system

Abstract

To provide a system.SOLUTION: A system includes: means for collecting messages received via a plurality of different communication means, including at least two of emails, communication tools, chats, and messenger applications; means for centralizing the collected messages by converting the collected messages into a common data format; means for storing the centralized messages in a database in association with identification information indicating the type of communication means.SELECTED DRAWING: Figure 1

Description

[[Technical Field]]

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

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction associated with a description about a character of a chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance. [[Prior Art Literature]] [[Patent Literature]]

[0003] [[Patent Document 1]] Japanese Unexamined Patent Application Publication No. 2022-180282 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] Currently, since contact tools are divided into a plurality of types, it is difficult to grasp which tool has received a contact at which place. In addition, it is difficult to determine whether a message is work-related or private, and convert it into a task for management accordingly. [[Means for Solving the Problem]]

[0005] The present invention provides means for centrally displaying messages from a plurality of contact tools, means for classifying whether a message is related to work or private based on the content of the message, and means for converting the message into a task for management based on the content of the message. Accordingly, a user can grasp at a glance from which tool a contact is received, and can appropriately perform task management according to the content of the message. [Brief explanation of the drawing]

[0006] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] It is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Embodiment 3. [Figure 17] It is a sequence diagram showing the processing flow of the data processing system in Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 18] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Embodiment 1 when an emotion engine is combined. [Figure 19] It is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2 when an emotion engine is combined. [Figure 20] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Embodiment 2 when an emotion engine is combined. [Figure 21] It is a sequence diagram showing the processing flow of the data processing system in Example 3 of Embodiment 3 when an emotion engine is combined. [Figure 22] It is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Embodiment 3 when an emotion engine is combined. DETAILED DESCRIPTION OF EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, terms used in the following description will be explained.

[0009] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic device or a combination of a plurality of arithmetic devices. Further, the processor may be one type of arithmetic device or a combination of a plurality of 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), an APU (Accelerated Processing Unit), and a TPU (TENSOR PROCESSING UNIT (Registered Trademark)).

[0010] In the following embodiments, the labeled RAM (Random Access Memory) is a memory that temporarily stores information, and is used as a work memory by the processor.

[0011] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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), and Bluetooth (Registered Trademark).

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0019] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] The system of the present invention has means for centrally displaying messages from multiple communication tools. Specifically, it collects messages from email, communication tools, chat, messenger apps, etc., and displays them in a list on a single interface. This allows the user to see at a glance which tool a message originated from.

[0029] "Example of form 2"

[0030] Furthermore, the system of the present invention has means for distinguishing between work-related and personal messages based on their content. Specifically, it analyzes the sender and content of a message and automatically determines whether it is work-related or personal. For example, if the sender of a message is a work email address, or if the message content contains work-related keywords, the message is determined to be work-related.

[0031] "Example of form 3"

[0032] Furthermore, the system of the present invention has means for creating and managing tasks based on the content of messages. Specifically, it analyzes the content of a message and automatically generates tasks based on it. For example, if the content of a message includes a phrase indicating an action such as "prepare for the meeting," it generates a task based on that phrase and adds it to the task list. This allows the user to manage tasks appropriately according to the content of the message.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: The system collects messages from email, communication tools, chat, messenger apps, etc.

[0036] Step 2: Display the collected messages in a list on a single interface.

[0037] Step 3: Users can see at a glance which tool a message is from by looking at the list of messages.

[0038] "Example of form 2"

[0039] Step 1: The system analyzes the source and content of the message.

[0040] Step 2: Based on the analysis, the system automatically determines whether the message is work-related or personal.

[0041] Step 3: For example, if the message is sent from a work email address or contains work-related keywords, the message is considered work-related.

[0042] "Example of form 3"

[0043] Step 1: The system analyzes the content of the message.

[0044] Step 2: Based on the analysis results, automatically generate tasks based on the messages.

[0045] Step 3: For example, if the message contains a phrase indicating an action, such as "prepare for the meeting," generate a task based on that phrase and add it to the task list.

[0046] Step 4: This allows users to manage tasks appropriately based on the content of the message.

[0047] (Example 1)

[0048] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0049] In today's business environment, it's common for users to receive messages using multiple communication methods. However, this makes message management cumbersome and increases the risk of missing important messages. Furthermore, there's the challenge of categorizing messages as work-related or personal based on their content, and then managing them as tasks.

[0050] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0051] In this invention, the server includes means for collecting messages from multiple communication means, means for centralizing the collected messages, and means for storing the centralized messages. This allows the user to view messages from multiple communication means through a single interface and manage them efficiently without missing important messages.

[0052] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0053] "Means for collecting messages" refers to a function for obtaining new messages from multiple communication methods.

[0054] "A means of centralizing messages" refers to a function that converts collected messages into a common data format and manages them uniformly.

[0055] "Means of saving messages" refers to a function for storing centralized messages in a storage device such as a database.

[0056] "Means for displaying messages" refers to a function that displays saved messages on the interface so that users can view them.

[0057] "Means of manipulating messages" refer to functions that allow users to click on displayed messages to view details or to reply.

[0058] "Means for distinguishing between work and personal matters" refers to a function that determines whether a message is work-related or personal based on its content.

[0059] "A means of creating and managing tasks" refers to a function that classifies messages into tasks based on their content and manages them according to their importance and urgency.

[0060] Modes for carrying out the invention

[0061] This invention is a system that centrally displays messages from multiple communication methods, further categorizes them as either work-related or personal based on their content, and manages them as tasks. A specific embodiment of this system is described below.

[0062] Server Role

[0063] The server is responsible for collecting messages from multiple communication channels. Specifically, it retrieves new messages using APIs from email servers, communication tools (e.g., Slack, Microsoft Teams), chat apps (e.g., WhatsApp, LINE), and messenger apps (e.g., Facebook Messenger). The server centralizes these messages and converts them into a common data format. The converted messages are then stored in relational databases such as MySQL or PostgreSQL.

[0064] Terminal role

[0065] The device provides an interface for users to view and interact with messages. Specifically, it displays a list of messages retrieved from the server via a web or mobile application. For example, the frontend could be built using React or Vue.js to allow users to visually review messages. Messages are color-coded by tool: emails are displayed in blue, communication tools in green, and chat apps in red.

