System

Abstract

A system is provided.SOLUTION: The system includes a means for analyzing an electronic mail, a means for extracting a corresponding date from the analyzed electronic mail, a means for listing tasks on the basis of the extracted corresponding date, a means for arranging links and corresponding contents related to the listed tasks, and a means for displaying the generated task list.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] Today, businesspeople face the burden of receiving a large volume of emails and identifying and responding to important tasks. Furthermore, there is a high risk that tasks with deadlines will be overlooked, hindering the smooth progress of work. Conventional task management systems require users to manually analyze emails received in their mailboxes and extract important tasks, which is time-consuming and inefficient. There is a need for a system that can solve these issues and automatically extract and list tasks from emails. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system including the following means: a means for analyzing emails, a means for extracting action due dates from the analyzed emails, a means for listing tasks based on the extracted action due dates, a means for organizing links and action details related to the listed tasks, and a means for displaying the generated task list. Furthermore, the system uses a generative AI model to analyze emails and evaluates the credibility of task information based on specific keywords, thereby efficiently and accurately extracting and managing important tasks.

[0006] "Email" is a means of transmitting information that refers to documents, messages, and files sent and received in digital form.

[0007] "Analysis" is a processing method for organizing data and information and extracting specific meanings and patterns.

[0008] A "deadline" is a deadline for completing a particular task or job.

[0009] A "task" refers to the work or actions required to achieve a specific goal.

[0010] "Listing" refers to arranging multiple items and organizing them into a list.

[0011] A "link" is a hyperlink within a web page or digital document that connects to other resources or information.

[0012] A "generative AI model" is a form of artificial intelligence that uses machine learning and deep learning to analyze data and generate text.

[0013] "Keywords" are important words or phrases used to search, filter, and evaluate specific information.

[0014] "Credibility" refers to information or data being accurate and trustworthy.

[0015] A "task list" is a list of all tasks, organized with details such as their outline and deadlines. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention relates to a system that analyzes emails and extracts and manages deadlines and task information. The server collects all emails from mailboxes and analyzes them using AI (generative AI models), automatically extracting and organizing important task information.

[0038] 1. Email Collection

[0039] The server connects to your mailbox using your email account information. The server uses IMAP or POP3 protocols to access your mailbox and download all unread and existing emails, ensuring that you receive the most up-to-date information.

[0040] 2. Email Analysis

[0041] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. A natural language processing model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by," "deadline," etc.) are used to identify due dates, task content, and links.

[0042] 3. Task extraction

[0043] The server extracts important task information (deadline, task content, related links) from the analysis results of the AI ​​model. The extracted information is organized by each item and used in the next step.

[0044] 4. Task list generation

[0045] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing users to quickly grasp the overall picture of the tasks.

[0046] 5. Task List Notifications

[0047] The server sends the generated task list to the user's terminal, where it can be viewed. The user receives a notification and can check the task list.

[0048] 6. Review and Track

[0049] Users can view task lists on their devices and manage the progress of the tasks they need to complete. They can update task completion status and progress as needed and add notes and comments as needed.

[0050] Specific examples

[0051] For example, consider the following email:

[0052] Subject: Project X progress check

[0053] Main text:

[0054] Hello,

[0055] Please report on the progress of Project X by March 25th.

[0056] You can download the necessary materials from the following links:

[0057] http: / / example.com / resource

[0058] thank you.

[0059] Email collection

[0060] The server collects this mail from the user's mailbox.

[0061] Email Analysis

[0062] The server sends the email body to a generative AI model for analysis. The model extracts:

[0063] Response date: March 25th

[0064] Task: Project X progress report

[0065] Related link: http: / / example.com / resource

[0066] Task Extraction

[0067] The server extracts the following information from the output of the generative AI model:

[0068] Response date: March 25th

[0069] Task: Project X progress report

[0070] Related link: http: / / example.com / resource

[0071] Task list generation

[0072] The server generates a task list based on the extracted information in the following format:

[0073] 1. [Title] Project X Progress Check

[0074] [Response date] March 25th

[0075] [Task Content] Project X progress report

[0076] [Related Links] http: / / example.com / resource

[0077] Task List Notifications

[0078] The server transmits the generated task list to the user's terminal.

[0079] Review and Track

[0080] Users can view their task list on their device and ensure they take necessary action in their daily work, update their progress, and record the completion of tasks.

[0081] The above is an embodiment of the present invention, which allows a user to manage important task information from a large volume of emails without missing it, and to respond quickly.

[0082] The processing flow will be explained below.

[0083] Step 1:

[0084] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[0085] Step 2:

[0086] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[0087] Step 3:

[0088] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[0089] Step 4:

[0090] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[0091] Step 5:

[0092] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[0093] Step 6:

[0094] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[0095] Step 7:

[0096] Users can view their task list on their device, manage the progress and completion status of each task, update the task completion status, and even enter any necessary notes or comments.

[0097] Step 8:

[0098] Users can carry out tasks and work based on deadlines and task content. By checking progress on their devices, they can prevent tasks from being overlooked and work can be done efficiently.

[0099] Example 1

[0100] 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."

[0101] With conventional email systems, users have to manually sort and extract important task information from a large volume of emails, which is extremely time-consuming. There's also a high risk of missing task deadlines or important links. This reduces work efficiency and makes it difficult to manage task progress.

[0102] 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.

[0103] In this invention, the server includes means for connecting to an email server using a user's account information and collecting emails stored in a mailbox, means for using a generative AI model to analyze the body and header information of the collected emails, means for extracting due dates, task contents, and related links from the analysis results of the generative AI model, means for generating a task list based on the extracted information, means for notifying the user's terminal of the generated task list, and means for the user to check the task list on the terminal and manage progress. This allows the user to automatically extract and organize important task information from emails, significantly improving work efficiency.

[0104] "User account information" refers to authentication information required to connect to an email server, including an email address, password, and other necessary authentication information.

[0105] An "email server" is a server for sending, receiving, and storing emails, and is a server system that is accessed using protocols such as IMAP and POP3.

[0106] A "mailbox" is a digital storage area associated with a user's email account for storing received email.

[0107] An "email" is a digital message sent and received over the Internet, and includes information such as the body, subject, sender, recipient, and date and time of sending.

[0108] A "generative AI model" is a machine learning model for natural language processing, capable of understanding the meaning of language based on large amounts of text data, and analyzing and extracting specific information.

[0109] A "prompt" is an instruction given to a generative AI model to perform a specific task, providing the model with criteria and context for analysis and generation.

[0110] "Task information" is information such as due dates, task contents, and related links extracted from emails, and refers to specific action items that the user should manage.

[0111] A "task list" is extracted task information that is organized and displayed in a list format, and includes the title of each task, the due date, the task content, related links, and the like.

[0112] A "terminal" is a digital device used by a user to check the task list and manage the progress of tasks, and includes a PC, smartphone, tablet, etc.

[0113] "Notification" refers to the alert function or message sending that notifies the user of the generated task list, and is done via email, push notification, or a dedicated app.

[0114] This invention relates to a system that analyzes emails and extracts and manages response deadlines and task information. In this system, a server collects all emails from mailboxes and analyzes them using a generative AI model to automatically extract and organize important task information. A specific embodiment of this system is described below.

[0115] Email collection

[0116] The server connects to an email server (e.g., a server using IMAP or POP3 protocols) using the user's account information (email address, password). After connecting, the server downloads all unread and read emails in the mailbox and retrieves the latest email information. This data is temporarily stored in local storage.

[0117] Email Analysis

[0118] The server extracts the downloaded email's body and header information (subject, sender, date, etc.) and inputs it into a generative AI model. The generative AI model (e.g., a natural language processing model) is given a specific prompt and uses this to analyze the email content. This analysis identifies due dates, task details, and related links based on specific keywords and phrases (e.g., "by," "deadline," etc.).

[0119] Task Extraction

[0120] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized into categories such as deadline, task content, and related links.

[0121] Task list generation

[0122] The server generates a task list based on the extracted task information. This task list includes the title, due date, task content, and related links for each task. The list is saved in a structured format so that users can easily view it.

[0123] For example, the generated task list might look like this:

[0124] 1. [Title] Project X Progress Check

[0125] [Response date] March 25th

[0126] [Task Content] Project X progress report

[0127] [Related Links] http: / / example.com / resource

[0128] Task List Notifications

[0129] The server then notifies the user of the generated task list via email or push notification from a dedicated application.

[0130] Review and Track

[0131] Users can view the received task list on their device and manage the progress of each task. Users can update the task completion status at any time and add comments or notes as needed, allowing users to manage tasks efficiently and meet important deadlines.

[0132] Specific examples

[0133] For example, suppose the following email arrives in a user's mailbox:

[0134] Subject: Project X progress check

[0135] Main text:

[0136] Hello,

[0137] Please report on the progress of Project X by March 25th.

[0138] You can download the necessary materials from the following links:

[0139] http: / / example.com / resource

[0140] thank you.

[0141] When the server collects this email and asks the generative AI model to analyze it, it uses the following prompt:

[0142] "Please extract the due date, task details, and related links from this email."

[0143] The generative AI model analyzes the content of the email and extracts the following information:

[0144] Response date: March 25th

[0145] Task: Project X progress report

[0146] Related link: http: / / example.com / resource

[0147] Based on this, the server generates a task list and notifies the user's device, allowing the user to check the list and take the necessary actions quickly.

[0148] This system allows users to automatically extract important task information from emails and manage it efficiently, significantly improving the efficiency of their overall work.

[0149] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0150] Step 1:

[0151] Connecting to a mail server

[0152] The server connects to the email server (IMAP or POP3 protocol) using the user's account information (email address, password).

[0153] Input: User's email account information

[0154] Output: Connecting to the mail server

[0155] This connection gives the server permission to access the email in your mailbox.

[0156] Step 2:

[0157] Email collection

[0158] After connecting to the mail server, the server downloads all unread and read emails in the mailbox, which are then temporarily stored in local storage.

[0159] Input: Email in mailbox

[0160] Output: Email data saved in local storage

[0161] In this step, the server obtains the latest mail information and prepares it for the next analysis step.

[0162] Step 3:

[0163] Preparation for email analysis

[0164] The server extracts the body text and header information (subject, sender, date, etc.) of the collected emails and prepares them for input into the generative AI model.

[0165] Input: Email data stored in local storage

[0166] Output: Email body and header information for analysis

[0167] The information required for analysis is ready to be passed to the generative AI model.

[0168] Step 4:

[0169] Analysis using generative AI models

[0170] The server sends the email body and header information to the generative AI model and requests analysis using specific prompts.

[0171] Example prompt: "Extract due dates, tasks, and related links from this email."

[0172] Input: Email body and header information for analysis, prompt text

[0173] Output: Analysis results (response due date, task details, related links)

[0174] In this step, the generative AI model understands the content of the email and extracts important task information.

[0175] Step 5:

[0176] Extracting and organizing task information

[0177] The server extracts response deadlines, task details, and related links from the analysis results of the generative AI model and organizes them into their respective categories.

[0178] Input: Analysis results of the generative AI model

[0179] Output: Organized task information (deadline, task content, related links)

[0180] This ensures that important task information is clearly categorized.

[0181] Step 6:

[0182] Generate a task list

[0183] The server generates a task list based on the organized task information, which includes the title, due date, task content, and related links for each task.

[0184] Input: Organized task information

[0185] Output: Generated task list

[0186] The generated task list is saved in a format that is easy for the user to check.

[0187] Step 7:

[0188] Task List Notifications

[0189] The server notifies the user of the generated task list via email or push notification from a dedicated application.

[0190] Input: Generated task list

[0191] Output: Notification to the user's device

[0192] The user receives this notification and can check the task list.

[0193] Step 8:

[0194] Review and track your task list

[0195] The user can check the received task list on the device, manage the progress of each task, add comments and notes as needed, and update the task progress as needed.

[0196] Input: User task management actions (status update, comment addition, etc.)

[0197] Output: Updated task list

[0198] This allows users to efficiently manage their tasks and ensure that they do not miss important deadlines or task details.

[0199] (Application example 1)

[0200] 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."

[0201] Conventional industrial robot management systems require manual management of instructions and reports, resulting in inefficiencies and errors. Extracting necessary task information from a large volume of emails is time-consuming and places a significant burden on the manager. The present invention aims to solve these problems and provide a method for automatically and efficiently managing robot work schedules.

[0202] 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.

[0203] In this invention, the server includes means for analyzing emails, means for extracting action dates from the analyzed emails, means for listing tasks based on the extracted action dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for analyzing instructions and reports from the industrial robot and extracting and managing action dates and specific work details, means for notifying the generated robot task list to a manager's terminal, and means for the manager to monitor the robot's work progress in real time and issue correction instructions as necessary, thereby enabling automatic management of the robot's work schedule and efficient response.

[0204] "Email" means written communication sent or received in digital form, a message transmitted through an electronic device.

[0205] "Analyzing" means examining collected data in detail and breaking down its content and structure into an understandable format.

[0206] A "due date" is the date by which a particular task or action is required to be completed.

[0207] A "task" is a specific activity or task that must be performed to achieve a specific goal.

[0208] "Listing" means arranging items in a list format in a particular order.

[0209] A "link" is a hypertext reference that directs a user to a particular resource or piece of information.

[0210] "Organizing" is the process of compiling data and information in an efficient and easy-to-understand format.

[0211] "Displaying" means visually presenting data or information to a user.

[0212] An "industrial robot" is a programmable mechanical device used to perform automated tasks in industry.

[0213] An "instruction" is an order or instruction to perform a specific action or task.

[0214] A "report" is a report on the progress and results of work.

[0215] To "manage" means to effectively manage, supervise, and control a specific resource or task.

[0216] "Notifying" is the act of informing others of specific information.

[0217] "Monitoring" means continuously observing a series of actions or processes and responding if an abnormality occurs.

[0218] "Modification instructions" means instructions to make changes or improvements to existing plans or schedules.

[0219] A "generative AI model" is an artificial intelligence technology that uses models trained by machine learning algorithms to process and analyze new data and tasks.

[0220] The present invention relates to a management system for industrial robots, and is a system that analyzes emails to extract due dates and task information, and reflects this information in the robot's work schedule. Specific embodiments for carrying out the present invention will be described below.

[0221] System Overview

[0222] This system operates on a server, collects and analyzes emails, and manages instructions and reports for industrial robots as tasks. Specifically, it uses the following hardware and software:

[0223] Server: Performs email collection and analysis.

[0224] IMAP library: Used to collect emails.

[0225] BERT model (generative AI model): Used to analyze emails and extract due dates and tasks.

[0226] Django: A web application framework for generating and displaying task lists.

[0227] Program processing explanation

[0228] 1. Email Collection

[0229] The server uses the IMAP protocol to access the factory's instruction and report email accounts and collect emails. The server connects to the IMAP server using the user's email account information and downloads all unread and existing emails. This ensures that the latest email information is obtained.

[0230] 2. Email Analysis

[0231] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. The BERT model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by" or "deadline") are used to identify due dates, task content, and links.

[0232] 3. Task extraction

[0233] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized by each item and used in the next step.

[0234] 4. Task list generation

[0235] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing the administrator to quickly grasp the overall picture of the tasks.

[0236] 5. Task List Notifications

[0237] The server sends the generated task list to the terminal of the administrator, and the administrator can view the task list on the terminal. The administrator receives a notification and can check the task list.

[0238] 6. Review and Track

[0239] The administrator can view the task list on their device and manage the progress of the necessary tasks. They can update the completion status and progress of tasks as needed, and add notes and comments as needed.

[0240] Specific examples

[0241] For example, consider the following email:

[0242] Email content

[0243] text

[0244] Subject: Scheduled maintenance for Machine A

[0245] Main text:

[0246] Please carry out regular maintenance on Machine A by October 15th.

[0247] Detailed instructions can be found at the following link:

[0248] http: / / factory.com / maintenance_guideline

[0249] Prompt Sentence Examples

[0250] "Please generate a code that extracts deadlines and task details from received emails and generates a task list."

[0251] For this email, the system will extract the following tasks and add them to the task list:

[0252] text

[0253] 1. Title: Scheduled Maintenance of Machine A

[0254] Response date: October 15th

[0255] Task: Regular maintenance of machine A

[0256] Related link: http: / / factory.com / maintenance_guideline

[0257] In this way, automatic management and efficient response of work schedules for industrial robots becomes possible.

[0258] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0259] Step 1:

[0260] The server uses the IMAP protocol to access the factory's instruction and report email account and collect all unread and existing emails. The user's email account information is used as input. Based on this, the server connects to the IMAP server and retrieves the latest email information from the mailbox. The email data is obtained as output.

[0261] Step 2:

[0262] The server obtains the body text and header information (subject, sender, date, etc.) of the collected emails. The email data collected in step 1 is used as input. Data processing is performed to convert the email data into a data format for analysis. The output is email data formatted in an analyzable format.

[0263] Step 3:

[0264] The server inputs the email text into a generative AI model (BERT model) to understand the context and patterns within the email. In this step, due dates, task content, and links are identified based on specific keywords. The formatted email data is used as input. Task information is extracted by natural language processing using the generative AI model. The extracted task information (due dates, task content, and related links) is obtained as output.

[0265] Step 4:

[0266] The server organizes the task information extracted from the analysis results of the generative AI model by each item. The extracted task information is used as input. Data shaping and filtering are performed to obtain organized task information. The organized task information is generated as output.

[0267] Step 5:

[0268] The server generates a task list based on the organized task information. The organized task information is used as input. Based on this, data processing is performed to list information such as the title, due date, task content, and related links for each task. The generated task list is obtained as output.

[0269] Step 6:

[0270] The server sends the generated task list to the administrator's terminal, allowing the administrator to view the task list on the terminal. The generated task list is used as input. To notify the administrator's terminal of this task list, data is transmitted using a communication protocol. The task list displayed on the terminal is obtained as output.

[0271] Step 7:

[0272] The administrator checks the task list on the terminal and manages the progress of the required tasks. The task list notified to the terminal is used as input. The administrator can update the task completion status and progress and make corrections as necessary. The updated task list and task progress are obtained as output.

[0273] 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.

[0274] This invention is a system that analyzes emails, extracts deadlines and task information, and manages them. This system also combines an emotion engine that recognizes the user's emotions, enabling flexible task management according to the user's situation.

