System

Abstract

A system is provided.SOLUTION: The system includes a means for acquiring a mail or a chat message by a server, a means for analyzing the message by a natural language processing algorithm to extract a task, a means for determining importance of the extracted task, and a means for notifying a user of a remind or an alert on the basis of the importance of the task.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] As businesspeople make more requests and communicate more frequently via email and chat, tasks that need to be done can become buried. In particular, there are cases where requests sent via email are not read by the recipient, or important information is buried in a huge amount of text, making it difficult to find. The present invention aims to solve these problems and provide a means to improve work efficiency. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The system includes a server that receives emails and chat messages. It also includes a natural language processing algorithm that analyzes the messages and extracts tasks. It also includes a server that determines the importance of the extracted tasks and sends reminders and alerts to the user based on the importance. It also includes a server that stores task content in a database, analyzes deadline information related to the extracted tasks, and sets reminder timing based on the analysis. The system further includes a machine learning model that determines task importance, a user notification method that includes email, chat, or a dedicated app, a user interface that displays notifications, and a natural language generation algorithm that summarizes task content. This allows tasks to be properly notified and important tasks to be notified to the user at the appropriate time.

[0007] "Mail" refers to electronic mail, a digital message sent and received via the Internet or other means.

[0008] A "chat message" is a short text message exchanged in real time via an instant messaging or chat application.

[0009] A "server" is a computer system that provides services to other computers on a network.

[0010] "Natural language processing algorithm" is a general term for technical methods that allow computers to understand, analyze, and generate human language.

[0011] A "task" refers to a specific task or activity that must be performed to achieve a particular goal.

[0012] "Importance" is a measure for assessing the priority and urgency of a task or issue.

[0013] A "remind" is an act of sending a notification or alert to a user to prompt them to perform a specific task or matter.

[0014] An "alert" is a notification method used to warn a user about a particular situation or event.

[0015] A "database" is a structured collection of data for efficiently storing, retrieving, and managing large amounts of data.

[0016] A "machine learning model" is a mathematical model that uses algorithms to learn from data and make predictions or classifications.

[0017] "User interface" is a general term for the screens and operating means through which users and computer systems exchange information.

[0018] "Natural language generation algorithms" is a general term for technical methods that allow computers to generate human language and construct sentences.

[0019] A "summary" is a concise summary of the main points or overview of a document or piece of information. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. Below, we will explain the program processing of the system of the present invention in natural language, and also provide specific examples.

[0042] 1. Email / chat capture

[0043] server:

[0044] The server periodically connects to the mail or chat server to retrieve new messages. For example, for email, it scans the user's inbox using the IMAP protocol to retrieve unread messages. For chat, it retrieves new messages from a particular channel or thread.

[0045] Examples:

[0046] The server connects to the email server multiple times a day to retrieve new emails and convert them into text format.

[0047] The server periodically retrieves new messages from the chat server and stores them for analysis.

[0048] 2. Message Analysis

[0049] server:

[0050] The server then analyzes the messages using natural language processing (NLP) algorithms. This involves morphological analysis of the documents to extract keywords and phrases related to the request or task. It then identifies action items based on the extracted keywords.

[0051] Examples:

[0052] The server analyzes the message "Can you prepare the budget report by next Monday?" using an NLP algorithm and extracts the keywords "prepare," "budget report," and "next Monday."

[0053] This analysis identifies the task "Create a budget report by next Monday."

[0054] 3. Task Generation and Importance Determination

[0055] server:

[0056] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data and the importance of similar tasks, as well as deadlines and the requester's priorities.

[0057] Examples:

[0058] The server determines the identified task "Create a budget report by next Monday" as "Importance 2 / 3" and stores it in the database.

[0059] When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored.

[0060] 4. Notice to Users

[0061] server:

[0062] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[0063] Device:

[0064] The device displays the notification sent from the server on the user interface. When the user clicks on the notification, a screen showing detailed information is launched.

[0065] Examples:

[0066] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[0067] The device will receive this notification and display it to the user as a Slack notification.

[0068] 5. Request Summary Generation

[0069] Device:

[0070] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to summarize the request, including the request, deadline, and important information.

[0071] Examples:

[0072] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[0073] In this way, the system of the present invention provides a function to extract important tasks from emails and chats and notify users at the appropriate time, allowing business people to efficiently manage their tasks without missing any requests.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The server periodically connects to the mail server and chat server to retrieve new messages, for example, by logging in to the mail server using the IMAP protocol to search for unread emails, or by using a REST API to retrieve new messages from the chat application.

[0077] Step 2:

[0078] The server converts the received messages into text and analyzes them using natural language processing (NLP) algorithms. Morphological analysis is used to extract the words and phrases that make up the sentence and identify the parts that are relevant to requests or action items.

[0079] Step 3:

[0080] The server extracts task candidates from the parsed messages, generates task items including information such as the request content, deadline, and requester, and lists them. For example, it generates a task such as "Create a budget report by next Monday."

[0081] Step 4:

[0082] The server stores the generated tasks in a database. Each task contains information such as the task ID, task content, requester, deadline, and importance. Task management is based on this information.

[0083] Step 5:

[0084] The server uses a machine learning model to determine the importance of a task. It determines the priority of a task by referring to past data and information on similar tasks. For example, a task with a deadline of "by next Monday" may be determined to be high priority.

[0085] Step 6:

[0086] The server sets the timing of reminders and alerts based on the determined importance. High-priority tasks are notified early, and low-priority tasks are notified later. Notifications are sent according to the set reminder timing.

[0087] Step 7:

[0088] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[0089] Step 8:

[0090] The device displays the notification received from the server in the user interface, notifying the user in the form of a pop-up notification, an in-app banner, etc. The user can click the notification to display more information.

[0091] Step 9:

[0092] When a user clicks on a notification, the device uses a natural language generation (NLG) algorithm to display a screen summarizing the message content, such as a simple summary like "Budget report request: Deadline next Monday."

[0093] In this way, by linking the server, terminals, and users, a system is realized that efficiently extracts important tasks from emails and chats and notifies users at the appropriate time.

[0094] Example 1

[0095] 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."

[0096] In today's world, where people are often overwhelmed by a huge amount of information, it is extremely difficult for business people to efficiently extract and properly manage important tasks from emails and chat messages. Overlooking or forgetting important tasks not only reduces work efficiency, but also leads to problems such as missing important deadlines. There is a need for a solution to these problems and a way for business people to efficiently manage their tasks.

[0097] 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.

[0098] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for using a machine learning model to determine the importance of the extracted tasks, means for notifying a user terminal of a reminder or an alert based on the importance of the tasks, means for displaying detailed information on the terminal of the user who received the reminder or alert, and means for summarizing the detailed information using a natural language generation algorithm. This makes it possible to automatically extract important tasks from emails and chat messages and notify the user at the appropriate time.

[0099] A "server" is a computer system that sends, receives, and processes data over a network.

[0100] "Means for acquiring emails and chat messages" refers to a function that enables the server to connect to an email server or chat server and periodically acquire user messages.

[0101] A "natural language processing algorithm" is a computational method for analyzing text data, understanding grammar and meaning, and extracting information.

[0102] "Means for extracting tasks" refers to a function that uses natural language processing algorithms to identify task-related keywords and phrases from emails and chat messages and recognize them as tasks.

[0103] A "machine learning model" is an algorithm that learns patterns based on past data and makes predictions and classifications for new data.

[0104] The "means of using a machine learning model to determine the importance of a task" is a function that inputs the extracted task into a machine learning model and calculates and determines its importance.

[0105] A "terminal" is an information display device used by a user, such as a computer, smartphone, or tablet.

[0106] The "means for notifying reminders and alerts" is a function that sends reminder and alert messages to the user's terminal based on the importance of the task determined by the server.

[0107] The "means for displaying detailed information" is a function that displays the contents of reminders and alerts received by the user's terminal from the server.

[0108] A "natural language generation algorithm" is a computational method for generating sentences in natural language from text data.

[0109] "Means for summarizing detailed information using a natural language generation algorithm" refers to a function in which the user's device summarizes and displays the contents of reminders and alerts using a natural language generation algorithm.

[0110] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. A specific implementation method of the system will be described below.

[0111] System Overview

[0112] The system of the present invention is broadly composed of the following elements:

[0113] 1. How to retrieve emails and chat messages

[0114] 2. A way to analyze messages with natural language processing (NLP) algorithms

[0115] 3. Using machine learning models to determine the importance of extracted tasks

[0116] 4. A method for sending reminders and alerts to the user's device based on the determined importance of the task

[0117] 5. A way to display detailed information on the device of the user who received the reminder or alert.

[0118] 6. A method for summarizing the displayed details using a natural language generation (NLG) algorithm

[0119] These elements allow the system to efficiently manage tasks and prevent users from missing important tasks.

[0120] Get email / chat

[0121] server:

[0122] The server periodically connects to the mail server using the IMAP protocol to retrieve new or unread emails from the user's inbox, and also uses the API of a chat service, such as the Slack API, to access a specific chat channel to retrieve new messages.

[0123] Message Parsing

[0124] server:

[0125] The server analyzes the received messages using a natural language processing algorithm. Specifically, it performs morphological analysis to extract keywords and phrases related to requests and tasks from the messages. Action items are identified based on the extracted keywords.

[0126] Examples:

[0127] By analyzing the message "Can you prepare the budget report by next Monday?", the keywords "prepare," "budget report," and "next Monday" are extracted, and the task "prepare the budget report by next Monday" is identified.

[0128] Task generation and importance determination

[0129] server:

[0130] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, the importance of similar tasks, deadlines, and the requester's priority.

[0131] Examples:

[0132] The machine learning model determines that the task "Create a budget report by next Monday" is an "Importance Level 2 / 3," and the server stores this task in the database along with details such as the task ID, task content, requester, deadline, and importance.

[0133] User Notification

[0134] server:

[0135] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[0136] Device:

[0137] The device displays the notification sent from the server in the user interface, and when the user clicks on the notification, a screen appears displaying more information.

[0138] Examples:

[0139] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please create a budget report by next Monday." The device receives this notification and displays it to the user as a Slack notification. When the user clicks on the notification, detailed task information is displayed.

[0140] Generate a summary of the request

[0141] Device:

[0142] When the user clicks on the notification, the device displays a screen that uses a natural language generation algorithm to summarize the request, including the request, deadline, and important information.

[0143] Examples:

[0144] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[0145] Prompt Sentence Examples

[0146] "Please explain in natural language the steps required to design a system that extracts important tasks from new emails or chat messages and notifies the user via push notifications, along with specific examples."

[0147] This system allows business people to efficiently extract important tasks from emails and chat messages and receive notifications at the appropriate time, thereby improving work efficiency and preventing tasks from being overlooked.

[0148] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0149] Step 1: Get email / chat

[0150] server:

[0151] The server periodically connects to the mail server and chat server to retrieve new messages. Specifically, it logs in to the mail server using the IMAP protocol and scans the user's inbox for new emails. It also accesses specific chat channels using a provided API on the chat server to retrieve new messages.

[0152] input:

[0153] User's mail and chat server credentials

[0154] output:

[0155] New emails and new chat messages converted to plain text

[0156] Specific behavior:

[0157] The server uses the IMAP protocol to log into the email server and read the new, unread emails.

[0158] The server converts the email into text and converts it into a format that can be processed internally.

[0159] The server uses the Slack API to access a specific channel and retrieve any new messages that have not yet been processed.

[0160] Step 2: Message analysis

[0161] server:

[0162] The server then analyzes the messages using natural language processing (NLP) algorithms, morphologically analyzing the messages to identify key keywords and phrases, and extracting action items based on relevant keywords.

[0163] input:

[0164] New emails and new chat messages converted to plain text

[0165] output:

[0166] Extracted tasks and related keywords

[0167] Specific behavior:

[0168] The server uses NLP algorithms to parse the message: "Can you prepare the budget report by next Monday?"

[0169] The server performs morphological analysis and extracts the keywords "prepare," "budget report," and "next Monday."

[0170] Based on these keywords, the server identifies the action item "Create budget report by next Monday."

[0171] Step 3: Task generation and importance determination

[0172] server:

[0173] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, information about similar tasks, deadlines, and the requester's priority.

[0174] input:

[0175] Extracted tasks and related keywords

[0176] output:

[0177] Tasks with determined importance and detailed information

[0178] Specific behavior:

[0179] The server inputs the extracted task information into the machine learning model and calculates the importance.

[0180] As a result, a task "Create a budget report by next Monday" is generated, which is determined to have an importance of "2 / 3."

[0181] The server stores this task in a database, along with details such as the task ID, task content, requester, deadline, and importance.

[0182] Step 4: Notify users

[0183] server:

[0184] Based on the determined importance, the server pushes reminders and alerts to the user's device via email, chat, a dedicated app, or other means.

[0185] input:

[0186] Tasks with determined importance and detailed information

[0187] output:

[0188] Reminders and alerts sent to users' devices

[0189] Specific behavior:

[0190] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[0191] The device will receive this notification and display the notification content in the Slack interface.

[0192] Step 5: Generate a summary of the request

[0193] Device:

[0194] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to generate a summary of the request, including the request, deadline, and important keywords.

[0195] input:

[0196] Reminder and alert notification content

[0197] output:

[0198] Summarized action item details

[0199] Specific behavior:

[0200] When a user clicks on the Slack notification, a dedicated app is launched and a concise summary is generated and displayed using an NLG algorithm: "Budget report request: due next Monday."

[0201] (Application example 1)

[0202] 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."

[0203] In conventional factory environments, managing production lines and maintenance tasks is complex, and efficient operation requires a great deal of time and effort. In particular, when multiple tasks occur simultaneously, it is difficult to immediately identify and appropriately handle them, increasing the risk of reduced productivity and human error. To solve this problem, a system is needed that can automatically extract tasks, determine their importance, and provide real-time notifications in a unified manner.

[0204] 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.

[0205] In this invention, the server includes means for receiving emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for notifying the user of reminders and alerts based on the task importance, means for generating task summaries using a generative AI model, and means for displaying the reminders and alerts on the user's head-mounted display. This enables workers in a factory to check important tasks in real time without using their hands and respond efficiently.

[0206] A "server" is a device that stores, processes, and manages data on a network.

[0207] "Email and chat messages" are text data exchanged between users via email or instant messaging platforms.

[0208] A "natural language processing algorithm" is a computer program that analyzes human language and extracts information.

[0209] A "task" refers to an action or work requested of a user with a specific purpose and deadline.

[0210] "Importance" is an indicator of the priority and urgency of a task.

[0211] "Reminders and alerts" are notifications that inform the user of the existence, deadlines, and importance of tasks.

[0212] A "generative AI model" is an artificial intelligence algorithm that generates new information based on existing data.

[0213] The "task summary" is information that briefly summarizes the main points of the extracted task.

[0214] A "head-mounted display" is a display device that is worn on the user's head and provides visual information.

[0215] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications.

[0216] A system for implementing this invention is designed to combine multiple different technologies to streamline task management for factory robots. This system can extract tasks from emails and chat messages, determine their importance, and notify the user. Furthermore, it generates task summaries using a generative AI model and displays them on a head-mounted display.

[0217] 1. Email / chat capture

[0218] The server retrieves emails and chat messages sent from each department and automation system in the factory. Specifically, it connects to the mail server using the IMAP protocol and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels.

[0219] 2. Message Analysis

[0220] The server analyzes emails and chat messages using natural language processing (NLP) algorithms to extract task-related keywords and phrases from the messages and identify specific action items.

[0221] 3. Task Generation and Importance Determination

[0222] The server stores the extracted tasks in a database and uses a machine learning model to determine the importance of each task, which is trained based on past data and the importance of similar tasks, and also takes into account the deadline and the importance of the requester.

[0223] 4. Notice to Users

[0224] The server then sends notifications to the user's head-mounted display based on the determined task importance. This notification is sent in real time, allowing the user to check important tasks without using their hands.

[0225] 5. Request Summary Generation

[0226] Once the user confirms the notification, the server uses a generative AI model to generate a task summary and display it on the head-mounted display, including specific tasks, deadlines, and important information.

[0227] Hardware and software used

[0228] IMAP Server: A general mail server

[0229] Chat Server: Internal messaging system

[0230] Natural Language Processing: Python's NLTK library

[0231] Machine learning model: scikit-learn library

[0232] Push notifications: Pushbullet API

[0233] Head-mounted display: A visual information providing device worn by the user.

[0234] Specific examples

[0235] For example, suppose a message is sent via chat stating that "Part X on Machine A needs to be replaced" on a factory line. This message is captured by the server, and the keywords "replacement work," "machine A," and "part X" are extracted using natural language processing. After that, a machine learning model determines that this task is very important, and a notification is sent to the user's head-mounted display.

[0236] Prompt Sentence Examples

[0237] You have received a new factory task, "Replace part X on machine A," with high priority. Please provide details and priority for this task to your generative AI model.

[0238] In this way, the system of the present invention can efficiently manage important tasks within a factory in real time and provide users with the information they need immediately.

[0239] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0240] Step 1:

[0241] The server retrieves emails and chat messages sent from each department and automation system in the factory. The server uses the IMAP protocol to access the mail server and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels. The input is the text data of emails and chat messages, and the output is the retrieved raw messages.

[0242] Step 2:

[0243] The server analyzes the received emails and chat messages using natural language processing (NLP) algorithms. Specifically, it performs morphological analysis on the received text data and analyzes its grammatical structure to extract keywords and phrases related to the task. The input is the raw message text data, and the output is the extracted keywords and phrases.

[0244] Step 3:

[0245] The server identifies tasks based on the extracted keywords and phrases. The identified tasks are stored in a database. The database records detailed information for each task, such as the ID, content, requester, deadline, and importance. The input is the keywords and phrases obtained in step 2, and the output is the database record where the identified tasks are stored.

[0246] Step 4:

[0247] The server uses a machine learning model to determine the importance of the identified task. The model calculates the urgency and priority of the task based on past data and the importance of similar tasks. The input is the task details, and the output is the determined importance.

[0248] Step 5:

[0249] The server sends a notification to the user's head-mounted display based on the determined task importance. The notification is sent in real time using the Pushbullet API. The input is the determined importance and task information, and the output is the notification displayed on the user's device.

[0250] Step 6:

[0251] When a user receives a notification, the server uses a generative AI model to generate a task summary, including the specific work content, deadline, and important information, to confirm the task details. The input is the task information, and the output is the generated summary.

