:00

[1677] The server then uses an emotion analysis engine to analyze the detailed information and identify the emotion "joy." These analysis results are stored in memory, allowing interested parties to view progress and emotion information.

[1678] This system enables efficient organization of progress reports and integration of emotional information, allowing stakeholders to more accurately grasp the progress of the project. Furthermore, by taking into account the user's emotions, a more comprehensive understanding of the actual status of the project can be achieved.

[1679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1680] Step 1:

[1681] Starting the Server

[1682] The server is started using the Flask framework. The server configures the / submit_report and / get_reports endpoints to accept HTTP requests. It is now ready to receive report data from devices and users. The server output indicates that the endpoints are up and running and ready to accept requests.

[1683] Step 2:

[1684] Receiving progress reports from users

[1685] The user creates project progress information in text format and sends it to the server. Specifically, JSON data containing the user ID, task content, progress rate, and detailed information is sent. The input to the server is this JSON data, and the server receives it. The output of the server is the received progress report data.

[1686] Step 3:

[1687] Analyzing and organizing progress reports using generative AI models

[1688] The server passes the received progress report data to the generative AI model for analysis and organization. The generative AI model evaluates the progress and status of the task and generates a summary and status. The input is the received progress report data, and the output is a summary and status information as the analysis result. Specific operations include analyzing the data and generating a summary.

[1689] Step 4:

[1690] Emotion analysis engine for emotional information analysis

[1691] After analysis by the generative AI model, the server passes the text details of the progress report to the sentiment analysis engine, which analyzes the emotional information. The sentiment analysis engine analyzes emotional keywords and context within the text to evaluate the user's emotions. The input is the text data of the detailed information, and the output is emotional information (joy, anger, sadness, etc.). Specific operations include text analysis and emotion classification.

[1692] Step 5:

[1693] Saving progress and emotion information

[1694] The server integrates the analysis results from the generative AI model with the emotional information from the emotion analysis engine and stores them in a list in memory. The stored data includes a summary, status, emotional information, timestamp, etc. The input is the analyzed progress information and emotional information, and the output is the integrated data stored in memory. Specific operations include data integration and storage.

[1695] Step 6:

[1696] Providing reports to stakeholders

[1697] The server provides a web interface for stakeholders to access the saved progress and emotion information. Stakeholders can check the progress in real time by accessing the / get_reports endpoint. The input is a request from the stakeholder, and the output is the saved progress and emotion information. Specific operations include retrieving data and displaying the web interface.

[1698] These are the specific processing steps of the program. This system improves the accuracy and efficiency of project management, allowing those involved to accurately grasp the progress status.

[1699] (Application example 2)

[1700] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1701] Conventional methods for measuring the effectiveness of advertising campaigns and reporting progress often only provide quantitative data, making it difficult for advertisers and other stakeholders to grasp the actual situation and user sentiment. Furthermore, the lack of a means to efficiently analyze user sentiment information and incorporate it into reports reduces the accuracy and effectiveness of project management. As a result, the effectiveness of advertising campaigns cannot be accurately evaluated, making it difficult to develop effective strategies.

[1702] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports, means for saving the organized information, means for reporting the saved information to relevant parties, means for generating emotional information using an emotion engine that analyzes emotional information from the content of the progress reports, and means for incorporating the generated emotional information into the content of the progress reports and notifying the relevant parties. This makes it possible to simultaneously report not only information about the progress of an advertising campaign but also user emotional information, enabling more detailed and accurate evaluations and effective strategy planning.

[1703] A "generative artificial intelligence model" is an artificial intelligence model that generates new content or summaries from given data or information.

[1704] A "progress report" is information used to report on the progress of a particular task or project.

[1705] "Information organization" refers to the process or method used to analyze and reconstruct received progress reports in an understandable format.

[1706] "Information storage" refers to the processes and systems used to store organized information and make it accessible at a later time.

[1707] "Means of reporting to stakeholders" refers to methods for providing organized data and information to stakeholders and sharing progress and status.

[1708] An "emotion engine" is a technology or model that analyzes emotions from text, voice, etc., and identifies the type and intensity of those emotions.

[1709] "Emotion information" is data such as the type and intensity of emotions obtained through analysis.

[1710] "Task progress" refers to the state of a task that indicates how far a particular task or operation has progressed.

[1711] An "advertising campaign" is a planned promotional activity to widely publicize a particular product or service and increase its awareness and sales.

[1712] "User emotion information" is emotional data obtained from the user's statements and actions, and indicates an emotional state such as joy, sadness, or anger.

[1713] The system for realizing this invention includes a server, a front-end terminal, and software components such as a generative artificial intelligence model and an emotion engine.

[1714] 1. Server configuration and processing

[1715] The server uses the Flask framework to handle HTTP requests and provides the following main endpoints:

[1716] / submit_report: Receive progress reports from users.

[1717] / get_reports: Provides organized progress and sentiment information.