[0066] User actions

[0067] Users interact with messages using an interface on their device. Specifically, they can click on a particular message to view details or reply to it. Users can also use a filter function to display only messages from specific communication methods. Furthermore, they can categorize messages as work-related or personal based on their content and manage them as tasks. Task creation is based on the importance and urgency of the message.

[0068] Specific example

[0069] For example, consider a scenario where a user receives messages from multiple communication channels while at work. This system allows the user to view messages from email, Slack, WhatsApp, and Facebook Messenger in a single interface. This enables them to quickly identify the source of each message and respond promptly.

[0070] Example of a prompt

[0071] Examples of prompt statements to input into a generative AI model include the following:

[0072] Please describe a system that centralizes and displays messages from multiple communication methods. Specifically, please specify what hardware and software are used, and what kind of data processing and calculations are performed. Also, please provide concrete examples.

[0073] By using this prompt statement, the generative AI model can generate a detailed description of the system.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Program processing flow

[0076] Step 1: Collecting Messages

[0077] The server collects messages from multiple communication methods. It uses API endpoints such as email servers, communication tools (e.g., Slack, Microsoft Teams), chat apps (e.g., WhatsApp, LINE), and messenger apps (e.g., Facebook Messenger) as input. The server sends requests to these APIs to retrieve new messages. The output is message data obtained from each communication method.

[0078] Step 2: Centralize messages

[0079] The server centralizes the collected messages. It uses the message data collected in Step 1 as input. Specifically, it converts messages obtained from each communication method into a common data format. For example, an email message has fields such as "sender," "subject," "body," and "received date and time," while a Slack message has fields such as "sender," "channel," "message content," and "sent date and time." The server unifies these fields and converts them into a single data format. The output is the centralized message data.

[0080] Step 3: Save the message

[0081] The server stores the centralized messages in a database. It uses the message data centralized in step 2 as input. Specifically, it uses a relational database such as MySQL or PostgreSQL to store the message data in a table. For example, the message table may have columns such as "Message ID," "Sender," "Content," "Tool Name," and "Received Date and Time," ensuring each message is uniquely identified. The output is the message data stored in the database.

[0082] Step 4: Displaying the message

[0083] The device provides an interface for users to view messages. It uses message data retrieved from the server as input. Specifically, it displays a list of messages through a web or mobile application. For example, the frontend is built using React or Vue.js to allow users to visually view messages. Messages are color-coded by tool: email is displayed in blue, communication tools in green, and chat apps in red. The output is a list of messages viewable by the user.

[0084] Step 5: Message manipulation

[0085] Users interact with messages using an interface on their device. The displayed message list serves as input. Specifically, they can click on a particular message to view details or reply. Users can also use a filter function to display only messages from specific communication methods. Furthermore, they can categorize messages as work-related or personal based on their content and manage them as tasks. The output is the result of the user's actions.

[0086] (Application Example 1)

[0087] Next, we will describe Application Example 1 of Form 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."

[0088] In logistics centers, messages are scattered across multiple communication tools (email, communication tools, chat, messenger apps, etc.), making it difficult for staff to quickly grasp and respond to information. This also reduces operational efficiency and increases the risk of important communications being overlooked.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on their content, means for integrating messages collected from multiple communication tools so that logistics center staff can understand them at a glance on their smartphones, and means for centrally displaying messages from multiple communication tools used within the logistics center. As a result, logistics center staff can quickly understand which tool a message is coming from and respond promptly.

[0091] "Multiple communication tools" refers to different types of messaging methods, such as email, communication tools, chat, and messenger apps.

[0092] "A means of centralized display" refers to a function that collects messages from multiple communication tools and displays them in a list on a single interface.

[0093] "Means of sorting" refers to the function of classifying messages based on their content, determining whether they are work-related or personal.

[0094] "A means of creating and managing tasks" refers to a function that generates tasks based on the content of a message and manages those tasks.

[0095] A "logistics center" refers to a facility that stores, sorts, and distributes goods.

[0096] "Staff" refers to employees working at the logistics center.

[0097] A "smartphone" refers to a mobile phone that is capable of connecting to the internet and using applications.

[0098] "Means of integration" refers to the function of consolidating messages collected from multiple communication tools into a single system.

[0099] "Responding quickly" means taking the necessary action promptly after receiving a message.

[0100] The system for implementing this invention is for centrally displaying messages from multiple communication tools in a logistics center. Specifically, the server includes the following means:

[0101] First, the server collects messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.). This involves using Python's imaplib and email libraries to retrieve emails from an IMAP server, using the slack_sdk library to collect Slack messages, and using the WhatsApp API to collect WhatsApp messages.

[0102] Next, the server uses Flask to provide an API endpoint for centrally displaying the collected messages. This allows logistics center staff to view all messages on a single interface using their smartphones.

[0103] Furthermore, the server categorizes messages based on their content, determining whether they are work-related or personal. This allows staff to quickly identify and respond to important messages.

[0104] Furthermore, the server generates and manages tasks based on the content of the messages. This makes it possible to take appropriate actions based on the importance and urgency of the messages.

[0105] As a concrete example, when a logistics center staff member opens the "Logistics Messaging Integration App" on their smartphone, messages from email, Slack, and WhatsApp are displayed in a single screen. This allows staff to see at a glance which tool a message originated from and respond quickly.

[0106] Examples of prompt statements are as follows:

[0107] When logistics center staff open the "Logistics Messaging Integration App" on their smartphones, messages from email, Slack, and WhatsApp are displayed in a single screen. This allows staff to see at a glance which tool a message is coming from and respond quickly.

[0108] In this way, the efficiency of message management in logistics centers can be significantly improved.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server retrieves email from the IMAP server. Specifically, it uses the imaplib and email libraries to log in to the specified email account and retrieve all emails from the inbox. The input is the email server's authentication information, and the output is data including the email sender, subject, and body.

[0112] Step 2:

[0113] The server retrieves messages from Slack. Specifically, it uses the slack_sdk library to retrieve messages from a specified Slack channel. The input is the Slack API token and channel ID, and the output is data containing the user ID and message text.

[0114] Step 3:

[0115] The server retrieves messages from WhatsApp. Specifically, it uses the WhatsApp API to retrieve messages from a specified WhatsApp account. The input is a WhatsApp API token, and the output is data containing the sender and message text.

[0116] Step 4:

[0117] The server centralizes all acquired messages. Specifically, it integrates messages from email, Slack, and WhatsApp, and combines them into a single data structure. The input is message data acquired from each communication tool, and the output is an integrated message list.