[0252] Step 7:

[0253] The user checks the summary through a head-mounted display and receives specific instructions and information for performing the corresponding task. The input is the generated summary, and the output is the summary information that the user checks.

[0254] This allows workers in the factory to check important tasks in real time without using their hands and respond efficiently.

[0255] 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.

[0256] The present invention is a system that allows business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of tasks while taking into account the user's emotional state. Below, we will explain the processing of the system's program for implementing the invention in natural language, and also provide specific examples.

[0257] 1. Email / chat capture

[0258] server:

[0259] The server periodically connects to the mail and chat servers to retrieve new messages, for example, emails using the IMAP protocol and chat messages using a REST API, which are converted to text format and stored for analysis.

[0260] Examples:

[0261] The server retrieves unread emails from the mail server every 10 minutes and saves them in text format.

[0262] The server uses the Slack API to retrieve new messages from the chat room.

[0263] 2. Message Analysis

[0264] server:

[0265] The server uses natural language processing (NLP) algorithms to analyze the messages received. It performs string analysis to extract keywords and phrases related to requests and action items. This analysis identifies candidate tasks.

[0266] Examples:

[0267] The server analyzes the email "Please review the attached document by Friday." and extracts the keywords "review," "document," and "Friday."

[0268] From the analysis results, the task "Review the attached documents by Friday" is identified.

[0269] 3. Task Generation and Importance Determination

[0270] server:

[0271] The identified tasks are stored in a database. When saved, information such as the task ID, task content, requester, deadline, and importance is included. Furthermore, the importance of the task is determined using a machine learning model. Priority is determined by referring to past data and information on similar tasks.

[0272] Examples:

[0273] The server determines that the task "Review attached documents by Friday" is "Importance 2 / 3" and stores it in the database.

[0274] The database stores detailed information about the task (e.g., requester, deadline, importance).

[0275] 4. Recognition of user emotions using an emotion engine

[0276] server:

[0277] The server uses an emotion engine to analyze the user's emotional state as they perform tasks. Emotion recognition uses data from the user's past interactions and data from biometric sensors to determine the user's stress level and mood.

[0278] Examples:

[0279] The server analyzes the user's recent chat messages and data from the wearable device to determine whether the user is "feeling stressed."

[0280] 5. User Notifications and Reminders

[0281] server:

[0282] The content and timing of reminders and alerts are adjusted based on the user's emotional state and the importance of the task. If the user is under stress, the system will take measures such as reducing the frequency of reminders. Notifications are sent via email, chat, a dedicated application, etc.

[0283] Device:

[0284] The device displays the notification sent from the server on the user interface, and the user can click on the notification to display detailed information.

[0285] Examples:

[0286] Because the user is stressed, the server sends a notification in a softer tone than usual saying, "Review required by Friday. Please do it within reasonable time."

[0287] The device will display this notification in the form of a pop-up.

[0288] 6. Request Summary Generation

[0289] Device:

[0290] When a user clicks on the notification, a natural language generation (NLG) algorithm is used to display a summary of the request, including key details and deadlines.

[0291] Examples:

[0292] When the user clicks on the notification, the summary "Attachment Review Request: Due Friday" appears.

[0293] In this way, the system of the present invention supports efficient task management by extracting important tasks from emails and chats while taking into account the user's emotional state using an emotion engine and notifying them at the appropriate time.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] The server periodically connects to the mail server and chat server to retrieve new messages. For example, it logs in to the mail server using the IMAP protocol to retrieve unread emails. For the chat server, it uses the REST API to retrieve new messages from a specific chat room.

[0297] Step 2:

[0298] The server converts the received messages into text format and stores them in a pool for analysis, in order to convert them into a format that can be used in other processing steps.

[0299] Step 3:

[0300] The server analyzes the stored messages using natural language processing (NLP) algorithms. It performs morphological analysis to extract keywords and phrases related to requests and action items. For example, keywords such as "send," "create," and "deadline" are extracted.

[0301] Step 4:

[0302] The server then creates a list of candidate tasks based on the analysis results, including information such as the request content, deadline, and requester. For example, a task such as "Create a report by next Friday" may be identified.

[0303] Step 5:

[0304] The server saves the extracted tasks in a database. When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored. This allows tasks to be managed centrally.

[0305] Step 6:

[0306] The server uses machine learning models to determine the importance of a task. It uses past data and information from similar tasks to determine the priority of the task. For example, if a task has a specific deadline, it will be assigned a "high priority."

[0307] Step 7:

[0308] The server uses an emotion engine to analyze the emotional state of the user performing a task. Emotion recognition is based on past interaction data and data from biometric sensors. For example, it may determine that the user is in a stressful state.

[0309] Step 8:

[0310] The server adjusts the content and timing of reminders and alerts based on the user's emotional state and the importance of the task as determined by the emotion engine. For example, if the user is under stress, the server reduces the frequency of reminders and softens their content.

[0311] Step 9:

[0312] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[0313] Step 10:

[0314] The device displays notifications received from the server in its user interface. When the user clicks on a notification, a screen with more information will be displayed, usually in the form of a pop-up or an in-app banner.

[0315] Step 11:

[0316] When the user clicks on the notification, the device uses a natural language generation (NLG) algorithm to display a summary of the request, such as "Report request: Deadline next Friday."

[0317] Through these steps, the system combines an emotion engine and natural language processing technology to extract important tasks from emails and chats, and notify users at the appropriate time, taking into account their emotional state.

[0318] Example 2

[0319] 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."

[0320] Conventional task management systems do not take into account the user's emotional state when extracting and managing tasks from emails and chat messages, which can lead to stress for users and can lead to inappropriate task prioritization and reminder timing. Furthermore, the lack of flexible reminders and alert notifications that adapt to the user's emotional state reduces the efficiency of task management.

[0321] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0322] In this invention, the server includes a means for receiving emails and chat messages, a means for analyzing messages using a natural language processing algorithm to extract tasks, a means for determining the importance of the extracted tasks, and a means for notifying reminders and alerts based on the importance of the tasks and the user's emotional state. This makes it possible to provide timely and appropriate reminders of important tasks while taking into consideration the user's emotional state.

[0323] A "server" is a computer system that processes and manages information and transmits and receives data to and from clients over a network.

[0324] "Email" is a means of communication that is an electronic message sent and received over the Internet and can include text, images, files, etc.

[0325] A "chat message" is a message used to communicate text with others in real time, primarily used in chat applications and platforms.

[0326] "Natural language processing" refers to techniques and algorithms that enable computers to understand, interpret, and generate natural human language.

[0327] A "task" is a specific action or unit of behavior that must be performed to achieve a specific purpose.

[0328] "Importance" is an index that indicates how much priority a task should have compared to other tasks.

[0329] "Remind" refers to notifying the user again of a specific task or event to draw their attention.

[0330] An "alert" is a notification that indicates important information or a situation that requires attention, and prompts the user to take prompt action.

[0331] An "emotion engine" is an algorithm and technology that analyzes a user's emotions and moods to determine their stress level and emotional state.

[0332] "Interaction data" is data generated when a user interacts with a system or other people, and includes text messages and operation logs.

[0333] A "biosensor" is a device for measuring biological signals such as heart rate, body temperature, and brain waves.

[0334] A "database" is a system and structure for efficiently storing, managing, retrieving, and updating data.

[0335] "Natural language generation" refers to techniques and algorithms that allow computers to generate text in natural human languages.

[0336] The present invention provides a system for business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of the tasks while taking into account the user's emotional state. This system achieves this through multiple processing steps. A specific embodiment of the system is described below.

[0337] First, the server periodically connects to the mail server using the IMAP protocol to retrieve new emails. It also retrieves messages from chat rooms in chat applications (e.g., Slack) using REST APIs. The retrieved emails and chat messages are converted into text format and temporarily stored in a database for analysis.

[0338] The server then uses natural language processing (NLP) algorithms to analyze the retrieved messages. Specific libraries used include SpaCy and NLTK, which are used to extract keywords and phrases from the messages and identify those related to tasks. For example, from the message "Please review the attached document by Friday," the server extracts the keywords "review," "document," and "Friday" to identify the task "Review the attached document by Friday."

[0339] The identified tasks are stored in a database by the server. Items stored include the task ID, task content, requester, deadline, and importance. The importance of the task is also determined using a machine learning model (e.g., Scikit-learn or TensorFlow). This allows the priority of the task to be determined by referring to past data and information on similar tasks. For example, a task "review attached documents by Friday" is stored as "Importance 2 / 3."

[0340] The server then uses an emotion engine to analyze the user's emotional state. The data used for emotion recognition includes the user's past interaction data and data from biometric sensors. For example, recent chat messages can be analyzed to identify positive and negative expressions, and heart rate information from a wearable device can be received to determine the user's stress level.

[0341] Based on the user's emotional state and the importance of the task, the server adjusts the content and timing of reminders and alerts. Notifications can be sent via email, chat, a dedicated application, etc. For example, if the user is stressed, a soft-spoken notification will be sent saying, "A review is required by Friday. Please do it within reasonable limits."

[0342] The user's device displays the notification sent from the server in a user interface. When the user clicks on the notification, a summary of the request, generated by a natural language generation (NLG) algorithm, is displayed. This summary includes a concise summary of important information and deadlines. For example, when the user clicks on the notification, the summary "Request for attachment review: Deadline is Friday" is displayed.

[0343] An example of a prompt is as follows:

[0344] "How can we determine a user's stress level and emotional state by analyzing their past interaction data and data from wearable devices?"

[0345] Through these various processing steps, the system of the present invention automatically extracts, manages, and notifies important tasks while taking into account the user's emotional state, thereby realizing efficient task management for business people.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Step 1:

[0348] The server periodically connects to the mail server using the IMAP protocol to retrieve new emails, as well as new messages from the chat application using a REST API, which are converted to text format and temporarily stored in a database.

[0349] Input: New messages from mail servers and chat applications

[0350] Data processing: Use the protocol to obtain messages and convert them into text format

[0351] Output: Message in text format (save to database)

[0352] Specific behavior:

[0353] The server connects to "imap.gmail.com:993" and retrieves new emails using the IMAP protocol.

[0354] Use the Slack API to get the latest messages from the “project-update” chat room.

[0355] Step 2:

[0356] The server analyzes the received messages using natural language processing (NLP) algorithms (e.g., SpaCy, NLTK), extracting keywords and phrases from the messages and identifying whether they are relevant to the task.

[0357] Input: A plain text message

[0358] Data Computing: Extracting keywords and phrases using NLP algorithms

[0359] Output: Extracted task candidates

[0360] Specific behavior:

[0361] Extract the keywords "review," "document," and "Friday" from the message "Please review the attached document by Friday."

[0362] Use entity recognition to identify the task "Review attached documents by Friday."

[0363] Step 3:

[0364] The server stores the identified tasks in a database. The stored items include the task ID, task content, requester, deadline, importance, etc. The importance of the task is determined using a machine learning model (e.g., Scikit-learn, TensorFlow).

[0365] Input: Extracted task candidates

[0366] Data processing: Task information is stored in a database and importance is determined using a machine learning model.

[0367] Output: Task information stored in the database

[0368] Specific behavior:

[0369] The server stores the task "Review attachments by Friday" in the database with an importance of 2 / 3.

[0370] The machine learning model references past task data and determines importance based on trends in similar tasks.

[0371] Step 4:

[0372] The server uses an emotion engine to analyze the user's emotional state, utilizing data from the user's past interactions and biometric sensors to determine stress levels and mood.

[0373] Input: User's past interaction data, data from biometric sensors

[0374] Data Computation: Emotional State Analysis with Emotion Engine

[0375] Output: User's emotional state

[0376] Specific behavior:

[0377] The server analyzes recent chat messages and identifies positive and negative expressions.

[0378] Heart rate data is received from a wearable device to determine whether a person is in a high stress state.

[0379] Step 5:

[0380] Based on the emotional state and importance of the task, the system adjusts the content and timing of reminders and alerts. Notifications are sent via email, chat, or a dedicated app.

[0381] Input: Task importance, user emotional state

[0382] Data processing: Adjustment of notification content and timing of reminders and alerts

[0383] Output: Notification sent to the user

[0384] Specific behavior:

[0385] The server sends a soft-spoken notification saying, "Review required by Friday. Please do so within reason."

[0386] Step 6:

[0387] When the user clicks on the notification on their device, a screen summarizing the request is displayed using a natural language generation (NLG) algorithm.

[0388] Input: The notification the user clicked

[0389] Data Computing: Summary Generation with NLG Algorithms

[0390] Output: Summarized request details

[0391] Specific behavior:

[0392] When the user clicks on the notification, a popup will appear with the summary "Attachment Review Request: Due Friday."

[0393] (Application example 2)

[0394] 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."

[0395] Traditionally, task management in factories has often been done manually by managers, hindering efficient work progress. Furthermore, reminders and instructions are given without considering the emotional state of employees, which can lead to stress and reduced work efficiency. This invention aims to improve work efficiency in factories by automatically extracting tasks from emails and chat messages and providing reminders at appropriate times, taking into account the emotional state of employees.

[0396] 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.

[0397] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for analyzing the user's emotional state, and means for issuing reminders and alerts based on the task importance and the user's emotional state. This automates task organization and management, and further enables adjustment of the content and timing of reminders according to the employee's emotional state.

[0398] "Email or chat messages" refers to email or text messages sent or received over the Internet.

[0399] A "server" refers to a computer system that provides services to other computers over a network.

[0400] A "natural language processing algorithm" refers to an algorithm for analyzing and understanding the natural language used by humans on a daily basis.

[0401] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[0402] "Importance" refers to an indicator that evaluates the priority and urgency of a task.

[0403] "Emotional state" refers to the user's psychological and physiological state, including stress, mood, and the like.

[0404] "Reminders and alerts" refer to notifications or warnings that remind a user about a particular task or event.

[0405] "Database" refers to a collection of information in digital form organized so that the data can be efficiently searched, managed, and stored.

[0406] "Analysis" refers to the act of examining information or data in detail to understand its meaning and structure.

[0407] "Reminder timing" refers to the appropriate time to notify the person to re-recognize the task.

[0408] This invention is aimed at a task management system in a factory. Specifically, it extracts and manages important tasks from emails and chat messages, and effectively reminds employees by taking into account their emotional state.

[0409] Hardware Configuration

[0410] 1. Server: A high-performance computer system is required to connect to the mail server and chat server, retrieve messages, and analyze them. The server retrieves emails using the IMAP protocol and chat messages using a REST API.

[0411] 2. Devices: Employees need devices (computers, smartphones, etc.) that have a user interface for displaying reminders and notifications.

[0412] Software Configuration

[0413] 1. Natural Language Processing (NLP) algorithms: used to parse text messages and extract tasks (e.g., TextBlob).

[0414] 2. Emotion Engine: A machine learning model is required to analyze the user's emotional state, analyzing historical data and biometric sensor data.

[0415] 3. Database: A digital database is required to store task information and emotion recognition results (e.g., SQLite).

[0416] System Operation

[0417] 1. Server: Periodically connects to the mail server and chat server to retrieve new messages, convert them to text format, and save them. Analyzes the retrieved messages using a natural language processing algorithm and extracts tasks. Stores the tasks in a database and determines their importance. Analyzes the user's emotional state using an emotion engine.

[0418] 2. Terminal: Reminders and alerts sent from the server are displayed in the user interface. When the user clicks on the notification, detailed task information and a summary are displayed.

[0419] Specific examples

[0420] For example, a factory manager receives an email saying, "Please prepare the inspection report for Product A by Friday." This email is retrieved by the server, analyzed by a natural language processing algorithm, and tasks are extracted. The importance of the tasks is then evaluated and stored in a database. If the emotion engine analyzes the manager's emotional state and determines that the manager is "highly stressed," the manager is reminded in a soft tone with the message, "The deadline for preparing the inspection report for Product A is Friday. Please prepare it within your limits."

[0421] Prompt Sentence Examples

[0422] "Extract important tasks from emails and chat messages, prioritize them, and set deadlines. Also, take into account the user's emotional state to provide appropriate reminders."

[0423] In this way, the present invention provides a system that realizes efficient task management within a factory and reduces employee stress.

[0424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0425] Step 1:

[0426] The server periodically connects to the mail server or chat server to retrieve new messages. The input is unread messages from the mail server or chat server, and the output is messages converted to text format. Specifically, the server retrieves emails using the IMAP protocol and chat messages using a REST API.

[0427] Step 2:

[0428] The server analyzes the received messages using a natural language processing algorithm and extracts tasks. The input is the message converted into text format, and the output is a list of important keywords and phrases that become tasks. Specifically, the server scans the content of emails and chats, extracts keywords such as "review," "document," and "Friday," and identifies requests and action items.

[0429] Step 3:

[0430] The server determines the importance of the extracted tasks and stores them in a database. The inputs are task keywords, phrases, deadline information, etc., and the output is detailed task information stored in the database. Specifically, the server rates the task "Review attached documents by Friday" as "Importance 2 / 3" and stores information such as the task ID, requester, deadline, and importance in the database.

[0431] Step 4:

[0432] The server analyzes the user's emotional state using an emotion engine. The input is the user's past chat messages and biometric data from the wearable device, and the output is the user's emotional state. Specifically, the server analyzes the user's recent interactions and biometric data such as heart rate to determine whether the user is "feeling stressed."

[0433] Step 5:

[0434] The server adjusts the content and timing of reminders and alerts based on the task's importance and the user's emotional state. The input is the task's importance information and the user's emotional state, and the output is a customized reminder message. Specifically, the server generates a soft-toned notification to the user saying, "Review is required by Friday. Please complete it within reasonable limits."

[0435] Step 6:

[0436] The terminal displays the notification sent from the server on the user interface. The input is the reminder message sent from the server, and the output is a pop-up notification displayed to the user. Specifically, the terminal displays the reminder message in a pop-up format, and by clicking the notification, the user can see detailed information about the task.

[0437] Step 7:

[0438] When the user clicks on the notification, a natural language generation algorithm displays a screen summarizing the request. The input is the reminder message and detailed task information, and the output is summarized task information. Specifically, the summary "Request for attached document review: Deadline is Friday" is displayed on the screen, allowing the user to quickly understand the task details.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] [Second embodiment]

[0443] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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."

[0455] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. Below, we will explain the program processing of the system of the present invention in natural language, and also provide specific examples.