[1718] The server has the following roles:

[1719] 1. Receive progress reports from users.

[1720] 2. Analyze the report content using a generative AI model and generate a summary.

[1721] 3. Analyze the emotional information of progress reports using an emotion engine.

[1722] 4. Store organized progress and emotional information.

[1723] 5. Report the stored information to the relevant parties.

[1724] 2. User behavior and device usage

[1725] The user enters the following information from a smartphone or other front-end device:

[1726] User ID

[1727] Campaign ID

[1728] Description (progress details)

[1729] Progress rate

[1730] This information is sent to the server in JSON format.

[1731] 3. Use of generative AI models and emotion engines

[1732] When the server receives a progress report, a generative AI model analyzes the report and generates a summary. An emotion engine analyzes the emotional information from the progress report text and identifies the emotion. The analyzed emotional information is incorporated into the report as a specific emotion (e.g., joy or sadness).

[1733] 4. Storage and reporting

[1734] The organized progress information and emotion information are stored in a server and provided to the participants in real time, who can check the progress information and emotion information in real time through a web interface.

[1735] Specific examples

[1736] For example, in an ad campaign progress report, a user submits the following:

[1737] User ID: 123

[1738] Campaign ID: 456

[1739] Explanation: Campaign A's webpage traffic is skyrocketing, and sales conversions are steadily increasing.

[1740] Progress: 75%

[1741] The server performs the following process.

[1742] 1. Pass the progress report to a generative AI model to generate a summary (e.g., "Campaign A is progressing well.").

[1743] 2. Use the emotion engine to analyze the emotion "joy" from the report content.

[1744] 3. Store organized information and emotional information and report it to the relevant parties.

[1745] Prompt Sentence Examples

[1746] An example of a prompt for the user to report progress is as follows:

[1747] Please send us your campaign progress report using the following information:

[1748] User ID: Enter your user ID

[1749] Campaign ID: Enter the campaign ID.

[1750] Description: Give specific details about the progress of your campaign

[1751] Progress rate: Enter the progress rate in %

[1752] Through the above process, the system can simultaneously report information about the progress of the advertising campaign and user sentiment information, helping stakeholders make more specific and accurate evaluations.

[1753] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1754] Step 1:

[1755] The user enters a progress report using a smartphone or front-end device. The input includes the user ID, campaign ID, detailed progress description, and progress rate. This information is sent to the server in JSON format. For example, enter the following:

[1756] {

[1757] "user_id": "123",

[1758] "campaign_id": "456",

[1759] "explanation": "Webpage traffic for Campaign A has skyrocketed, and sales conversions are steadily increasing.",

[1760] "progress": 75

[1761] }

[1762] Input: User ID, Campaign ID, Description, Progress Rate

[1763] Output: Progress report data in JSON format

[1764] Step 2:

[1765] The server processes the received progress report data. Specifically, it passes the progress report data to a generative AI model, which analyzes and summarizes the report content. The generative AI model analyzes the explanatory text and generates a summary such as "Campaign A is progressing smoothly."

[1766] Input: Progress report data in JSON format

[1767] Output: A summary of the analyzed progress report

[1768] Step 3:

[1769] The server uses an emotion engine to analyze the emotional information from the report content. Specifically, it extracts emotional keywords such as "rapid increase" and "steady rise" from the text and evaluates the emotion of "joy."

[1770] Input: Progress report description text

[1771] Output: Parsed emotion information (e.g., joy)

[1772] Step 4:

[1773] The server combines the generated summary with the analyzed emotion information to construct organized progress information, which includes progress report content, summary, emotion information, and timestamp.

[1774] Input: Summary, sentiment information, progress report details

[1775] Output: Organized progress information

[1776] Step 5:

[1777] The server stores organized progress information in memory, including summaries, emotion information, status, and timestamps.

[1778] Input: Organized progress information

[1779] Output: Saved progress information

[1780] Step 6:

[1781] The server reports the saved progress information to the participants through a web interface, which participants can access from a browser and view the progress information and emotion information in real time.

[1782] Input: Saved progress information

[1783] Output: Progress and sentiment information provided to stakeholders

[1784] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1785] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1786] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1787] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1788] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1789] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1790] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1791] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1792] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1793] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1794] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1795] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1796] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1797] 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.

[1798] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1799] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1800] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1801] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1802] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1803] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1804] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1805] The following is further disclosed regarding the above embodiment.

[1806] (Claim 1)

[1807] a means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports;

[1808] A means of storing organized information;

[1809] a means of reporting the stored information to interested parties;

[1810] A system including:

[1811] (Claim 2)

[1812] 10. The system of claim 1, wherein the generative artificial intelligence model includes means for evaluating progress of a particular user task.

[1813] (Claim 3)

[1814] 2. The system of claim 1, further comprising means for extracting the state and progress of the task from the progress report and assigning a status such as in progress or completed based thereon.