[0118] Step 5:

[0119] The server will serve the integrated messages from the API endpoint using Flask. Specifically, it will use the Flask framework to build an API that returns an integrated message list in JSON format. The input is the integrated message list, and the output is the JSON data provided from the API endpoint.

[0120] Step 6:

[0121] The user opens the "Logistics Message Integration App" on their smartphone. Specifically, they access the server's API endpoint using their smartphone's browser or a dedicated app. The input is the URL of the API endpoint, and the output is a list of integrated messages.

[0122] Step 7:

[0123] The user reviews the displayed messages and takes action as needed. Specifically, they review the message content and take appropriate action based on its importance and urgency. The input is a list of integrated messages, and the output is the user's actions.

[0124] (Example 2)

[0125] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0126] In today's business environment, there is a need to efficiently manage messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.). However, it is difficult to centralize these messages, further categorize them based on their content as work-related or personal, and manage them appropriately as tasks. In particular, there is a need to accurately analyze the sender and content of messages and quickly notify users of the classification results, but current systems cannot do this efficiently.

[0127] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0128] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for analyzing the source addresses of messages, means for analyzing the content of messages using a generative AI model and distinguishing between work and personal messages, means for creating and managing tasks based on the content of the messages, and means for notifying the user's terminal of the classification results. This makes it possible to efficiently centrally manage messages from multiple communication means, appropriately classify and create tasks based on their content, and quickly notify the user.

[0129] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0130] "Sender address" refers to information such as the email address or user ID of the sender who sent the message.

[0131] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze text data and understand and classify its content.

[0132] "Message content" refers to the main body of text data sent and received through a communication method.

[0133] "Means of centralized display" refers to a function that integrates messages obtained from multiple communication methods into a single interface for display.

[0134] "Means of analysis" refers to a function that analyzes the sender address and content of a message and extracts its characteristics.

[0135] "Means of sorting" refers to a function that automatically classifies whether a message is work-related or personal based on its analyzed content.

[0136] "A means of creating and managing tasks" refers to a function that generates tasks based on categorized messages and manages those tasks.

[0137] "Means for notifying of classification results" refers to a function that informs the user's device of the results of the sorting process.

[0138] This invention relates to a system that centrally displays messages from multiple communication methods, analyzes the source address and content of the messages to distinguish between work and personal messages, and further manages them as tasks based on their content. A specific embodiment of this system is shown below.

[0139] System Configuration

[0140] The server is comprised of the following hardware and software:

[0141] Hardware: A server machine equipped with a high-performance processor, sufficient memory, storage devices, and network interfaces.

[0142] Software: Mail server (supports IMAP protocol), generative AI model (e.g., OpenAI®'s GPT-4®), natural language processing library (e.g., NLTK and spaCy), notification system (e.g., Pushbullet).

[0143] Message received

[0144] The server receives messages sent by users. Specifically, it retrieves messages through email servers and chat application APIs. For example, it retrieves messages from an email server using the IMAP protocol.

[0145] Source analysis

[0146] The server analyzes the message's sender address. Specifically, it analyzes the message's header information to extract the sender address. For example, if the sender is a business email address like "@company.com", the server determines that the message is work-related.

[0147] Content analysis

[0148] The server analyzes the message content using natural language processing (NLP) techniques. This analysis uses a generative AI model (for example, OpenAI's GPT-4). Specifically, the following prompt sentences are input to the generative AI model.

[0149] Prompt: "Please determine whether the following message is work-related or personal. Message: 'Please prepare the materials for tomorrow's meeting.'"

[0150] The server receives the response from the generated AI model and determines whether the message is work-related or personal.

[0151] Notification of classification results

[0152] The server classifies messages as "work" or "personal" based on the analysis results and notifies the user's device of the result. Specifically, the result is notified via push notification or email. For example, the Pushbullet library is used to send push notifications.

[0153] Specific example

[0154] When a user receives the message "Please prepare the materials for tomorrow's meeting," the server processes it as follows:

[0155] 1. Verify that the message is sent from a business email address ending in "@company.com".

[0156] 2. Analyze the message content to determine if it contains business-related keywords such as "meeting" or "documents."

[0157] 3. Based on this information, categorize the messages as "work."

[0158] 4. Notify the user's device of the classification results.

[0159] In this way, it becomes possible to efficiently centrally manage messages from multiple communication methods, appropriately classify and assign tasks based on their content, and quickly notify users.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] Message received

[0163] The server receives messages sent by users. Specifically, it retrieves messages through email servers and chat application APIs. For example, it retrieves messages from an email server using the IMAP protocol.

[0164] Input: Message sent by the user

[0165] Output: Message data stored on the server

[0166] Step 2:

[0167] Source analysis

[0168] The server analyzes the message's sender address. Specifically, it analyzes the message's header information to extract the sender address. For example, if the sender is a business email address like "@company.com", the server determines that the message is work-related.

[0169] Input: Message data stored on the server

[0170] Output: Source address analysis results

[0171] Step 3:

[0172] Content analysis

[0173] The server analyzes the message content using natural language processing (NLP) techniques. This analysis uses a generative AI model (for example, OpenAI's GPT-4). Specifically, the following prompt sentences are input to the generative AI model.

[0174] Prompt: "Please determine whether the following message is work-related or personal. Message: 'Please prepare the materials for tomorrow's meeting.'"

[0175] The server receives the response from the generated AI model and determines whether the message is work-related or personal.

[0176] Input: Message content

[0177] Output: Message classification result (work or personal)

[0178] Step 4:

[0179] Notification of classification results

[0180] The server classifies messages as "work" or "personal" based on the analysis results and notifies the user's device of the result. Specifically, the result is notified via push notification or email. For example, the Pushbullet library is used to send push notifications.

[0181] Input: Message classification result

[0182] Output: Notification sent to the user's device

[0183] Step 5:

[0184] Task creation and management

[0185] The server generates and manages tasks based on classified messages. Specifically, it prioritizes tasks based on the importance and urgency of the messages and notifies users at the appropriate time.

[0186] Input: Classified message

[0187] Output: Tasks registered in the task management system

[0188] The above describes the specific processing flow of this system's program.

[0189] (Application Example 2)

[0190] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] Many modern users utilize multiple communication tools, resulting in a mix of work-related and personal messages. This makes message management cumbersome, particularly in determining whether expense-related messages are work-related or personal. Furthermore, improper expense classification can lead to problems with expense reimbursement and personal financial management. Therefore, a system is needed that automatically categorizes expenses based on message content, allowing users to easily review them.