[0456] 1. Email / chat capture

[0457] server:

[0458] The server periodically connects to the mail or chat server to retrieve new messages. For example, for email, it scans the user's inbox using the IMAP protocol to retrieve unread messages. For chat, it retrieves new messages from a particular channel or thread.

[0459] Examples:

[0460] The server connects to the email server multiple times a day to retrieve new emails and convert them into text format.

[0461] The server periodically retrieves new messages from the chat server and stores them for analysis.

[0462] 2. Message Analysis

[0463] server:

[0464] The server then analyzes the messages using natural language processing (NLP) algorithms. This involves morphological analysis of the documents to extract keywords and phrases related to the request or task. It then identifies action items based on the extracted keywords.

[0465] Examples:

[0466] The server analyzes the message "Can you prepare the budget report by next Monday?" using an NLP algorithm and extracts the keywords "prepare," "budget report," and "next Monday."

[0467] This analysis identifies the task "Create a budget report by next Monday."

[0468] 3. Task Generation and Importance Determination

[0469] server:

[0470] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data and the importance of similar tasks, as well as deadlines and the requester's priorities.

[0471] Examples:

[0472] The server determines the identified task "Create a budget report by next Monday" as "Importance 2 / 3" and stores it in the database.

[0473] When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored.

[0474] 4. Notice to Users

[0475] server:

[0476] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[0477] Device:

[0478] The device displays the notification sent from the server on the user interface. When the user clicks on the notification, a screen showing detailed information is launched.

[0479] Examples:

[0480] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[0481] The device will receive this notification and display it to the user as a Slack notification.

[0482] 5. Request Summary Generation

[0483] Device:

[0484] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to summarize the request, including the request, deadline, and important information.

[0485] Examples:

[0486] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[0487] In this way, the system of the present invention provides a function to extract important tasks from emails and chats and notify users at the appropriate time, allowing business people to efficiently manage their tasks without missing any requests.

[0488] The processing flow will be explained below.

[0489] Step 1:

[0490] The server periodically connects to the mail server and chat server to retrieve new messages, for example, by logging in to the mail server using the IMAP protocol to search for unread emails, or by using a REST API to retrieve new messages from the chat application.

[0491] Step 2:

[0492] The server converts the received messages into text and analyzes them using natural language processing (NLP) algorithms. Morphological analysis is used to extract the words and phrases that make up the sentence and identify the parts that are relevant to requests or action items.

[0493] Step 3:

[0494] The server extracts task candidates from the parsed messages, generates task items including information such as the request content, deadline, and requester, and lists them. For example, it generates a task such as "Create a budget report by next Monday."

[0495] Step 4:

[0496] The server stores the generated tasks in a database. Each task contains information such as the task ID, task content, requester, deadline, and importance. Task management is based on this information.

[0497] Step 5:

[0498] The server uses a machine learning model to determine the importance of a task. It determines the priority of a task by referring to past data and information on similar tasks. For example, a task with a deadline of "by next Monday" may be determined to be high priority.

[0499] Step 6:

[0500] The server sets the timing of reminders and alerts based on the determined importance. High-priority tasks are notified early, and low-priority tasks are notified later. Notifications are sent according to the set reminder timing.

[0501] Step 7:

[0502] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[0503] Step 8:

[0504] The device displays the notification received from the server in the user interface, notifying the user in the form of a pop-up notification, an in-app banner, etc. The user can click the notification to display more information.

[0505] Step 9:

[0506] When a user clicks on a notification, the device uses a natural language generation (NLG) algorithm to display a screen summarizing the message content, such as a simple summary like "Budget report request: Deadline next Monday."

[0507] In this way, by linking the server, terminals, and users, a system is realized that efficiently extracts important tasks from emails and chats and notifies users at the appropriate time.

[0508] Example 1

[0509] 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."

[0510] In today's world, where people are often overwhelmed by a huge amount of information, it is extremely difficult for business people to efficiently extract and properly manage important tasks from emails and chat messages. Overlooking or forgetting important tasks not only reduces work efficiency, but also leads to problems such as missing important deadlines. There is a need for a solution to these problems and a way for business people to efficiently manage their tasks.

[0511] 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.

[0512] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for using a machine learning model to determine the importance of the extracted tasks, means for notifying a user terminal of a reminder or an alert based on the importance of the tasks, means for displaying detailed information on the terminal of the user who received the reminder or alert, and means for summarizing the detailed information using a natural language generation algorithm. This makes it possible to automatically extract important tasks from emails and chat messages and notify the user at the appropriate time.

[0513] A "server" is a computer system that sends, receives, and processes data over a network.

[0514] "Means for acquiring emails and chat messages" refers to a function that enables the server to connect to an email server or chat server and periodically acquire user messages.

[0515] A "natural language processing algorithm" is a computational method for analyzing text data, understanding grammar and meaning, and extracting information.

[0516] "Means for extracting tasks" refers to a function that uses natural language processing algorithms to identify task-related keywords and phrases from emails and chat messages and recognize them as tasks.

[0517] A "machine learning model" is an algorithm that learns patterns based on past data and makes predictions and classifications for new data.

[0518] The "means of using a machine learning model to determine the importance of a task" is a function that inputs the extracted task into a machine learning model and calculates and determines its importance.

[0519] A "terminal" is an information display device used by a user, such as a computer, smartphone, or tablet.

[0520] The "means for notifying reminders and alerts" is a function that sends reminder and alert messages to the user's terminal based on the importance of the task determined by the server.

[0521] The "means for displaying detailed information" is a function that displays the contents of reminders and alerts received by the user's terminal from the server.

[0522] A "natural language generation algorithm" is a computational method for generating sentences in natural language from text data.

[0523] "Means for summarizing detailed information using a natural language generation algorithm" refers to a function in which the user's device summarizes and displays the contents of reminders and alerts using a natural language generation algorithm.

[0524] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. A specific implementation method of the system will be described below.

[0525] System Overview

[0526] The system of the present invention is broadly composed of the following elements:

[0527] 1. How to retrieve emails and chat messages

[0528] 2. A way to analyze messages with natural language processing (NLP) algorithms

[0529] 3. Using machine learning models to determine the importance of extracted tasks

[0530] 4. A method for sending reminders and alerts to the user's device based on the determined importance of the task

[0531] 5. A way to display detailed information on the device of the user who received the reminder or alert.

[0532] 6. A method for summarizing the displayed details using a natural language generation (NLG) algorithm

[0533] These elements allow the system to efficiently manage tasks and prevent users from missing important tasks.

[0534] Get email / chat

[0535] server:

[0536] The server periodically connects to the mail server using the IMAP protocol to retrieve new or unread emails from the user's inbox, and also uses the API of a chat service, such as the Slack API, to access a specific chat channel to retrieve new messages.

[0537] Message Parsing

[0538] server:

[0539] The server analyzes the received messages using a natural language processing algorithm. Specifically, it performs morphological analysis to extract keywords and phrases related to requests and tasks from the messages. Action items are identified based on the extracted keywords.

[0540] Examples:

[0541] By analyzing the message "Can you prepare the budget report by next Monday?", the keywords "prepare," "budget report," and "next Monday" are extracted, and the task "prepare the budget report by next Monday" is identified.

[0542] Task generation and importance determination

[0543] server:

[0544] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, the importance of similar tasks, deadlines, and the requester's priority.

[0545] Examples:

[0546] The machine learning model determines that the task "Create a budget report by next Monday" is an "Importance Level 2 / 3," and the server stores this task in the database along with details such as the task ID, task content, requester, deadline, and importance.

[0547] User Notification

[0548] server:

[0549] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[0550] Device:

[0551] The device displays the notification sent from the server in the user interface, and when the user clicks on the notification, a screen appears displaying more information.

[0552] Examples:

[0553] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please create a budget report by next Monday." The device receives this notification and displays it to the user as a Slack notification. When the user clicks on the notification, detailed task information is displayed.

[0554] Generate a summary of the request

[0555] Device:

[0556] When the user clicks on the notification, the device displays a screen that uses a natural language generation algorithm to summarize the request, including the request, deadline, and important information.

[0557] Examples:

[0558] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[0559] Prompt Sentence Examples

[0560] "Please explain in natural language the steps required to design a system that extracts important tasks from new emails or chat messages and notifies the user via push notifications, along with specific examples."

[0561] This system allows business people to efficiently extract important tasks from emails and chat messages and receive notifications at the appropriate time, thereby improving work efficiency and preventing tasks from being overlooked.

[0562] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0563] Step 1: Get email / chat

[0564] server:

[0565] The server periodically connects to the mail server and chat server to retrieve new messages. Specifically, it logs in to the mail server using the IMAP protocol and scans the user's inbox for new emails. It also accesses specific chat channels using a provided API on the chat server to retrieve new messages.

[0566] input:

[0567] User's mail and chat server credentials

[0568] output:

[0569] New emails and new chat messages converted to plain text

[0570] Specific behavior:

[0571] The server uses the IMAP protocol to log into the email server and read the new, unread emails.

[0572] The server converts the email into text and converts it into a format that can be processed internally.

[0573] The server uses the Slack API to access a specific channel and retrieve any new messages that have not yet been processed.

[0574] Step 2: Message analysis

[0575] server:

[0576] The server then analyzes the messages using natural language processing (NLP) algorithms, morphologically analyzing the messages to identify key keywords and phrases, and extracting action items based on relevant keywords.

[0577] input:

[0578] New emails and new chat messages converted to plain text

[0579] output:

[0580] Extracted tasks and related keywords

[0581] Specific behavior:

[0582] The server uses NLP algorithms to parse the message: "Can you prepare the budget report by next Monday?"

[0583] The server performs morphological analysis and extracts the keywords "prepare," "budget report," and "next Monday."

[0584] Based on these keywords, the server identifies the action item "Create budget report by next Monday."

[0585] Step 3: Task generation and importance determination

[0586] server:

[0587] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, information about similar tasks, deadlines, and the requester's priority.

[0588] input:

[0589] Extracted tasks and related keywords

[0590] output:

[0591] Tasks with determined importance and detailed information

[0592] Specific behavior:

[0593] The server inputs the extracted task information into the machine learning model and calculates the importance.

[0594] As a result, a task "Create a budget report by next Monday" is generated, which is determined to have an importance of "2 / 3."

[0595] The server stores this task in a database, along with details such as the task ID, task content, requester, deadline, and importance.

[0596] Step 4: Notify users

[0597] server:

[0598] Based on the determined importance, the server pushes reminders and alerts to the user's device via email, chat, a dedicated app, or other means.

[0599] input:

[0600] Tasks with determined importance and detailed information

[0601] output:

[0602] Reminders and alerts sent to users' devices

[0603] Specific behavior:

[0604] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[0605] The device will receive this notification and display the notification content in the Slack interface.

[0606] Step 5: Generate a summary of the request

[0607] Device:

[0608] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to generate a summary of the request, including the request, deadline, and important keywords.

[0609] input:

[0610] Reminder and alert notification content

[0611] output:

[0612] Summarized action item details

[0613] Specific behavior:

[0614] When a user clicks on the Slack notification, a dedicated app is launched and a concise summary is generated and displayed using an NLG algorithm: "Budget report request: due next Monday."

[0615] (Application example 1)

[0616] 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."

[0617] In conventional factory environments, managing production lines and maintenance tasks is complex, and efficient operation requires a great deal of time and effort. In particular, when multiple tasks occur simultaneously, it is difficult to immediately identify and appropriately handle them, increasing the risk of reduced productivity and human error. To solve this problem, a system is needed that can automatically extract tasks, determine their importance, and provide real-time notifications in a unified manner.

[0618] 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.

[0619] In this invention, the server includes means for receiving emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for notifying the user of reminders and alerts based on the task importance, means for generating task summaries using a generative AI model, and means for displaying the reminders and alerts on the user's head-mounted display. This enables workers in a factory to check important tasks in real time without using their hands and respond efficiently.

[0620] A "server" is a device that stores, processes, and manages data on a network.

[0621] "Email and chat messages" are text data exchanged between users via email or instant messaging platforms.

[0622] A "natural language processing algorithm" is a computer program that analyzes human language and extracts information.

[0623] A "task" refers to an action or work requested of a user with a specific purpose and deadline.

[0624] "Importance" is an indicator of the priority and urgency of a task.

[0625] "Reminders and alerts" are notifications that inform the user of the existence, deadlines, and importance of tasks.

[0626] A "generative AI model" is an artificial intelligence algorithm that generates new information based on existing data.

[0627] The "task summary" is information that briefly summarizes the main points of the extracted task.

[0628] A "head-mounted display" is a display device that is worn on the user's head and provides visual information.

[0629] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications.

[0630] A system for implementing this invention is designed to combine multiple different technologies to streamline task management for factory robots. This system can extract tasks from emails and chat messages, determine their importance, and notify the user. Furthermore, it generates task summaries using a generative AI model and displays them on a head-mounted display.

[0631] 1. Email / chat capture

[0632] The server retrieves emails and chat messages sent from each department and automation system in the factory. Specifically, it connects to the mail server using the IMAP protocol and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels.

[0633] 2. Message Analysis

[0634] The server analyzes emails and chat messages using natural language processing (NLP) algorithms to extract task-related keywords and phrases from the messages and identify specific action items.

[0635] 3. Task Generation and Importance Determination

[0636] The server stores the extracted tasks in a database and uses a machine learning model to determine the importance of each task, which is trained based on past data and the importance of similar tasks, and also takes into account the deadline and the importance of the requester.

[0637] 4. Notice to Users

[0638] The server then sends notifications to the user's head-mounted display based on the determined task importance. This notification is sent in real time, allowing the user to check important tasks without using their hands.

[0639] 5. Request Summary Generation

[0640] Once the user confirms the notification, the server uses a generative AI model to generate a task summary and display it on the head-mounted display, including specific tasks, deadlines, and important information.

[0641] Hardware and software used

[0642] IMAP Server: A general mail server

[0643] Chat Server: Internal messaging system

[0644] Natural Language Processing: Python's NLTK library

[0645] Machine learning model: scikit-learn library

[0646] Push notifications: Pushbullet API

[0647] Head-mounted display: A visual information providing device worn by the user.

[0648] Specific examples

[0649] For example, suppose a message is sent via chat stating that "Part X on Machine A needs to be replaced" on a factory line. This message is captured by the server, and the keywords "replacement work," "machine A," and "part X" are extracted using natural language processing. After that, a machine learning model determines that this task is very important, and a notification is sent to the user's head-mounted display.

[0650] Prompt Sentence Examples

[0651] You have received a new factory task, "Replace part X on machine A," with high priority. Please provide details and priority for this task to your generative AI model.

[0652] In this way, the system of the present invention can efficiently manage important tasks within a factory in real time and provide users with the information they need immediately.

[0653] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0654] Step 1:

[0655] The server retrieves emails and chat messages sent from each department and automation system in the factory. The server uses the IMAP protocol to access the mail server and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels. The input is the text data of emails and chat messages, and the output is the retrieved raw messages.

[0656] Step 2:

[0657] The server analyzes the received emails and chat messages using natural language processing (NLP) algorithms. Specifically, it performs morphological analysis on the received text data and analyzes its grammatical structure to extract keywords and phrases related to the task. The input is the raw message text data, and the output is the extracted keywords and phrases.

[0658] Step 3:

[0659] The server identifies tasks based on the extracted keywords and phrases. The identified tasks are stored in a database. The database records detailed information for each task, such as the ID, content, requester, deadline, and importance. The input is the keywords and phrases obtained in step 2, and the output is the database record where the identified tasks are stored.

[0660] Step 4:

[0661] The server uses a machine learning model to determine the importance of the identified task. The model calculates the urgency and priority of the task based on past data and the importance of similar tasks. The input is the task details, and the output is the determined importance.

[0662] Step 5:

[0663] The server sends a notification to the user's head-mounted display based on the determined task importance. The notification is sent in real time using the Pushbullet API. The input is the determined importance and task information, and the output is the notification displayed on the user's device.

[0664] Step 6:

[0665] When a user receives a notification, the server uses a generative AI model to generate a task summary, including the specific work content, deadline, and important information, to confirm the task details. The input is the task information, and the output is the generated summary.

[0666] Step 7:

[0667] The user checks the summary through a head-mounted display and receives specific instructions and information for performing the corresponding task. The input is the generated summary, and the output is the summary information that the user checks.

[0668] This allows workers in the factory to check important tasks in real time without using their hands and respond efficiently.

[0669] 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.

[0670] The present invention is a system that allows business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of tasks while taking into account the user's emotional state. Below, we will explain the processing of the system's program for implementing the invention in natural language, and also provide specific examples.

[0671] 1. Email / chat capture

[0672] server:

[0673] The server periodically connects to the mail and chat servers to retrieve new messages, for example, emails using the IMAP protocol and chat messages using a REST API, which are converted to text format and stored for analysis.

[0674] Examples:

[0675] The server retrieves unread emails from the mail server every 10 minutes and saves them in text format.

[0676] The server uses the Slack API to retrieve new messages from the chat room.

[0677] 2. Message Analysis

[0678] server:

[0679] The server uses natural language processing (NLP) algorithms to analyze the messages received. It performs string analysis to extract keywords and phrases related to requests and action items. This analysis identifies candidate tasks.

[0680] Examples:

[0681] The server analyzes the email "Please review the attached document by Friday." and extracts the keywords "review," "document," and "Friday."

[0682] From the analysis results, the task "Review the attached documents by Friday" is identified.

[0683] 3. Task Generation and Importance Determination

[0684] server:

[0685] The identified tasks are stored in a database. When saved, information such as the task ID, task content, requester, deadline, and importance is included. Furthermore, the importance of the task is determined using a machine learning model. Priority is determined by referring to past data and information on similar tasks.

[0686] Examples:

[0687] The server determines that the task "Review attached documents by Friday" is "Importance 2 / 3" and stores it in the database.

[0688] The database stores detailed information about the task (e.g., requester, deadline, importance).

[0689] 4. Recognition of user emotions using an emotion engine

[0690] server:

[0691] The server uses an emotion engine to analyze the user's emotional state as they perform tasks. Emotion recognition uses data from the user's past interactions and data from biometric sensors to determine the user's stress level and mood.

[0692] Examples:

[0693] The server analyzes the user's recent chat messages and data from the wearable device to determine whether the user is "feeling stressed."

[0694] 5. User Notifications and Reminders

[0695] server:

[0696] The content and timing of reminders and alerts are adjusted based on the user's emotional state and the importance of the task. If the user is under stress, the system will take measures such as reducing the frequency of reminders. Notifications are sent via email, chat, a dedicated application, etc.