[0275] 1. Email Collection

[0276] The server connects to the mailbox using the user's email account information and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[0277] 2. Email Analysis

[0278] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, received date, etc.) are sent to a generative AI model to extract important task information (deadline, task content, related links). This information is also evaluated for credibility based on specific keywords.

[0279] 3. Task extraction

[0280] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model, thereby minimizing the risk of missing or misidentifying tasks.

[0281] 4. Task list generation

[0282] The server organizes the extracted task information to generate a task list. The list includes information such as the title of each task, the due date, the task content, and related links. The list is formatted appropriately so that the user can quickly grasp the overall picture of the tasks.

[0283] 5. Task List Notifications

[0284] The server sends the generated task list to the user's terminal, where it can be viewed. Real-time notifications are provided using an appropriate communication protocol.

[0285] 6. Emotion recognition

[0286] As a user reviews their task list, an emotion engine recognizes their emotional state by analyzing their facial expressions, tone of voice, and typing patterns to identify their current emotional state.

[0287] 7. Adjust task management

[0288] The server can then prioritize tasks and adjust reminder notifications based on the user's emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[0289] Specific examples

[0290] For example, consider the following email:

[0291] Subject: Project X progress check

[0292] Main text:

[0293] Hello,

[0294] Please report on the progress of Project X by March 25th.

[0295] You can download the necessary materials from the following links:

[0296] http: / / example.com / resource

[0297] thank you.

[0298] Email collection

[0299] The server collects this mail from the user's mailbox.

[0300] Email Analysis

[0301] The server sends the email body to a generative AI model for analysis. The model extracts the following:

[0302] Response date: March 25th

[0303] Task: Project X progress report

[0304] Related link: http: / / example.com / resource

[0305] Task Extraction

[0306] The server extracts the following information from the output of the generative AI model:

[0307] Response date: March 25th

[0308] Task: Project X progress report

[0309] Related link: http: / / example.com / resource

[0310] Task list generation

[0311] The server uses the extracted information to generate a task list in the following format:

[0312] 1. [Title] Project X Progress Check

[0313] [Response date] March 25th

[0314] [Task Content] Project X progress report

[0315] [Related Links] http: / / example.com / resource

[0316] Task List Notifications

[0317] The server sends the generated task list to the user's terminal.

[0318] emotion recognition

[0319] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[0320] Task management adjustments

[0321] The server adjusts the priority of the task list based on the user's emotional state, for example by prioritizing only tasks that require immediate attention, reducing the user's stress.

[0322] This allows users to focus on important tasks without feeling stressed, improving work efficiency.The present invention is a system that realizes flexible and effective task management by combining task information extracted from emails with the user's emotional state.

[0323] The processing flow will be explained below.

[0324] Step 1:

[0325] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols.

[0326] Step 2:

[0327] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[0328] Step 3:

[0329] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[0330] Step 4:

[0331] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[0332] Step 5:

[0333] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[0334] Step 6:

[0335] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[0336] Step 7:

[0337] Users can view their task list on their device, manage the progress and status of each task, update the task completion status, and even enter any necessary notes or comments.

[0338] Step 8:

[0339] The device is equipped with an emotion engine that recognizes the user's emotional state when checking the task list by analyzing the user's facial expressions, tone of voice, input patterns, etc.

[0340] Step 9:

[0341] The server changes the priority of the task list based on the user's emotional state (e.g., stress, fatigue, etc.) recognized by the emotion engine. Reminder notifications are also adjusted according to the user's emotional state.

[0342] Step 10:

[0343] The device displays a prioritized task list for the user to easily review. This allows users to focus on important tasks without feeling stressed. For example, if a user is feeling stressed, only tasks that require immediate attention will be displayed as priority.

[0344] This allows users to effectively manage tasks and improve work efficiency.

[0345] Example 2

[0346] 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."

[0347] In today's business environment, many tasks and actions are notified via email, but manually organizing and managing them is extremely difficult. Furthermore, the lack of a flexible task management method that takes into account the user's stress and emotional state leads to a decline in work efficiency. A system that can solve these issues is needed.

[0348] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting electronic messages, means for analyzing the collected electronic messages using a natural language processing engine, means for extracting due dates and task information from the analyzed electronic messages using a generative AI model, means for evaluating the extracted task information based on credibility criteria using prompt sentences from the generative AI model, means for organizing the evaluated task information and generating a task list, means for notifying and displaying the generated task list on an output device, and means for adjusting the priority of the listed tasks using an emotion engine that recognizes the user's emotional state. This enables automatic and reliable extraction of task information from emails and flexible task management that takes the user's emotional state into consideration.

[0349] "Electronic message" refers to documents or information sent or received by electronic means, including emails, chat messages, and social media messages.

[0350] A "natural language processing engine" refers to computer technology that analyzes and understands the language used by humans on a daily basis, allowing it to extract and structure the meaning of text data.

[0351] A "generative AI model" is a form of artificial intelligence that refers to an algorithm that learns from large amounts of data and generates meaningful information in response to new data.

[0352] A "prompt" refers to input data or instructions that direct a generative AI model to perform a specific analysis or generation task.

[0353] "Credibility criteria" refers to the standards and rules for evaluating the accuracy and validity of extracted information. Based on these standards, the accuracy and reliability of information are judged.

[0354] A "task list" is a list of tasks or matters to be done that have a specific purpose or deadline, and includes information such as the task title, due date, task content, and related links.

[0355] An "emotion engine" refers to the technology and algorithms used to recognize and analyze human emotions. It identifies the user's emotional state based on facial expressions, tone of voice, input patterns, etc.

[0356] An "output device" refers to a device that displays information sent from a server in a form that can be viewed by a user, and includes a computer display, a smartphone screen, etc.

[0357] This invention is a system that analyzes electronic messages and automatically extracts and manages due dates and task information. It also has a function that flexibly adjusts task priorities by taking into account the user's emotional state. This system is characterized by combining a generative AI model and a natural language processing engine to extract reliable task information from electronic messages.

[0358] System configuration

[0359] 1. Server

[0360] The server collects the electronic messages using the user's email account information, authenticates using IMAP or POP3 protocols, and retrieves all unread and read electronic messages, which downloads the latest message information.

[0361] 2. Natural Language Processing Engine

[0362] The server analyzes the received electronic message using a natural language processing engine (e.g., Spacy, NLTK), thereby extracting the body and header information (subject, sender, received date and time, etc.) of the electronic message as structured data.

[0363] 3. Generative AI Models

[0364] The server sends prompts to a generative AI model (e.g., OpenAI (registered trademark) API) based on the analysis results of the electronic message, extracting important task information (deadline, task content, related links). The generative AI model returns the necessary information based on the specified prompts.

[0365] 4. Credibility Assessment

[0366] The server evaluates the task information returned by the generative AI model based on credibility criteria, which helps to avoid extracting inaccurate information and organize reliable data.

[0367] 5. Task list generation

[0368] The server aggregates the verified task information and generates a task list, which includes task titles, due dates, specific task contents, and related links.

[0369] 6. Notices and Displays

[0370] The server sends the generated task list to the user's device so that it can be displayed in real time on the device. For example, data can be sent in JSON format via a REST API, and the device displays the received data in an appropriate format.

[0371] 7. Emotion recognition

[0372] As a user reviews their task list, an emotion engine (e.g., Microsoft® Azure® Emotion API) collects the user's facial expressions and tone of voice via the camera and microphone to identify the user's emotional state.

[0373] 8. Adjust task management

[0374] The server adjusts the priority of the task list based on the user's emotional state received from the emotion engine. For example, if a user is feeling stressed, it may postpone low-priority tasks.

[0375] Specific examples

[0376] Example of a progress confirmation email for Project X

[0377] text

[0378] Subject: Project X progress check

[0379] Main text:

[0380] Hello,

[0381] Please report on the progress of Project X by March 25th.

[0382] You can download the necessary materials from the following links:

[0383] http: / / example.com / resource

[0384] thank you.

[0385] Email collection

[0386] The server collects this mail from the user's mailbox.

[0387] Email Analysis

[0388] The server analyzes the email body using a natural language processing engine and extracts the following structured data:

[0389] Subject: Project X progress check

[0390] Body: Please report the progress of Project X by March 25th.

[0391] Link: http: / / example.com / resource

[0392] Task information extraction

[0393] The server sends the following prompt to the generative AI model:

[0394] "Project X progress check. Report required by March 25th. Related link: http: / / example.com / resource"

[0395] The task information returned by the generative AI model is as follows:

[0396] Response date: March 25th

[0397] Task: Project X progress report

[0398] Related link: http: / / example.com / resource

[0399] Task list generation

[0400] The server uses the extracted information to generate a task list in the following format:

[0401] text

[0402] 1. [Title] Project X Progress Check

[0403] [Response date] March 25th

[0404] [Task Content] Project X progress report

[0405] [Related Links] http: / / example.com / resource

[0406] Coordination of emotion recognition and task management

[0407] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[0408] The server adjusts the priority of the task list based on the user's emotional state, for example, by prioritizing only tasks that require immediate attention, reducing the user's stress.

[0409] As described above, the present invention makes it possible to flexibly and effectively manage tasks by taking into account task information extracted from electronic messages and the emotional state of the user.

[0410] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0411] Program processing flow

[0412] Processing Steps

[0413] Step 1:

[0414] Input: User's email account information (username, password)

[0415] Processing: The server connects to the mailbox using IMAP or POP3 protocol and retrieves all unread and read emails. The server authenticates by calling an API such as "mailbox.login('username', 'password')". After that, it retrieves messages using commands such as "mailbox.fetch('ALL')".

[0416] Output: A dataset of retrieved emails

[0417] Step 2:

[0418] Input: Dataset of retrieved emails

[0419] Processing: The server analyzes the received email using a natural language processing engine (e.g., Spacy, NLTK). The server initializes the natural language processing engine using "nlp = spacy.load('en_core_web_sm')" and analyzes the email body and header information using "doc = nlp(email_body)". Specifically, it extracts text data such as the email body, subject, sender, and received date and time.

[0420] Output: Structured data of the parsed email (subject, body, sender, received date and time)

[0421] Step 3:

[0422] Input: Parsed email structured data

[0423] Processing: The server sends a prompt to the generative AI model (e.g., OpenAI API) and extracts important task information (deadline, task content, related links). The server generates a prompt like "prompt_text = 'Check the progress of Project X. Report required by March 25th. Related links: http: / / example.com / resource'" and sends it to the generative AI model. Task information is obtained using "result = ai_model.generate(prompt_text)".

[0424] Output: Task information from the generative AI model (deadline, task content, related links)

[0425] Step 4:

[0426] Input: Task information from the generative AI model

[0427] Processing: The server evaluates the task information returned by the generative AI model based on credibility criteria. The credibility evaluation uses regular expressions based on specific keywords, and is performed using the following formula: "re.search(pattern, result)".

[0428] Output: Task information whose authenticity has been confirmed

[0429] Step 5:

[0430] Input: Task information whose authenticity has been confirmed

[0431] Processing: The server generates a task list based on the authenticated task information. The server creates a data structure like this: task_list = [{'title': title, 'due_date': due_date, 'content': content, 'link': link}].

[0432] Output: Generated task list

[0433] Step 6:

[0434] Input: Generated task list

[0435] Processing: The server sends the generated task list to the user's device. The server sends the data in JSON format via the REST API using the following method: "requests.post('http: / / example.com / api / tasks', json=task_list)". The device receives the data using "fetch(' / api / tasks')" and displays it in the appropriate format.

[0436] Output: The task list displayed on the user's device.

[0437] Step 7:

[0438] Input: Facial expressions, tone of voice, and input patterns when users check their task list

[0439] Processing: When a user checks their task list, an emotion engine (e.g., Microsoft Azure Emotion API) recognizes the user's emotional state. The device captures an image using "face_recognition.capture_frame()" and performs emotion analysis using "azure_emotion_api.detect_emotion(image)".

[0440] Output: Recognized emotional state of the user

[0441] Step 8:

[0442] Input: The perceived emotional state of the user

[0443] Processing: The server rearranges the task list based on the user's emotional state. The server rearranges the task list based on the user's emotional state, as follows: if emotion == 'stressed': prioritize_urgent_tasks()

[0444] Output: Reconciled task list

[0445] Through the above processing steps, the present invention automatically extracts task information from electronic messages and realizes flexible task management according to the user's emotional state.

[0446] (Application example 2)

[0447] 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."

[0448] Conventional task management systems can extract task information from emails, but because they list and manage tasks without considering the user's emotional state, users may feel stressed or their work efficiency may decrease. Another issue is the insufficient evaluation of the credibility of task information extracted from emails. The present invention aims to solve these issues and provide a system that realizes flexible task management according to the user's emotional state.

[0449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0450] In this invention, the server includes means for analyzing emails, means for extracting due dates from the analyzed emails, means for listing tasks based on the extracted due dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for adjusting task priorities by recognizing the user's emotional state, and means for adjusting reminder notifications based on the user's emotional state. This enables the user to manage tasks in a less stressful manner, thereby improving overall work efficiency.

[0451] The "means for analyzing e-mail" is a means having a function of acquiring a user's e-mail, analyzing the mail body and header information, and extracting due dates and task information.

[0452] The "means for extracting correspondence dates" is a means having a function for detecting and extracting date information such as deadlines and deadlines from analyzed emails.

[0453] The "means for listing tasks" is a means having a function for organizing extracted task information and displaying it in a list format so that the user can easily understand it.

[0454] The "means for organizing links and correspondence content" is a means having a function for collecting and organizing links and specific correspondence content related to the listed tasks.

[0455] The "means for displaying a task list" is a means having a function for displaying the generated task list on the user's terminal so that the user can visually confirm it.

[0456] "Means for recognizing the user's emotional state and adjusting task priorities" refers to means that has the function of recognizing the user's emotional state from facial expressions, tone of voice, etc., and dynamically changing task priorities according to that state.

[0457] The "means for adjusting reminder notifications based on the user's emotional state" refers to a means that has the function of changing the timing and content of reminder notifications according to the user's emotional state, thereby reducing the burden on the user.

[0458] The system that realizes this application example is a production management support system installed on factory robots. This system is equipped with multiple functions that enable users (workers) to efficiently manage tasks.

[0459] First, the server connects to your mailbox using your email account information and collects your emails. It uses IMAP or POP3 protocols to retrieve all unread and read emails. This allows the server to download the latest email information.

[0460] The server then analyzes the email using natural language processing. The email body and header information (e.g., subject, sender, and date and time of receipt) are sent to a generative AI model to extract important task information (deadline, task content, and related links). This information is also evaluated for credibility based on specific keywords.

[0461] The server then extracts and organizes task information whose credibility has been assessed from the analysis results of the generative AI model. This minimizes the risk of missing or misidentifying tasks. The server then organizes the extracted task information to generate a task list. The list includes information such as each task's title, due date, task content, and related links. The list is organized in an appropriate format so that users can quickly grasp the overall picture of the tasks.

[0462] The generated task list is sent from the server to the user's device (e.g., tablet or smart glasses) and can be viewed on the device. Real-time notifications are provided using an appropriate communication protocol.

[0463] A distinctive feature of this system is the ability of the emotion engine to recognize the user's emotional state when they check their task list. This engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. This emotion recognition is performed by the emotion engine, and appropriate countermeasures are presented according to the situation.

[0464] Additionally, the server can reprioritize task lists and adjust reminder notifications based on the user's perceived emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[0465] As a concrete example, consider the following email:

[0466] Subject: Project Y progress check

[0467] Main text:

[0468] Hello,

[0469] Please report the progress of Project Y by April 1st.

[0470] You can download the necessary materials from the following links:

[0471] http: / / example.com / resource

[0472] thank you.

[0473] Based on the email above, the server extracts the following:

[0474] Response date: April 1st

[0475] Task: Report on the progress of Project Y

[0476] Related link: http: / / example.com / resource

[0477] Based on this extracted information, a task list is generated and notified to the user. Furthermore, if the emotion recognition engine detects signs of stress when the user checks the task list, the priority of the tasks is appropriately adjusted.

[0478] An example of a prompt for a generative AI model is:

[0479] Extract the task information from the following email:

[0480] Subject: Project Y progress check

[0481] Main text:

[0482] Hello,

[0483] Please report the progress of Project Y by April 1st.

[0484] You can download the necessary materials from the following links:

[0485] http: / / example.com / resource

[0486] thank you.

[0487] In this way, the system of the present invention realizes flexible and effective task management according to the user's emotional state. This technology can improve factory productivity while reducing the burden on workers.

[0488] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0489] Step 1:

[0490] The server connects to the mailbox using the user's email account information and collects emails. The protocol used is IMAP or POP3. The input is the user's email account information, and the output is the retrieved email data. This email data includes all unread and read emails.

[0491] Step 2:

[0492] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, date and time of receipt, etc.) are sent to the generative AI model, which extracts important task information (deadline, task content, related links). The input is the email data, and the output is the extracted task information. At this point, a prompt is sent to the generative AI model, and the analysis results are received.

[0493] Step 3:

[0494] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model. The input is the analysis results from the generative AI model, and the output is the task information whose credibility has been evaluated.

[0495] Step 4:

[0496] The server organizes the extracted task information and generates a task list, which includes information such as the title, due date, task content, and related links for each task. The input is the task information whose credibility has been evaluated, and the output is a generated task list.

[0497] Step 5:

[0498] The server sends the generated task list to the user's terminal, where it can be viewed by the user. Notifications are given in real time using an appropriate communication protocol. The input is the task list, and the output is the task list displayed on the user's terminal.

[0499] Step 6:

[0500] When a user checks their task list, the emotion engine recognizes their emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. The input is the user's emotional data, and the output is the recognized emotional state.

[0501] Step 7:

[0502] The server changes the priority of the task list and adjusts reminder notifications based on the recognized emotional state. For example, if it recognizes that the user is feeling stressed, it will postpone low-priority tasks. The inputs are the recognized emotional state and the task list, and the output is the prioritized task list and notifications.

[0503] 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.

[0504] 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.

[0505] 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.

[0506] [Second embodiment]

[0507] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0508] 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.

[0509] 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).

[0510] 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.

[0511] 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.

[0512] 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).

[0513] 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. 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] 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."

[0519] This invention relates to a system that analyzes emails and extracts and manages deadlines and task information. The server collects all emails from mailboxes and analyzes them using AI (generative AI models), automatically extracting and organizing important task information.