[0192] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for classifying messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for analyzing the source and content of messages to automatically determine whether an expense is work-related or personal, and means for displaying the expense classification results so that the user can confirm them. As a result, the user can centrally manage messages from multiple communication tools and automatically classify and confirm expenses.

[0193] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0194] A "message" refers to information such as text, images, audio, and video that is sent and received through communication tools.

[0195] "Centralization" refers to consolidating and displaying messages from multiple communication tools into a single interface.

[0196] "Classification" refers to judging and classifying messages based on their content, determining whether they are work-related or personal.

[0197] "Tasking" refers to managing a message by breaking it down into specific work items based on its content.

[0198] "Sender information" refers to the information of the person who sent the message.

[0199] "Analysis" refers to the process of analyzing the source and content of a message and making decisions based on specific criteria.

[0200] "Expenses" refers to information related to monetary payments.

[0201] "Classification result" refers to the result of classifying expenditures based on the content of the message.

[0202] "Display" refers to providing classification results visually so that users can confirm them.

[0203] A system for carrying out this invention includes means for centrally displaying messages from multiple communication tools, means for classifying messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for analyzing the sender and content of messages to automatically determine whether an expense is work-related or personal, and means for displaying the expense classification results so that the user can review them.

[0204] System program

[0205] The program for this system will be implemented using a programming language such as Python. The program will perform the following operations:

[0206] 1. Centralizing messages:

[0207] The server collects messages from email, communication tools, chat, messenger apps, etc., and aggregates them into a single interface. This allows users to view messages from multiple communication tools in one place.

[0208] 2. Message sorting:

[0209] The server analyzes the sender and content of messages to automatically determine whether they are work-related or personal. For example, if the sender is a work email address, or if the message contains work-related keywords such as "meeting expenses" or "travel expenses," the message will be classified as work-related.

[0210] 3. Taskification:

[0211] The server creates tasks based on sorted messages. Task creation is based on the importance and urgency of the messages. This allows users to prioritize and manage important tasks.

[0212] 4. Classification of expenditures:

[0213] The server analyzes the source and content of messages to automatically determine whether an expense is work-related or personal. For example, if a payment notification is sent from a work email address, or if the message contains work-related keywords such as "meeting expenses" or "travel expenses," the expense will be classified as work-related.

[0214] 5. Displaying classification results:

[0215] The server displays the expenditure classification results so that users can easily review and properly manage their spending.

[0216] Hardware and software to be used

[0217] Hardware: Smartphones, servers

[0218] Software: Python, database management systems (e.g., MySQL), messaging APIs (e.g., Gmail API)

[0219] Specific example

[0220] For example, consider a scenario where a user receives the following message.

[0221] Sender: "boss@work-email.com"

[0222] Message: "Regarding the cost of the next meeting"

[0223] In this case, the server classifies this message as "work" and manages the expense as work-related.

[0224] Example of a prompt

[0225] The following are examples of prompts to input into the generating AI model.

[0226] Sender: "boss@work-email.com"

[0227] Message: "Regarding the cost of the next meeting"

[0228] Is this message work-related or personal?

[0229] This prompt can be used to ask a generative AI model to classify a message.

[0230] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0231] Step 1:

[0232] The server collects messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.). It receives message data obtained through the APIs of each communication tool as input. As output, it stores these messages in a centralized database. Specifically, the server calls the API of each communication tool, retrieves the message data, and stores it in the database.

[0233] Step 2:

[0234] The server analyzes the source and content of collected messages and automatically determines whether they are work-related or personal. It receives message data stored in a database as input and generates a classification result (work or personal) for each message as output. Specifically, the server analyzes message content using regular expressions and keyword matching and stores the classification results in the database.

[0235] Step 3:

[0236] The server creates tasks based on the sorted messages. It receives message data, including the classification results, as input. It generates tasked data as output. Specifically, the server evaluates the importance and urgency of messages and saves them as tasks in the database.

[0237] Step 4:

[0238] The server analyzes the source and content of messages to automatically determine whether an expense is work-related or personal. It receives message data stored in a database as input and generates expense classification results as output. Specifically, the server classifies expenses based on message content and saves the results to the database.

[0239] Step 5:

[0240] The server displays the expenditure classification results for the user to review. It receives data containing expenditure classification results as input and generates data to display in the user interface as output. Specifically, the server provides the classification results visually to the user through a web page or mobile application.

[0241] Step 6:

[0242] The user inputs a prompt message into the generative AI model and requests that it classify the message. The input is the prompt message sent to the generative AI model. The output is the classification result received from the generative AI model. Specifically, the user inputs a prompt message like the following:

[0243] Sender: "boss@work-email.com"

[0244] Message: "Regarding the cost of the next meeting"

[0245] Is this message work-related or personal?

[0246] This prompt can be used to ask a generative AI model to classify a message.

[0247] (Example 3)

[0248] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0249] In today's business environment, it is common to use multiple communication methods (email, communication tools, chat, messenger apps, etc.). However, it is difficult to centrally manage messages from these communication methods, separate work and personal matters, and automatically generate and manage tasks based on the content of the messages. As a result, users have to manually check the content of messages and manually generate tasks, which presents a challenge in efficient task management.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0251] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for analyzing the content of messages and automatically generating tasks based on the analysis results, and means for adding the generated tasks to a task list and managing them. This enables users to centrally manage messages from multiple communication means, distinguish between business and personal messages, and automatically generate tasks based on the content of messages, thereby enabling efficient task management.

[0252] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0253] "Centralization" refers to the process of consolidating and displaying messages from multiple communication methods in a single location.

[0254] "Work" refers to activities and tasks related to one's duties or job.

[0255] "Personal business" refers to personal errands or private activities.

[0256] "Distinguishing" refers to distinguishing between business and personal messages based on their content.

[0257] "Analysis" refers to the process of analyzing the content of a message using natural language processing techniques to understand its meaning.

[0258] A "task" refers to a specific action or task, and is a concrete work item generated based on the content of a message.

[0259] A "task list" is a list used to display and manage tasks that have been generated.

[0260] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[0261] This invention is a system that centralizes messages from multiple communication methods, categorizes them as either business or personal based on their content, analyzes the message content to automatically generate tasks, and adds them to a task list for management.