[0697] Device:

[0698] The device displays the notification sent from the server on the user interface, and the user can click on the notification to display detailed information.

[0699] Examples:

[0700] Because the user is stressed, the server sends a notification in a softer tone than usual saying, "Review required by Friday. Please do it within reasonable time."

[0701] The device will display this notification in the form of a pop-up.

[0702] 6. Request Summary Generation

[0703] Device:

[0704] When a user clicks on the notification, a natural language generation (NLG) algorithm is used to display a summary of the request, including key details and deadlines.

[0705] Examples:

[0706] When the user clicks on the notification, the summary "Attachment Review Request: Due Friday" appears.

[0707] In this way, the system of the present invention supports efficient task management by extracting important tasks from emails and chats while taking into account the user's emotional state using an emotion engine and notifying them at the appropriate time.

[0708] The processing flow will be explained below.

[0709] Step 1:

[0710] The server periodically connects to the mail server and chat server to retrieve new messages. For example, it logs in to the mail server using the IMAP protocol to retrieve unread emails. For the chat server, it uses the REST API to retrieve new messages from a specific chat room.

[0711] Step 2:

[0712] The server converts the received messages into text format and stores them in a pool for analysis, in order to convert them into a format that can be used in other processing steps.

[0713] Step 3:

[0714] The server analyzes the stored messages using natural language processing (NLP) algorithms. It performs morphological analysis to extract keywords and phrases related to requests and action items. For example, keywords such as "send," "create," and "deadline" are extracted.

[0715] Step 4:

[0716] The server then creates a list of candidate tasks based on the analysis results, including information such as the request content, deadline, and requester. For example, a task such as "Create a report by next Friday" may be identified.

[0717] Step 5:

[0718] The server saves the extracted tasks in a database. When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored. This allows tasks to be managed centrally.

[0719] Step 6:

[0720] The server uses machine learning models to determine the importance of a task. It uses past data and information from similar tasks to determine the priority of the task. For example, if a task has a specific deadline, it will be assigned a "high priority."

[0721] Step 7:

[0722] The server uses an emotion engine to analyze the emotional state of the user performing a task. Emotion recognition is based on past interaction data and data from biometric sensors. For example, it may determine that the user is in a stressful state.

[0723] Step 8:

[0724] The server adjusts the content and timing of reminders and alerts based on the user's emotional state and the importance of the task as determined by the emotion engine. For example, if the user is under stress, the server reduces the frequency of reminders and softens their content.

[0725] Step 9:

[0726] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[0727] Step 10:

[0728] The device displays notifications received from the server in its user interface. When the user clicks on a notification, a screen with more information will be displayed, usually in the form of a pop-up or an in-app banner.

[0729] Step 11:

[0730] When the user clicks on the notification, the device uses a natural language generation (NLG) algorithm to display a summary of the request, such as "Report request: Deadline next Friday."

[0731] Through these steps, the system combines an emotion engine and natural language processing technology to extract important tasks from emails and chats, and notify users at the appropriate time, taking into account their emotional state.

[0732] Example 2

[0733] 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."

[0734] Conventional task management systems do not take into account the user's emotional state when extracting and managing tasks from emails and chat messages, which can lead to stress for users and can lead to inappropriate task prioritization and reminder timing. Furthermore, the lack of flexible reminders and alert notifications that adapt to the user's emotional state reduces the efficiency of task management.

[0735] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0736] In this invention, the server includes a means for receiving emails and chat messages, a means for analyzing messages using a natural language processing algorithm to extract tasks, a means for determining the importance of the extracted tasks, and a means for notifying reminders and alerts based on the importance of the tasks and the user's emotional state. This makes it possible to provide timely and appropriate reminders of important tasks while taking into consideration the user's emotional state.

[0737] A "server" is a computer system that processes and manages information and transmits and receives data to and from clients over a network.

[0738] "Email" is a means of communication that is an electronic message sent and received over the Internet and can include text, images, files, etc.

[0739] A "chat message" is a message used to communicate text with others in real time, primarily used in chat applications and platforms.

[0740] "Natural language processing" refers to techniques and algorithms that enable computers to understand, interpret, and generate natural human language.

[0741] A "task" is a specific action or unit of behavior that must be performed to achieve a specific purpose.

[0742] "Importance" is an index that indicates how much priority a task should have compared to other tasks.

[0743] "Remind" refers to notifying the user again of a specific task or event to draw their attention.

[0744] An "alert" is a notification that indicates important information or a situation that requires attention, and prompts the user to take prompt action.

[0745] An "emotion engine" is an algorithm and technology that analyzes a user's emotions and moods to determine their stress level and emotional state.

[0746] "Interaction data" is data generated when a user interacts with a system or other people, and includes text messages and operation logs.

[0747] A "biosensor" is a device for measuring biological signals such as heart rate, body temperature, and brain waves.

[0748] A "database" is a system and structure for efficiently storing, managing, retrieving, and updating data.

[0749] "Natural language generation" refers to techniques and algorithms that allow computers to generate text in natural human languages.

[0750] The present invention provides a system for business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of the tasks while taking into account the user's emotional state. This system achieves this through multiple processing steps. A specific embodiment of the system is described below.

[0751] First, the server periodically connects to the mail server using the IMAP protocol to retrieve new emails. It also retrieves messages from chat rooms in chat applications (e.g., Slack) using REST APIs. The retrieved emails and chat messages are converted into text format and temporarily stored in a database for analysis.

[0752] The server then uses natural language processing (NLP) algorithms to analyze the retrieved messages. Specific libraries used include SpaCy and NLTK, which are used to extract keywords and phrases from the messages and identify those related to tasks. For example, from the message "Please review the attached document by Friday," the server extracts the keywords "review," "document," and "Friday" to identify the task "Review the attached document by Friday."

[0753] The identified tasks are stored in a database by the server. Items stored include the task ID, task content, requester, deadline, and importance. The importance of the task is also determined using a machine learning model (e.g., Scikit-learn or TensorFlow). This allows the priority of the task to be determined by referring to past data and information on similar tasks. For example, a task "review attached documents by Friday" is stored as "Importance 2 / 3."

[0754] The server then uses an emotion engine to analyze the user's emotional state. The data used for emotion recognition includes the user's past interaction data and data from biometric sensors. For example, recent chat messages can be analyzed to identify positive and negative expressions, and heart rate information from a wearable device can be received to determine the user's stress level.

[0755] Based on the user's emotional state and the importance of the task, the server adjusts the content and timing of reminders and alerts. Notifications can be sent via email, chat, a dedicated application, etc. For example, if the user is stressed, a soft-spoken notification will be sent saying, "A review is required by Friday. Please do it within reasonable limits."

[0756] The user's device displays the notification sent from the server in a user interface. When the user clicks on the notification, a summary of the request, generated by a natural language generation (NLG) algorithm, is displayed. This summary includes a concise summary of important information and deadlines. For example, when the user clicks on the notification, the summary "Request for attachment review: Deadline is Friday" is displayed.

[0757] An example of a prompt is as follows:

[0758] "How can we determine a user's stress level and emotional state by analyzing their past interaction data and data from wearable devices?"

[0759] Through these various processing steps, the system of the present invention automatically extracts, manages, and notifies important tasks while taking into account the user's emotional state, thereby realizing efficient task management for business people.

[0760] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0761] Step 1:

[0762] The server periodically connects to the mail server using the IMAP protocol to retrieve new emails, as well as new messages from the chat application using a REST API, which are converted to text format and temporarily stored in a database.

[0763] Input: New messages from mail servers and chat applications

[0764] Data processing: Use the protocol to obtain messages and convert them into text format

[0765] Output: Message in text format (save to database)

[0766] Specific behavior:

[0767] The server connects to "imap.gmail.com:993" and retrieves new emails using the IMAP protocol.

[0768] Use the Slack API to get the latest messages from the “project-update” chat room.

[0769] Step 2:

[0770] The server analyzes the received messages using natural language processing (NLP) algorithms (e.g., SpaCy, NLTK), extracting keywords and phrases from the messages and identifying whether they are relevant to the task.

[0771] Input: A plain text message

[0772] Data Computing: Extracting keywords and phrases using NLP algorithms

[0773] Output: Extracted task candidates

[0774] Specific behavior:

[0775] Extract the keywords "review," "document," and "Friday" from the message "Please review the attached document by Friday."

[0776] Use entity recognition to identify the task "Review attached documents by Friday."

[0777] Step 3:

[0778] The server stores the identified tasks in a database. The stored items include the task ID, task content, requester, deadline, importance, etc. The importance of the task is determined using a machine learning model (e.g., Scikit-learn, TensorFlow).

[0779] Input: Extracted task candidates

[0780] Data processing: Task information is stored in a database and importance is determined using a machine learning model.

[0781] Output: Task information stored in the database

[0782] Specific behavior:

[0783] The server stores the task "Review attachments by Friday" in the database with an importance of 2 / 3.

[0784] The machine learning model references past task data and determines importance based on trends in similar tasks.

[0785] Step 4:

[0786] The server uses an emotion engine to analyze the user's emotional state, utilizing data from the user's past interactions and biometric sensors to determine stress levels and mood.

[0787] Input: User's past interaction data, data from biometric sensors

[0788] Data Computation: Emotional State Analysis with Emotion Engine

[0789] Output: User's emotional state

[0790] Specific behavior:

[0791] The server analyzes recent chat messages and identifies positive and negative expressions.

[0792] Heart rate data is received from a wearable device to determine whether a person is in a high stress state.

[0793] Step 5:

[0794] Based on the emotional state and importance of the task, the system adjusts the content and timing of reminders and alerts. Notifications are sent via email, chat, or a dedicated app.

[0795] Input: Task importance, user emotional state

[0796] Data processing: Adjustment of notification content and timing of reminders and alerts

[0797] Output: Notification sent to the user

[0798] Specific behavior:

[0799] The server sends a soft-spoken notification saying, "Review required by Friday. Please do so within reason."

[0800] Step 6:

[0801] When the user clicks on the notification on their device, a screen summarizing the request is displayed using a natural language generation (NLG) algorithm.

[0802] Input: The notification the user clicked

[0803] Data Computing: Summary Generation with NLG Algorithms

[0804] Output: Summarized request details

[0805] Specific behavior:

[0806] When the user clicks on the notification, a popup will appear with the summary "Attachment Review Request: Due Friday."

[0807] (Application example 2)

[0808] 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."

[0809] Traditionally, task management in factories has often been done manually by managers, hindering efficient work progress. Furthermore, reminders and instructions are given without considering the emotional state of employees, which can lead to stress and reduced work efficiency. This invention aims to improve work efficiency in factories by automatically extracting tasks from emails and chat messages and providing reminders at appropriate times, taking into account the emotional state of employees.

[0810] 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.

[0811] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for analyzing the user's emotional state, and means for issuing reminders and alerts based on the task importance and the user's emotional state. This automates task organization and management, and further enables adjustment of the content and timing of reminders according to the employee's emotional state.

[0812] "Email or chat messages" refers to email or text messages sent or received over the Internet.

[0813] A "server" refers to a computer system that provides services to other computers over a network.

[0814] A "natural language processing algorithm" refers to an algorithm for analyzing and understanding the natural language used by humans on a daily basis.

[0815] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[0816] "Importance" refers to an indicator that evaluates the priority and urgency of a task.

[0817] "Emotional state" refers to the user's psychological and physiological state, including stress, mood, and the like.

[0818] "Reminders and alerts" refer to notifications or warnings that remind a user about a particular task or event.

[0819] "Database" refers to a collection of information in digital form organized so that the data can be efficiently searched, managed, and stored.

[0820] "Analysis" refers to the act of examining information or data in detail to understand its meaning and structure.

[0821] "Reminder timing" refers to the appropriate time to notify the person to re-recognize the task.

[0822] This invention is aimed at a task management system in a factory. Specifically, it extracts and manages important tasks from emails and chat messages, and effectively reminds employees by taking into account their emotional state.

[0823] Hardware Configuration

[0824] 1. Server: A high-performance computer system is required to connect to the mail server and chat server, retrieve messages, and analyze them. The server retrieves emails using the IMAP protocol and chat messages using a REST API.

[0825] 2. Devices: Employees need devices (computers, smartphones, etc.) that have a user interface for displaying reminders and notifications.

[0826] Software Configuration

[0827] 1. Natural Language Processing (NLP) algorithms: used to parse text messages and extract tasks (e.g., TextBlob).

[0828] 2. Emotion Engine: A machine learning model is required to analyze the user's emotional state, analyzing historical data and biometric sensor data.

[0829] 3. Database: A digital database is required to store task information and emotion recognition results (e.g., SQLite).

[0830] System Operation

[0831] 1. Server: Periodically connects to the mail server and chat server to retrieve new messages, convert them to text format, and save them. Analyzes the retrieved messages using a natural language processing algorithm and extracts tasks. Stores the tasks in a database and determines their importance. Analyzes the user's emotional state using an emotion engine.

[0832] 2. Terminal: Reminders and alerts sent from the server are displayed in the user interface. When the user clicks on the notification, detailed task information and a summary are displayed.

[0833] Specific examples

[0834] For example, a factory manager receives an email saying, "Please prepare the inspection report for Product A by Friday." This email is retrieved by the server, analyzed by a natural language processing algorithm, and tasks are extracted. The importance of the tasks is then evaluated and stored in a database. If the emotion engine analyzes the manager's emotional state and determines that the manager is "highly stressed," the manager is reminded in a soft tone with the message, "The deadline for preparing the inspection report for Product A is Friday. Please prepare it within your limits."

[0835] Prompt Sentence Examples

[0836] "Extract important tasks from emails and chat messages, prioritize them, and set deadlines. Also, take into account the user's emotional state to provide appropriate reminders."

[0837] In this way, the present invention provides a system that realizes efficient task management within a factory and reduces employee stress.

[0838] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0839] Step 1:

[0840] The server periodically connects to the mail server or chat server to retrieve new messages. The input is unread messages from the mail server or chat server, and the output is messages converted to text format. Specifically, the server retrieves emails using the IMAP protocol and chat messages using a REST API.

[0841] Step 2:

[0842] The server analyzes the received messages using a natural language processing algorithm and extracts tasks. The input is the message converted into text format, and the output is a list of important keywords and phrases that become tasks. Specifically, the server scans the content of emails and chats, extracts keywords such as "review," "document," and "Friday," and identifies requests and action items.

[0843] Step 3:

[0844] The server determines the importance of the extracted tasks and stores them in a database. The inputs are task keywords, phrases, deadline information, etc., and the output is detailed task information stored in the database. Specifically, the server rates the task "Review attached documents by Friday" as "Importance 2 / 3" and stores information such as the task ID, requester, deadline, and importance in the database.

[0845] Step 4:

[0846] The server analyzes the user's emotional state using an emotion engine. The input is the user's past chat messages and biometric data from the wearable device, and the output is the user's emotional state. Specifically, the server analyzes the user's recent interactions and biometric data such as heart rate to determine whether the user is "feeling stressed."

[0847] Step 5:

[0848] The server adjusts the content and timing of reminders and alerts based on the task's importance and the user's emotional state. The input is the task's importance information and the user's emotional state, and the output is a customized reminder message. Specifically, the server generates a soft-toned notification to the user saying, "Review is required by Friday. Please complete it within reasonable limits."

[0849] Step 6:

[0850] The terminal displays the notification sent from the server on the user interface. The input is the reminder message sent from the server, and the output is a pop-up notification displayed to the user. Specifically, the terminal displays the reminder message in a pop-up format, and by clicking the notification, the user can see detailed information about the task.

[0851] Step 7:

[0852] When the user clicks on the notification, a natural language generation algorithm displays a screen summarizing the request. The input is the reminder message and detailed task information, and the output is summarized task information. Specifically, the summary "Request for attached document review: Deadline is Friday" is displayed on the screen, allowing the user to quickly understand the task details.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] [Third embodiment]

[0857] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0858] 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.

[0859] 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).

[0860] 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.

[0861] 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.

[0862] 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).

[0863] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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."

[0869] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. Below, we will explain the program processing of the system of the present invention in natural language, and also provide specific examples.

[0870] 1. Email / chat capture

[0871] server:

[0872] The server periodically connects to the mail or chat server to retrieve new messages. For example, for email, it scans the user's inbox using the IMAP protocol to retrieve unread messages. For chat, it retrieves new messages from a particular channel or thread.

[0873] Examples:

[0874] The server connects to the email server multiple times a day to retrieve new emails and convert them into text format.

[0875] The server periodically retrieves new messages from the chat server and stores them for analysis.

[0876] 2. Message Analysis

[0877] server:

[0878] The server then analyzes the messages using natural language processing (NLP) algorithms. This involves morphological analysis of the documents to extract keywords and phrases related to the request or task. It then identifies action items based on the extracted keywords.

[0879] Examples:

[0880] The server analyzes the message "Can you prepare the budget report by next Monday?" using an NLP algorithm and extracts the keywords "prepare," "budget report," and "next Monday."

[0881] This analysis identifies the task "Create a budget report by next Monday."

[0882] 3. Task Generation and Importance Determination

[0883] server:

[0884] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data and the importance of similar tasks, as well as deadlines and the requester's priorities.

[0885] Examples:

[0886] The server determines the identified task "Create a budget report by next Monday" as "Importance 2 / 3" and stores it in the database.

[0887] When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored.

[0888] 4. Notice to Users

[0889] server:

[0890] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[0891] Device:

[0892] The device displays the notification sent from the server on the user interface. When the user clicks on the notification, a screen showing detailed information is launched.

[0893] Examples:

[0894] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[0895] The device will receive this notification and display it to the user as a Slack notification.

[0896] 5. Request Summary Generation

[0897] Device:

[0898] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to summarize the request, including the request, deadline, and important information.

[0899] Examples:

[0900] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[0901] In this way, the system of the present invention provides a function to extract important tasks from emails and chats and notify users at the appropriate time, allowing business people to efficiently manage their tasks without missing any requests.

[0902] The processing flow will be explained below.

[0903] Step 1:

[0904] The server periodically connects to the mail server and chat server to retrieve new messages, for example, by logging in to the mail server using the IMAP protocol to search for unread emails, or by using a REST API to retrieve new messages from the chat application.

[0905] Step 2:

[0906] The server converts the received messages into text and analyzes them using natural language processing (NLP) algorithms. Morphological analysis is used to extract the words and phrases that make up the sentence and identify the parts that are relevant to requests or action items.