[0520] 1. Email Collection

[0521] The server connects to your mailbox using your email account information. The server uses IMAP or POP3 protocols to access your mailbox and download all unread and existing emails, ensuring that you receive the most up-to-date information.

[0522] 2. Email Analysis

[0523] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. A natural language processing model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by," "deadline," etc.) are used to identify due dates, task content, and links.

[0524] 3. Task extraction

[0525] The server extracts important task information (deadline, task content, related links) from the analysis results of the AI ​​model. The extracted information is organized by each item and used in the next step.

[0526] 4. Task list generation

[0527] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing users to quickly grasp the overall picture of the tasks.

[0528] 5. Task List Notifications

[0529] The server sends the generated task list to the user's terminal, where it can be viewed. The user receives a notification and can check the task list.

[0530] 6. Review and Track

[0531] Users can view task lists on their devices and manage the progress of the tasks they need to complete. They can update task completion status and progress as needed and add notes and comments as needed.

[0532] Specific examples

[0533] For example, consider the following email:

[0534] Subject: Project X progress check

[0535] Main text:

[0536] Hello,

[0537] Please report on the progress of Project X by March 25th.

[0538] You can download the necessary materials from the following links:

[0539] http: / / example.com / resource

[0540] thank you.

[0541] Email collection

[0542] The server collects this mail from the user's mailbox.

[0543] Email Analysis

[0544] The server sends the email body to a generative AI model for analysis. The model extracts:

[0545] Response date: March 25th

[0546] Task: Project X progress report

[0547] Related link: http: / / example.com / resource

[0548] Task Extraction

[0549] The server extracts the following information from the output of the generative AI model:

[0550] Response date: March 25th

[0551] Task: Project X progress report

[0552] Related link: http: / / example.com / resource

[0553] Task list generation

[0554] The server generates a task list based on the extracted information in the following format:

[0555] 1. [Title] Project X Progress Check

[0556] [Response date] March 25th

[0557] [Task Content] Project X progress report

[0558] [Related Links] http: / / example.com / resource

[0559] Task List Notifications

[0560] The server transmits the generated task list to the user's terminal.

[0561] Review and Track

[0562] Users can view their task list on their device and ensure they take necessary action in their daily work, update their progress, and record the completion of tasks.

[0563] The above is an embodiment of the present invention, which allows a user to manage important task information from a large volume of emails without missing it, and to respond quickly.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[0567] Step 2:

[0568] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[0569] Step 3:

[0570] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[0571] Step 4:

[0572] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[0573] Step 5:

[0574] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[0575] Step 6:

[0576] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[0577] Step 7:

[0578] Users can view their task list on their device, manage the progress and completion status of each task, update the task completion status, and even enter any necessary notes or comments.

[0579] Step 8:

[0580] Users can carry out tasks and work based on deadlines and task content. By checking progress on their devices, they can prevent tasks from being overlooked and work can be done efficiently.

[0581] Example 1

[0582] 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."

[0583] With conventional email systems, users have to manually sort and extract important task information from a large volume of emails, which is extremely time-consuming. There's also a high risk of missing task deadlines or important links. This reduces work efficiency and makes it difficult to manage task progress.

[0584] 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.

[0585] In this invention, the server includes means for connecting to an email server using a user's account information and collecting emails stored in a mailbox, means for using a generative AI model to analyze the body and header information of the collected emails, means for extracting due dates, task contents, and related links from the analysis results of the generative AI model, means for generating a task list based on the extracted information, means for notifying the user's terminal of the generated task list, and means for the user to check the task list on the terminal and manage progress. This allows the user to automatically extract and organize important task information from emails, significantly improving work efficiency.

[0586] "User account information" refers to authentication information required to connect to an email server, including an email address, password, and other necessary authentication information.

[0587] An "email server" is a server for sending, receiving, and storing emails, and is a server system that is accessed using protocols such as IMAP and POP3.

[0588] A "mailbox" is a digital storage area associated with a user's email account for storing received email.

[0589] An "email" is a digital message sent and received over the Internet, and includes information such as the body, subject, sender, recipient, and date and time of sending.

[0590] A "generative AI model" is a machine learning model for natural language processing, capable of understanding the meaning of language based on large amounts of text data, and analyzing and extracting specific information.

[0591] A "prompt" is an instruction given to a generative AI model to perform a specific task, providing the model with criteria and context for analysis and generation.

[0592] "Task information" is information such as due dates, task contents, and related links extracted from emails, and refers to specific action items that the user should manage.

[0593] A "task list" is extracted task information that is organized and displayed in a list format, and includes the title of each task, the due date, the task content, related links, and the like.

[0594] A "terminal" is a digital device used by a user to check the task list and manage the progress of tasks, and includes a PC, smartphone, tablet, etc.

[0595] "Notification" refers to the alert function or message sending that notifies the user of the generated task list, and is done via email, push notification, or a dedicated app.

[0596] This invention relates to a system that analyzes emails and extracts and manages response deadlines and task information. In this system, a server collects all emails from mailboxes and analyzes them using a generative AI model to automatically extract and organize important task information. A specific embodiment of this system is described below.

[0597] Email collection

[0598] The server connects to an email server (e.g., a server using IMAP or POP3 protocols) using the user's account information (email address, password). After connecting, the server downloads all unread and read emails in the mailbox and retrieves the latest email information. This data is temporarily stored in local storage.

[0599] Email Analysis

[0600] The server extracts the downloaded email's body and header information (subject, sender, date, etc.) and inputs it into a generative AI model. The generative AI model (e.g., a natural language processing model) is given a specific prompt and uses this to analyze the email content. This analysis identifies due dates, task details, and related links based on specific keywords and phrases (e.g., "by," "deadline," etc.).

[0601] Task Extraction

[0602] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized into categories such as deadline, task content, and related links.

[0603] Task list generation

[0604] The server generates a task list based on the extracted task information. This task list includes the title, due date, task content, and related links for each task. The list is saved in a structured format so that users can easily view it.

[0605] For example, the generated task list might look like this:

[0606] 1. [Title] Project X Progress Check

[0607] [Response date] March 25th

[0608] [Task Content] Project X progress report

[0609] [Related Links] http: / / example.com / resource

[0610] Task List Notifications

[0611] The server then notifies the user of the generated task list via email or push notification from a dedicated application.

[0612] Review and Track

[0613] Users can view the received task list on their device and manage the progress of each task. Users can update the task completion status at any time and add comments or notes as needed, allowing users to manage tasks efficiently and meet important deadlines.

[0614] Specific examples

[0615] For example, suppose the following email arrives in a user's mailbox:

[0616] Subject: Project X progress check

[0617] Main text:

[0618] Hello,

[0619] Please report on the progress of Project X by March 25th.

[0620] You can download the necessary materials from the following links:

[0621] http: / / example.com / resource

[0622] thank you.

[0623] When the server collects this email and asks the generative AI model to analyze it, it uses the following prompt:

[0624] "Please extract the due date, task details, and related links from this email."

[0625] The generative AI model analyzes the content of the email and extracts the following information:

[0626] Response date: March 25th

[0627] Task: Project X progress report

[0628] Related link: http: / / example.com / resource

[0629] Based on this, the server generates a task list and notifies the user's device, allowing the user to check the list and take the necessary actions quickly.

[0630] This system allows users to automatically extract important task information from emails and manage it efficiently, significantly improving the efficiency of their overall work.

[0631] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0632] Step 1:

[0633] Connecting to a mail server

[0634] The server connects to the email server (IMAP or POP3 protocol) using the user's account information (email address, password).

[0635] Input: User's email account information

[0636] Output: Connecting to the mail server

[0637] This connection gives the server permission to access the email in your mailbox.

[0638] Step 2:

[0639] Email collection

[0640] After connecting to the mail server, the server downloads all unread and read emails in the mailbox, which are then temporarily stored in local storage.

[0641] Input: Email in mailbox

[0642] Output: Email data saved in local storage

[0643] In this step, the server obtains the latest mail information and prepares it for the next analysis step.

[0644] Step 3:

[0645] Preparation for email analysis

[0646] The server extracts the body text and header information (subject, sender, date, etc.) of the collected emails and prepares them for input into the generative AI model.

[0647] Input: Email data stored in local storage

[0648] Output: Email body and header information for analysis

[0649] The information required for analysis is ready to be passed to the generative AI model.

[0650] Step 4:

[0651] Analysis using generative AI models

[0652] The server sends the email body and header information to the generative AI model and requests analysis using specific prompts.

[0653] Example prompt: "Extract due dates, tasks, and related links from this email."

[0654] Input: Email body and header information for analysis, prompt text

[0655] Output: Analysis results (response due date, task details, related links)

[0656] In this step, the generative AI model understands the content of the email and extracts important task information.

[0657] Step 5:

[0658] Extracting and organizing task information

[0659] The server extracts response deadlines, task details, and related links from the analysis results of the generative AI model and organizes them into their respective categories.

[0660] Input: Analysis results of the generative AI model

[0661] Output: Organized task information (deadline, task content, related links)

[0662] This ensures that important task information is clearly categorized.

[0663] Step 6:

[0664] Generate a task list

[0665] The server generates a task list based on the organized task information, which includes the title, due date, task content, and related links for each task.

[0666] Input: Organized task information

[0667] Output: Generated task list

[0668] The generated task list is saved in a format that is easy for the user to check.

[0669] Step 7:

[0670] Task List Notifications

[0671] The server notifies the user of the generated task list via email or push notification from a dedicated application.

[0672] Input: Generated task list

[0673] Output: Notification to the user's device

[0674] The user receives this notification and can check the task list.

[0675] Step 8:

[0676] Review and track your task list

[0677] The user can check the received task list on the device, manage the progress of each task, add comments and notes as needed, and update the task progress as needed.

[0678] Input: User task management actions (status update, comment addition, etc.)

[0679] Output: Updated task list

[0680] This allows users to efficiently manage their tasks and ensure that they do not miss important deadlines or task details.

[0681] (Application example 1)

[0682] 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."

[0683] Conventional industrial robot management systems require manual management of instructions and reports, resulting in inefficiencies and errors. Extracting necessary task information from a large volume of emails is time-consuming and places a significant burden on the manager. The present invention aims to solve these problems and provide a method for automatically and efficiently managing robot work schedules.

[0684] 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.

[0685] In this invention, the server includes means for analyzing emails, means for extracting action dates from the analyzed emails, means for listing tasks based on the extracted action dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for analyzing instructions and reports from the industrial robot and extracting and managing action dates and specific work details, means for notifying the generated robot task list to a manager's terminal, and means for the manager to monitor the robot's work progress in real time and issue correction instructions as necessary, thereby enabling automatic management of the robot's work schedule and efficient response.

[0686] "Email" means written communication sent or received in digital form, a message transmitted through an electronic device.

[0687] "Analyzing" means examining collected data in detail and breaking down its content and structure into an understandable format.

[0688] A "due date" is the date by which a particular task or action is required to be completed.

[0689] A "task" is a specific activity or task that must be performed to achieve a specific goal.

[0690] "Listing" means arranging items in a list format in a particular order.

[0691] A "link" is a hypertext reference that directs a user to a particular resource or piece of information.

[0692] "Organizing" is the process of compiling data and information in an efficient and easy-to-understand format.

[0693] "Displaying" means visually presenting data or information to a user.

[0694] An "industrial robot" is a programmable mechanical device used to perform automated tasks in industry.

[0695] An "instruction" is an order or instruction to perform a specific action or task.

[0696] A "report" is a report on the progress and results of work.

[0697] To "manage" means to effectively manage, supervise, and control a specific resource or task.

[0698] "Notifying" is the act of informing others of specific information.

[0699] "Monitoring" means continuously observing a series of actions or processes and responding if an abnormality occurs.

[0700] "Modification instructions" means instructions to make changes or improvements to existing plans or schedules.

[0701] A "generative AI model" is an artificial intelligence technology that uses models trained by machine learning algorithms to process and analyze new data and tasks.

[0702] The present invention relates to a management system for industrial robots, and is a system that analyzes emails to extract due dates and task information, and reflects this information in the robot's work schedule. Specific embodiments for carrying out the present invention will be described below.

[0703] System Overview

[0704] This system operates on a server, collects and analyzes emails, and manages instructions and reports for industrial robots as tasks. Specifically, it uses the following hardware and software:

[0705] Server: Performs email collection and analysis.

[0706] IMAP library: Used to collect emails.

[0707] BERT model (generative AI model): Used to analyze emails and extract due dates and tasks.

[0708] Django: A web application framework for generating and displaying task lists.

[0709] Program processing explanation

[0710] 1. Email Collection

[0711] The server uses the IMAP protocol to access the factory's instruction and report email accounts and collect emails. The server connects to the IMAP server using the user's email account information and downloads all unread and existing emails. This ensures that the latest email information is obtained.

[0712] 2. Email Analysis

[0713] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. The BERT model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by" or "deadline") are used to identify due dates, task content, and links.

[0714] 3. Task extraction

[0715] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized by each item and used in the next step.

[0716] 4. Task list generation

[0717] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing the administrator to quickly grasp the overall picture of the tasks.

[0718] 5. Task List Notifications

[0719] The server sends the generated task list to the terminal of the administrator, and the administrator can view the task list on the terminal. The administrator receives a notification and can check the task list.

[0720] 6. Review and Track

[0721] The administrator can view the task list on their device and manage the progress of the necessary tasks. They can update the completion status and progress of tasks as needed, and add notes and comments as needed.

[0722] Specific examples

[0723] For example, consider the following email:

[0724] Email content

[0725] text

[0726] Subject: Scheduled maintenance for Machine A

[0727] Main text:

[0728] Please carry out regular maintenance on Machine A by October 15th.

[0729] Detailed instructions can be found at the following link:

[0730] http: / / factory.com / maintenance_guideline

[0731] Prompt Sentence Examples

[0732] "Please generate a code that extracts deadlines and task details from received emails and generates a task list."

[0733] For this email, the system will extract the following tasks and add them to the task list:

[0734] text

[0735] 1. Title: Scheduled Maintenance of Machine A

[0736] Response date: October 15th

[0737] Task: Regular maintenance of machine A

[0738] Related link: http: / / factory.com / maintenance_guideline

[0739] In this way, automatic management and efficient response of work schedules for industrial robots becomes possible.

[0740] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0741] Step 1:

[0742] The server uses the IMAP protocol to access the factory's instruction and report email account and collect all unread and existing emails. The user's email account information is used as input. Based on this, the server connects to the IMAP server and retrieves the latest email information from the mailbox. The email data is obtained as output.

[0743] Step 2:

[0744] The server obtains the body text and header information (subject, sender, date, etc.) of the collected emails. The email data collected in step 1 is used as input. Data processing is performed to convert the email data into a data format for analysis. The output is email data formatted in an analyzable format.

[0745] Step 3:

[0746] The server inputs the email text into a generative AI model (BERT model) to understand the context and patterns within the email. In this step, due dates, task content, and links are identified based on specific keywords. The formatted email data is used as input. Task information is extracted by natural language processing using the generative AI model. The extracted task information (due dates, task content, and related links) is obtained as output.

[0747] Step 4:

[0748] The server organizes the task information extracted from the analysis results of the generative AI model by each item. The extracted task information is used as input. Data shaping and filtering are performed to obtain organized task information. The organized task information is generated as output.

[0749] Step 5:

[0750] The server generates a task list based on the organized task information. The organized task information is used as input. Based on this, data processing is performed to list information such as the title, due date, task content, and related links for each task. The generated task list is obtained as output.

[0751] Step 6:

[0752] The server sends the generated task list to the administrator's terminal, allowing the administrator to view the task list on the terminal. The generated task list is used as input. To notify the administrator's terminal of this task list, data is transmitted using a communication protocol. The task list displayed on the terminal is obtained as output.

[0753] Step 7:

[0754] The administrator checks the task list on the terminal and manages the progress of the required tasks. The task list notified to the terminal is used as input. The administrator can update the task completion status and progress and make corrections as necessary. The updated task list and task progress are obtained as output.

[0755] 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.

[0756] This invention is a system that analyzes emails, extracts deadlines and task information, and manages them. This system also combines an emotion engine that recognizes the user's emotions, enabling flexible task management according to the user's situation.

[0757] 1. Email Collection

[0758] The server connects to the mailbox using the user's email account information and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[0759] 2. Email Analysis

[0760] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, received date, etc.) are sent to a generative AI model to extract important task information (deadline, task content, related links). This information is also evaluated for credibility based on specific keywords.

[0761] 3. Task extraction

[0762] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model, thereby minimizing the risk of missing or misidentifying tasks.

[0763] 4. Task list generation

[0764] The server organizes the extracted task information to generate a task list. The list includes information such as the title of each task, the due date, the task content, and related links. The list is formatted appropriately so that the user can quickly grasp the overall picture of the tasks.

[0765] 5. Task List Notifications

[0766] The server sends the generated task list to the user's terminal, where it can be viewed. Real-time notifications are provided using an appropriate communication protocol.

[0767] 6. Emotion recognition

[0768] As a user reviews their task list, an emotion engine recognizes their emotional state by analyzing their facial expressions, tone of voice, and typing patterns to identify their current emotional state.

[0769] 7. Adjust task management

[0770] The server can then prioritize tasks and adjust reminder notifications based on the user's emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[0771] Specific examples

[0772] For example, consider the following email:

[0773] Subject: Project X progress check

[0774] Main text:

[0775] Hello,

[0776] Please report on the progress of Project X by March 25th.

[0777] You can download the necessary materials from the following links:

[0778] http: / / example.com / resource

[0779] thank you.

[0780] Email collection

[0781] The server collects this mail from the user's mailbox.

[0782] Email Analysis

[0783] The server sends the email body to a generative AI model for analysis. The model extracts the following:

[0784] Response date: March 25th

[0785] Task: Project X progress report

[0786] Related link: http: / / example.com / resource

[0787] Task Extraction

[0788] The server extracts the following information from the output of the generative AI model:

[0789] Response date: March 25th

[0790] Task: Project X progress report

[0791] Related link: http: / / example.com / resource

[0792] Task list generation

[0793] The server uses the extracted information to generate a task list in the following format:

[0794] 1. [Title] Project X Progress Check

[0795] [Response date] March 25th

[0796] [Task Content] Project X progress report

[0797] [Related Links] http: / / example.com / resource

[0798] Task List Notifications

[0799] The server sends the generated task list to the user's terminal.