[0262] Hardware and software to be used

[0263] hardware

[0264] User's device (PC, smartphone, etc.)

[0265] software

[0266] Natural language processing technologies (such as Google® Cloud Natural Language API and IBM Watson® Natural Language Understanding)

[0267] Program processing

[0268] Server Processing

[0269] The server analyzes messages received from users. Specifically, the server uses natural language processing techniques to analyze the message content and extract phrases that indicate actions. This analysis utilizes software such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[0270] Once the analysis is complete, the server automatically generates tasks based on the extracted phrases. The generated tasks are added to a task list and managed so that the user can review them later. For example, if the message contains the phrase "prepare for the meeting," the server generates a task called "prepare for the meeting" and adds it to the task list.

[0271] Terminal processing

[0272] The terminal's role is to send messages entered by the user to the server. When the user enters a message and presses the send button, the terminal sends that message to the server. For example, if the user enters "I need to prepare for tomorrow's meeting," that message will be sent from the terminal to the server.

[0273] User processing

[0274] Users manage tasks by typing messages using their devices. When a user types a message, it is sent to the server via the device. The server parses the message and generates a task, which the user can then view in their task list. For example, if a user types "Create presentation materials for next week," a task titled "Create presentation materials" will be generated based on that content.

[0275] Specific example

[0276] Example of a prompt

[0277] When a user inputs the message "I need to prepare for tomorrow's meeting", the server generates the task "prepare for the meeting" and adds it to the task list.

[0278] With this system, tasks can be automatically generated based on the content of user messages, allowing users to perform task management efficiently. The flow of specific processing in Embodiment 3 will be described with reference to FIG. 15.

[0279] Step 1: The user inputs a message

[0280] The user inputs a message using a terminal (such as a PC or a smartphone). For example, the user inputs "I need to prepare for tomorrow's meeting". This input is saved in the terminal as a text-format message.

[0281] Step 2: The terminal transmits the message to the server

[0282] When the user inputs a message and presses the send button, the terminal transmits the message to the server. Specifically, the terminal transmits the text-format message data to the server via an Internet connection. The input is the user's message, and the output is the transmission of the message to the server.

[0283] Step 3: The server receives the message

[0284] The server receives the message transmitted from the terminal. The received message is saved in the server as text-format data. The input is the message data from the terminal, and the output is the message data saved in the server.

[0285] Step 4: The server parses the message

[0286] The server analyzes the received message. Specifically, the server uses natural language processing technologies (such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding) to analyze the message content and extract action phrases. The input is the message data stored on the server, and the output is the extracted action phrases.

[0287] Step 5: The server generates the task.

[0288] The server automatically generates tasks based on the analysis results. It creates specific tasks based on the extracted phrases. For example, it generates the task "Prepare for the meeting" from the phrase "Prepare for the meeting." The input is the extracted action phrase, and the output is the generated task.

[0289] Step 6: The server updates the task list.

[0290] The server adds the generated tasks to the task list. The task list is stored in a database and managed so that users can review it later. The input is the generated tasks, and the output is the updated task list.

[0291] Step 7: The user checks the task list.

[0292] The user uses a terminal to view the task list. The task list displays tasks generated by the server. This allows the user to view and manage tasks that have been automatically generated based on the content of messages. The input is the updated task list, and the output is the task list displayed on the user's screen.

[0293] (Application Example 3)

[0294] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0295] Conventional message management systems lacked the ability to automatically generate tasks based on message content and issue instructions to machines, resulting in decreased work efficiency within factories. Furthermore, the inability to analyze message content and generate appropriate tasks could lead to delays and errors. This, in turn, compromised factory productivity and safety.

[0296] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0297] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on the message content, means for analyzing the message content, generating specific tasks for a machine based on the analysis results, and adding them to a task list, and means for instructing the machine on the generated tasks. This makes it possible to automatically generate appropriate tasks based on the message content and instruct the machine. As a result, the work efficiency in the factory can be improved and delays and errors in work can be reduced.

[0298] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0299] "Messages" refer to text information and instructions sent and received through communication tools.

[0300] "Centralization" refers to consolidating messages from multiple communication tools into a single platform or interface.

[0301] The term "classification" refers to distinguishing whether a message is work-related or private based on the content of the message.

[0302] The term "task conversion" refers to analyzing the content of a message, and generating specific tasks and instructions as tasks based on the analysis result.

[0303] The term "management" refers to adding generated tasks to a list and tracking the progress and completion status of the tasks.

[0304] The term "analysis" refers to understanding the content of a message using technologies such as natural language processing and extracting meaning from the message.

[0305] The term "machine" refers to robots and automated devices used in factories.

[0306] The term "task list" refers to a list for displaying and managing generated tasks in a list format.

[0307] The term "instruction" refers to commanding a machine to perform specific actions based on a generated task.

[0308] A system for carrying out the present invention includes an application installed on a robot used in a factory. Specific embodiments of the system are described below.

[0309] System Configuration

[0310] The system includes the following main components:

[0311] 1. Server: Centralizes and displays messages from a plurality of communication tools.

[0312] 2. Natural Language Processing (NLP) Engine: Analyzes the content of messages and generates tasks based on the analysis results.

[0313] 3. Task Manager: Add and manage generated tasks in the task list.

[0314] 4. Robot Controller: Instructs the robot on the generated tasks.

[0315] Hardware and software to be used

[0316] Hardware: Robots in factories

[0317] Software: Python, spaCy (natural language processing library), TaskManager (task management system), RobotController (robot control system)

[0318] Processing flow

[0319] 1. Receiving messages: The server receives messages from communication tools such as email, communication tools, chat, and messenger apps.

[0320] 2. Message centralization: Received messages are aggregated and displayed on a single platform.

[0321] 3. Message Analysis: The content of the message is analyzed using a natural language processing engine (spaCy) and its meaning is extracted.

[0322] 4. Task Generation: Based on the analysis results, specific tasks are generated. For example, if the message "Perform maintenance on line 1" is received, a maintenance task is generated.

[0323] 5. Add to task list: Add the generated task to the task list and manage it.

[0324] 6. Instructions to the robot: Instruct the robot to execute the tasks added to the task list.

[0325] Specific example

[0326] For example, consider the case where the following message is received:

[0327] Message: "Performing maintenance on line 1"

[0328] Program processing: Analyzes messages, generates "maintenance" tasks, and issues instructions to the robot.