[0907] Step 3:

[0908] The server extracts task candidates from the parsed messages, generates task items including information such as the request content, deadline, and requester, and lists them. For example, it generates a task such as "Create a budget report by next Monday."

[0909] Step 4:

[0910] The server stores the generated tasks in a database. Each task contains information such as the task ID, task content, requester, deadline, and importance. Task management is based on this information.

[0911] Step 5:

[0912] The server uses a machine learning model to determine the importance of a task. It determines the priority of a task by referring to past data and information on similar tasks. For example, a task with a deadline of "by next Monday" may be determined to be high priority.

[0913] Step 6:

[0914] The server sets the timing of reminders and alerts based on the determined importance. High-priority tasks are notified early, and low-priority tasks are notified later. Notifications are sent according to the set reminder timing.

[0915] Step 7:

[0916] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[0917] Step 8:

[0918] The device displays the notification received from the server in the user interface, notifying the user in the form of a pop-up notification, an in-app banner, etc. The user can click the notification to display more information.

[0919] Step 9:

[0920] When a user clicks on a notification, the device uses a natural language generation (NLG) algorithm to display a screen summarizing the message content, such as a simple summary like "Budget report request: Deadline next Monday."

[0921] In this way, by linking the server, terminals, and users, a system is realized that efficiently extracts important tasks from emails and chats and notifies users at the appropriate time.

[0922] Example 1

[0923] 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."

[0924] In today's world, where people are often overwhelmed by a huge amount of information, it is extremely difficult for business people to efficiently extract and properly manage important tasks from emails and chat messages. Overlooking or forgetting important tasks not only reduces work efficiency, but also leads to problems such as missing important deadlines. There is a need for a solution to these problems and a way for business people to efficiently manage their tasks.

[0925] 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.

[0926] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for using a machine learning model to determine the importance of the extracted tasks, means for notifying a user terminal of a reminder or an alert based on the importance of the tasks, means for displaying detailed information on the terminal of the user who received the reminder or alert, and means for summarizing the detailed information using a natural language generation algorithm. This makes it possible to automatically extract important tasks from emails and chat messages and notify the user at the appropriate time.

[0927] A "server" is a computer system that sends, receives, and processes data over a network.

[0928] "Means for acquiring emails and chat messages" refers to a function that enables the server to connect to an email server or chat server and periodically acquire user messages.

[0929] A "natural language processing algorithm" is a computational method for analyzing text data, understanding grammar and meaning, and extracting information.

[0930] "Means for extracting tasks" refers to a function that uses natural language processing algorithms to identify task-related keywords and phrases from emails and chat messages and recognize them as tasks.

[0931] A "machine learning model" is an algorithm that learns patterns based on past data and makes predictions and classifications for new data.

[0932] The "means of using a machine learning model to determine the importance of a task" is a function that inputs the extracted task into a machine learning model and calculates and determines its importance.

[0933] A "terminal" is an information display device used by a user, such as a computer, smartphone, or tablet.

[0934] The "means for notifying reminders and alerts" is a function that sends reminder and alert messages to the user's terminal based on the importance of the task determined by the server.

[0935] The "means for displaying detailed information" is a function that displays the contents of reminders and alerts received by the user's terminal from the server.

[0936] A "natural language generation algorithm" is a computational method for generating sentences in natural language from text data.

[0937] "Means for summarizing detailed information using a natural language generation algorithm" refers to a function in which the user's device summarizes and displays the contents of reminders and alerts using a natural language generation algorithm.

[0938] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. A specific implementation method of the system will be described below.

[0939] System Overview

[0940] The system of the present invention is broadly composed of the following elements:

[0941] 1. How to retrieve emails and chat messages

[0942] 2. A way to analyze messages with natural language processing (NLP) algorithms

[0943] 3. Using machine learning models to determine the importance of extracted tasks

[0944] 4. A method for sending reminders and alerts to the user's device based on the determined importance of the task

[0945] 5. A way to display detailed information on the device of the user who received the reminder or alert.

[0946] 6. A method for summarizing the displayed details using a natural language generation (NLG) algorithm

[0947] These elements allow the system to efficiently manage tasks and prevent users from missing important tasks.

[0948] Get email / chat

[0949] server:

[0950] The server periodically connects to the mail server using the IMAP protocol to retrieve new or unread emails from the user's inbox, and also uses the API of a chat service, such as the Slack API, to access a specific chat channel to retrieve new messages.

[0951] Message Parsing

[0952] server:

[0953] The server analyzes the received messages using a natural language processing algorithm. Specifically, it performs morphological analysis to extract keywords and phrases related to requests and tasks from the messages. Action items are identified based on the extracted keywords.

[0954] Examples:

[0955] By analyzing the message "Can you prepare the budget report by next Monday?", the keywords "prepare," "budget report," and "next Monday" are extracted, and the task "prepare the budget report by next Monday" is identified.

[0956] Task generation and importance determination

[0957] server:

[0958] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, the importance of similar tasks, deadlines, and the requester's priority.

[0959] Examples:

[0960] The machine learning model determines that the task "Create a budget report by next Monday" is an "Importance Level 2 / 3," and the server stores this task in the database along with details such as the task ID, task content, requester, deadline, and importance.

[0961] User Notification

[0962] server:

[0963] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[0964] Device:

[0965] The device displays the notification sent from the server in the user interface, and when the user clicks on the notification, a screen appears displaying more information.

[0966] Examples:

[0967] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please create a budget report by next Monday." The device receives this notification and displays it to the user as a Slack notification. When the user clicks on the notification, detailed task information is displayed.

[0968] Generate a summary of the request

[0969] Device:

[0970] When the user clicks on the notification, the device displays a screen that uses a natural language generation algorithm to summarize the request, including the request, deadline, and important information.

[0971] Examples:

[0972] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[0973] Prompt Sentence Examples

[0974] "Please explain in natural language the steps required to design a system that extracts important tasks from new emails or chat messages and notifies the user via push notifications, along with specific examples."

[0975] This system allows business people to efficiently extract important tasks from emails and chat messages and receive notifications at the appropriate time, thereby improving work efficiency and preventing tasks from being overlooked.

[0976] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0977] Step 1: Get email / chat

[0978] server:

[0979] The server periodically connects to the mail server and chat server to retrieve new messages. Specifically, it logs in to the mail server using the IMAP protocol and scans the user's inbox for new emails. It also accesses specific chat channels using a provided API on the chat server to retrieve new messages.

[0980] input:

[0981] User's mail and chat server credentials

[0982] output:

[0983] New emails and new chat messages converted to plain text

[0984] Specific behavior:

[0985] The server uses the IMAP protocol to log into the email server and read the new, unread emails.

[0986] The server converts the email into text and converts it into a format that can be processed internally.

[0987] The server uses the Slack API to access a specific channel and retrieve any new messages that have not yet been processed.

[0988] Step 2: Message analysis

[0989] server:

[0990] The server then analyzes the messages using natural language processing (NLP) algorithms, morphologically analyzing the messages to identify key keywords and phrases, and extracting action items based on relevant keywords.

[0991] input:

[0992] New emails and new chat messages converted to plain text

[0993] output:

[0994] Extracted tasks and related keywords

[0995] Specific behavior:

[0996] The server uses NLP algorithms to parse the message: "Can you prepare the budget report by next Monday?"

[0997] The server performs morphological analysis and extracts the keywords "prepare," "budget report," and "next Monday."

[0998] Based on these keywords, the server identifies the action item "Create budget report by next Monday."

[0999] Step 3: Task generation and importance determination

[1000] server:

[1001] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, information about similar tasks, deadlines, and the requester's priority.

[1002] input:

[1003] Extracted tasks and related keywords

[1004] output:

[1005] Tasks with determined importance and detailed information

[1006] Specific behavior:

[1007] The server inputs the extracted task information into the machine learning model and calculates the importance.

[1008] As a result, a task "Create a budget report by next Monday" is generated, which is determined to have an importance of "2 / 3."

[1009] The server stores this task in a database, along with details such as the task ID, task content, requester, deadline, and importance.

[1010] Step 4: Notify users

[1011] server:

[1012] Based on the determined importance, the server pushes reminders and alerts to the user's device via email, chat, a dedicated app, or other means.

[1013] input:

[1014] Tasks with determined importance and detailed information

[1015] output:

[1016] Reminders and alerts sent to users' devices

[1017] Specific behavior:

[1018] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[1019] The device will receive this notification and display the notification content in the Slack interface.

[1020] Step 5: Generate a summary of the request

[1021] Device:

[1022] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to generate a summary of the request, including the request, deadline, and important keywords.

[1023] input:

[1024] Reminder and alert notification content

[1025] output:

[1026] Summarized action item details

[1027] Specific behavior:

[1028] When a user clicks on the Slack notification, a dedicated app is launched and a concise summary is generated and displayed using an NLG algorithm: "Budget report request: due next Monday."

[1029] (Application example 1)

[1030] 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."

[1031] In conventional factory environments, managing production lines and maintenance tasks is complex, and efficient operation requires a great deal of time and effort. In particular, when multiple tasks occur simultaneously, it is difficult to immediately identify and appropriately handle them, increasing the risk of reduced productivity and human error. To solve this problem, a system is needed that can automatically extract tasks, determine their importance, and provide real-time notifications in a unified manner.

[1032] 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.

[1033] In this invention, the server includes means for receiving emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for notifying the user of reminders and alerts based on the task importance, means for generating task summaries using a generative AI model, and means for displaying the reminders and alerts on the user's head-mounted display. This enables workers in a factory to check important tasks in real time without using their hands and respond efficiently.

[1034] A "server" is a device that stores, processes, and manages data on a network.

[1035] "Email and chat messages" are text data exchanged between users via email or instant messaging platforms.

[1036] A "natural language processing algorithm" is a computer program that analyzes human language and extracts information.

[1037] A "task" refers to an action or work requested of a user with a specific purpose and deadline.

[1038] "Importance" is an indicator of the priority and urgency of a task.

[1039] "Reminders and alerts" are notifications that inform the user of the existence, deadlines, and importance of tasks.

[1040] A "generative AI model" is an artificial intelligence algorithm that generates new information based on existing data.

[1041] The "task summary" is information that briefly summarizes the main points of the extracted task.

[1042] A "head-mounted display" is a display device that is worn on the user's head and provides visual information.

[1043] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications.

[1044] A system for implementing this invention is designed to combine multiple different technologies to streamline task management for factory robots. This system can extract tasks from emails and chat messages, determine their importance, and notify the user. Furthermore, it generates task summaries using a generative AI model and displays them on a head-mounted display.

[1045] 1. Email / chat capture

[1046] The server retrieves emails and chat messages sent from each department and automation system in the factory. Specifically, it connects to the mail server using the IMAP protocol and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels.

[1047] 2. Message Analysis

[1048] The server analyzes emails and chat messages using natural language processing (NLP) algorithms to extract task-related keywords and phrases from the messages and identify specific action items.

[1049] 3. Task Generation and Importance Determination

[1050] The server stores the extracted tasks in a database and uses a machine learning model to determine the importance of each task, which is trained based on past data and the importance of similar tasks, and also takes into account the deadline and the importance of the requester.

[1051] 4. Notice to Users

[1052] The server then sends notifications to the user's head-mounted display based on the determined task importance. This notification is sent in real time, allowing the user to check important tasks without using their hands.

[1053] 5. Request Summary Generation

[1054] Once the user confirms the notification, the server uses a generative AI model to generate a task summary and display it on the head-mounted display, including specific tasks, deadlines, and important information.

[1055] Hardware and software used

[1056] IMAP Server: A general mail server

[1057] Chat Server: Internal messaging system

[1058] Natural Language Processing: Python's NLTK library

[1059] Machine learning model: scikit-learn library

[1060] Push notifications: Pushbullet API

[1061] Head-mounted display: A visual information providing device worn by the user.

[1062] Specific examples

[1063] For example, suppose a message is sent via chat stating that "Part X on Machine A needs to be replaced" on a factory line. This message is captured by the server, and the keywords "replacement work," "machine A," and "part X" are extracted using natural language processing. After that, a machine learning model determines that this task is very important, and a notification is sent to the user's head-mounted display.

[1064] Prompt Sentence Examples

[1065] You have received a new factory task, "Replace part X on machine A," with high priority. Please provide details and priority for this task to your generative AI model.

[1066] In this way, the system of the present invention can efficiently manage important tasks within a factory in real time and provide users with the information they need immediately.

[1067] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1068] Step 1:

[1069] The server retrieves emails and chat messages sent from each department and automation system in the factory. The server uses the IMAP protocol to access the mail server and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels. The input is the text data of emails and chat messages, and the output is the retrieved raw messages.

[1070] Step 2:

[1071] The server analyzes the received emails and chat messages using natural language processing (NLP) algorithms. Specifically, it performs morphological analysis on the received text data and analyzes its grammatical structure to extract keywords and phrases related to the task. The input is the raw message text data, and the output is the extracted keywords and phrases.

[1072] Step 3:

[1073] The server identifies tasks based on the extracted keywords and phrases. The identified tasks are stored in a database. The database records detailed information for each task, such as the ID, content, requester, deadline, and importance. The input is the keywords and phrases obtained in step 2, and the output is the database record where the identified tasks are stored.

[1074] Step 4:

[1075] The server uses a machine learning model to determine the importance of the identified task. The model calculates the urgency and priority of the task based on past data and the importance of similar tasks. The input is the task details, and the output is the determined importance.

[1076] Step 5:

[1077] The server sends a notification to the user's head-mounted display based on the determined task importance. The notification is sent in real time using the Pushbullet API. The input is the determined importance and task information, and the output is the notification displayed on the user's device.

[1078] Step 6:

[1079] When a user receives a notification, the server uses a generative AI model to generate a task summary, including the specific work content, deadline, and important information, to confirm the task details. The input is the task information, and the output is the generated summary.

[1080] Step 7:

[1081] The user checks the summary through a head-mounted display and receives specific instructions and information for performing the corresponding task. The input is the generated summary, and the output is the summary information that the user checks.

[1082] This allows workers in the factory to check important tasks in real time without using their hands and respond efficiently.

[1083] 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.

[1084] The present invention is a system that allows business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of tasks while taking into account the user's emotional state. Below, we will explain the processing of the system's program for implementing the invention in natural language, and also provide specific examples.

[1085] 1. Email / chat capture

[1086] server:

[1087] The server periodically connects to the mail and chat servers to retrieve new messages, for example, emails using the IMAP protocol and chat messages using a REST API, which are converted to text format and stored for analysis.

[1088] Examples:

[1089] The server retrieves unread emails from the mail server every 10 minutes and saves them in text format.

[1090] The server uses the Slack API to retrieve new messages from the chat room.

[1091] 2. Message Analysis

[1092] server:

[1093] The server uses natural language processing (NLP) algorithms to analyze the messages received. It performs string analysis to extract keywords and phrases related to requests and action items. This analysis identifies candidate tasks.

[1094] Examples:

[1095] The server analyzes the email "Please review the attached document by Friday." and extracts the keywords "review," "document," and "Friday."

[1096] From the analysis results, the task "Review the attached documents by Friday" is identified.

[1097] 3. Task Generation and Importance Determination

[1098] server:

[1099] The identified tasks are stored in a database. When saved, information such as the task ID, task content, requester, deadline, and importance is included. Furthermore, the importance of the task is determined using a machine learning model. Priority is determined by referring to past data and information on similar tasks.

[1100] Examples:

[1101] The server determines that the task "Review attached documents by Friday" is "Importance 2 / 3" and stores it in the database.

[1102] The database stores detailed information about the task (e.g., requester, deadline, importance).

[1103] 4. Recognition of user emotions using an emotion engine

[1104] server:

[1105] The server uses an emotion engine to analyze the user's emotional state as they perform tasks. Emotion recognition uses data from the user's past interactions and data from biometric sensors to determine the user's stress level and mood.

[1106] Examples:

[1107] The server analyzes the user's recent chat messages and data from the wearable device to determine whether the user is "feeling stressed."

[1108] 5. User Notifications and Reminders

[1109] server:

[1110] The content and timing of reminders and alerts are adjusted based on the user's emotional state and the importance of the task. If the user is under stress, the system will take measures such as reducing the frequency of reminders. Notifications are sent via email, chat, a dedicated application, etc.

[1111] Device:

[1112] The device displays the notification sent from the server on the user interface, and the user can click on the notification to display detailed information.

[1113] Examples:

[1114] Because the user is stressed, the server sends a notification in a softer tone than usual saying, "Review required by Friday. Please do it within reasonable time."

[1115] The device will display this notification in the form of a pop-up.

[1116] 6. Request Summary Generation

[1117] Device:

[1118] When a user clicks on the notification, a natural language generation (NLG) algorithm is used to display a summary of the request, including key details and deadlines.

[1119] Examples:

[1120] When the user clicks on the notification, the summary "Attachment Review Request: Due Friday" appears.

[1121] In this way, the system of the present invention supports efficient task management by extracting important tasks from emails and chats while taking into account the user's emotional state using an emotion engine and notifying them at the appropriate time.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] The server periodically connects to the mail server and chat server to retrieve new messages. For example, it logs in to the mail server using the IMAP protocol to retrieve unread emails. For the chat server, it uses the REST API to retrieve new messages from a specific chat room.

[1125] Step 2:

[1126] The server converts the received messages into text format and stores them in a pool for analysis, in order to convert them into a format that can be used in other processing steps.

[1127] Step 3:

[1128] The server analyzes the stored messages using natural language processing (NLP) algorithms. It performs morphological analysis to extract keywords and phrases related to requests and action items. For example, keywords such as "send," "create," and "deadline" are extracted.

[1129] Step 4:

[1130] The server then creates a list of candidate tasks based on the analysis results, including information such as the request content, deadline, and requester. For example, a task such as "Create a report by next Friday" may be identified.

[1131] Step 5:

[1132] The server saves the extracted tasks in a database. When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored. This allows tasks to be managed centrally.

[1133] Step 6:

[1134] The server uses machine learning models to determine the importance of a task. It uses past data and information from similar tasks to determine the priority of the task. For example, if a task has a specific deadline, it will be assigned a "high priority."

[1135] Step 7:

[1136] The server uses an emotion engine to analyze the emotional state of the user performing a task. Emotion recognition is based on past interaction data and data from biometric sensors. For example, it may determine that the user is in a stressful state.