[0800] emotion recognition

[0801] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[0802] Task management adjustments

[0803] The server adjusts the priority of the task list based on the user's emotional state, for example by prioritizing only tasks that require immediate attention, reducing the user's stress.

[0804] This allows users to focus on important tasks without feeling stressed, improving work efficiency.The present invention is a system that realizes flexible and effective task management by combining task information extracted from emails with the user's emotional state.

[0805] The processing flow will be explained below.

[0806] Step 1:

[0807] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols.

[0808] Step 2:

[0809] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[0810] Step 3:

[0811] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[0812] Step 4:

[0813] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[0814] Step 5:

[0815] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[0816] Step 6:

[0817] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[0818] Step 7:

[0819] Users can view their task list on their device, manage the progress and status of each task, update the task completion status, and even enter any necessary notes or comments.

[0820] Step 8:

[0821] The device is equipped with an emotion engine that recognizes the user's emotional state when checking the task list by analyzing the user's facial expressions, tone of voice, input patterns, etc.

[0822] Step 9:

[0823] The server changes the priority of the task list based on the user's emotional state (e.g., stress, fatigue, etc.) recognized by the emotion engine. Reminder notifications are also adjusted according to the user's emotional state.

[0824] Step 10:

[0825] The device displays a prioritized task list for the user to easily review. This allows users to focus on important tasks without feeling stressed. For example, if a user is feeling stressed, only tasks that require immediate attention will be displayed as priority.

[0826] This allows users to effectively manage tasks and improve work efficiency.

[0827] Example 2

[0828] 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."

[0829] In today's business environment, many tasks and actions are notified via email, but manually organizing and managing them is extremely difficult. Furthermore, the lack of a flexible task management method that takes into account the user's stress and emotional state leads to a decline in work efficiency. A system that can solve these issues is needed.

[0830] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting electronic messages, means for analyzing the collected electronic messages using a natural language processing engine, means for extracting due dates and task information from the analyzed electronic messages using a generative AI model, means for evaluating the extracted task information based on credibility criteria using prompt sentences from the generative AI model, means for organizing the evaluated task information and generating a task list, means for notifying and displaying the generated task list on an output device, and means for adjusting the priority of the listed tasks using an emotion engine that recognizes the user's emotional state. This enables automatic and reliable extraction of task information from emails and flexible task management that takes the user's emotional state into consideration.

[0831] "Electronic message" refers to documents or information sent or received by electronic means, including emails, chat messages, and social media messages.

[0832] A "natural language processing engine" refers to computer technology that analyzes and understands the language used by humans on a daily basis, allowing it to extract and structure the meaning of text data.

[0833] A "generative AI model" is a form of artificial intelligence that refers to an algorithm that learns from large amounts of data and generates meaningful information in response to new data.

[0834] A "prompt" refers to input data or instructions that direct a generative AI model to perform a specific analysis or generation task.

[0835] "Credibility criteria" refers to the standards and rules for evaluating the accuracy and validity of extracted information. Based on these standards, the accuracy and reliability of information are judged.

[0836] A "task list" is a list of tasks or matters to be done that have a specific purpose or deadline, and includes information such as the task title, due date, task content, and related links.

[0837] An "emotion engine" refers to the technology and algorithms used to recognize and analyze human emotions. It identifies the user's emotional state based on facial expressions, tone of voice, input patterns, etc.

[0838] An "output device" refers to a device that displays information sent from a server in a form that can be viewed by a user, and includes a computer display, a smartphone screen, etc.

[0839] This invention is a system that analyzes electronic messages and automatically extracts and manages due dates and task information. It also has a function that flexibly adjusts task priorities by taking into account the user's emotional state. This system is characterized by combining a generative AI model and a natural language processing engine to extract reliable task information from electronic messages.

[0840] System configuration

[0841] 1. Server

[0842] The server collects the electronic messages using the user's email account information, authenticates using IMAP or POP3 protocols, and retrieves all unread and read electronic messages, which downloads the latest message information.

[0843] 2. Natural Language Processing Engine

[0844] The server analyzes the received electronic message using a natural language processing engine (e.g., Spacy, NLTK), thereby extracting the body and header information (subject, sender, received date and time, etc.) of the electronic message as structured data.

[0845] 3. Generative AI Models

[0846] The server sends a prompt to a generative AI model (e.g., OpenAI API) based on the analysis results of the electronic message, extracting important task information (deadline, task content, related links). The generative AI model returns the necessary information based on the specified prompt.

[0847] 4. Credibility Assessment

[0848] The server evaluates the task information returned by the generative AI model based on credibility criteria, which helps to avoid extracting inaccurate information and organize reliable data.

[0849] 5. Task list generation

[0850] The server aggregates the verified task information and generates a task list, which includes task titles, due dates, specific task contents, and related links.

[0851] 6. Notices and Displays

[0852] The server sends the generated task list to the user's device so that it can be displayed in real time on the device. For example, data can be sent in JSON format via a REST API, and the device displays the received data in an appropriate format.

[0853] 7. Emotion recognition

[0854] As a user reviews their task list, an emotion engine (e.g., Microsoft Azure Emotion API) collects their facial expressions and tone of voice via the camera and microphone to identify their emotional state.

[0855] 8. Adjust task management

[0856] The server adjusts the priority of the task list based on the user's emotional state received from the emotion engine. For example, if a user is feeling stressed, it may postpone low-priority tasks.

[0857] Specific examples

[0858] Example of a progress confirmation email for Project X

[0859] text

[0860] Subject: Project X progress check

[0861] Main text:

[0862] Hello,

[0863] Please report on the progress of Project X by March 25th.

[0864] You can download the necessary materials from the following links:

[0865] http: / / example.com / resource

[0866] thank you.

[0867] Email collection

[0868] The server collects this mail from the user's mailbox.

[0869] Email Analysis

[0870] The server analyzes the email body using a natural language processing engine and extracts the following structured data:

[0871] Subject: Project X progress check

[0872] Body: Please report the progress of Project X by March 25th.

[0873] Link: http: / / example.com / resource

[0874] Task information extraction

[0875] The server sends the following prompt to the generative AI model:

[0876] "Project X progress check. Report required by March 25th. Related link: http: / / example.com / resource"

[0877] The task information returned by the generative AI model is as follows:

[0878] Response date: March 25th

[0879] Task: Project X progress report

[0880] Related link: http: / / example.com / resource

[0881] Task list generation

[0882] The server uses the extracted information to generate a task list in the following format:

[0883] text

[0884] 1. [Title] Project X Progress Check

[0885] [Response date] March 25th

[0886] [Task Content] Project X progress report

[0887] [Related Links] http: / / example.com / resource

[0888] Coordination of emotion recognition and task management

[0889] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[0890] The server adjusts the priority of the task list based on the user's emotional state, for example, by prioritizing only tasks that require immediate attention, reducing the user's stress.

[0891] As described above, the present invention makes it possible to flexibly and effectively manage tasks by taking into account task information extracted from electronic messages and the emotional state of the user.

[0892] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0893] Program processing flow

[0894] Processing Steps

[0895] Step 1:

[0896] Input: User's email account information (username, password)

[0897] Processing: The server connects to the mailbox using IMAP or POP3 protocol and retrieves all unread and read emails. The server authenticates by calling an API such as "mailbox.login('username', 'password')". After that, it retrieves messages using commands such as "mailbox.fetch('ALL')".

[0898] Output: A dataset of retrieved emails

[0899] Step 2:

[0900] Input: Dataset of retrieved emails

[0901] Processing: The server analyzes the received email using a natural language processing engine (e.g., Spacy, NLTK). The server initializes the natural language processing engine using "nlp = spacy.load('en_core_web_sm')" and analyzes the email body and header information using "doc = nlp(email_body)". Specifically, it extracts text data such as the email body, subject, sender, and received date and time.

[0902] Output: Structured data of the parsed email (subject, body, sender, received date and time)

[0903] Step 3:

[0904] Input: Parsed email structured data

[0905] Processing: The server sends a prompt to the generative AI model (e.g., OpenAI API) and extracts important task information (deadline, task content, related links). The server generates a prompt like "prompt_text = 'Check the progress of Project X. Report required by March 25th. Related links: http: / / example.com / resource'" and sends it to the generative AI model. Task information is obtained using "result = ai_model.generate(prompt_text)".

[0906] Output: Task information from the generative AI model (deadline, task content, related links)

[0907] Step 4:

[0908] Input: Task information from the generative AI model

[0909] Processing: The server evaluates the task information returned by the generative AI model based on credibility criteria. The credibility evaluation uses regular expressions based on specific keywords, and is performed using the following formula: "re.search(pattern, result)".

[0910] Output: Task information whose authenticity has been confirmed

[0911] Step 5:

[0912] Input: Task information whose authenticity has been confirmed

[0913] Processing: The server generates a task list based on the authenticated task information. The server creates a data structure like this: task_list = [{'title': title, 'due_date': due_date, 'content': content, 'link': link}].

[0914] Output: Generated task list

[0915] Step 6:

[0916] Input: Generated task list

[0917] Processing: The server sends the generated task list to the user's device. The server sends the data in JSON format via the REST API using the following method: "requests.post('http: / / example.com / api / tasks', json=task_list)". The device receives the data using "fetch(' / api / tasks')" and displays it in the appropriate format.

[0918] Output: The task list displayed on the user's device.

[0919] Step 7:

[0920] Input: Facial expressions, tone of voice, and input patterns when users check their task list

[0921] Processing: When a user checks their task list, an emotion engine (e.g., Microsoft Azure Emotion API) recognizes the user's emotional state. The device captures an image using "face_recognition.capture_frame()" and performs emotion analysis using "azure_emotion_api.detect_emotion(image)".

[0922] Output: Recognized emotional state of the user

[0923] Step 8:

[0924] Input: Perceived emotional state of the user

[0925] Processing: The server rearranges the task list based on the user's emotional state. The server rearranges the task list based on the user's emotional state, as follows: if emotion == 'stressed': prioritize_urgent_tasks()

[0926] Output: Reconciled task list

[0927] Through the above processing steps, the present invention automatically extracts task information from electronic messages and realizes flexible task management according to the user's emotional state.

[0928] (Application example 2)

[0929] 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."

[0930] Conventional task management systems can extract task information from emails, but because they list and manage tasks without considering the user's emotional state, users may feel stressed or their work efficiency may decrease. Another issue is the insufficient evaluation of the credibility of task information extracted from emails. The present invention aims to solve these issues and provide a system that realizes flexible task management according to the user's emotional state.

[0931] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0932] In this invention, the server includes means for analyzing emails, means for extracting due dates from the analyzed emails, means for listing tasks based on the extracted due dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for adjusting task priorities by recognizing the user's emotional state, and means for adjusting reminder notifications based on the user's emotional state. This enables the user to manage tasks in a less stressful manner, thereby improving overall work efficiency.

[0933] The "means for analyzing e-mail" is a means having a function of acquiring a user's e-mail, analyzing the mail body and header information, and extracting due dates and task information.

[0934] The "means for extracting correspondence dates" is a means having a function for detecting and extracting date information such as deadlines and deadlines from analyzed emails.

[0935] The "means for listing tasks" is a means having a function for organizing extracted task information and displaying it in a list format so that the user can easily understand it.

[0936] The "means for organizing links and correspondence content" is a means having a function for collecting and organizing links and specific correspondence content related to the listed tasks.

[0937] The "means for displaying a task list" is a means having a function for displaying the generated task list on the user's terminal so that the user can visually confirm it.

[0938] "Means for recognizing the user's emotional state and adjusting task priorities" refers to means that has the function of recognizing the user's emotional state from facial expressions, tone of voice, etc., and dynamically changing task priorities according to that state.

[0939] The "means for adjusting reminder notifications based on the user's emotional state" refers to a means that has the function of changing the timing and content of reminder notifications according to the user's emotional state, thereby reducing the burden on the user.

[0940] The system that realizes this application example is a production management support system installed on factory robots. This system is equipped with multiple functions that enable users (workers) to efficiently manage tasks.

[0941] First, the server connects to your mailbox using your email account information and collects your emails. It uses IMAP or POP3 protocols to retrieve all unread and read emails. This allows the server to download the latest email information.

[0942] The server then analyzes the email using natural language processing. The email body and header information (e.g., subject, sender, and date and time of receipt) are sent to a generative AI model to extract important task information (deadline, task content, and related links). This information is also evaluated for credibility based on specific keywords.

[0943] The server then extracts and organizes task information whose credibility has been assessed from the analysis results of the generative AI model. This minimizes the risk of missing or misidentifying tasks. The server then organizes the extracted task information to generate a task list. The list includes information such as each task's title, due date, task content, and related links. The list is organized in an appropriate format so that users can quickly grasp the overall picture of the tasks.

[0944] The generated task list is sent from the server to the user's device (e.g., tablet or smart glasses) and can be viewed on the device. Real-time notifications are provided using an appropriate communication protocol.

[0945] A distinctive feature of this system is the ability of the emotion engine to recognize the user's emotional state when they check their task list. This engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. This emotion recognition is performed by the emotion engine, and appropriate countermeasures are presented according to the situation.

[0946] Additionally, the server can reprioritize task lists and adjust reminder notifications based on the user's perceived emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[0947] As a concrete example, consider the following email:

[0948] Subject: Project Y progress check

[0949] Main text:

[0950] Hello,

[0951] Please report the progress of Project Y by April 1st.

[0952] You can download the necessary materials from the following links:

[0953] http: / / example.com / resource

[0954] thank you.

[0955] Based on the email above, the server extracts the following:

[0956] Response date: April 1st

[0957] Task: Report on the progress of Project Y

[0958] Related link: http: / / example.com / resource

[0959] Based on this extracted information, a task list is generated and notified to the user. Furthermore, if the emotion recognition engine detects signs of stress when the user checks the task list, the priority of the tasks is appropriately adjusted.

[0960] An example of a prompt for a generative AI model is:

[0961] Extract the task information from the following email:

[0962] Subject: Project Y progress check

[0963] Main text:

[0964] Hello,

[0965] Please report the progress of Project Y by April 1st.

[0966] You can download the necessary materials from the following links:

[0967] http: / / example.com / resource

[0968] thank you.

[0969] In this way, the system of the present invention realizes flexible and effective task management according to the user's emotional state. This technology can improve factory productivity while reducing the burden on workers.

[0970] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0971] Step 1:

[0972] The server connects to the mailbox using the user's email account information and collects emails. The protocol used is IMAP or POP3. The input is the user's email account information, and the output is the retrieved email data. This email data includes all unread and read emails.

[0973] Step 2:

[0974] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, date and time of receipt, etc.) are sent to the generative AI model, which extracts important task information (deadline, task content, related links). The input is the email data, and the output is the extracted task information. At this point, a prompt is sent to the generative AI model, and the analysis results are received.

[0975] Step 3:

[0976] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model. The input is the analysis results from the generative AI model, and the output is the task information whose credibility has been evaluated.

[0977] Step 4:

[0978] The server organizes the extracted task information and generates a task list, which includes information such as the title, due date, task content, and related links for each task. The input is the task information whose credibility has been evaluated, and the output is a generated task list.

[0979] Step 5:

[0980] The server sends the generated task list to the user's terminal, where it can be viewed by the user. Notifications are given in real time using an appropriate communication protocol. The input is the task list, and the output is the task list displayed on the user's terminal.

[0981] Step 6:

[0982] When a user checks their task list, the emotion engine recognizes their emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. The input is the user's emotional data, and the output is the recognized emotional state.

[0983] Step 7:

[0984] The server changes the priority of the task list and adjusts reminder notifications based on the recognized emotional state. For example, if it recognizes that the user is feeling stressed, it will postpone low-priority tasks. The inputs are the recognized emotional state and the task list, and the output is the prioritized task list and notifications.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] [Third embodiment]

[0989] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0990] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0991] 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).

[0992] 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.

[0993] 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.

[0994] 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).

[0995] 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. 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.

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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."

[1001] This invention relates to a system that analyzes emails and extracts and manages deadlines and task information. The server collects all emails from mailboxes and analyzes them using AI (generative AI models), automatically extracting and organizing important task information.

[1002] 1. Email Collection

[1003] The server connects to your mailbox using your email account information. The server uses IMAP or POP3 protocols to access your mailbox and download all unread and existing emails, ensuring that you receive the most up-to-date information.

[1004] 2. Email Analysis

[1005] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. A natural language processing model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by," "deadline," etc.) are used to identify due dates, task content, and links.

[1006] 3. Task extraction

[1007] The server extracts important task information (deadline, task content, related links) from the analysis results of the AI ​​model. The extracted information is organized by each item and used in the next step.

[1008] 4. Task list generation

[1009] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing users to quickly grasp the overall picture of the tasks.

[1010] 5. Task List Notifications

[1011] The server sends the generated task list to the user's terminal, where it can be viewed. The user receives a notification and can check the task list.

[1012] 6. Review and Track

[1013] Users can view task lists on their devices and manage the progress of the tasks they need to complete. They can update task completion status and progress as needed and add notes and comments as needed.

[1014] Specific examples

[1015] For example, consider the following email:

[1016] Subject: Project X progress check

[1017] Main text:

[1018] Hello,

[1019] Please report on the progress of Project X by March 25th.

[1020] You can download the necessary materials from the following links:

[1021] http: / / example.com / resource

[1022] thank you.

[1023] Email collection

[1024] The server collects this mail from the user's mailbox.

[1025] Email Analysis

[1026] The server sends the email body to a generative AI model for analysis. The model extracts:

[1027] Response date: March 25th

[1028] Task: Project X progress report

[1029] Related link: http: / / example.com / resource

[1030] Task Extraction

[1031] The server extracts the following information from the output of the generative AI model:

[1032] Response date: March 25th

[1033] Task: Project X progress report

[1034] Related link: http: / / example.com / resource

[1035] Task list generation

[1036] The server generates a task list based on the extracted information in the following format:

[1037] 1. [Title] Project X Progress Check

[1038] [Response date] March 25th

[1039] [Task Content] Project X progress report

[1040] [Related Links] http: / / example.com / resource

[1041] Task List Notifications

[1042] The server transmits the generated task list to the user's terminal.