[0329] Examples of prompts to input into a generative AI model:

[0330] "We have received a message indicating that maintenance will be performed on line 1. Based on this message, generate a maintenance task and issue instructions to the robot."

[0331] In this way, it becomes possible to automatically generate tasks and issue instructions to robots based on messages within the factory. This improves work efficiency within the factory and reduces delays and errors.

[0332] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0333] Step 1:

[0334] The server receives messages from communication tools such as email, communication tools, chat, and messenger apps. The input is messages sent from each communication tool, and the output is centralized message data. Specifically, messages are retrieved using the APIs of each communication tool and stored in a database.

[0335] Step 2:

[0336] The server aggregates and displays received messages on a single platform. The input is centralized message data, and the output is a user-accessible integrated message interface. Specifically, it retrieves messages from a database and displays them on a web interface or application screen.

[0337] Step 3:

[0338] The server uses a natural language processing engine (spaCy) to analyze message content and extract meaning. The input is centralized message data, and the output is the analyzed message content. Specifically, the spaCy model is loaded, and the message text is analyzed to extract important keywords and phrases.

[0339] Step 4:

[0340] The server generates specific tasks based on the analysis results. The input is the analyzed message content, and the output is the generated task. Specifically, it determines the type and details of the task based on the extracted keywords and phrases, and generates a task object.

[0341] Step 5:

[0342] The server adds and manages the generated tasks to a task list. The input is the generated tasks, and the output is the updated task list. Specifically, it saves task objects to the database and updates the task list.

[0343] Step 6:

[0344] The server instructs the robot to execute tasks added to the task list. The input is the updated task list, and the output is the robot's execution status. Specifically, the generated tasks are sent to the robot via the robot controller, and their execution status is monitored.

[0345] In this way, it becomes possible to automatically generate tasks and issue instructions to robots based on messages within the factory. This improves work efficiency within the factory and reduces delays and errors.

[0346] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0347] "Example of form 1"

[0348] One embodiment of the present invention provides a system that combines an emotion engine. This system includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, and an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions, for example, from the user's tone of voice, facial expressions, and the context of the message.

[0349] "Example of form 2"

[0350] As one embodiment of a system using an emotion engine, a function is provided that adjusts the priority of messages based on the user's emotions. For example, if a user receives a message expressing anger or dissatisfaction, that message is determined to have high priority and is displayed so that it is immediately visible to the user.

[0351] "Example of form 3"

[0352] As one embodiment of a system using an emotion engine, a function is provided that adjusts task priorities based on the user's emotions. For example, if a user receives a message indicating joy or excitement, tasks related to that message are determined to have a high priority and are displayed higher up in the task list.

[0353] The following describes the processing flow for each example of the form.

[0354] "Example of form 1"

[0355] Step 1: The system centralizes and displays messages from multiple communication tools.

[0356] Step 2: Next, the system sorts the message into work-related or personal based on its content.

[0357] Step 3: The system then breaks down the message content into tasks and manages them accordingly.

[0358] Step 4: Finally, the emotion engine recognizes the user's emotions based on factors such as the user's tone of voice, facial expressions, and the context of the message.

[0359] "Example of form 2"

[0360] Step 1: The system adjusts message priorities based on the user's emotions.

[0361] Step 2: For example, if a user receives a message expressing anger or dissatisfaction, that message is judged to have high priority.

[0362] Step 3: As a result, the message is displayed so that it is immediately visible to the user. (Example 3)

[0363] Step 1: The system adjusts task priorities based on the user's emotions.

[0364] Step 2: For example, if a user receives a message expressing joy or excitement, the task associated with that message will be judged to have a high priority.

[0365] Step 3: As a result, the task will appear higher up in the task list.

[0366] (Example 1)

[0367] Next, we will describe Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0368] In today's business environment, users utilize multiple communication methods (email, communication tools, chat, messaging applications, etc.), requiring them to individually check messages from each tool. This makes message checking and management cumbersome, increasing the risk of missing important messages. Furthermore, users need to categorize messages as either work-related or personal, and manage them as tasks, but doing this manually is time-consuming and laborious. Additionally, recognizing user emotions and providing appropriate feedback is crucial, but current systems do not adequately address this.

[0369] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0370] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for recognizing the user's emotions, and means for providing feedback based on the recognized emotions. This allows the user to centrally manage messages from multiple communication means, efficiently manage tasks without missing important messages, and improve user satisfaction and productivity by recognizing the user's emotions and providing appropriate feedback.

[0371] "Communication methods" refer to various means that users use to send and receive messages, such as email, communication tools, chat, and messaging applications.

[0372] "Means of centralized display" refers to methods for displaying messages collected from multiple communication methods in a list on a single interface.

[0373] "Means of sorting" refers to methods for analyzing the content of a message and classifying whether it is work-related or personal.

[0374] "Means of task creation and management" refers to methods for generating tasks based on the content of a message and managing those tasks.

[0375] "Means of recognizing emotions" refers to methods for recognizing a user's emotions from their tone of voice, facial expressions, message context, etc.

[0376] "Means of providing feedback" refers to means of providing users with appropriate advice and information based on their perceived emotions.

[0377] This invention is a system that centrally displays messages from multiple communication methods, categorizes them as either work-related or personal based on their content, and further manages them as tasks. It also includes a function to recognize the user's emotions and provide appropriate feedback.

[0378] Message collection and centralized display

[0379] The server collects messages from multiple communication methods used by the user (e.g., email, communication tools, chat, messaging applications). This is done by utilizing the APIs of each communication method. For example, the email API is used to collect emails, the communication API for communication tools, the chat API for chats, and the messaging API for messaging applications. The collected messages are stored in a database, and the terminal displays an interface accessible to the user, showing the collected messages in a list format.

[0380] Message Classification

[0381] The server analyzes the content of the collected messages and distinguishes between work-related and personal matters. This is done using natural language processing (NLP) techniques. Specifically, it uses a natural language processing API to analyze the message content and determine the category. For example, a message like "Please prepare the materials for tomorrow's meeting" is classified as work-related, while a message like "Let's go see a movie this weekend" is classified as personal.

[0382] Task creation and management

[0383] The server generates tasks based on classified messages and adds them to the task management tool. Task management uses a task management API. For example, a new task can be generated using the task management tool's API and added to the user's task management board. Users can then view the generated tasks and manage their progress.