[1137] Step 8:

[1138] The server adjusts the content and timing of reminders and alerts based on the user's emotional state and the importance of the task as determined by the emotion engine. For example, if the user is under stress, the server reduces the frequency of reminders and softens their content.

[1139] Step 9:

[1140] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[1141] Step 10:

[1142] The device displays notifications received from the server in its user interface. When the user clicks on a notification, a screen with more information will be displayed, usually in the form of a pop-up or an in-app banner.

[1143] Step 11:

[1144] When the user clicks on the notification, the device uses a natural language generation (NLG) algorithm to display a summary of the request, such as "Report request: Deadline next Friday."

[1145] Through these steps, the system combines an emotion engine and natural language processing technology to extract important tasks from emails and chats, and notify users at the appropriate time, taking into account their emotional state.

[1146] Example 2

[1147] 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."

[1148] Conventional task management systems do not take into account the user's emotional state when extracting and managing tasks from emails and chat messages, which can lead to stress for users and can lead to inappropriate task prioritization and reminder timing. Furthermore, the lack of flexible reminders and alert notifications that adapt to the user's emotional state reduces the efficiency of task management.

[1149] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1150] In this invention, the server includes a means for receiving emails and chat messages, a means for analyzing messages using a natural language processing algorithm to extract tasks, a means for determining the importance of the extracted tasks, and a means for notifying reminders and alerts based on the importance of the tasks and the user's emotional state. This makes it possible to provide timely and appropriate reminders of important tasks while taking into consideration the user's emotional state.

[1151] A "server" is a computer system that processes and manages information and transmits and receives data to and from clients over a network.

[1152] "Email" is a means of communication that is an electronic message sent and received over the Internet and can include text, images, files, etc.

[1153] A "chat message" is a message used to communicate text with others in real time, primarily used in chat applications and platforms.

[1154] "Natural language processing" refers to techniques and algorithms that enable computers to understand, interpret, and generate natural human language.

[1155] A "task" is a specific action or unit of behavior that must be performed to achieve a specific purpose.

[1156] "Importance" is an index that indicates how much priority a task should have compared to other tasks.

[1157] "Remind" refers to notifying the user again of a specific task or event to draw their attention.

[1158] An "alert" is a notification that indicates important information or a situation that requires attention, and prompts the user to take prompt action.

[1159] An "emotion engine" is an algorithm and technology that analyzes a user's emotions and moods to determine their stress level and emotional state.

[1160] "Interaction data" is data generated when a user interacts with a system or other people, and includes text messages and operation logs.

[1161] A "biosensor" is a device for measuring biological signals such as heart rate, body temperature, and brain waves.

[1162] A "database" is a system and structure for efficiently storing, managing, retrieving, and updating data.

[1163] "Natural language generation" refers to techniques and algorithms that allow computers to generate text in natural human languages.

[1164] The present invention provides a system for business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of the tasks while taking into account the user's emotional state. This system achieves this through multiple processing steps. A specific embodiment of the system is described below.

[1165] First, the server periodically connects to the mail server using the IMAP protocol to retrieve new emails. It also retrieves messages from chat rooms in chat applications (e.g., Slack) using REST APIs. The retrieved emails and chat messages are converted into text format and temporarily stored in a database for analysis.

[1166] The server then uses natural language processing (NLP) algorithms to analyze the retrieved messages. Specific libraries used include SpaCy and NLTK, which are used to extract keywords and phrases from the messages and identify those related to tasks. For example, from the message "Please review the attached document by Friday," the server extracts the keywords "review," "document," and "Friday" to identify the task "Review the attached document by Friday."

[1167] The identified tasks are stored in a database by the server. Items stored include the task ID, task content, requester, deadline, and importance. The importance of the task is also determined using a machine learning model (e.g., Scikit-learn or TensorFlow). This allows the priority of the task to be determined by referring to past data and information on similar tasks. For example, a task "review attached documents by Friday" is stored as "Importance 2 / 3."

[1168] The server then uses an emotion engine to analyze the user's emotional state. The data used for emotion recognition includes the user's past interaction data and data from biometric sensors. For example, recent chat messages can be analyzed to identify positive and negative expressions, and heart rate information from a wearable device can be received to determine the user's stress level.

[1169] Based on the user's emotional state and the importance of the task, the server adjusts the content and timing of reminders and alerts. Notifications can be sent via email, chat, a dedicated application, etc. For example, if the user is stressed, a soft-spoken notification will be sent saying, "A review is required by Friday. Please do it within reasonable limits."

[1170] The user's device displays the notification sent from the server in a user interface. When the user clicks on the notification, a summary of the request, generated by a natural language generation (NLG) algorithm, is displayed. This summary includes a concise summary of important information and deadlines. For example, when the user clicks on the notification, the summary "Request for attachment review: Deadline is Friday" is displayed.

[1171] An example of a prompt is as follows:

[1172] "How can we determine a user's stress level and emotional state by analyzing their past interaction data and data from wearable devices?"

[1173] Through these various processing steps, the system of the present invention automatically extracts, manages, and notifies important tasks while taking into account the user's emotional state, thereby realizing efficient task management for business people.

[1174] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1175] Step 1:

[1176] The server periodically connects to the mail server using the IMAP protocol to retrieve new emails, as well as new messages from the chat application using a REST API, which are converted to text format and temporarily stored in a database.

[1177] Input: New messages from mail servers and chat applications

[1178] Data processing: Use the protocol to obtain messages and convert them into text format

[1179] Output: Message in text format (save to database)

[1180] Specific behavior:

[1181] The server connects to "imap.gmail.com:993" and retrieves new emails using the IMAP protocol.

[1182] Use the Slack API to get the latest messages from the “project-update” chat room.

[1183] Step 2:

[1184] The server analyzes the received messages using natural language processing (NLP) algorithms (e.g., SpaCy, NLTK), extracting keywords and phrases from the messages and identifying whether they are relevant to the task.

[1185] Input: A plain text message

[1186] Data Computing: Extracting keywords and phrases using NLP algorithms

[1187] Output: Extracted task candidates

[1188] Specific behavior:

[1189] Extract the keywords "review," "document," and "Friday" from the message "Please review the attached document by Friday."

[1190] Use entity recognition to identify the task "Review attached documents by Friday."

[1191] Step 3:

[1192] The server stores the identified tasks in a database. The stored items include the task ID, task content, requester, deadline, importance, etc. The importance of the task is determined using a machine learning model (e.g., Scikit-learn, TensorFlow).

[1193] Input: Extracted task candidates

[1194] Data processing: Task information is stored in a database and importance is determined using a machine learning model.

[1195] Output: Task information stored in the database

[1196] Specific behavior:

[1197] The server stores the task "Review attachments by Friday" in the database with an importance of 2 / 3.

[1198] The machine learning model references past task data and determines importance based on trends in similar tasks.

[1199] Step 4:

[1200] The server uses an emotion engine to analyze the user's emotional state, utilizing data from the user's past interactions and biometric sensors to determine stress levels and mood.

[1201] Input: User's past interaction data, data from biometric sensors

[1202] Data Computation: Emotional State Analysis with Emotion Engine

[1203] Output: User's emotional state

[1204] Specific behavior:

[1205] The server analyzes recent chat messages and identifies positive and negative expressions.

[1206] Heart rate data is received from a wearable device to determine whether a person is in a high stress state.

[1207] Step 5:

[1208] Based on the emotional state and importance of the task, the system adjusts the content and timing of reminders and alerts. Notifications are sent via email, chat, or a dedicated app.

[1209] Input: Task importance, user emotional state

[1210] Data processing: Adjustment of notification content and timing of reminders and alerts

[1211] Output: Notification sent to the user

[1212] Specific behavior:

[1213] The server sends a soft-spoken notification saying, "Review required by Friday. Please do so within reason."

[1214] Step 6:

[1215] When the user clicks on the notification on their device, a screen summarizing the request is displayed using a natural language generation (NLG) algorithm.

[1216] Input: The notification the user clicked

[1217] Data Computing: Summary Generation with NLG Algorithms

[1218] Output: Summarized request details

[1219] Specific behavior:

[1220] When the user clicks on the notification, a popup will appear with the summary "Attachment Review Request: Due Friday."

[1221] (Application example 2)

[1222] 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."

[1223] Traditionally, task management in factories has often been done manually by managers, hindering efficient work progress. Furthermore, reminders and instructions are given without considering the emotional state of employees, which can lead to stress and reduced work efficiency. This invention aims to improve work efficiency in factories by automatically extracting tasks from emails and chat messages and providing reminders at appropriate times, taking into account the emotional state of employees.

[1224] 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.

[1225] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for analyzing the user's emotional state, and means for issuing reminders and alerts based on the task importance and the user's emotional state. This automates task organization and management, and further enables adjustment of the content and timing of reminders according to the employee's emotional state.

[1226] "Email or chat messages" refers to email or text messages sent or received over the Internet.

[1227] A "server" refers to a computer system that provides services to other computers over a network.

[1228] A "natural language processing algorithm" refers to an algorithm for analyzing and understanding the natural language used by humans on a daily basis.

[1229] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1230] "Importance" refers to an indicator that evaluates the priority and urgency of a task.

[1231] "Emotional state" refers to the user's psychological and physiological state, including stress, mood, and the like.

[1232] "Reminders and alerts" refer to notifications or warnings that remind a user about a particular task or event.

[1233] "Database" refers to a collection of information in digital form organized so that the data can be efficiently searched, managed, and stored.

[1234] "Analysis" refers to the act of examining information or data in detail to understand its meaning and structure.

[1235] "Reminder timing" refers to the appropriate time to notify the person to re-recognize the task.

[1236] This invention is aimed at a task management system in a factory. Specifically, it extracts and manages important tasks from emails and chat messages, and effectively reminds employees by taking into account their emotional state.

[1237] Hardware Configuration

[1238] 1. Server: A high-performance computer system is required to connect to the mail server and chat server, retrieve messages, and analyze them. The server retrieves emails using the IMAP protocol and chat messages using a REST API.

[1239] 2. Devices: Employees need devices (computers, smartphones, etc.) that have a user interface for displaying reminders and notifications.

[1240] Software Configuration

[1241] 1. Natural Language Processing (NLP) algorithms: used to parse text messages and extract tasks (e.g., TextBlob).

[1242] 2. Emotion Engine: A machine learning model is required to analyze the user's emotional state, analyzing historical data and biometric sensor data.

[1243] 3. Database: A digital database is required to store task information and emotion recognition results (e.g., SQLite).

[1244] System Operation

[1245] 1. Server: Periodically connects to the mail server and chat server to retrieve new messages, convert them to text format, and save them. Analyzes the retrieved messages using a natural language processing algorithm and extracts tasks. Stores the tasks in a database and determines their importance. Analyzes the user's emotional state using an emotion engine.

[1246] 2. Terminal: Reminders and alerts sent from the server are displayed in the user interface. When the user clicks on the notification, detailed task information and a summary are displayed.

[1247] Specific examples

[1248] For example, a factory manager receives an email saying, "Please prepare the inspection report for Product A by Friday." This email is retrieved by the server, analyzed by a natural language processing algorithm, and tasks are extracted. The importance of the tasks is then evaluated and stored in a database. If the emotion engine analyzes the manager's emotional state and determines that the manager is "highly stressed," the manager is reminded in a soft tone with the message, "The deadline for preparing the inspection report for Product A is Friday. Please prepare it within your limits."

[1249] Prompt Sentence Examples

[1250] "Extract important tasks from emails and chat messages, prioritize them, and set deadlines. Also, take into account the user's emotional state to provide appropriate reminders."

[1251] In this way, the present invention provides a system that realizes efficient task management within a factory and reduces employee stress.

[1252] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1253] Step 1:

[1254] The server periodically connects to the mail server or chat server to retrieve new messages. The input is unread messages from the mail server or chat server, and the output is messages converted to text format. Specifically, the server retrieves emails using the IMAP protocol and chat messages using a REST API.

[1255] Step 2:

[1256] The server analyzes the received messages using a natural language processing algorithm and extracts tasks. The input is the message converted into text format, and the output is a list of important keywords and phrases that become tasks. Specifically, the server scans the content of emails and chats, extracts keywords such as "review," "document," and "Friday," and identifies requests and action items.

[1257] Step 3:

[1258] The server determines the importance of the extracted tasks and stores them in a database. The inputs are task keywords, phrases, deadline information, etc., and the output is detailed task information stored in the database. Specifically, the server rates the task "Review attached documents by Friday" as "Importance 2 / 3" and stores information such as the task ID, requester, deadline, and importance in the database.

[1259] Step 4:

[1260] The server analyzes the user's emotional state using an emotion engine. The input is the user's past chat messages and biometric data from the wearable device, and the output is the user's emotional state. Specifically, the server analyzes the user's recent interactions and biometric data such as heart rate to determine whether the user is "feeling stressed."

[1261] Step 5:

[1262] The server adjusts the content and timing of reminders and alerts based on the task's importance and the user's emotional state. The input is the task's importance information and the user's emotional state, and the output is a customized reminder message. Specifically, the server generates a soft-toned notification to the user saying, "Review is required by Friday. Please complete it within reasonable limits."

[1263] Step 6:

[1264] The terminal displays the notification sent from the server on the user interface. The input is the reminder message sent from the server, and the output is a pop-up notification displayed to the user. Specifically, the terminal displays the reminder message in a pop-up format, and by clicking the notification, the user can see detailed information about the task.

[1265] Step 7:

[1266] When the user clicks on the notification, a natural language generation algorithm displays a screen summarizing the request. The input is the reminder message and detailed task information, and the output is summarized task information. Specifically, the summary "Request for attached document review: Deadline is Friday" is displayed on the screen, allowing the user to quickly understand the task details.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] [Fourth embodiment]

[1271] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1272] 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.

[1273] 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).

[1274] 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.

[1275] 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.

[1276] 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).

[1277] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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."

[1284] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. Below, we will explain the program processing of the system of the present invention in natural language, and also provide specific examples.

[1285] 1. Email / chat capture

[1286] server:

[1287] The server periodically connects to the mail or chat server to retrieve new messages. For example, for email, it scans the user's inbox using the IMAP protocol to retrieve unread messages. For chat, it retrieves new messages from a particular channel or thread.

[1288] Examples:

[1289] The server connects to the email server multiple times a day to retrieve new emails and convert them into text format.

[1290] The server periodically retrieves new messages from the chat server and stores them for analysis.

[1291] 2. Message Analysis

[1292] server:

[1293] The server then analyzes the messages using natural language processing (NLP) algorithms. This involves morphological analysis of the documents to extract keywords and phrases related to the request or task. It then identifies action items based on the extracted keywords.

[1294] Examples:

[1295] The server analyzes the message "Can you prepare the budget report by next Monday?" using an NLP algorithm and extracts the keywords "prepare," "budget report," and "next Monday."

[1296] This analysis identifies the task "Create a budget report by next Monday."

[1297] 3. Task Generation and Importance Determination

[1298] server:

[1299] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data and the importance of similar tasks, as well as deadlines and the requester's priorities.

[1300] Examples:

[1301] The server determines the identified task "Create a budget report by next Monday" as "Importance 2 / 3" and stores it in the database.

[1302] When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored.

[1303] 4. Notice to Users

[1304] server:

[1305] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[1306] Device:

[1307] The device displays the notification sent from the server on the user interface. When the user clicks on the notification, a screen showing detailed information is launched.

[1308] Examples:

[1309] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[1310] The device will receive this notification and display it to the user as a Slack notification.

[1311] 5. Request Summary Generation

[1312] Device:

[1313] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to summarize the request, including the request, deadline, and important information.

[1314] Examples:

[1315] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[1316] In this way, the system of the present invention provides a function to extract important tasks from emails and chats and notify users at the appropriate time, allowing business people to efficiently manage their tasks without missing any requests.

[1317] The processing flow will be explained below.

[1318] Step 1:

[1319] The server periodically connects to the mail server and chat server to retrieve new messages, for example, by logging in to the mail server using the IMAP protocol to search for unread emails, or by using a REST API to retrieve new messages from the chat application.

[1320] Step 2:

[1321] The server converts the received messages into text and analyzes them using natural language processing (NLP) algorithms. Morphological analysis is used to extract the words and phrases that make up the sentence and identify the parts that are relevant to requests or action items.

[1322] Step 3:

[1323] The server extracts task candidates from the parsed messages, generates task items including information such as the request content, deadline, and requester, and lists them. For example, it generates a task such as "Create a budget report by next Monday."

[1324] Step 4:

[1325] The server stores the generated tasks in a database. Each task contains information such as the task ID, task content, requester, deadline, and importance. Task management is based on this information.

[1326] Step 5:

[1327] The server uses a machine learning model to determine the importance of a task. It determines the priority of a task by referring to past data and information on similar tasks. For example, a task with a deadline of "by next Monday" may be determined to be high priority.

[1328] Step 6:

[1329] The server sets the timing of reminders and alerts based on the determined importance. High-priority tasks are notified early, and low-priority tasks are notified later. Notifications are sent according to the set reminder timing.

[1330] Step 7:

[1331] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[1332] Step 8:

[1333] The device displays the notification received from the server in the user interface, notifying the user in the form of a pop-up notification, an in-app banner, etc. The user can click the notification to display more information.

[1334] Step 9:

[1335] When a user clicks on a notification, the device uses a natural language generation (NLG) algorithm to display a screen summarizing the message content, such as a simple summary like "Budget report request: Deadline next Monday."

[1336] In this way, by linking the server, terminals, and users, a system is realized that efficiently extracts important tasks from emails and chats and notifies users at the appropriate time.

[1337] Example 1

[1338] 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."

[1339] In today's world, where people are often overwhelmed by a huge amount of information, it is extremely difficult for business people to efficiently extract and properly manage important tasks from emails and chat messages. Overlooking or forgetting important tasks not only reduces work efficiency, but also leads to problems such as missing important deadlines. There is a need for a solution to these problems and a way for business people to efficiently manage their tasks.

[1340] 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.

[1341] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for using a machine learning model to determine the importance of the extracted tasks, means for notifying a user terminal of a reminder or an alert based on the importance of the tasks, means for displaying detailed information on the terminal of the user who received the reminder or alert, and means for summarizing the detailed information using a natural language generation algorithm. This makes it possible to automatically extract important tasks from emails and chat messages and notify the user at the appropriate time.

[1342] A "server" is a computer system that sends, receives, and processes data over a network.