[1043] Review and Track

[1044] Users can view their task list on their device and ensure they take necessary action in their daily work, update their progress, and record the completion of tasks.

[1045] The above is an embodiment of the present invention, which allows a user to manage important task information from a large volume of emails without missing it, and to respond quickly.

[1046] The processing flow will be explained below.

[1047] Step 1:

[1048] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[1049] Step 2:

[1050] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[1051] Step 3:

[1052] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[1053] Step 4:

[1054] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[1055] Step 5:

[1056] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[1057] Step 6:

[1058] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[1059] Step 7:

[1060] Users can view their task list on their device, manage the progress and completion status of each task, update the task completion status, and even enter any necessary notes or comments.

[1061] Step 8:

[1062] Users can carry out tasks and work based on deadlines and task content. By checking progress on their devices, they can prevent tasks from being overlooked and work can be done efficiently.

[1063] Example 1

[1064] 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."

[1065] With conventional email systems, users have to manually sort and extract important task information from a large volume of emails, which is extremely time-consuming. There's also a high risk of missing task deadlines or important links. This reduces work efficiency and makes it difficult to manage task progress.

[1066] 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.

[1067] In this invention, the server includes means for connecting to an email server using a user's account information and collecting emails stored in a mailbox, means for using a generative AI model to analyze the body and header information of the collected emails, means for extracting due dates, task contents, and related links from the analysis results of the generative AI model, means for generating a task list based on the extracted information, means for notifying the user's terminal of the generated task list, and means for the user to check the task list on the terminal and manage progress. This allows the user to automatically extract and organize important task information from emails, significantly improving work efficiency.

[1068] "User account information" refers to authentication information required to connect to an email server, including an email address, password, and other necessary authentication information.

[1069] An "email server" is a server for sending, receiving, and storing emails, and is a server system that is accessed using protocols such as IMAP and POP3.

[1070] A "mailbox" is a digital storage area associated with a user's email account for storing received email.

[1071] An "email" is a digital message sent and received over the Internet, and includes information such as the body, subject, sender, recipient, and date and time of sending.

[1072] A "generative AI model" is a machine learning model for natural language processing, capable of understanding the meaning of language based on large amounts of text data, and analyzing and extracting specific information.

[1073] A "prompt" is an instruction given to a generative AI model to perform a specific task, providing the model with criteria and context for analysis and generation.

[1074] "Task information" is information such as due dates, task contents, and related links extracted from emails, and refers to specific action items that the user should manage.

[1075] A "task list" is extracted task information that is organized and displayed in a list format, and includes the title of each task, the due date, the task content, related links, and the like.

[1076] A "terminal" is a digital device used by a user to check the task list and manage the progress of tasks, and includes a PC, smartphone, tablet, etc.

[1077] "Notification" refers to the alert function or message sending that notifies the user of the generated task list, and is done via email, push notification, or a dedicated app.

[1078] This invention relates to a system that analyzes emails and extracts and manages response deadlines and task information. In this system, a server collects all emails from mailboxes and analyzes them using a generative AI model to automatically extract and organize important task information. A specific embodiment of this system is described below.

[1079] Email collection

[1080] The server connects to an email server (e.g., a server using IMAP or POP3 protocols) using the user's account information (email address, password). After connecting, the server downloads all unread and read emails in the mailbox and retrieves the latest email information. This data is temporarily stored in local storage.

[1081] Email Analysis

[1082] The server extracts the downloaded email's body and header information (subject, sender, date, etc.) and inputs it into a generative AI model. The generative AI model (e.g., a natural language processing model) is given a specific prompt and uses this to analyze the email content. This analysis identifies due dates, task details, and related links based on specific keywords and phrases (e.g., "by," "deadline," etc.).

[1083] Task Extraction

[1084] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized into categories such as deadline, task content, and related links.

[1085] Task list generation

[1086] The server generates a task list based on the extracted task information. This task list includes the title, due date, task content, and related links for each task. The list is saved in a structured format so that users can easily view it.

[1087] For example, the generated task list might look like this:

[1088] 1. [Title] Project X Progress Check

[1089] [Response date] March 25th

[1090] [Task Content] Project X progress report

[1091] [Related Links] http: / / example.com / resource

[1092] Task List Notifications

[1093] The server then notifies the user of the generated task list via email or push notification from a dedicated application.

[1094] Review and Track

[1095] Users can view the received task list on their device and manage the progress of each task. Users can update the task completion status at any time and add comments or notes as needed, allowing users to manage tasks efficiently and meet important deadlines.

[1096] Specific examples

[1097] For example, suppose the following email arrives in a user's mailbox:

[1098] Subject: Project X progress check

[1099] Main text:

[1100] Hello,

[1101] Please report on the progress of Project X by March 25th.

[1102] You can download the necessary materials from the following links:

[1103] http: / / example.com / resource

[1104] thank you.

[1105] When the server collects this email and asks the generative AI model to analyze it, it uses the following prompt:

[1106] "Please extract the due date, task details, and related links from this email."

[1107] The generative AI model analyzes the content of the email and extracts the following information:

[1108] Response date: March 25th

[1109] Task: Project X progress report

[1110] Related link: http: / / example.com / resource

[1111] Based on this, the server generates a task list and notifies the user's device, allowing the user to check the list and take the necessary actions quickly.

[1112] This system allows users to automatically extract important task information from emails and manage it efficiently, significantly improving the efficiency of their overall work.

[1113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1114] Step 1:

[1115] Connecting to a mail server

[1116] The server connects to the email server (IMAP or POP3 protocol) using the user's account information (email address, password).

[1117] Input: User's email account information

[1118] Output: Connecting to the mail server

[1119] This connection gives the server permission to access the email in your mailbox.

[1120] Step 2:

[1121] Email collection

[1122] After connecting to the mail server, the server downloads all unread and read emails in the mailbox, which are then temporarily stored in local storage.

[1123] Input: Email in mailbox

[1124] Output: Email data saved in local storage

[1125] In this step, the server obtains the latest mail information and prepares it for the next analysis step.

[1126] Step 3:

[1127] Preparation for email analysis

[1128] The server extracts the body text and header information (subject, sender, date, etc.) of the collected emails and prepares them for input into the generative AI model.

[1129] Input: Email data stored in local storage

[1130] Output: Email body and header information for analysis

[1131] The information required for analysis is ready to be passed to the generative AI model.

[1132] Step 4:

[1133] Analysis using generative AI models

[1134] The server sends the email body and header information to the generative AI model and requests analysis using specific prompts.

[1135] Example prompt: "Extract due dates, tasks, and related links from this email."

[1136] Input: Email body and header information for analysis, prompt text

[1137] Output: Analysis results (response due date, task details, related links)

[1138] In this step, the generative AI model understands the content of the email and extracts important task information.

[1139] Step 5:

[1140] Extracting and organizing task information

[1141] The server extracts response deadlines, task details, and related links from the analysis results of the generative AI model and organizes them into their respective categories.

[1142] Input: Analysis results of the generative AI model

[1143] Output: Organized task information (deadline, task content, related links)

[1144] This ensures that important task information is clearly categorized.

[1145] Step 6:

[1146] Generate a task list

[1147] The server generates a task list based on the organized task information, which includes the title, due date, task content, and related links for each task.

[1148] Input: Organized task information

[1149] Output: Generated task list

[1150] The generated task list is saved in a format that is easy for the user to check.

[1151] Step 7:

[1152] Task List Notifications

[1153] The server notifies the user of the generated task list via email or push notification from a dedicated application.

[1154] Input: Generated task list

[1155] Output: Notification to the user's device

[1156] The user receives this notification and can check the task list.

[1157] Step 8:

[1158] Review and track your task list

[1159] The user can check the received task list on the device, manage the progress of each task, add comments and notes as needed, and update the task progress as needed.

[1160] Input: User task management actions (status update, comment addition, etc.)

[1161] Output: Updated task list

[1162] This allows users to efficiently manage their tasks and ensure that they do not miss important deadlines or task details.

[1163] (Application example 1)

[1164] 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."

[1165] Conventional industrial robot management systems require manual management of instructions and reports, resulting in inefficiencies and errors. Extracting necessary task information from a large volume of emails is time-consuming and places a significant burden on the manager. The present invention aims to solve these problems and provide a method for automatically and efficiently managing robot work schedules.

[1166] 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.

[1167] In this invention, the server includes means for analyzing emails, means for extracting action dates from the analyzed emails, means for listing tasks based on the extracted action dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for analyzing instructions and reports from the industrial robot and extracting and managing action dates and specific work details, means for notifying the generated robot task list to a manager's terminal, and means for the manager to monitor the robot's work progress in real time and issue correction instructions as necessary, thereby enabling automatic management of the robot's work schedule and efficient response.

[1168] "Email" means written communication sent or received in digital form, a message transmitted through an electronic device.

[1169] "Analyzing" means examining collected data in detail and breaking down its content and structure into an understandable format.

[1170] A "due date" is the date by which a particular task or action is required to be completed.

[1171] A "task" is a specific activity or task that must be performed to achieve a specific goal.

[1172] "Listing" means arranging items in a list format in a particular order.

[1173] A "link" is a hypertext reference that directs a user to a particular resource or piece of information.

[1174] "Organizing" is the process of compiling data and information in an efficient and easy-to-understand format.

[1175] "Displaying" means visually presenting data or information to a user.

[1176] An "industrial robot" is a programmable mechanical device used to perform automated tasks in industry.

[1177] An "instruction" is an order or instruction to perform a specific action or task.

[1178] A "report" is a report on the progress and results of work.

[1179] To "manage" means to effectively manage, supervise, and control a specific resource or task.

[1180] "Notifying" is the act of informing others of specific information.

[1181] "Monitoring" means continuously observing a series of actions or processes and responding if an abnormality occurs.

[1182] "Modification instructions" means instructions to make changes or improvements to existing plans or schedules.

[1183] A "generative AI model" is an artificial intelligence technology that uses models trained by machine learning algorithms to process and analyze new data and tasks.

[1184] The present invention relates to a management system for industrial robots, and is a system that analyzes emails to extract due dates and task information, and reflects this information in the robot's work schedule. Specific embodiments for carrying out the present invention will be described below.

[1185] System Overview

[1186] This system operates on a server, collects and analyzes emails, and manages instructions and reports for industrial robots as tasks. Specifically, it uses the following hardware and software:

[1187] Server: Performs email collection and analysis.

[1188] IMAP library: Used to collect emails.

[1189] BERT model (generative AI model): Used to analyze emails and extract due dates and tasks.

[1190] Django: A web application framework for generating and displaying task lists.

[1191] Program processing explanation

[1192] 1. Email Collection

[1193] The server uses the IMAP protocol to access the factory's instruction and report email accounts and collect emails. The server connects to the IMAP server using the user's email account information and downloads all unread and existing emails. This ensures that the latest email information is obtained.

[1194] 2. Email Analysis

[1195] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. The BERT model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by" or "deadline") are used to identify due dates, task content, and links.

[1196] 3. Task extraction

[1197] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized by each item and used in the next step.

[1198] 4. Task list generation

[1199] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing the administrator to quickly grasp the overall picture of the tasks.

[1200] 5. Task List Notifications

[1201] The server sends the generated task list to the terminal of the administrator, and the administrator can view the task list on the terminal. The administrator receives a notification and can check the task list.

[1202] 6. Review and Track

[1203] The administrator can view the task list on their device and manage the progress of the necessary tasks. They can update the completion status and progress of tasks as needed, and add notes and comments as needed.

[1204] Specific examples

[1205] For example, consider the following email:

[1206] Email content

[1207] text

[1208] Subject: Scheduled maintenance for Machine A

[1209] Main text:

[1210] Please carry out regular maintenance on Machine A by October 15th.

[1211] Detailed instructions can be found at the following link:

[1212] http: / / factory.com / maintenance_guideline

[1213] Prompt Sentence Examples

[1214] "Please generate a code that extracts deadlines and task details from received emails and generates a task list."

[1215] For this email, the system will extract the following tasks and add them to the task list:

[1216] text

[1217] 1. Title: Scheduled Maintenance of Machine A

[1218] Response date: October 15th

[1219] Task: Regular maintenance of machine A

[1220] Related link: http: / / factory.com / maintenance_guideline

[1221] In this way, automatic management and efficient response of work schedules for industrial robots becomes possible.

[1222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1223] Step 1:

[1224] The server uses the IMAP protocol to access the factory's instruction and report email account and collect all unread and existing emails. The user's email account information is used as input. Based on this, the server connects to the IMAP server and retrieves the latest email information from the mailbox. The email data is obtained as output.

[1225] Step 2:

[1226] The server obtains the body text and header information (subject, sender, date, etc.) of the collected emails. The email data collected in step 1 is used as input. Data processing is performed to convert the email data into a data format for analysis. The output is email data formatted in an analyzable format.

[1227] Step 3:

[1228] The server inputs the email text into a generative AI model (BERT model) to understand the context and patterns within the email. In this step, due dates, task content, and links are identified based on specific keywords. The formatted email data is used as input. Task information is extracted by natural language processing using the generative AI model. The extracted task information (due dates, task content, and related links) is obtained as output.

[1229] Step 4:

[1230] The server organizes the task information extracted from the analysis results of the generative AI model by each item. The extracted task information is used as input. Data shaping and filtering are performed to obtain organized task information. The organized task information is generated as output.

[1231] Step 5:

[1232] The server generates a task list based on the organized task information. The organized task information is used as input. Based on this, data processing is performed to list information such as the title, due date, task content, and related links for each task. The generated task list is obtained as output.

[1233] Step 6:

[1234] The server sends the generated task list to the administrator's terminal, allowing the administrator to view the task list on the terminal. The generated task list is used as input. To notify the administrator's terminal of this task list, data is transmitted using a communication protocol. The task list displayed on the terminal is obtained as output.

[1235] Step 7:

[1236] The administrator checks the task list on the terminal and manages the progress of the required tasks. The task list notified to the terminal is used as input. The administrator can update the task completion status and progress and make corrections as necessary. The updated task list and task progress are obtained as output.

[1237] 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.

[1238] This invention is a system that analyzes emails, extracts deadlines and task information, and manages them. This system also combines an emotion engine that recognizes the user's emotions, enabling flexible task management according to the user's situation.

[1239] 1. Email Collection

[1240] The server connects to the mailbox using the user's email account information and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[1241] 2. Email Analysis

[1242] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, received date, etc.) are sent to a generative AI model to extract important task information (deadline, task content, related links). This information is also evaluated for credibility based on specific keywords.

[1243] 3. Task extraction

[1244] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model, thereby minimizing the risk of missing or misidentifying tasks.

[1245] 4. Task list generation

[1246] The server organizes the extracted task information to generate a task list. The list includes information such as the title of each task, the due date, the task content, and related links. The list is formatted appropriately so that the user can quickly grasp the overall picture of the tasks.

[1247] 5. Task List Notifications

[1248] The server sends the generated task list to the user's terminal, where it can be viewed. Real-time notifications are provided using an appropriate communication protocol.

[1249] 6. Emotion recognition

[1250] As a user reviews their task list, an emotion engine recognizes their emotional state by analyzing their facial expressions, tone of voice, and typing patterns to identify their current emotional state.

[1251] 7. Adjust task management

[1252] The server can then prioritize tasks and adjust reminder notifications based on the user's emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[1253] Specific examples

[1254] For example, consider the following email:

[1255] Subject: Project X progress check

[1256] Main text:

[1257] Hello,

[1258] Please report on the progress of Project X by March 25th.

[1259] You can download the necessary materials from the following links:

[1260] http: / / example.com / resource

[1261] thank you.

[1262] Email collection

[1263] The server collects this mail from the user's mailbox.

[1264] Email Analysis

[1265] The server sends the email body to a generative AI model for analysis. The model extracts the following:

[1266] Response date: March 25th

[1267] Task: Project X progress report

[1268] Related link: http: / / example.com / resource

[1269] Task Extraction

[1270] The server extracts the following information from the output of the generative AI model:

[1271] Response date: March 25th

[1272] Task: Project X progress report

[1273] Related link: http: / / example.com / resource

[1274] Task list generation

[1275] The server uses the extracted information to generate a task list in the following format:

[1276] 1. [Title] Project X Progress Check

[1277] [Response date] March 25th

[1278] [Task Content] Project X progress report

[1279] [Related Links] http: / / example.com / resource

[1280] Task List Notifications

[1281] The server sends the generated task list to the user's terminal.

[1282] emotion recognition

[1283] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[1284] Task management adjustments

[1285] The server adjusts the priority of the task list based on the user's emotional state, for example by prioritizing only tasks that require immediate attention, reducing the user's stress.

[1286] This allows users to focus on important tasks without feeling stressed, improving work efficiency.The present invention is a system that realizes flexible and effective task management by combining task information extracted from emails with the user's emotional state.

[1287] The processing flow will be explained below.

[1288] Step 1:

[1289] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols.

[1290] Step 2:

[1291] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[1292] Step 3:

[1293] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[1294] Step 4:

[1295] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[1296] Step 5:

[1297] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[1298] Step 6:

[1299] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[1300] Step 7:

[1301] Users can view their task list on their device, manage the progress and status of each task, update the task completion status, and even enter any necessary notes or comments.

[1302] Step 8:

[1303] The device is equipped with an emotion engine that recognizes the user's emotional state when checking the task list by analyzing the user's facial expressions, tone of voice, input patterns, etc.

[1304] Step 9:

[1305] The server changes the priority of the task list based on the user's emotional state (e.g., stress, fatigue, etc.) recognized by the emotion engine. Reminder notifications are also adjusted according to the user's emotional state.

[1306] Step 10:

[1307] The device displays a prioritized task list for the user to easily review. This allows users to focus on important tasks without feeling stressed. For example, if a user is feeling stressed, only tasks that require immediate attention will be displayed as priority.

[1308] This allows users to effectively manage tasks and improve work efficiency.

[1309] Example 2

[1310] 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."

[1311] In today's business environment, many tasks and actions are notified via email, but manually organizing and managing them is extremely difficult. Furthermore, the lack of a flexible task management method that takes into account the user's stress and emotional state leads to a decline in work efficiency. A system that can solve these issues is needed.