[0384] Emotional Recognition and Feedback

[0385] The server uses an emotion engine to recognize the user's emotions. This involves using speech recognition and facial recognition technologies. For example, it uses a speech recognition API to analyze the tone of the user's voice and a facial recognition API to analyze the user's facial expressions. Based on the recognized emotions, the server provides appropriate feedback to the user. For example, if the user sends the message "I'm very tired today," the emotion engine recognizes the user's fatigue and provides advice on how to relax.

[0386] Specific example

[0387] When users are using email, communication tools, chat, and messaging applications, the server collects messages from these tools and displays them in a single interface. Users can see at a glance which tool a message originated from. They can also categorize messages as work-related or personal based on their content, and generate and manage tasks accordingly. Furthermore, by recognizing user emotions and providing appropriate feedback, the system can improve user satisfaction and productivity.

[0388] Example of a prompt

[0389] "Collect messages from email, communication tools, chat, and messaging applications and display them in a single interface. Furthermore, categorize messages as either work-related or personal based on their content, generate and manage tasks accordingly, and recognize user sentiment to provide appropriate feedback."

[0390] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0391] Step 1:

[0392] The server collects messages from multiple communication methods.

[0393] Input: Message data from email, communication tools, chat, and messaging application APIs.

[0394] Specific operation: The server retrieves new messages by calling the API for each communication method. For example, it uses the email API to retrieve new emails and the communication tool API to retrieve new chat messages.

[0395] Output: The collected message data is saved to the database.

[0396] Step 2:

[0397] The server retrieves messages from the database in order to centrally display the collected messages.

[0398] Input: Message data stored in the database.

[0399] Specific operation: The server retrieves messages collected from the database and sends them to the interface accessed by the user.

[0400] Output: A centralized list of messages displayed on the terminal.

[0401] Step 3:

[0402] The server analyzes the content of the collected messages and distinguishes between work-related and personal messages.

[0403] Input: Message data retrieved from the database.

[0404] Specific operation: The server calls a natural language processing API to analyze the message content and determine its category. For example, the message "Please prepare the materials for tomorrow's meeting" is classified as work-related, while the message "Let's go see a movie this weekend" is classified as personal.

[0405] Output: Classified message data.

[0406] Step 4:

[0407] The server generates tasks based on the classified messages and adds them to the task management tool.

[0408] Input: Classified message data.

[0409] Specific operation: The server calls the task management API to generate a new task and adds it to the user's task management board. For example, it uses the task management tool's API to generate a task called "Prepare meeting materials" and adds it to the user's task management board.

[0410] Output: A new task added to the task management tool.

[0411] Step 5:

[0412] The server uses an emotion engine to recognize the user's emotions.

[0413] Input: User's tone of voice, facial expression, and message context.

[0414] Specific operation: The server calls a speech recognition API to analyze the tone of the user's voice and a facial recognition API to analyze the user's facial expressions. For example, if the user sends the message "I'm very tired today," the emotion engine recognizes the user's level of fatigue.

[0415] Output: Sentiment data of recognized users.

[0416] Step 6:

[0417] The server provides appropriate feedback to the user based on the emotions it perceives.

[0418] Input: Sentiment data of the recognized user.

[0419] Specific operation: The server provides the user with advice and information to help them relax based on the emotions it perceives. For example, if the server perceives the user as tired, it will suggest relaxing music or taking a break.

[0420] Output: Feedback provided to the user.

[0421] (Application Example 1)

[0422] Next, we will describe Application Example 1 of Form 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."

[0423] Traditional factory robots lacked features such as the ability to centrally display messages from multiple communication tools, differentiate between work-related and personal messages based on their content, and manage tasks based on message content. Furthermore, they lacked the ability to recognize the emotions of factory staff and prompt appropriate responses, making efficient communication and appropriate responses based on staff emotions difficult.

[0424] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on their content, means including an emotion engine that recognizes the user's emotions, and means for recognizing the emotions of factory staff and prompting appropriate responses. This enables more efficient communication within the factory and appropriate responses based on the emotions of the staff.

[0425] "Multiple communication tools" refers to different types of communication methods such as email, communication tools, chat, and messenger apps.

[0426] "A means of centralized display" refers to a function that integrates and displays messages from multiple communication tools on a single interface.

[0427] "Means of sorting" refers to a function that automatically categorizes messages based on their content, determining whether they are work-related or personal.

[0428] "A means of creating and managing tasks" refers to a function that generates tasks based on the content of a message and manages those tasks.

[0429] An "emotion engine" refers to technology that recognizes a user's emotions based on factors such as the tone of their voice, facial expressions, and the context of their message.

[0430] "Means of recognizing the emotions of factory staff and prompting appropriate responses" refers to a function that uses an emotion engine to recognize the emotions of staff working in the factory and takes appropriate action based on those emotions.

[0431] The system for carrying out this invention is configured as an application installed on a factory robot. A specific embodiment is shown below.

[0432] System Configuration

[0433] The server includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means including an emotion engine for recognizing user emotions, and means for recognizing the emotions of factory staff and prompting appropriate responses.

[0434] Hardware and software to be used

[0435] Hardware: Factory robots (e.g., KUKA, Fanuc)

[0436] Software: Python, smtplib, imaplib, email library, TextBlob, json

[0437] Data processing and data calculation

[0438] The server performs the following data processing and calculations:

[0439] 1. Retrieve emails:

[0440] The server retrieves email from the IMAP server. This is done using the imaplib library.

[0441] 2. Message analysis:

[0442] The server analyzes the content of the retrieved emails and performs sentiment analysis. This is done using the TextBlob library.

[0443] 3. Centralizing messages:

[0444] The server centralizes the analysis results and displays them on an integrated interface. This is done using the JSON library.

[0445] 4. Emotional Engine:

[0446] The server recognizes the user's emotions based on factors such as the user's tone of voice, facial expressions, and the context of the message. This is done using emotion recognition technology.

[0447] 5. Facilitating appropriate responses:

[0448] The server recognizes the emotions of the staff in the factory and takes appropriate action based on those emotions.

[0449] Specific example

[0450] For example, if a staff member in a factory tells a robot that "the production line is behind schedule today," the robot registers that message as a task and notifies the manager. Also, if the robot detects that a staff member is tired, it sends a message encouraging them to take a break.