[1343] "Means for acquiring emails and chat messages" refers to a function that enables the server to connect to an email server or chat server and periodically acquire user messages.

[1344] A "natural language processing algorithm" is a computational method for analyzing text data, understanding grammar and meaning, and extracting information.

[1345] "Means for extracting tasks" refers to a function that uses natural language processing algorithms to identify task-related keywords and phrases from emails and chat messages and recognize them as tasks.

[1346] A "machine learning model" is an algorithm that learns patterns based on past data and makes predictions and classifications for new data.

[1347] The "means of using a machine learning model to determine the importance of a task" is a function that inputs the extracted task into a machine learning model and calculates and determines its importance.

[1348] A "terminal" is an information display device used by a user, such as a computer, smartphone, or tablet.

[1349] The "means for notifying reminders and alerts" is a function that sends reminder and alert messages to the user's terminal based on the importance of the task determined by the server.

[1350] The "means for displaying detailed information" is a function that displays the contents of reminders and alerts received by the user's terminal from the server.

[1351] A "natural language generation algorithm" is a computational method for generating sentences in natural language from text data.

[1352] "Means for summarizing detailed information using a natural language generation algorithm" refers to a function in which the user's device summarizes and displays the contents of reminders and alerts using a natural language generation algorithm.

[1353] The system of the present invention provides an efficient method for business people to extract important tasks from emails and chat messages and manage them appropriately. A specific implementation method of the system will be described below.

[1354] System Overview

[1355] The system of the present invention is broadly composed of the following elements:

[1356] 1. How to retrieve emails and chat messages

[1357] 2. A way to analyze messages with natural language processing (NLP) algorithms

[1358] 3. Using machine learning models to determine the importance of extracted tasks

[1359] 4. A method for sending reminders and alerts to the user's device based on the determined importance of the task

[1360] 5. A way to display detailed information on the device of the user who received the reminder or alert.

[1361] 6. A method for summarizing the displayed details using a natural language generation (NLG) algorithm

[1362] These elements allow the system to efficiently manage tasks and prevent users from missing important tasks.

[1363] Get email / chat

[1364] server:

[1365] The server periodically connects to the mail server using the IMAP protocol to retrieve new or unread emails from the user's inbox, and also uses the API of a chat service, such as the Slack API, to access a specific chat channel to retrieve new messages.

[1366] Message Parsing

[1367] server:

[1368] The server analyzes the received messages using a natural language processing algorithm. Specifically, it performs morphological analysis to extract keywords and phrases related to requests and tasks from the messages. Action items are identified based on the extracted keywords.

[1369] Examples:

[1370] By analyzing the message "Can you prepare the budget report by next Monday?", the keywords "prepare," "budget report," and "next Monday" are extracted, and the task "prepare the budget report by next Monday" is identified.

[1371] Task generation and importance determination

[1372] server:

[1373] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, the importance of similar tasks, deadlines, and the requester's priority.

[1374] Examples:

[1375] The machine learning model determines that the task "Create a budget report by next Monday" is an "Importance Level 2 / 3," and the server stores this task in the database along with details such as the task ID, task content, requester, deadline, and importance.

[1376] User Notification

[1377] server:

[1378] Based on the determined importance, the server will push reminders and alerts to the user's device via email, chat, a dedicated app, etc.

[1379] Device:

[1380] The device displays the notification sent from the server in the user interface, and when the user clicks on the notification, a screen appears displaying more information.

[1381] Examples:

[1382] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please create a budget report by next Monday." The device receives this notification and displays it to the user as a Slack notification. When the user clicks on the notification, detailed task information is displayed.

[1383] Generate a summary of the request

[1384] Device:

[1385] When the user clicks on the notification, the device displays a screen that uses a natural language generation algorithm to summarize the request, including the request, deadline, and important information.

[1386] Examples:

[1387] When a user clicks on the Slack notification, a dedicated app launches and displays a brief summary: "Budget report request: due next Monday."

[1388] Prompt Sentence Examples

[1389] "Please explain in natural language the steps required to design a system that extracts important tasks from new emails or chat messages and notifies the user via push notifications, along with specific examples."

[1390] This system allows business people to efficiently extract important tasks from emails and chat messages and receive notifications at the appropriate time, thereby improving work efficiency and preventing tasks from being overlooked.

[1391] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1392] Step 1: Get email / chat

[1393] server:

[1394] The server periodically connects to the mail server and chat server to retrieve new messages. Specifically, it logs in to the mail server using the IMAP protocol and scans the user's inbox for new emails. It also accesses specific chat channels using a provided API on the chat server to retrieve new messages.

[1395] input:

[1396] User's mail and chat server credentials

[1397] output:

[1398] New emails and new chat messages converted to plain text

[1399] Specific behavior:

[1400] The server uses the IMAP protocol to log into the email server and read the new, unread emails.

[1401] The server converts the email into text and converts it into a format that can be processed internally.

[1402] The server uses the Slack API to access a specific channel and retrieve any new messages that have not yet been processed.

[1403] Step 2: Message analysis

[1404] server:

[1405] The server then analyzes the messages using natural language processing (NLP) algorithms, morphologically analyzing the messages to identify key keywords and phrases, and extracting action items based on relevant keywords.

[1406] input:

[1407] New emails and new chat messages converted to plain text

[1408] output:

[1409] Extracted tasks and related keywords

[1410] Specific behavior:

[1411] The server uses NLP algorithms to parse the message: "Can you prepare the budget report by next Monday?"

[1412] The server performs morphological analysis and extracts the keywords "prepare," "budget report," and "next Monday."

[1413] Based on these keywords, the server identifies the action item "Create budget report by next Monday."

[1414] Step 3: Task generation and importance determination

[1415] server:

[1416] The server stores the identified tasks in a database and uses machine learning models to determine the importance of each task, taking into account past data, information about similar tasks, deadlines, and the requester's priority.

[1417] input:

[1418] Extracted tasks and related keywords

[1419] output:

[1420] Tasks with determined importance and detailed information

[1421] Specific behavior:

[1422] The server inputs the extracted task information into the machine learning model and calculates the importance.

[1423] As a result, a task "Create a budget report by next Monday" is generated, which is determined to have an importance of "2 / 3."

[1424] The server stores this task in a database, along with details such as the task ID, task content, requester, deadline, and importance.

[1425] Step 4: Notify users

[1426] server:

[1427] Based on the determined importance, the server pushes reminders and alerts to the user's device via email, chat, a dedicated app, or other means.

[1428] input:

[1429] Tasks with determined importance and detailed information

[1430] output:

[1431] Reminders and alerts sent to users' devices

[1432] Specific behavior:

[1433] The server uses the Slack API to send a notification to the user's Slack channel saying, "Please submit your budget report by next Monday."

[1434] The device will receive this notification and display the notification content in the Slack interface.

[1435] Step 5: Generate a summary of the request

[1436] Device:

[1437] When the user clicks on the notification, the device displays a screen that uses a natural language generation (NLG) algorithm to generate a summary of the request, including the request, deadline, and important keywords.

[1438] input:

[1439] Reminder and alert notification content

[1440] output:

[1441] Summarized action item details

[1442] Specific behavior:

[1443] When a user clicks on the Slack notification, a dedicated app is launched and a concise summary is generated and displayed using an NLG algorithm: "Budget report request: due next Monday."

[1444] (Application example 1)

[1445] 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."

[1446] In conventional factory environments, managing production lines and maintenance tasks is complex, and efficient operation requires a great deal of time and effort. In particular, when multiple tasks occur simultaneously, it is difficult to immediately identify and appropriately handle them, increasing the risk of reduced productivity and human error. To solve this problem, a system is needed that can automatically extract tasks, determine their importance, and provide real-time notifications in a unified manner.

[1447] 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.

[1448] In this invention, the server includes means for receiving emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for notifying the user of reminders and alerts based on the task importance, means for generating task summaries using a generative AI model, and means for displaying the reminders and alerts on the user's head-mounted display. This enables workers in a factory to check important tasks in real time without using their hands and respond efficiently.

[1449] A "server" is a device that stores, processes, and manages data on a network.

[1450] "Email and chat messages" are text data exchanged between users via email or instant messaging platforms.

[1451] A "natural language processing algorithm" is a computer program that analyzes human language and extracts information.

[1452] A "task" refers to an action or work requested of a user with a specific purpose and deadline.

[1453] "Importance" is an indicator of the priority and urgency of a task.

[1454] "Reminders and alerts" are notifications that inform the user of the existence, deadlines, and importance of tasks.

[1455] A "generative AI model" is an artificial intelligence algorithm that generates new information based on existing data.

[1456] The "task summary" is information that briefly summarizes the main points of the extracted task.

[1457] A "head-mounted display" is a display device that is worn on the user's head and provides visual information.

[1458] A "machine learning model" is an algorithm that learns from past data and makes predictions and classifications.

[1459] A system for implementing this invention is designed to combine multiple different technologies to streamline task management for factory robots. This system can extract tasks from emails and chat messages, determine their importance, and notify the user. Furthermore, it generates task summaries using a generative AI model and displays them on a head-mounted display.

[1460] 1. Email / chat capture

[1461] The server retrieves emails and chat messages sent from each department and automation system in the factory. Specifically, it connects to the mail server using the IMAP protocol and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels.

[1462] 2. Message Analysis

[1463] The server analyzes emails and chat messages using natural language processing (NLP) algorithms to extract task-related keywords and phrases from the messages and identify specific action items.

[1464] 3. Task Generation and Importance Determination

[1465] The server stores the extracted tasks in a database and uses a machine learning model to determine the importance of each task, which is trained based on past data and the importance of similar tasks, and also takes into account the deadline and the importance of the requester.

[1466] 4. Notice to Users

[1467] The server then sends notifications to the user's head-mounted display based on the determined task importance. This notification is sent in real time, allowing the user to check important tasks without using their hands.

[1468] 5. Request Summary Generation

[1469] Once the user confirms the notification, the server uses a generative AI model to generate a task summary and display it on the head-mounted display, including specific tasks, deadlines, and important information.

[1470] Hardware and software used

[1471] IMAP Server: A general mail server

[1472] Chat Server: Internal messaging system

[1473] Natural Language Processing: Python's NLTK library

[1474] Machine learning model: scikit-learn library

[1475] Push notifications: Pushbullet API

[1476] Head-mounted display: A visual information providing device worn by the user.

[1477] Specific examples

[1478] For example, suppose a message is sent via chat stating that "Part X on Machine A needs to be replaced" on a factory line. This message is captured by the server, and the keywords "replacement work," "machine A," and "part X" are extracted using natural language processing. After that, a machine learning model determines that this task is very important, and a notification is sent to the user's head-mounted display.

[1479] Prompt Sentence Examples

[1480] You have received a new factory task, "Replace part X on machine A," with high priority. Please provide details and priority for this task to your generative AI model.

[1481] In this way, the system of the present invention can efficiently manage important tasks within a factory in real time and provide users with the information they need immediately.

[1482] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1483] Step 1:

[1484] The server retrieves emails and chat messages sent from each department and automation system in the factory. The server uses the IMAP protocol to access the mail server and periodically retrieves unread emails. It also works with the chat server to retrieve new messages from specific channels. The input is the text data of emails and chat messages, and the output is the retrieved raw messages.

[1485] Step 2:

[1486] The server analyzes the received emails and chat messages using natural language processing (NLP) algorithms. Specifically, it performs morphological analysis on the received text data and analyzes its grammatical structure to extract keywords and phrases related to the task. The input is the raw message text data, and the output is the extracted keywords and phrases.

[1487] Step 3:

[1488] The server identifies tasks based on the extracted keywords and phrases. The identified tasks are stored in a database. The database records detailed information for each task, such as the ID, content, requester, deadline, and importance. The input is the keywords and phrases obtained in step 2, and the output is the database record where the identified tasks are stored.

[1489] Step 4:

[1490] The server uses a machine learning model to determine the importance of the identified task. The model calculates the urgency and priority of the task based on past data and the importance of similar tasks. The input is the task details, and the output is the determined importance.

[1491] Step 5:

[1492] The server sends a notification to the user's head-mounted display based on the determined task importance. The notification is sent in real time using the Pushbullet API. The input is the determined importance and task information, and the output is the notification displayed on the user's device.

[1493] Step 6:

[1494] When a user receives a notification, the server uses a generative AI model to generate a task summary, including the specific work content, deadline, and important information, to confirm the task details. The input is the task information, and the output is the generated summary.

[1495] Step 7:

[1496] The user checks the summary through a head-mounted display and receives specific instructions and information for performing the corresponding task. The input is the generated summary, and the output is the summary information that the user checks.

[1497] This allows workers in the factory to check important tasks in real time without using their hands and respond efficiently.

[1498] 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.

[1499] The present invention is a system that allows business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of tasks while taking into account the user's emotional state. Below, we will explain the processing of the system's program for implementing the invention in natural language, and also provide specific examples.

[1500] 1. Email / chat capture

[1501] server:

[1502] The server periodically connects to the mail and chat servers to retrieve new messages, for example, emails using the IMAP protocol and chat messages using a REST API, which are converted to text format and stored for analysis.

[1503] Examples:

[1504] The server retrieves unread emails from the mail server every 10 minutes and saves them in text format.

[1505] The server uses the Slack API to retrieve new messages from the chat room.

[1506] 2. Message Analysis

[1507] server:

[1508] The server uses natural language processing (NLP) algorithms to analyze the messages received. It performs string analysis to extract keywords and phrases related to requests and action items. This analysis identifies candidate tasks.

[1509] Examples:

[1510] The server analyzes the email "Please review the attached document by Friday." and extracts the keywords "review," "document," and "Friday."

[1511] From the analysis results, the task "Review the attached documents by Friday" is identified.

[1512] 3. Task Generation and Importance Determination

[1513] server:

[1514] The identified tasks are stored in a database. When saved, information such as the task ID, task content, requester, deadline, and importance is included. Furthermore, the importance of the task is determined using a machine learning model. Priority is determined by referring to past data and information on similar tasks.

[1515] Examples:

[1516] The server determines that the task "Review attached documents by Friday" is "Importance 2 / 3" and stores it in the database.

[1517] The database stores detailed information about the task (e.g., requester, deadline, importance).

[1518] 4. Recognition of user emotions using an emotion engine

[1519] server:

[1520] The server uses an emotion engine to analyze the user's emotional state as they perform tasks. Emotion recognition uses data from the user's past interactions and data from biometric sensors to determine the user's stress level and mood.

[1521] Examples:

[1522] The server analyzes the user's recent chat messages and data from the wearable device to determine whether the user is "feeling stressed."

[1523] 5. User Notifications and Reminders

[1524] server:

[1525] The content and timing of reminders and alerts are adjusted based on the user's emotional state and the importance of the task. If the user is under stress, the system will take measures such as reducing the frequency of reminders. Notifications are sent via email, chat, a dedicated application, etc.

[1526] Device:

[1527] The device displays the notification sent from the server on the user interface, and the user can click on the notification to display detailed information.

[1528] Examples:

[1529] Because the user is stressed, the server sends a notification in a softer tone than usual saying, "Review required by Friday. Please do it within reasonable time."

[1530] The device will display this notification in the form of a pop-up.

[1531] 6. Request Summary Generation

[1532] Device:

[1533] When a user clicks on the notification, a natural language generation (NLG) algorithm is used to display a summary of the request, including key details and deadlines.

[1534] Examples:

[1535] When the user clicks on the notification, the summary "Attachment Review Request: Due Friday" appears.

[1536] In this way, the system of the present invention supports efficient task management by extracting important tasks from emails and chats while taking into account the user's emotional state using an emotion engine and notifying them at the appropriate time.

[1537] The processing flow will be explained below.

[1538] Step 1:

[1539] The server periodically connects to the mail server and chat server to retrieve new messages. For example, it logs in to the mail server using the IMAP protocol to retrieve unread emails. For the chat server, it uses the REST API to retrieve new messages from a specific chat room.

[1540] Step 2:

[1541] The server converts the received messages into text format and stores them in a pool for analysis, in order to convert them into a format that can be used in other processing steps.

[1542] Step 3:

[1543] The server analyzes the stored messages using natural language processing (NLP) algorithms. It performs morphological analysis to extract keywords and phrases related to requests and action items. For example, keywords such as "send," "create," and "deadline" are extracted.

[1544] Step 4:

[1545] The server then creates a list of candidate tasks based on the analysis results, including information such as the request content, deadline, and requester. For example, a task such as "Create a report by next Friday" may be identified.

[1546] Step 5:

[1547] The server saves the extracted tasks in a database. When saving, detailed information such as the task ID, task content, requester, deadline, and importance is also stored. This allows tasks to be managed centrally.

[1548] Step 6:

[1549] The server uses machine learning models to determine the importance of a task. It uses past data and information from similar tasks to determine the priority of the task. For example, if a task has a specific deadline, it will be assigned a "high priority."

[1550] Step 7:

[1551] The server uses an emotion engine to analyze the emotional state of the user performing a task. Emotion recognition is based on past interaction data and data from biometric sensors. For example, it may determine that the user is in a stressful state.

[1552] Step 8:

[1553] The server adjusts the content and timing of reminders and alerts based on the user's emotional state and the importance of the task as determined by the emotion engine. For example, if the user is under stress, the server reduces the frequency of reminders and softens their content.

[1554] Step 9:

[1555] The server pushes reminders and alerts to the user's device via email, chat, a dedicated application, etc. For example, it uses the Slack API to send notifications to the user's Slack channel.

[1556] Step 10:

[1557] The device displays notifications received from the server in its user interface. When the user clicks on a notification, a screen with more information will be displayed, usually in the form of a pop-up or an in-app banner.

[1558] Step 11:

[1559] When the user clicks on the notification, the device uses a natural language generation (NLG) algorithm to display a summary of the request, such as "Report request: Deadline next Friday."

[1560] Through these steps, the system combines an emotion engine and natural language processing technology to extract important tasks from emails and chats, and notify users at the appropriate time, taking into account their emotional state.

[1561] Example 2

[1562] 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."

[1563] Conventional task management systems do not take into account the user's emotional state when extracting and managing tasks from emails and chat messages, which can lead to stress for users and can lead to inappropriate task prioritization and reminder timing. Furthermore, the lack of flexible reminders and alert notifications that adapt to the user's emotional state reduces the efficiency of task management.