[1312] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting electronic messages, means for analyzing the collected electronic messages using a natural language processing engine, means for extracting due dates and task information from the analyzed electronic messages using a generative AI model, means for evaluating the extracted task information based on credibility criteria using prompt sentences from the generative AI model, means for organizing the evaluated task information and generating a task list, means for notifying and displaying the generated task list on an output device, and means for adjusting the priority of the listed tasks using an emotion engine that recognizes the user's emotional state. This enables automatic and reliable extraction of task information from emails and flexible task management that takes the user's emotional state into consideration.

[1313] "Electronic message" refers to documents or information sent or received by electronic means, including emails, chat messages, and social media messages.

[1314] A "natural language processing engine" refers to computer technology that analyzes and understands the language used by humans on a daily basis, allowing it to extract and structure the meaning of text data.

[1315] A "generative AI model" is a form of artificial intelligence that refers to an algorithm that learns from large amounts of data and generates meaningful information in response to new data.

[1316] A "prompt" refers to input data or instructions that direct a generative AI model to perform a specific analysis or generation task.

[1317] "Credibility criteria" refers to the standards and rules for evaluating the accuracy and validity of extracted information. Based on these standards, the accuracy and reliability of information are judged.

[1318] A "task list" is a list of tasks or matters to be done that have a specific purpose or deadline, and includes information such as the task title, due date, task content, and related links.

[1319] An "emotion engine" refers to the technology and algorithms used to recognize and analyze human emotions. It identifies the user's emotional state based on facial expressions, tone of voice, input patterns, etc.

[1320] An "output device" refers to a device that displays information sent from a server in a form that can be viewed by a user, and includes a computer display, a smartphone screen, etc.

[1321] This invention is a system that analyzes electronic messages and automatically extracts and manages due dates and task information. It also has a function that flexibly adjusts task priorities by taking into account the user's emotional state. This system is characterized by combining a generative AI model and a natural language processing engine to extract reliable task information from electronic messages.

[1322] System configuration

[1323] 1. Server

[1324] The server collects the electronic messages using the user's email account information, authenticates using IMAP or POP3 protocols, and retrieves all unread and read electronic messages, which downloads the latest message information.

[1325] 2. Natural Language Processing Engine

[1326] The server analyzes the received electronic message using a natural language processing engine (e.g., Spacy, NLTK), thereby extracting the body and header information (subject, sender, received date and time, etc.) of the electronic message as structured data.

[1327] 3. Generative AI Models

[1328] The server sends a prompt to a generative AI model (e.g., OpenAI API) based on the analysis results of the electronic message, extracting important task information (deadline, task content, related links). The generative AI model returns the necessary information based on the specified prompt.

[1329] 4. Credibility Assessment

[1330] The server evaluates the task information returned by the generative AI model based on credibility criteria, which helps to avoid extracting inaccurate information and organize reliable data.

[1331] 5. Task list generation

[1332] The server aggregates the verified task information and generates a task list, which includes task titles, due dates, specific task contents, and related links.

[1333] 6. Notices and Displays

[1334] The server sends the generated task list to the user's device so that it can be displayed in real time on the device. For example, data can be sent in JSON format via a REST API, and the device displays the received data in an appropriate format.

[1335] 7. Emotion recognition

[1336] As a user reviews their task list, an emotion engine (e.g., Microsoft Azure Emotion API) collects their facial expressions and tone of voice via the camera and microphone to identify their emotional state.

[1337] 8. Adjust task management

[1338] The server adjusts the priority of the task list based on the user's emotional state received from the emotion engine. For example, if a user is feeling stressed, it may postpone low-priority tasks.

[1339] Specific examples

[1340] Example of a progress confirmation email for Project X

[1341] text

[1342] Subject: Project X progress check

[1343] Main text:

[1344] Hello,

[1345] Please report on the progress of Project X by March 25th.

[1346] You can download the necessary materials from the following links:

[1347] http: / / example.com / resource

[1348] thank you.

[1349] Email collection

[1350] The server collects this mail from the user's mailbox.

[1351] Email Analysis

[1352] The server analyzes the email body using a natural language processing engine and extracts the following structured data:

[1353] Subject: Project X progress check

[1354] Body: Please report the progress of Project X by March 25th.

[1355] Link: http: / / example.com / resource

[1356] Task information extraction

[1357] The server sends the following prompt to the generative AI model:

[1358] "Project X progress check. Report required by March 25th. Related link: http: / / example.com / resource"

[1359] The task information returned by the generative AI model is as follows:

[1360] Response date: March 25th

[1361] Task: Project X progress report

[1362] Related link: http: / / example.com / resource

[1363] Task list generation

[1364] The server uses the extracted information to generate a task list in the following format:

[1365] text

[1366] 1. [Title] Project X Progress Check

[1367] [Response date] March 25th

[1368] [Task Content] Project X progress report

[1369] [Related Links] http: / / example.com / resource

[1370] Coordination of emotion recognition and task management

[1371] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[1372] The server adjusts the priority of the task list based on the user's emotional state, for example, by prioritizing only tasks that require immediate attention, reducing the user's stress.

[1373] As described above, the present invention makes it possible to flexibly and effectively manage tasks by taking into account task information extracted from electronic messages and the emotional state of the user.

[1374] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1375] Program processing flow

[1376] Processing Steps

[1377] Step 1:

[1378] Input: User's email account information (username, password)

[1379] Processing: The server connects to the mailbox using IMAP or POP3 protocol and retrieves all unread and read emails. The server authenticates by calling an API such as "mailbox.login('username', 'password')". After that, it retrieves messages using commands such as "mailbox.fetch('ALL')".

[1380] Output: A dataset of retrieved emails

[1381] Step 2:

[1382] Input: Dataset of retrieved emails

[1383] Processing: The server analyzes the received email using a natural language processing engine (e.g., Spacy, NLTK). The server initializes the natural language processing engine using "nlp = spacy.load('en_core_web_sm')" and analyzes the email body and header information using "doc = nlp(email_body)". Specifically, it extracts text data such as the email body, subject, sender, and received date and time.

[1384] Output: Structured data of the parsed email (subject, body, sender, received date and time)

[1385] Step 3:

[1386] Input: Parsed email structured data

[1387] Processing: The server sends a prompt to the generative AI model (e.g., OpenAI API) and extracts important task information (deadline, task content, related links). The server generates a prompt like "prompt_text = 'Check the progress of Project X. Report required by March 25th. Related links: http: / / example.com / resource'" and sends it to the generative AI model. Task information is obtained using "result = ai_model.generate(prompt_text)".

[1388] Output: Task information from the generative AI model (deadline, task content, related links)

[1389] Step 4:

[1390] Input: Task information from the generative AI model

[1391] Processing: The server evaluates the task information returned by the generative AI model based on credibility criteria. The credibility evaluation uses regular expressions based on specific keywords, and is performed using the following formula: "re.search(pattern, result)".

[1392] Output: Task information whose authenticity has been confirmed

[1393] Step 5:

[1394] Input: Task information whose authenticity has been confirmed

[1395] Processing: The server generates a task list based on the authenticated task information. The server creates a data structure like this: task_list = [{'title': title, 'due_date': due_date, 'content': content, 'link': link}].

[1396] Output: Generated task list

[1397] Step 6:

[1398] Input: Generated task list

[1399] Processing: The server sends the generated task list to the user's device. The server sends the data in JSON format via the REST API using the following method: "requests.post('http: / / example.com / api / tasks', json=task_list)". The device receives the data using "fetch(' / api / tasks')" and displays it in the appropriate format.

[1400] Output: The task list displayed on the user's device.

[1401] Step 7:

[1402] Input: Facial expressions, tone of voice, and input patterns when users check their task list

[1403] Processing: When a user checks their task list, an emotion engine (e.g., Microsoft Azure Emotion API) recognizes the user's emotional state. The device captures an image using "face_recognition.capture_frame()" and performs emotion analysis using "azure_emotion_api.detect_emotion(image)".

[1404] Output: Recognized emotional state of the user

[1405] Step 8:

[1406] Input: Perceived emotional state of the user

[1407] Processing: The server rearranges the task list based on the user's emotional state. The server rearranges the task list based on the user's emotional state, as follows: if emotion == 'stressed': prioritize_urgent_tasks()

[1408] Output: Reconciled task list

[1409] Through the above processing steps, the present invention automatically extracts task information from electronic messages and realizes flexible task management according to the user's emotional state.

[1410] (Application example 2)

[1411] 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."

[1412] Conventional task management systems can extract task information from emails, but because they list and manage tasks without considering the user's emotional state, users may feel stressed or their work efficiency may decrease. Another issue is the insufficient evaluation of the credibility of task information extracted from emails. The present invention aims to solve these issues and provide a system that realizes flexible task management according to the user's emotional state.

[1413] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1414] In this invention, the server includes means for analyzing emails, means for extracting due dates from the analyzed emails, means for listing tasks based on the extracted due dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for adjusting task priorities by recognizing the user's emotional state, and means for adjusting reminder notifications based on the user's emotional state. This enables the user to manage tasks in a less stressful manner, thereby improving overall work efficiency.

[1415] The "means for analyzing e-mail" is a means having a function of acquiring a user's e-mail, analyzing the mail body and header information, and extracting due dates and task information.

[1416] The "means for extracting correspondence dates" is a means having a function for detecting and extracting date information such as deadlines and deadlines from analyzed emails.

[1417] The "means for listing tasks" is a means having a function for organizing extracted task information and displaying it in a list format so that the user can easily understand it.

[1418] The "means for organizing links and correspondence content" is a means having a function for collecting and organizing links and specific correspondence content related to the listed tasks.

[1419] The "means for displaying a task list" is a means having a function for displaying the generated task list on the user's terminal so that the user can visually confirm it.

[1420] "Means for recognizing the user's emotional state and adjusting task priorities" refers to means that has the function of recognizing the user's emotional state from facial expressions, tone of voice, etc., and dynamically changing task priorities according to that state.

[1421] The "means for adjusting reminder notifications based on the user's emotional state" refers to a means that has the function of changing the timing and content of reminder notifications according to the user's emotional state, thereby reducing the burden on the user.

[1422] The system that realizes this application example is a production management support system installed on factory robots. This system is equipped with multiple functions that enable users (workers) to efficiently manage tasks.

[1423] First, the server connects to your mailbox using your email account information and collects your emails. It uses IMAP or POP3 protocols to retrieve all unread and read emails. This allows the server to download the latest email information.

[1424] The server then analyzes the email using natural language processing. The email body and header information (e.g., subject, sender, and date and time of receipt) are sent to a generative AI model to extract important task information (deadline, task content, and related links). This information is also evaluated for credibility based on specific keywords.

[1425] The server then extracts and organizes task information whose credibility has been assessed from the analysis results of the generative AI model. This minimizes the risk of missing or misidentifying tasks. The server then organizes the extracted task information to generate a task list. The list includes information such as each task's title, due date, task content, and related links. The list is organized in an appropriate format so that users can quickly grasp the overall picture of the tasks.

[1426] The generated task list is sent from the server to the user's device (e.g., tablet or smart glasses) and can be viewed on the device. Real-time notifications are provided using an appropriate communication protocol.

[1427] A distinctive feature of this system is the ability of the emotion engine to recognize the user's emotional state when they check their task list. This engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. This emotion recognition is performed by the emotion engine, and appropriate countermeasures are presented according to the situation.

[1428] Additionally, the server can reprioritize task lists and adjust reminder notifications based on the user's perceived emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[1429] As a concrete example, consider the following email:

[1430] Subject: Project Y progress check

[1431] Main text:

[1432] Hello,

[1433] Please report the progress of Project Y by April 1st.

[1434] You can download the necessary materials from the following links:

[1435] http: / / example.com / resource

[1436] thank you.

[1437] Based on the email above, the server extracts the following:

[1438] Response date: April 1st

[1439] Task: Report on the progress of Project Y

[1440] Related link: http: / / example.com / resource

[1441] Based on this extracted information, a task list is generated and notified to the user. Furthermore, if the emotion recognition engine detects signs of stress when the user checks the task list, the priority of the tasks is appropriately adjusted.

[1442] An example of a prompt for a generative AI model is:

[1443] Extract the task information from the following email:

[1444] Subject: Project Y progress check

[1445] Main text:

[1446] Hello,

[1447] Please report the progress of Project Y by April 1st.

[1448] You can download the necessary materials from the following links:

[1449] http: / / example.com / resource

[1450] thank you.

[1451] In this way, the system of the present invention realizes flexible and effective task management according to the user's emotional state. This technology can improve factory productivity while reducing the burden on workers.

[1452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1453] Step 1:

[1454] The server connects to the mailbox using the user's email account information and collects emails. The protocol used is IMAP or POP3. The input is the user's email account information, and the output is the retrieved email data. This email data includes all unread and read emails.

[1455] Step 2:

[1456] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, date and time of receipt, etc.) are sent to the generative AI model, which extracts important task information (deadline, task content, related links). The input is the email data, and the output is the extracted task information. At this point, a prompt is sent to the generative AI model, and the analysis results are received.

[1457] Step 3:

[1458] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model. The input is the analysis results from the generative AI model, and the output is the task information whose credibility has been evaluated.

[1459] Step 4:

[1460] The server organizes the extracted task information and generates a task list, which includes information such as the title, due date, task content, and related links for each task. The input is the task information whose credibility has been evaluated, and the output is a generated task list.

[1461] Step 5:

[1462] The server sends the generated task list to the user's terminal, where it can be viewed by the user. Notifications are given in real time using an appropriate communication protocol. The input is the task list, and the output is the task list displayed on the user's terminal.

[1463] Step 6:

[1464] When a user checks their task list, the emotion engine recognizes their emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. The input is the user's emotional data, and the output is the recognized emotional state.

[1465] Step 7:

[1466] The server changes the priority of the task list and adjusts reminder notifications based on the recognized emotional state. For example, if it recognizes that the user is feeling stressed, it will postpone low-priority tasks. The inputs are the recognized emotional state and the task list, and the output is the prioritized task list and notifications.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] [Fourth embodiment]

[1471] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1472] 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.

[1473] 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).

[1474] 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.

[1475] 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.

[1476] 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).

[1477] 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. 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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.

[1483] 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."

[1484] This invention relates to a system that analyzes emails and extracts and manages deadlines and task information. The server collects all emails from mailboxes and analyzes them using AI (generative AI models), automatically extracting and organizing important task information.

[1485] 1. Email Collection

[1486] The server connects to your mailbox using your email account information. The server uses IMAP or POP3 protocols to access your mailbox and download all unread and existing emails, ensuring that you receive the most up-to-date information.

[1487] 2. Email Analysis

[1488] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. A natural language processing model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by," "deadline," etc.) are used to identify due dates, task content, and links.

[1489] 3. Task extraction

[1490] The server extracts important task information (deadline, task content, related links) from the analysis results of the AI ​​model. The extracted information is organized by each item and used in the next step.

[1491] 4. Task list generation

[1492] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing users to quickly grasp the overall picture of the tasks.

[1493] 5. Task List Notifications

[1494] The server sends the generated task list to the user's terminal, where it can be viewed. The user receives a notification and can check the task list.

[1495] 6. Review and Track

[1496] Users can view task lists on their devices and manage the progress of the tasks they need to complete. They can update task completion status and progress as needed and add notes and comments as needed.

[1497] Specific examples

[1498] For example, consider the following email:

[1499] Subject: Project X progress check

[1500] Main text:

[1501] Hello,

[1502] Please report on the progress of Project X by March 25th.

[1503] You can download the necessary materials from the following links:

[1504] http: / / example.com / resource

[1505] thank you.

[1506] Email collection

[1507] The server collects this mail from the user's mailbox.

[1508] Email Analysis

[1509] The server sends the email body to a generative AI model for analysis. The model extracts:

[1510] Response date: March 25th

[1511] Task: Project X progress report

[1512] Related link: http: / / example.com / resource

[1513] Task Extraction

[1514] The server extracts the following information from the output of the generative AI model:

[1515] Response date: March 25th

[1516] Task: Project X progress report

[1517] Related link: http: / / example.com / resource

[1518] Task list generation

[1519] The server generates a task list based on the extracted information in the following format:

[1520] 1. [Title] Project X Progress Check

[1521] [Response date] March 25th

[1522] [Task Content] Project X progress report

[1523] [Related Links] http: / / example.com / resource

[1524] Task List Notifications

[1525] The server transmits the generated task list to the user's terminal.

[1526] Review and Track

[1527] Users can view their task list on their device and ensure they take necessary action in their daily work, update their progress, and record the completion of tasks.

[1528] The above is an embodiment of the present invention, which allows a user to manage important task information from a large volume of emails without missing it, and to respond quickly.

[1529] The processing flow will be explained below.

[1530] Step 1:

[1531] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[1532] Step 2:

[1533] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[1534] Step 3:

[1535] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[1536] Step 4:

[1537] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[1538] Step 5:

[1539] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[1540] Step 6:

[1541] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[1542] Step 7:

[1543] Users can view their task list on their device, manage the progress and completion status of each task, update the task completion status, and even enter any necessary notes or comments.

[1544] Step 8:

[1545] Users can carry out tasks and work based on deadlines and task content. By checking progress on their devices, they can prevent tasks from being overlooked and work can be done efficiently.

[1546] Example 1

[1547] 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."

[1548] With conventional email systems, users have to manually sort and extract important task information from a large volume of emails, which is extremely time-consuming. There's also a high risk of missing task deadlines or important links. This reduces work efficiency and makes it difficult to manage task progress.

[1549] 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.

[1550] In this invention, the server includes means for connecting to an email server using a user's account information and collecting emails stored in a mailbox, means for using a generative AI model to analyze the body and header information of the collected emails, means for extracting due dates, task contents, and related links from the analysis results of the generative AI model, means for generating a task list based on the extracted information, means for notifying the user's terminal of the generated task list, and means for the user to check the task list on the terminal and manage progress. This allows the user to automatically extract and organize important task information from emails, significantly improving work efficiency.

[1551] "User account information" refers to authentication information required to connect to an email server, including an email address, password, and other necessary authentication information.

[1552] An "email server" is a server for sending, receiving, and storing emails, and is a server system that is accessed using protocols such as IMAP and POP3.

[1553] A "mailbox" is a digital storage area associated with a user's email account for storing received email.

[1554] An "email" is a digital message sent and received over the Internet, and includes information such as the body, subject, sender, recipient, and date and time of sending.