[1815] (Claim 4)

[1816] 2. The system of claim 1, further comprising means for receiving a progress report sent by a user in JSON format and storing the report in memory.

[1817] (Claim 5)

[1818] The system of claim 1, wherein the server includes means for receiving progress reports, storing information organized by the generative artificial intelligence model in list form, and providing a web interface that allows interested parties to access the information.

[1819] (Claim 6)

[1820] 10. The system of claim 1, further comprising means for transmitting the progress information in JSON format so that interested parties can access the stored progress information.

[1821] (Claim 7)

[1822] 10. The system of claim 1, wherein the server includes means for time-stamping each progress report to record the date and time the report was made.

[1823] "Example 1"

[1824] (Claim 1)

[1825] a means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports;

[1826] A means of storing organized information;

[1827] a means of reporting the stored information to interested parties;

[1828] The server runs, accepts HTTP requests from users, and analyzes and organizes progress reports.

[1829] A means for a user to input a progress report through a terminal and transmit the progress report to a server;

[1830] a means for analyzing and organizing the progress report using prompt sentences based on the generative artificial intelligence model;

[1831] means for storing the generated summary and status in memory;

[1832] A means for reporting the saved progress information to relevant parties through a web interface, allowing them to check the status in real time;

[1833] A system including:

[1834] (Claim 2)

[1835] 10. The system of claim 1, wherein the generative artificial intelligence model includes means for evaluating the progress of a particular user task and assigning a summary and status based thereon.

[1836] (Claim 3)

[1837] The system of claim 1 further comprising means for generating a prompt sentence based on the progress report by the generative artificial intelligence model, extracting the status and progress of the task using the prompt sentence, and assigning an appropriate status.

[1838] "Application Example 1"

[1839] (Claim 1)

[1840] means for receiving progress reports from the automation equipment using a generative artificial intelligence model and organizing information based on the progress reports;

[1841] A means of storing organized information;

[1842] a means for reporting the stored information to a controller;

[1843] A means of storing the organized information in a database;

[1844] A means for providing an interface for visualizing the organized information;

[1845] A system including:

[1846] (Claim 2)

[1847] 10. The system of claim 1, wherein the generative artificial intelligence model includes means for evaluating progress of a particular automation task.

[1848] (Claim 3)

[1849] 2. The system of claim 1, further comprising means for extracting the state and progress of the task from the progress report and assigning a status such as in progress or completed based thereon.

[1850] "Example 2: Combining Emotion Engines"

[1851] (Claim 1)

[1852] a means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports;

[1853] A means of storing organized information;

[1854] a means of reporting the stored information to interested parties;

[1855] emotion analysis means for analyzing user emotion information from the progress report;

[1856] a means for incorporating sentiment-analyzed information into progress reports;

[1857] A system including:

[1858] (Claim 2)

[1859] 10. The system of claim 1, wherein the generative artificial intelligence model includes means for evaluating progress of a particular user task.

[1860] (Claim 3)

[1861] 2. The system of claim 1, further comprising means for extracting the state and progress of the task from the progress report and assigning a status such as in progress or completed based thereon.

[1862] "Application example 2 when combining emotion engines"

[1863] (Claim 1)

[1864] a means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports;

[1865] A means of storing organized information;

[1866] a means of reporting the stored information to interested parties;

[1867] means for generating emotion information using an emotion engine that analyzes emotion information from the content of the progress report;

[1868] a means for incorporating the generated emotional information into progress reports and notifying the relevant parties;

[1869] A system including:

[1870] (Claim 2)

[1871] 2. The system of claim 1, wherein the generative artificial intelligence model includes means for assessing the progress of a particular user task and assigning a status such as in progress or completed based thereon.

[1872] (Claim 3)

[1873] 10. The system of claim 1, further comprising means for reporting the progress of an advertising campaign and analyzing sentiment information, summarizing and organizing the sentiment information using a generative artificial intelligence model, and reporting the same. [Explanation of symbols]

[1874] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for receiving progress reports from users using a generative artificial intelligence model and organizing information based on the progress reports; A means of storing organized information; a means of reporting the stored information to interested parties; A system including:

2. 2. The system of claim 1, wherein said generative artificial intelligence model includes means for assessing progress on a particular user task.

3. 2. The system according to claim 1, further comprising means for extracting the state and progress of the task from the progress report and assigning a status such as in progress or completed based thereon.

4. The system of claim 1 , further comprising means for receiving a progress report sent by a user in JSON format and storing the report in memory.

5. The system of claim 1, wherein the server includes means for receiving progress reports, storing information organized by the generative artificial intelligence model in list form, and providing a web interface that allows interested parties to access the information.

6. The system of claim 1 , further comprising means for transmitting the progress information in JSON format so that interested parties can access the stored progress information.

7. 2. The system of claim 1, wherein the server includes means for time-stamping each progress report to record the date and time the report was made.

Images