[1564] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1565] In this invention, the server includes a means for receiving emails and chat messages, a means for analyzing messages using a natural language processing algorithm to extract tasks, a means for determining the importance of the extracted tasks, and a means for notifying reminders and alerts based on the importance of the tasks and the user's emotional state. This makes it possible to provide timely and appropriate reminders of important tasks while taking into consideration the user's emotional state.

[1566] A "server" is a computer system that processes and manages information and transmits and receives data to and from clients over a network.

[1567] "Email" is a means of communication that is an electronic message sent and received over the Internet and can include text, images, files, etc.

[1568] A "chat message" is a message used to communicate text with others in real time, primarily used in chat applications and platforms.

[1569] "Natural language processing" refers to techniques and algorithms that enable computers to understand, interpret, and generate natural human language.

[1570] A "task" is a specific action or unit of behavior that must be performed to achieve a specific purpose.

[1571] "Importance" is an index that indicates how much priority a task should have compared to other tasks.

[1572] "Remind" refers to notifying the user again of a specific task or event to draw their attention.

[1573] An "alert" is a notification that indicates important information or a situation that requires attention, and prompts the user to take prompt action.

[1574] An "emotion engine" is an algorithm and technology that analyzes a user's emotions and moods to determine their stress level and emotional state.

[1575] "Interaction data" is data generated when a user interacts with a system or other people, and includes text messages and operation logs.

[1576] A "biosensor" is a device for measuring biological signals such as heart rate, body temperature, and brain waves.

[1577] A "database" is a system and structure for efficiently storing, managing, retrieving, and updating data.

[1578] "Natural language generation" refers to techniques and algorithms that allow computers to generate text in natural human languages.

[1579] The present invention provides a system for business people to extract important tasks from emails and chat messages, manage them appropriately, and effectively remind them of the tasks while taking into account the user's emotional state. This system achieves this through multiple processing steps. A specific embodiment of the system is described below.

[1580] First, the server periodically connects to the mail server using the IMAP protocol to retrieve new emails. It also retrieves messages from chat rooms in chat applications (e.g., Slack) using REST APIs. The retrieved emails and chat messages are converted into text format and temporarily stored in a database for analysis.

[1581] The server then uses natural language processing (NLP) algorithms to analyze the retrieved messages. Specific libraries used include SpaCy and NLTK, which are used to extract keywords and phrases from the messages and identify those related to tasks. For example, from the message "Please review the attached document by Friday," the server extracts the keywords "review," "document," and "Friday" to identify the task "Review the attached document by Friday."

[1582] The identified tasks are stored in a database by the server. Items stored include the task ID, task content, requester, deadline, and importance. The importance of the task is also determined using a machine learning model (e.g., Scikit-learn or TensorFlow). This allows the priority of the task to be determined by referring to past data and information on similar tasks. For example, a task "review attached documents by Friday" is stored as "Importance 2 / 3."

[1583] The server then uses an emotion engine to analyze the user's emotional state. The data used for emotion recognition includes the user's past interaction data and data from biometric sensors. For example, recent chat messages can be analyzed to identify positive and negative expressions, and heart rate information from a wearable device can be received to determine the user's stress level.

[1584] Based on the user's emotional state and the importance of the task, the server adjusts the content and timing of reminders and alerts. Notifications can be sent via email, chat, a dedicated application, etc. For example, if the user is stressed, a soft-spoken notification will be sent saying, "A review is required by Friday. Please do it within reasonable limits."

[1585] The user's device displays the notification sent from the server in a user interface. When the user clicks on the notification, a summary of the request, generated by a natural language generation (NLG) algorithm, is displayed. This summary includes a concise summary of important information and deadlines. For example, when the user clicks on the notification, the summary "Request for attachment review: Deadline is Friday" is displayed.

[1586] An example of a prompt is as follows:

[1587] "How can we determine a user's stress level and emotional state by analyzing their past interaction data and data from wearable devices?"

[1588] Through these various processing steps, the system of the present invention automatically extracts, manages, and notifies important tasks while taking into account the user's emotional state, thereby realizing efficient task management for business people.

[1589] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1590] Step 1:

[1591] The server periodically connects to the mail server using the IMAP protocol to retrieve new emails, as well as new messages from the chat application using a REST API, which are converted to text format and temporarily stored in a database.

[1592] Input: New messages from mail servers and chat applications

[1593] Data processing: Use the protocol to obtain messages and convert them into text format

[1594] Output: Message in text format (save to database)

[1595] Specific behavior:

[1596] The server connects to "imap.gmail.com:993" and retrieves new emails using the IMAP protocol.

[1597] Use the Slack API to get the latest messages from the “project-update” chat room.

[1598] Step 2:

[1599] The server analyzes the received messages using natural language processing (NLP) algorithms (e.g., SpaCy, NLTK), extracting keywords and phrases from the messages and identifying whether they are relevant to the task.

[1600] Input: A plain text message

[1601] Data Computing: Extracting keywords and phrases using NLP algorithms

[1602] Output: Extracted task candidates

[1603] Specific behavior:

[1604] Extract the keywords "review," "document," and "Friday" from the message "Please review the attached document by Friday."

[1605] Use entity recognition to identify the task "Review attached documents by Friday."

[1606] Step 3:

[1607] The server stores the identified tasks in a database. The stored items include the task ID, task content, requester, deadline, importance, etc. The importance of the task is determined using a machine learning model (e.g., Scikit-learn, TensorFlow).

[1608] Input: Extracted task candidates

[1609] Data processing: Task information is stored in a database and importance is determined using a machine learning model.

[1610] Output: Task information stored in the database

[1611] Specific behavior:

[1612] The server stores the task "Review attachments by Friday" in the database with an importance of 2 / 3.

[1613] The machine learning model references past task data and determines importance based on trends in similar tasks.

[1614] Step 4:

[1615] The server uses an emotion engine to analyze the user's emotional state, utilizing data from the user's past interactions and biometric sensors to determine stress levels and mood.

[1616] Input: User's past interaction data, data from biometric sensors

[1617] Data Computation: Emotional State Analysis with Emotion Engine

[1618] Output: User's emotional state

[1619] Specific behavior:

[1620] The server analyzes recent chat messages and identifies positive and negative expressions.

[1621] Heart rate data is received from a wearable device to determine whether a person is in a high stress state.

[1622] Step 5:

[1623] Based on the emotional state and importance of the task, the system adjusts the content and timing of reminders and alerts. Notifications are sent via email, chat, or a dedicated app.

[1624] Input: Task importance, user emotional state

[1625] Data processing: Adjustment of notification content and timing of reminders and alerts

[1626] Output: Notification sent to the user

[1627] Specific behavior:

[1628] The server sends a soft-spoken notification saying, "Review required by Friday. Please do so within reason."

[1629] Step 6:

[1630] When the user clicks on the notification on their device, a screen summarizing the request is displayed using a natural language generation (NLG) algorithm.

[1631] Input: The notification the user clicked

[1632] Data Computing: Summary Generation with NLG Algorithms

[1633] Output: Summarized request details

[1634] Specific behavior:

[1635] When the user clicks on the notification, a popup will appear with the summary "Attachment Review Request: Due Friday."

[1636] (Application example 2)

[1637] 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."

[1638] Traditionally, task management in factories has often been done manually by managers, hindering efficient work progress. Furthermore, reminders and instructions are given without considering the emotional state of employees, which can lead to stress and reduced work efficiency. This invention aims to improve work efficiency in factories by automatically extracting tasks from emails and chat messages and providing reminders at appropriate times, taking into account the emotional state of employees.

[1639] 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.

[1640] In this invention, the server includes means for acquiring emails and chat messages, means for analyzing the messages using a natural language processing algorithm to extract tasks, means for determining the importance of the extracted tasks, means for analyzing the user's emotional state, and means for issuing reminders and alerts based on the task importance and the user's emotional state. This automates task organization and management, and further enables adjustment of the content and timing of reminders according to the employee's emotional state.

[1641] "Email or chat messages" refers to email or text messages sent or received over the Internet.

[1642] A "server" refers to a computer system that provides services to other computers over a network.

[1643] A "natural language processing algorithm" refers to an algorithm for analyzing and understanding the natural language used by humans on a daily basis.

[1644] A "task" refers to the work or activity that must be performed to achieve a specific goal.

[1645] "Importance" refers to an indicator that evaluates the priority and urgency of a task.

[1646] "Emotional state" refers to the user's psychological and physiological state, including stress, mood, and the like.

[1647] "Reminders and alerts" refer to notifications or warnings that remind a user about a particular task or event.

[1648] "Database" refers to a collection of information in digital form organized so that the data can be efficiently searched, managed, and stored.

[1649] "Analysis" refers to the act of examining information or data in detail to understand its meaning and structure.

[1650] "Reminder timing" refers to the appropriate time to notify the person to re-recognize the task.

[1651] This invention is aimed at a task management system in a factory. Specifically, it extracts and manages important tasks from emails and chat messages, and effectively reminds employees by taking into account their emotional state.

[1652] Hardware Configuration

[1653] 1. Server: A high-performance computer system is required to connect to the mail server and chat server, retrieve messages, and analyze them. The server retrieves emails using the IMAP protocol and chat messages using a REST API.

[1654] 2. Devices: Employees need devices (computers, smartphones, etc.) that have a user interface for displaying reminders and notifications.

[1655] Software Configuration

[1656] 1. Natural Language Processing (NLP) algorithms: used to parse text messages and extract tasks (e.g., TextBlob).

[1657] 2. Emotion Engine: A machine learning model is required to analyze the user's emotional state, analyzing historical data and biometric sensor data.

[1658] 3. Database: A digital database is required to store task information and emotion recognition results (e.g., SQLite).

[1659] System Operation

[1660] 1. Server: Periodically connects to the mail server and chat server to retrieve new messages, convert them to text format, and save them. Analyzes the retrieved messages using a natural language processing algorithm and extracts tasks. Stores the tasks in a database and determines their importance. Analyzes the user's emotional state using an emotion engine.

[1661] 2. Terminal: Reminders and alerts sent from the server are displayed in the user interface. When the user clicks on the notification, detailed task information and a summary are displayed.

[1662] Specific examples

[1663] For example, a factory manager receives an email saying, "Please prepare the inspection report for Product A by Friday." This email is retrieved by the server, analyzed by a natural language processing algorithm, and tasks are extracted. The importance of the tasks is then evaluated and stored in a database. If the emotion engine analyzes the manager's emotional state and determines that the manager is "highly stressed," the manager is reminded in a soft tone with the message, "The deadline for preparing the inspection report for Product A is Friday. Please prepare it within your limits."

[1664] Prompt Sentence Examples

[1665] "Extract important tasks from emails and chat messages, prioritize them, and set deadlines. Also, take into account the user's emotional state to provide appropriate reminders."

[1666] In this way, the present invention provides a system that realizes efficient task management within a factory and reduces employee stress.

[1667] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1668] Step 1:

[1669] The server periodically connects to the mail server or chat server to retrieve new messages. The input is unread messages from the mail server or chat server, and the output is messages converted to text format. Specifically, the server retrieves emails using the IMAP protocol and chat messages using a REST API.

[1670] Step 2:

[1671] The server analyzes the received messages using a natural language processing algorithm and extracts tasks. The input is the message converted into text format, and the output is a list of important keywords and phrases that become tasks. Specifically, the server scans the content of emails and chats, extracts keywords such as "review," "document," and "Friday," and identifies requests and action items.

[1672] Step 3:

[1673] The server determines the importance of the extracted tasks and stores them in a database. The inputs are task keywords, phrases, deadline information, etc., and the output is detailed task information stored in the database. Specifically, the server rates the task "Review attached documents by Friday" as "Importance 2 / 3" and stores information such as the task ID, requester, deadline, and importance in the database.

[1674] Step 4:

[1675] The server analyzes the user's emotional state using an emotion engine. The input is the user's past chat messages and biometric data from the wearable device, and the output is the user's emotional state. Specifically, the server analyzes the user's recent interactions and biometric data such as heart rate to determine whether the user is "feeling stressed."

[1676] Step 5:

[1677] The server adjusts the content and timing of reminders and alerts based on the task's importance and the user's emotional state. The input is the task's importance information and the user's emotional state, and the output is a customized reminder message. Specifically, the server generates a soft-toned notification to the user saying, "Review is required by Friday. Please complete it within reasonable limits."

[1678] Step 6:

[1679] The terminal displays the notification sent from the server on the user interface. The input is the reminder message sent from the server, and the output is a pop-up notification displayed to the user. Specifically, the terminal displays the reminder message in a pop-up format, and by clicking the notification, the user can see detailed information about the task.

[1680] Step 7:

[1681] When the user clicks on the notification, a natural language generation algorithm displays a screen summarizing the request. The input is the reminder message and detailed task information, and the output is summarized task information. Specifically, the summary "Request for attached document review: Deadline is Friday" is displayed on the screen, allowing the user to quickly understand the task details.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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).

[1689] 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.

[1690] 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."

[1691] 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.

[1692] 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).

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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.

[1699] 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.

[1700] 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.

[1701] 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.

[1702] 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.

[1703] The following is further disclosed regarding the above embodiment.

[1704] (Claim 1)

[1705] A way to retrieve emails and chat messages on the server,

[1706] means for analyzing the message using a natural language processing algorithm to extract a task;

[1707] A means for determining the importance of the extracted tasks;

[1708] means for notifying a user of reminders or alerts based on the importance of the tasks;

[1709] A system including:

[1710] (Claim 2)

[1711] means for storing the contents of the task in a database on a server;

[1712] The system of claim 1 further comprising:

[1713] (Claim 3)

[1714] means for analyzing deadline information associated with the extracted tasks;

[1715] a means for setting a timing of a reminder based on the deadline information;

[1716] The system of claim 1 further comprising:

[1717] (Claim 4)

[1718] 2. The system of claim 1, wherein the server includes means for determining the importance of a task using a machine learning model.

[1719] (Claim 5)

[1720] 2. The system according to claim 1, wherein the means for notifying the user includes notification via email, chat, or a dedicated app.

[1721] (Claim 6)

[1722] 10. The system of claim 1, wherein the notification means includes means for displaying the notification in a user interface.

[1723] (Claim 7)

[1724] 2. The system according to claim 1, further comprising means for summarizing the content of the task using a natural language generation algorithm.

[1725] "Example 1"

[1726] (Claim 1)

[1727] A way to retrieve emails and chat messages on the server,

[1728] means for analyzing the message using a natural language processing algorithm to extract a task;

[1729] a means for using a machine learning model to determine the importance of the extracted tasks;

[1730] means for notifying a user of a reminder or an alert based on the importance of the task;

[1731] A means for displaying detailed information on the device of the user who received the reminder or alert;

[1732] means for summarizing the detailed information using a natural language generation algorithm;

[1733] A system including:

[1734] (Claim 2)

[1735] means for storing the contents of the task in a database on a server;

[1736] The system of claim 1 further comprising:

[1737] (Claim 3)

[1738] means for analyzing deadline information associated with the extracted tasks;

[1739] a means for setting a timing of a reminder based on the deadline information;

[1740] The system of claim 1 further comprising:

[1741] "Application Example 1"

[1742] (Claim 1)

[1743] A way to retrieve emails and chat messages on the server,

[1744] means for analyzing the message using a natural language processing algorithm to extract a task;

[1745] A means for determining the importance of the extracted tasks;

[1746] means for notifying a user of reminders or alerts based on the importance of the tasks;

[1747] a means for generating a task summary using a generative AI model;

[1748] means for displaying said reminders and alerts on a user's head mounted display;

[1749] A system including:

[1750] (Claim 2)

[1751] means for storing the contents of the task in a database on a server;

[1752] a means for determining task importance using a machine learning model;

[1753] The system of claim 1 further comprising:

[1754] (Claim 3)

[1755] means for analyzing deadline information associated with the extracted tasks;

[1756] a means for setting a timing of a reminder based on the deadline information;

[1757] means for generating a prompt sentence using the generative AI model;

[1758] The system of claim 1 further comprising:

[1759] "Example 2: Combining Emotion Engines"

[1760] (Claim 1)

[1761] A way to retrieve emails and chat messages on the server,

[1762] means for analyzing the message using a natural language processing algorithm to extract a task;

[1763] A means for determining the importance of the extracted tasks;

[1764] means for notifying reminders and alerts based on the importance of the task and the user's emotional state;

[1765] A system including:

[1766] (Claim 2)

[1767] means for storing the contents of the task in a database on a server;

[1768] The system of claim 1 further comprising:

[1769] (Claim 3)

[1770] means for analyzing deadline information associated with the extracted tasks;

[1771] a means for setting a timing of a reminder based on the deadline information;

[1772] a means for analyzing the user's past interaction data and data from biometric sensors using an emotion engine to determine the user's emotional state;

[1773] The system of claim 1 further comprising:

[1774] "Application example 2 when combining emotion engines"

[1775] (Claim 1)

[1776] A way to retrieve emails and chat messages on the server,

[1777] means for analyzing the message using a natural language processing algorithm to extract a task;

[1778] A means for determining the importance of the extracted tasks;

[1779] means for analyzing the emotional state of a user;

[1780] a means for providing reminders and alerts based on the importance of the task and the user's emotional state;

[1781] A system including:

[1782] (Claim 2)

[1783] means for storing the contents of the task in a database on a server;

[1784] a means for storing emotion recognition results in a database;

[1785] The system of claim 1 further comprising:

[1786] (Claim 3)

[1787] means for analyzing deadline information associated with the extracted tasks;

[1788] a means for setting a timing of a reminder based on the deadline information;

[1789] means for adjusting the content of the reminder based on said emotional state;

[1790] The system of claim 1 further comprising: [Explanation of symbols]

[1791] 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 way to retrieve emails and chat messages on the server, means for analyzing the message using a natural language processing algorithm to extract a task; A means for determining the importance of the extracted tasks; means for notifying a user of reminders or alerts based on the importance of the tasks; A system including:

2. means for storing the contents of the task in a database on a server; The system of claim 1 further comprising:

3. means for analyzing deadline information associated with the extracted tasks; a means for setting a timing of a reminder based on the deadline information; The system of claim 1 further comprising:

4. The system of claim 1 , wherein the server includes means for determining the importance of a task using a machine learning model.

5. The system according to claim 1 , wherein the means for notifying the user includes notification via email, chat, or a dedicated app.

6. The system of claim 1 , wherein the notification means includes means for displaying the notification in a user interface.

7. 2. The system according to claim 1, further comprising means for summarizing the content of the task using a natural language generation algorithm.

Images