[1555] A "generative AI model" is a machine learning model for natural language processing, capable of understanding the meaning of language based on large amounts of text data, and analyzing and extracting specific information.

[1556] A "prompt" is an instruction given to a generative AI model to perform a specific task, providing the model with criteria and context for analysis and generation.

[1557] "Task information" is information such as due dates, task contents, and related links extracted from emails, and refers to specific action items that the user should manage.

[1558] A "task list" is extracted task information that is organized and displayed in a list format, and includes the title of each task, the due date, the task content, related links, and the like.

[1559] A "terminal" is a digital device used by a user to check the task list and manage the progress of tasks, and includes a PC, smartphone, tablet, etc.

[1560] "Notification" refers to the alert function or message sending that notifies the user of the generated task list, and is done via email, push notification, or a dedicated app.

[1561] This invention relates to a system that analyzes emails and extracts and manages response deadlines and task information. In this system, a server collects all emails from mailboxes and analyzes them using a generative AI model to automatically extract and organize important task information. A specific embodiment of this system is described below.

[1562] Email collection

[1563] The server connects to an email server (e.g., a server using IMAP or POP3 protocols) using the user's account information (email address, password). After connecting, the server downloads all unread and read emails in the mailbox and retrieves the latest email information. This data is temporarily stored in local storage.

[1564] Email Analysis

[1565] The server extracts the downloaded email's body and header information (subject, sender, date, etc.) and inputs it into a generative AI model. The generative AI model (e.g., a natural language processing model) is given a specific prompt and uses this to analyze the email content. This analysis identifies due dates, task details, and related links based on specific keywords and phrases (e.g., "by," "deadline," etc.).

[1566] Task Extraction

[1567] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized into categories such as deadline, task content, and related links.

[1568] Task list generation

[1569] The server generates a task list based on the extracted task information. This task list includes the title, due date, task content, and related links for each task. The list is saved in a structured format so that users can easily view it.

[1570] For example, the generated task list might look like this:

[1571] 1. [Title] Project X Progress Check

[1572] [Response date] March 25th

[1573] [Task Content] Project X progress report

[1574] [Related Links] http: / / example.com / resource

[1575] Task List Notifications

[1576] The server then notifies the user of the generated task list via email or push notification from a dedicated application.

[1577] Review and Track

[1578] Users can view the received task list on their device and manage the progress of each task. Users can update the task completion status at any time and add comments or notes as needed, allowing users to manage tasks efficiently and meet important deadlines.

[1579] Specific examples

[1580] For example, suppose the following email arrives in a user's mailbox:

[1581] Subject: Project X progress check

[1582] Main text:

[1583] Hello,

[1584] Please report on the progress of Project X by March 25th.

[1585] You can download the necessary materials from the following links:

[1586] http: / / example.com / resource

[1587] thank you.

[1588] When the server collects this email and asks the generative AI model to analyze it, it uses the following prompt:

[1589] "Please extract the due date, task details, and related links from this email."

[1590] The generative AI model analyzes the content of the email and extracts the following information:

[1591] Response date: March 25th

[1592] Task: Project X progress report

[1593] Related link: http: / / example.com / resource

[1594] Based on this, the server generates a task list and notifies the user's device, allowing the user to check the list and take the necessary actions quickly.

[1595] This system allows users to automatically extract important task information from emails and manage it efficiently, significantly improving the efficiency of their overall work.

[1596] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1597] Step 1:

[1598] Connecting to a mail server

[1599] The server connects to the email server (IMAP or POP3 protocol) using the user's account information (email address, password).

[1600] Input: User's email account information

[1601] Output: Connecting to the mail server

[1602] This connection gives the server permission to access the email in your mailbox.

[1603] Step 2:

[1604] Email collection

[1605] After connecting to the mail server, the server downloads all unread and read emails in the mailbox, which are then temporarily stored in local storage.

[1606] Input: Email in mailbox

[1607] Output: Email data saved in local storage

[1608] In this step, the server obtains the latest mail information and prepares it for the next analysis step.

[1609] Step 3:

[1610] Preparation for email analysis

[1611] The server extracts the body text and header information (subject, sender, date, etc.) of the collected emails and prepares them for input into the generative AI model.

[1612] Input: Email data stored in local storage

[1613] Output: Email body and header information for analysis

[1614] The information required for analysis is ready to be passed to the generative AI model.

[1615] Step 4:

[1616] Analysis using generative AI models

[1617] The server sends the email body and header information to the generative AI model and requests analysis using specific prompts.

[1618] Example prompt: "Extract due dates, tasks, and related links from this email."

[1619] Input: Email body and header information for analysis, prompt text

[1620] Output: Analysis results (response due date, task details, related links)

[1621] In this step, the generative AI model understands the content of the email and extracts important task information.

[1622] Step 5:

[1623] Extracting and organizing task information

[1624] The server extracts response deadlines, task details, and related links from the analysis results of the generative AI model and organizes them into their respective categories.

[1625] Input: Analysis results of the generative AI model

[1626] Output: Organized task information (deadline, task content, related links)

[1627] This ensures that important task information is clearly categorized.

[1628] Step 6:

[1629] Generate a task list

[1630] The server generates a task list based on the organized task information, which includes the title, due date, task content, and related links for each task.

[1631] Input: Organized task information

[1632] Output: Generated task list

[1633] The generated task list is saved in a format that is easy for the user to check.

[1634] Step 7:

[1635] Task List Notifications

[1636] The server notifies the user of the generated task list via email or push notification from a dedicated application.

[1637] Input: Generated task list

[1638] Output: Notification to the user's device

[1639] The user receives this notification and can check the task list.

[1640] Step 8:

[1641] Review and track your task list

[1642] The user can check the received task list on the device, manage the progress of each task, add comments and notes as needed, and update the task progress as needed.

[1643] Input: User task management actions (status update, comment addition, etc.)

[1644] Output: Updated task list

[1645] This allows users to efficiently manage their tasks and ensure that they do not miss important deadlines or task details.

[1646] (Application example 1)

[1647] 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."

[1648] Conventional industrial robot management systems require manual management of instructions and reports, resulting in inefficiencies and errors. Extracting necessary task information from a large volume of emails is time-consuming and places a significant burden on the manager. The present invention aims to solve these problems and provide a method for automatically and efficiently managing robot work schedules.

[1649] 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.

[1650] In this invention, the server includes means for analyzing emails, means for extracting action dates from the analyzed emails, means for listing tasks based on the extracted action dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for analyzing instructions and reports from the industrial robot and extracting and managing action dates and specific work details, means for notifying the generated robot task list to a manager's terminal, and means for the manager to monitor the robot's work progress in real time and issue correction instructions as necessary, thereby enabling automatic management of the robot's work schedule and efficient response.

[1651] "Email" means written communication sent or received in digital form, a message transmitted through an electronic device.

[1652] "Analyzing" means examining collected data in detail and breaking down its content and structure into an understandable format.

[1653] A "due date" is the date by which a particular task or action is required to be completed.

[1654] A "task" is a specific activity or task that must be performed to achieve a specific goal.

[1655] "Listing" means arranging items in a list format in a particular order.

[1656] A "link" is a hypertext reference that directs a user to a particular resource or piece of information.

[1657] "Organizing" is the process of compiling data and information in an efficient and easy-to-understand format.

[1658] "Displaying" means visually presenting data or information to a user.

[1659] An "industrial robot" is a programmable mechanical device used to perform automated tasks in industry.

[1660] An "instruction" is an order or instruction to perform a specific action or task.

[1661] A "report" is a report on the progress and results of work.

[1662] To "manage" means to effectively manage, supervise, and control a specific resource or task.

[1663] "Notifying" is the act of informing others of specific information.

[1664] "Monitoring" means continuously observing a series of actions or processes and responding if an abnormality occurs.

[1665] "Modification instructions" means instructions to make changes or improvements to existing plans or schedules.

[1666] A "generative AI model" is an artificial intelligence technology that uses models trained by machine learning algorithms to process and analyze new data and tasks.

[1667] The present invention relates to a management system for industrial robots, and is a system that analyzes emails to extract due dates and task information, and reflects this information in the robot's work schedule. Specific embodiments for carrying out the present invention will be described below.

[1668] System Overview

[1669] This system operates on a server, collects and analyzes emails, and manages instructions and reports for industrial robots as tasks. Specifically, it uses the following hardware and software:

[1670] Server: Performs email collection and analysis.

[1671] IMAP library: Used to collect emails.

[1672] BERT model (generative AI model): Used to analyze emails and extract due dates and tasks.

[1673] Django: A web application framework for generating and displaying task lists.

[1674] Program processing explanation

[1675] 1. Email Collection

[1676] The server uses the IMAP protocol to access the factory's instruction and report email accounts and collect emails. The server connects to the IMAP server using the user's email account information and downloads all unread and existing emails. This ensures that the latest email information is obtained.

[1677] 2. Email Analysis

[1678] The server analyzes the body and header information (subject, sender, date, etc.) of the retrieved email. The BERT model is used for the analysis. The email content is input into a generative AI model, which then understands the context and patterns within the email to extract task information. During this process, specific keywords (e.g., "by" or "deadline") are used to identify due dates, task content, and links.

[1679] 3. Task extraction

[1680] The server extracts important task information (deadline, task content, related links) from the analysis results of the generative AI model. The extracted information is organized by each item and used in the next step.

[1681] 4. Task list generation

[1682] The server organizes the extracted task information and creates a task list, which includes information such as the title of each task, the due date, the task content, and related links, allowing the administrator to quickly grasp the overall picture of the tasks.

[1683] 5. Task List Notifications

[1684] The server sends the generated task list to the terminal of the administrator, and the administrator can view the task list on the terminal. The administrator receives a notification and can check the task list.

[1685] 6. Review and Track

[1686] The administrator can view the task list on their device and manage the progress of the necessary tasks. They can update the completion status and progress of tasks as needed, and add notes and comments as needed.

[1687] Specific examples

[1688] For example, consider the following email:

[1689] Email content

[1690] text

[1691] Subject: Scheduled maintenance for Machine A

[1692] Main text:

[1693] Please carry out regular maintenance on Machine A by October 15th.

[1694] Detailed instructions can be found at the following link:

[1695] http: / / factory.com / maintenance_guideline

[1696] Prompt Sentence Examples

[1697] "Please generate a code that extracts deadlines and task details from received emails and generates a task list."

[1698] For this email, the system will extract the following tasks and add them to the task list:

[1699] text

[1700] 1. Title: Scheduled Maintenance of Machine A

[1701] Response date: October 15th

[1702] Task: Regular maintenance of machine A

[1703] Related link: http: / / factory.com / maintenance_guideline

[1704] In this way, automatic management and efficient response of work schedules for industrial robots becomes possible.

[1705] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1706] Step 1:

[1707] The server uses the IMAP protocol to access the factory's instruction and report email account and collect all unread and existing emails. The user's email account information is used as input. Based on this, the server connects to the IMAP server and retrieves the latest email information from the mailbox. The email data is obtained as output.

[1708] Step 2:

[1709] The server obtains the body text and header information (subject, sender, date, etc.) of the collected emails. The email data collected in step 1 is used as input. Data processing is performed to convert the email data into a data format for analysis. The output is email data formatted in an analyzable format.

[1710] Step 3:

[1711] The server inputs the email text into a generative AI model (BERT model) to understand the context and patterns within the email. In this step, due dates, task content, and links are identified based on specific keywords. The formatted email data is used as input. Task information is extracted by natural language processing using the generative AI model. The extracted task information (due dates, task content, and related links) is obtained as output.

[1712] Step 4:

[1713] The server organizes the task information extracted from the analysis results of the generative AI model by each item. The extracted task information is used as input. Data shaping and filtering are performed to obtain organized task information. The organized task information is generated as output.

[1714] Step 5:

[1715] The server generates a task list based on the organized task information. The organized task information is used as input. Based on this, data processing is performed to list information such as the title, due date, task content, and related links for each task. The generated task list is obtained as output.

[1716] Step 6:

[1717] The server sends the generated task list to the administrator's terminal, allowing the administrator to view the task list on the terminal. The generated task list is used as input. To notify the administrator's terminal of this task list, data is transmitted using a communication protocol. The task list displayed on the terminal is obtained as output.

[1718] Step 7:

[1719] The administrator checks the task list on the terminal and manages the progress of the required tasks. The task list notified to the terminal is used as input. The administrator can update the task completion status and progress and make corrections as necessary. The updated task list and task progress are obtained as output.

[1720] 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.

[1721] This invention is a system that analyzes emails, extracts deadlines and task information, and manages them. This system also combines an emotion engine that recognizes the user's emotions, enabling flexible task management according to the user's situation.

[1722] 1. Email Collection

[1723] The server connects to the mailbox using the user's email account information and retrieves all unread and read emails using IMAP or POP3 protocols, which downloads the latest email information.

[1724] 2. Email Analysis

[1725] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, received date, etc.) are sent to a generative AI model to extract important task information (deadline, task content, related links). This information is also evaluated for credibility based on specific keywords.

[1726] 3. Task extraction

[1727] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model, thereby minimizing the risk of missing or misidentifying tasks.

[1728] 4. Task list generation

[1729] The server organizes the extracted task information to generate a task list. The list includes information such as the title of each task, the due date, the task content, and related links. The list is formatted appropriately so that the user can quickly grasp the overall picture of the tasks.

[1730] 5. Task List Notifications

[1731] The server sends the generated task list to the user's terminal, where it can be viewed. Real-time notifications are provided using an appropriate communication protocol.

[1732] 6. Emotion recognition

[1733] As a user reviews their task list, an emotion engine recognizes their emotional state by analyzing their facial expressions, tone of voice, and typing patterns to identify their current emotional state.

[1734] 7. Adjust task management

[1735] The server can then prioritize tasks and adjust reminder notifications based on the user's emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[1736] Specific examples

[1737] For example, consider the following email:

[1738] Subject: Project X progress check

[1739] Main text:

[1740] Hello,

[1741] Please report on the progress of Project X by March 25th.

[1742] You can download the necessary materials from the following links:

[1743] http: / / example.com / resource

[1744] thank you.

[1745] Email collection

[1746] The server collects this mail from the user's mailbox.

[1747] Email Analysis

[1748] The server sends the email body to a generative AI model for analysis. The model extracts the following:

[1749] Response date: March 25th

[1750] Task: Project X progress report

[1751] Related link: http: / / example.com / resource

[1752] Task Extraction

[1753] The server extracts the following information from the output of the generative AI model:

[1754] Response date: March 25th

[1755] Task: Project X progress report

[1756] Related link: http: / / example.com / resource

[1757] Task list generation

[1758] The server uses the extracted information to generate a task list in the following format:

[1759] 1. [Title] Project X Progress Check

[1760] [Response date] March 25th

[1761] [Task Content] Project X progress report

[1762] [Related Links] http: / / example.com / resource

[1763] Task List Notifications

[1764] The server sends the generated task list to the user's terminal.

[1765] emotion recognition

[1766] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[1767] Task management adjustments

[1768] The server adjusts the priority of the task list based on the user's emotional state, for example by prioritizing only tasks that require immediate attention, reducing the user's stress.

[1769] This allows users to focus on important tasks without feeling stressed, improving work efficiency.The present invention is a system that realizes flexible and effective task management by combining task information extracted from emails with the user's emotional state.

[1770] The processing flow will be explained below.

[1771] Step 1:

[1772] The server connects to the mailbox using the user's email account information (e.g. username, password) and retrieves all unread and read emails using IMAP or POP3 protocols.

[1773] Step 2:

[1774] The server reads the downloaded emails in order and extracts the body and header information (subject, sender, received date and time, etc.) of each email, preparing the email for analysis.

[1775] Step 3:

[1776] The server sends the extracted email text to the generative AI model, which then uses natural language processing to analyze the email content and extract important information (response deadlines, task details, related links).

[1777] Step 4:

[1778] The server receives the analysis results of the generative AI model and evaluates the veracity of the extracted information based on specific keywords (e.g., "by," "deadline"), rechecking the extracted information to minimize false positives.

[1779] Step 5:

[1780] The server organizes the task information (deadline, task content, related links) that has been evaluated for credibility and lists it as a task list, which centralizes the tasks in an easy-to-manage format.

[1781] Step 6:

[1782] The server sends the generated task list to the user's device using an appropriate communication protocol (e.g., HTTP, WebSocket) and provides real-time notifications.

[1783] Step 7:

[1784] Users can view their task list on their device, manage the progress and status of each task, update the task completion status, and even enter any necessary notes or comments.

[1785] Step 8:

[1786] The device is equipped with an emotion engine that recognizes the user's emotional state when checking the task list by analyzing the user's facial expressions, tone of voice, input patterns, etc.

[1787] Step 9:

[1788] The server changes the priority of the task list based on the user's emotional state (e.g., stress, fatigue, etc.) recognized by the emotion engine. Reminder notifications are also adjusted according to the user's emotional state.

[1789] Step 10:

[1790] The device displays a prioritized task list for the user to easily review. This allows users to focus on important tasks without feeling stressed. For example, if a user is feeling stressed, only tasks that require immediate attention will be displayed as priority.

[1791] This allows users to effectively manage tasks and improve work efficiency.

[1792] Example 2

[1793] 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."

[1794] In today's business environment, many tasks and actions are notified via email, but manually organizing and managing them is extremely difficult. Furthermore, the lack of a flexible task management method that takes into account the user's stress and emotional state leads to a decline in work efficiency. A system that can solve these issues is needed.

[1795] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting electronic messages, means for analyzing the collected electronic messages using a natural language processing engine, means for extracting due dates and task information from the analyzed electronic messages using a generative AI model, means for evaluating the extracted task information based on credibility criteria using prompt sentences from the generative AI model, means for organizing the evaluated task information and generating a task list, means for notifying and displaying the generated task list on an output device, and means for adjusting the priority of the listed tasks using an emotion engine that recognizes the user's emotional state. This enables automatic and reliable extraction of task information from emails and flexible task management that takes the user's emotional state into consideration.

[1796] "Electronic message" refers to documents or information sent or received by electronic means, including emails, chat messages, and social media messages.

[1797] A "natural language processing engine" refers to computer technology that analyzes and understands the language used by humans on a daily basis, allowing it to extract and structure the meaning of text data.

[1798] A "generative AI model" is a form of artificial intelligence that refers to an algorithm that learns from large amounts of data and generates meaningful information in response to new data.

[1799] A "prompt" refers to input data or instructions that direct a generative AI model to perform a specific analysis or generation task.

[1800] "Credibility criteria" refers to the standards and rules for evaluating the accuracy and validity of extracted information. Based on these standards, the accuracy and reliability of information are judged.

[1801] A "task list" is a list of tasks or matters to be done that have a specific purpose or deadline, and includes information such as the task title, due date, task content, and related links.

[1802] An "emotion engine" refers to the technology and algorithms used to recognize and analyze human emotions. It identifies the user's emotional state based on facial expressions, tone of voice, input patterns, etc.

[1803] An "output device" refers to a device that displays information sent from a server in a form that can be viewed by a user, and includes a computer display, a smartphone screen, etc.

[1804] This invention is a system that analyzes electronic messages and automatically extracts and manages due dates and task information. It also has a function that flexibly adjusts task priorities by taking into account the user's emotional state. This system is characterized by combining a generative AI model and a natural language processing engine to extract reliable task information from electronic messages.

[1805] System configuration

[1806] 1. Server

[1807] The server collects the electronic messages using the user's email account information, authenticates using IMAP or POP3 protocols, and retrieves all unread and read electronic messages, which downloads the latest message information.

[1808] 2. Natural Language Processing Engine

[1809] The server analyzes the received electronic message using a natural language processing engine (e.g., Spacy, NLTK), thereby extracting the body and header information (subject, sender, received date and time, etc.) of the electronic message as structured data.

[1810] 3. Generative AI Models

[1811] The server sends a prompt to a generative AI model (e.g., OpenAI API) based on the analysis results of the electronic message, extracting important task information (deadline, task content, related links). The generative AI model returns the necessary information based on the specified prompt.

[1812] 4. Credibility Assessment

[1813] The server evaluates the task information returned by the generative AI model based on credibility criteria, which helps to avoid extracting inaccurate information and organize reliable data.

[1814] 5. Task list generation

[1815] The server aggregates the verified task information and generates a task list, which includes task titles, due dates, specific task contents, and related links.

[1816] 6. Notices and Displays

[1817] The server sends the generated task list to the user's device so that it can be displayed in real time on the device. For example, data can be sent in JSON format via a REST API, and the device displays the received data in an appropriate format.

[1818] 7. Emotion recognition

[1819] As a user reviews their task list, an emotion engine (e.g., Microsoft Azure Emotion API) collects their facial expressions and tone of voice via the camera and microphone to identify their emotional state.

[1820] 8. Adjust task management

[1821] The server adjusts the priority of the task list based on the user's emotional state received from the emotion engine. For example, if a user is feeling stressed, it may postpone low-priority tasks.

[1822] Specific examples

[1823] Example of a progress confirmation email for Project X

[1824] text

[1825] Subject: Project X progress check

[1826] Main text:

[1827] Hello,

[1828] Please report on the progress of Project X by March 25th.

[1829] You can download the necessary materials from the following links:

[1830] http: / / example.com / resource

[1831] thank you.

[1832] Email collection

[1833] The server collects this mail from the user's mailbox.

[1834] Email Analysis

[1835] The server analyzes the email body using a natural language processing engine and extracts the following structured data:

[1836] Subject: Project X progress check

[1837] Body: Please report the progress of Project X by March 25th.

[1838] Link: http: / / example.com / resource

[1839] Task information extraction

[1840] The server sends the following prompt to the generative AI model:

[1841] "Project X progress check. Report required by March 25th. Related link: http: / / example.com / resource"

[1842] The task information returned by the generative AI model is as follows:

[1843] Response date: March 25th

[1844] Task: Project X progress report

[1845] Related link: http: / / example.com / resource

[1846] Task list generation

[1847] The server uses the extracted information to generate a task list in the following format:

[1848] text

[1849] 1. [Title] Project X Progress Check

[1850] [Response date] March 25th

[1851] [Task Content] Project X progress report

[1852] [Related Links] http: / / example.com / resource

[1853] Coordination of emotion recognition and task management

[1854] When a user checks their task list, the emotion engine analyzes their facial expressions and tone of voice and recognizes that they are feeling stressed.

[1855] The server adjusts the priority of the task list based on the user's emotional state, for example, by prioritizing only tasks that require immediate attention, reducing the user's stress.

[1856] As described above, the present invention makes it possible to flexibly and effectively manage tasks by taking into account task information extracted from electronic messages and the emotional state of the user.

[1857] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1858] Program processing flow

[1859] Processing Steps

[1860] Step 1:

[1861] Input: User's email account information (username, password)

[1862] Processing: The server connects to the mailbox using IMAP or POP3 protocol and retrieves all unread and read emails. The server authenticates by calling an API such as "mailbox.login('username', 'password')". After that, it retrieves messages using commands such as "mailbox.fetch('ALL')".

[1863] Output: A dataset of retrieved emails

[1864] Step 2:

[1865] Input: Dataset of retrieved emails

[1866] Processing: The server analyzes the received email using a natural language processing engine (e.g., Spacy, NLTK). The server initializes the natural language processing engine using "nlp = spacy.load('en_core_web_sm')" and analyzes the email body and header information using "doc = nlp(email_body)". Specifically, it extracts text data such as the email body, subject, sender, and received date and time.

[1867] Output: Structured data of the parsed email (subject, body, sender, received date and time)

[1868] Step 3:

[1869] Input: Parsed email structured data

[1870] Processing: The server sends a prompt to the generative AI model (e.g., OpenAI API) and extracts important task information (deadline, task content, related links). The server generates a prompt like "prompt_text = 'Check the progress of Project X. Report required by March 25th. Related links: http: / / example.com / resource'" and sends it to the generative AI model. Task information is obtained using "result = ai_model.generate(prompt_text)".

[1871] Output: Task information from the generative AI model (deadline, task content, related links)

[1872] Step 4:

[1873] Input: Task information from the generative AI model

[1874] Processing: The server evaluates the task information returned by the generative AI model based on credibility criteria. The credibility evaluation uses regular expressions based on specific keywords, and is performed using the following formula: "re.search(pattern, result)".

[1875] Output: Task information whose authenticity has been confirmed

[1876] Step 5:

[1877] Input: Task information whose authenticity has been confirmed

[1878] Processing: The server generates a task list based on the authenticated task information. The server creates a data structure like this: task_list = [{'title': title, 'due_date': due_date, 'content': content, 'link': link}].

[1879] Output: Generated task list

[1880] Step 6:

[1881] Input: Generated task list

[1882] Processing: The server sends the generated task list to the user's device. The server sends the data in JSON format via the REST API using the following method: "requests.post('http: / / example.com / api / tasks', json=task_list)". The device receives the data using "fetch(' / api / tasks')" and displays it in the appropriate format.

[1883] Output: The task list displayed on the user's device.

[1884] Step 7:

[1885] Input: Facial expressions, tone of voice, and input patterns when users check their task list

[1886] Processing: When a user checks their task list, an emotion engine (e.g., Microsoft Azure Emotion API) recognizes the user's emotional state. The device captures an image using "face_recognition.capture_frame()" and performs emotion analysis using "azure_emotion_api.detect_emotion(image)".

[1887] Output: Recognized emotional state of the user

[1888] Step 8:

[1889] Input: Perceived emotional state of the user

[1890] Processing: The server rearranges the task list based on the user's emotional state. The server rearranges the task list based on the user's emotional state, as follows: if emotion == 'stressed': prioritize_urgent_tasks()

[1891] Output: Reconciled task list

[1892] Through the above processing steps, the present invention automatically extracts task information from electronic messages and realizes flexible task management according to the user's emotional state.

[1893] (Application example 2)

[1894] 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."

[1895] Conventional task management systems can extract task information from emails, but because they list and manage tasks without considering the user's emotional state, users may feel stressed or their work efficiency may decrease. Another issue is the insufficient evaluation of the credibility of task information extracted from emails. The present invention aims to solve these issues and provide a system that realizes flexible task management according to the user's emotional state.

[1896] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1897] In this invention, the server includes means for analyzing emails, means for extracting due dates from the analyzed emails, means for listing tasks based on the extracted due dates, means for organizing links and action details related to the listed tasks, means for displaying the generated task list, means for adjusting task priorities by recognizing the user's emotional state, and means for adjusting reminder notifications based on the user's emotional state. This enables the user to manage tasks in a less stressful manner, thereby improving overall work efficiency.

[1898] The "means for analyzing e-mail" is a means having a function of acquiring a user's e-mail, analyzing the mail body and header information, and extracting due dates and task information.

[1899] The "means for extracting correspondence dates" is a means having a function for detecting and extracting date information such as deadlines and deadlines from analyzed emails.

[1900] The "means for listing tasks" is a means having a function for organizing extracted task information and displaying it in a list format so that the user can easily understand it.

[1901] The "means for organizing links and correspondence content" is a means having a function for collecting and organizing links and specific correspondence content related to the listed tasks.

[1902] The "means for displaying a task list" is a means having a function for displaying the generated task list on the user's terminal so that the user can visually confirm it.

[1903] "Means for recognizing the user's emotional state and adjusting task priorities" refers to means that has the function of recognizing the user's emotional state from facial expressions, tone of voice, etc., and dynamically changing task priorities according to that state.

[1904] The "means for adjusting reminder notifications based on the user's emotional state" refers to a means that has the function of changing the timing and content of reminder notifications according to the user's emotional state, thereby reducing the burden on the user.

[1905] The system that realizes this application example is a production management support system installed on factory robots. This system is equipped with multiple functions that enable users (workers) to efficiently manage tasks.

[1906] First, the server connects to your mailbox using your email account information and collects your emails. It uses IMAP or POP3 protocols to retrieve all unread and read emails. This allows the server to download the latest email information.

[1907] The server then analyzes the email using natural language processing. The email body and header information (e.g., subject, sender, and date and time of receipt) are sent to a generative AI model to extract important task information (deadline, task content, and related links). This information is also evaluated for credibility based on specific keywords.

[1908] The server then extracts and organizes task information whose credibility has been assessed from the analysis results of the generative AI model. This minimizes the risk of missing or misidentifying tasks. The server then organizes the extracted task information to generate a task list. The list includes information such as each task's title, due date, task content, and related links. The list is organized in an appropriate format so that users can quickly grasp the overall picture of the tasks.

[1909] The generated task list is sent from the server to the user's device (e.g., tablet or smart glasses) and can be viewed on the device. Real-time notifications are provided using an appropriate communication protocol.

[1910] A distinctive feature of this system is the ability of the emotion engine to recognize the user's emotional state when they check their task list. This engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. This emotion recognition is performed by the emotion engine, and appropriate countermeasures are presented according to the situation.

[1911] Additionally, the server can reprioritize task lists and adjust reminder notifications based on the user's perceived emotional state. For example, if the server detects that the user is feeling stressed, it can postpone low-priority tasks.

[1912] As a concrete example, consider the following email:

[1913] Subject: Project Y progress check

[1914] Main text:

[1915] Hello,

[1916] Please report the progress of Project Y by April 1st.

[1917] You can download the necessary materials from the following links:

[1918] http: / / example.com / resource

[1919] thank you.

[1920] Based on the email above, the server extracts the following:

[1921] Response date: April 1st

[1922] Task: Report on the progress of Project Y

[1923] Related link: http: / / example.com / resource

[1924] Based on this extracted information, a task list is generated and notified to the user. Furthermore, if the emotion recognition engine detects signs of stress when the user checks the task list, the priority of the tasks is appropriately adjusted.

[1925] An example of a prompt for a generative AI model is:

[1926] Extract the task information from the following email:

[1927] Subject: Project Y progress check

[1928] Main text:

[1929] Hello,

[1930] Please report the progress of Project Y by April 1st.

[1931] You can download the necessary materials from the following links:

[1932] http: / / example.com / resource

[1933] thank you.

[1934] In this way, the system of the present invention realizes flexible and effective task management according to the user's emotional state. This technology can improve factory productivity while reducing the burden on workers.

[1935] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1936] Step 1:

[1937] The server connects to the mailbox using the user's email account information and collects emails. The protocol used is IMAP or POP3. The input is the user's email account information, and the output is the retrieved email data. This email data includes all unread and read emails.

[1938] Step 2:

[1939] The server analyzes the received email using natural language processing. The email body and header information (subject, sender, date and time of receipt, etc.) are sent to the generative AI model, which extracts important task information (deadline, task content, related links). The input is the email data, and the output is the extracted task information. At this point, a prompt is sent to the generative AI model, and the analysis results are received.

[1940] Step 3:

[1941] The server extracts and organizes task information whose credibility has been evaluated from the analysis results of the generative AI model. The input is the analysis results from the generative AI model, and the output is the task information whose credibility has been evaluated.

[1942] Step 4:

[1943] The server organizes the extracted task information and generates a task list, which includes information such as the title, due date, task content, and related links for each task. The input is the task information whose credibility has been evaluated, and the output is a generated task list.

[1944] Step 5:

[1945] The server sends the generated task list to the user's terminal, where it can be viewed by the user. Notifications are given in real time using an appropriate communication protocol. The input is the task list, and the output is the task list displayed on the user's terminal.

[1946] Step 6:

[1947] When a user checks their task list, the emotion engine recognizes their emotional state. The emotion engine analyzes the user's facial expressions, tone of voice, input patterns, etc. to identify the user's current emotional state. The input is the user's emotional data, and the output is the recognized emotional state.

[1948] Step 7:

[1949] The server changes the priority of the task list and adjusts reminder notifications based on the recognized emotional state. For example, if it recognizes that the user is feeling stressed, it will postpone low-priority tasks. The inputs are the recognized emotional state and the task list, and the output is the prioritized task list and notifications.

[1950] 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.

[1951] 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.

[1952] 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.

[1953] 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.

[1954] 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.

[1955] 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.

[1956] 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).

[1957] 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.

[1958] 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."

[1959] 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.

[1960] 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).

[1961] 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.

[1962] 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.

[1963] 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.

[1964] 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.

[1965] 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.

[1966] 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.

[1967] 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.

[1968] 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.

[1969] 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.

[1970] 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.

[1971] The following is further disclosed regarding the above embodiment.

[1972] (Claim 1)

[1973] a means for analyzing email;

[1974] means for extracting response due dates from the analyzed emails;

[1975] A means for listing tasks based on the extracted due dates;

[1976] A way to organize the links and actions related to the listed tasks,

[1977] The system includes a means for displaying the generated task list.

[1978] (Claim 2)

[1979] 10. The system of claim 1, wherein the system uses a generative AI model for analyzing emails.

[1980] (Claim 3)

[1981] The system of claim 1, wherein the system evaluates the credibility of the task information based on specific keywords from the analyzed email.

[1982] "Example 1"

[1983] (Claim 1)

[1984] means for connecting to an email server using a user's account information and collecting emails stored in a mailbox;

[1985] a means for using a generative AI model to analyze collected email body and header information;

[1986] A means for extracting response deadlines, task contents, and related links from the analysis results of the generative AI model;

[1987] means for generating a task list based on the extracted information;

[1988] means for notifying a user terminal of the generated task list;

[1989] A system that includes a means for a user to view a task list and manage progress on a terminal.

[1990] (Claim 2)

[1991] The system of claim 1, wherein a specific prompt sentence is input to the generative AI model to understand the content of the collected emails and to request analysis.

[1992] (Claim 3)

[1993] The system of claim 1, which evaluates the credibility of task information based on specific keywords and context, based on the analysis results of the generative AI model.

[1994] "Application Example 1"

[1995] (Claim 1)

[1996] a means for analyzing email;

[1997] means for extracting response due dates from the analyzed emails;

[1998] A means for listing tasks based on the extracted due dates;

[1999] A way to organize the links and actions related to the listed tasks,

[2000] a means for displaying the generated task list;

[2001] A means for analyzing instructions and reports from industrial robots, extracting and managing response deadlines and specific work content;

[2002] a means for notifying a terminal of an administrator of the generated robot task list;

[2003] A means for management personnel to monitor the robot's work progress in real time and issue correction instructions as necessary;

[2004] A system including:

[2005] (Claim 2)

[2006] 10. The system of claim 1, wherein the system uses a generative AI model for analyzing emails.

[2007] (Claim 3)

[2008] The system of claim 1, wherein the system evaluates the credibility of the task information based on specific keywords from the analyzed email.

[2009] "Example 2: Combining Emotion Engines"

[2010] (Claim 1)

[2011] a means for collecting electronic messages;

[2012] means for analyzing the collected electronic messages using a natural language processing engine;

[2013] A means for extracting response deadlines and task information from the analyzed electronic messages using a generative AI model;

[2014] A means for evaluating the extracted task information using the prompt sentence of the generative AI model based on a credibility criterion;

[2015] A means for organizing the evaluated task information and generating a task list;

[2016] means for notifying and displaying the generated task list on an output device;

[2017] means for adjusting the priority of the listed tasks using an emotion engine that recognizes the user's emotional state;

[2018] A system including:

[2019] (Claim 2)

[2020] 10. The system of claim 1, wherein the system uses a generative AI model for analyzing emails.

[2021] (Claim 3)

[2022] The system of claim 1, wherein the system evaluates the credibility of the task information based on specific keywords from the analyzed email.

[2023] "Application example 2 when combining emotion engines"

[2024] (Claim 1)

[2025] a means for analyzing email;

[2026] means for extracting response due dates from the analyzed emails;

[2027] A means for listing tasks based on the extracted due dates;

[2028] A way to organize the links and actions related to the listed tasks,

[2029] a means for displaying the generated task list;

[2030] a means for recognizing a user's emotional state and adjusting task priorities;

[2031] A means for tailoring reminder notifications based on a user's emotional state

[2032] A system including:

[2033] (Claim 2)

[2034] 10. The system of claim 1, wherein the system uses a generative AI model for analyzing emails.

[2035] (Claim 3)

[2036] The system of claim 1, wherein the system evaluates the credibility of the task information based on specific keywords from the analyzed email. [Explanation of symbols]

[2037] 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 analyzing email; means for extracting response due dates from the analyzed emails; A means for listing tasks based on the extracted due dates; A way to organize the links and actions related to the listed tasks, The system includes a means for displaying the generated task list.

2. The system of claim 1 , which uses a generative AI model for email analysis.

3. The system of claim 1 , wherein the system evaluates the credibility of the task information based on specific keywords from the analyzed email.

Images