[0451] Example of a prompt

[0452] Design a system where, when a staff member speaks to a robot in a factory, the robot recognizes the staff member's emotions and responds appropriately. For example, if a staff member says, "The production line is behind schedule today," the robot should register that message as a task and notify the manager.

[0453] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0454] Step 1:

[0455] The server retrieves emails from the IMAP server. Specifically, it connects to the mail server using the imaplib library and logs into the user's email account. Next, it searches all emails in the inbox and obtains the ID of each email. This results in a list containing the email's metadata (sender, subject, date and time, etc.).

[0456] Input: IMAP server connection information, user's email account information

[0457] Output: Email metadata list

[0458] Step 2:

[0459] The server analyzes the content of the retrieved emails and performs sentiment analysis. Specifically, it uses the email library to extract the body of each email and the TextBlob library to perform sentiment analysis. As a result of the sentiment analysis, a sentiment score (positive, negative, neutral) is obtained for each email.

[0460] Input: Email metadata list

[0461] Output: Email data with sentiment scores

[0462] Step 3:

[0463] The server centralizes the analysis results and displays them on an integrated interface. Specifically, it converts email data with sentiment scores into JSON format using a JSON library and displays it on an interface accessible to users. This interface can be accessed via a web browser or a dedicated application.

[0464] Input: Email data with sentiment scores

[0465] Output: Display data on the integrated interface

[0466] Step 4:

[0467] The server recognizes the user's emotions from factors such as the tone of their voice, facial expressions, and the context of their messages. Specifically, it uses emotion recognition technology to analyze audio and video data to identify the user's emotional state. This allows the server to understand the user's emotional state in real time.

[0468] Input: Audio data, video data

[0469] Output: User emotional state data

[0470] Step 5:

[0471] The server recognizes the emotions of the factory staff and takes appropriate action based on those emotions. Specifically, based on emotional state data, it sends messages encouraging staff to take breaks if they are feeling stressed. It also notifies managers if important tasks are behind schedule.

[0472] Input: User's emotional state data

[0473] Output: Appropriate response message, notification to administrator

[0474] (Example 2)

[0475] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0476] In today's business environment, efficiently managing messages from multiple communication channels (email, communication tools, chat, messenger apps, etc.) is essential. However, it is difficult to centrally display these messages, differentiate between work and personal content, and adjust priorities based on emotions. Furthermore, while it is important to create and manage tasks based on message content, current systems cannot provide these functions in an integrated manner. This leads to problems such as users missing important messages and task management becoming cumbersome.

[0477] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0478] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between work and personal messages based on their content, means for analyzing message content and adjusting message priority based on sentiment, and means for creating and managing tasks based on message content. This enables users to centrally manage messages from multiple communication means, avoid missing important messages, and efficiently manage tasks.

[0479] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0480] A "message" refers to information such as text, images, audio, and video that is sent and received through communication methods.

[0481] "Unification" refers to integrating messages from multiple communication methods and displaying and managing them through a single interface.

[0482] "Classification" refers to the automatic categorization of messages based on their content and sender, determining whether they are work-related or personal.

[0483] "Emotional analysis" is the process of analyzing the content of a message and detecting the emotions contained within it (for example, joy, anger, sadness, etc.).

[0484] "Priority adjustment" refers to changing the display order and notification methods of messages based on the results of sentiment analysis.

[0485] "Tasking" refers to managing a message by breaking it down into specific work items based on its content.

[0486] "Management" refers to tracking task-based work items, checking their progress, and updating or correcting them as needed.

[0487] This invention is a system that centrally displays messages from multiple communication methods, categorizes messages as either work-related or personal based on their content, adjusts message priority based on emotions, and manages them as tasks based on their content.

[0488] Hardware and software to be used

[0489] Hardware: Servers, terminals (PCs, smartphones)

[0490] Software: Message analysis engine, emotion engine, generative AI model

[0491] System Overview

[0492] Message centralization

[0493] The server retrieves messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.) and displays them in a centralized manner. This allows users to view all messages in a single interface.

[0494] Message sorting

[0495] The server analyzes the sender address and content of received messages and automatically determines whether they are work-related or personal. Specifically, it makes this determination based on work email addresses and work-related keywords.

[0496] Prioritizing messages

[0497] The server uses an emotion engine to analyze the message content and detect the user's emotions (e.g., anger, frustration). Based on the intensity of the emotion, the server prioritizes the messages, and the terminal displays high-priority messages so that they are immediately visible to the user.

[0498] Tasking messages

[0499] The server creates and manages tasks based on the content of the messages. Task creation is based on the importance and urgency of the messages.

[0500] Specific example

[0501] Message sorting

[0502] Example: If a user receives a message from "boss@company.com" with the subject "Project Progress Report," the server will determine that the message is work-related. The server recognizes "boss@company.com" as a work email address and determines that the keyword "Project Progress Report" is work-related.

[0503] Prioritizing messages

[0504] Example: If a user receives the message "This project isn't progressing at all!", the emotion engine detects "anger" and sets the message as a high priority. The device then displays the message as a pop-up notification.

[0505] Example of a prompt

[0506] Prompt: "Analyze the following message and determine whether it is work-related or personal. Also, prioritize the message based on the user's sentiment. Message: 'This project is not progressing at all!'"

[0507] In this way, the system can automatically categorize messages based on their content, adjust message priorities based on the user's sentiment, and efficiently manage tasks.

[0508] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0509] Step 1:

[0510] Message received

[0511] The server retrieves new messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.).

[0512] Input: Message data from each communication method.

[0513] Output: List of retrieved messages.

[0514] Specific operation: The server calls the API of each communication method and polls to retrieve new messages.

[0515] Step 2:

[0516] Checking the sender address of the message

[0517] The server checks the sender address of the received message.

[0518] Input: A list of received messages.

[0519] Output: The source address of each message.

[0520] Specific operation: The server analyzes the message header information and extracts the source address.

[0521] Step 3:

[0522] Analysis of message content

[0523] The server analyzes the message body and checks if it contains business-related keywords.

[0524] Input: The body of each message.

[0525] Output: Analysis results for each message (presence or absence of keywords).

[0526] Specific operation: The server uses a natural language processing (NLP) engine to extract keywords from the message body.

[0527] Step 4:

[0528] Message Classification

[0529] The server automatically determines whether a message is work-related or personal based on the sender's address and content.

[0530] Input: The sender address and parsing result for each message.

[0531] Output: Classification result for each message (work-related or personal).

[0532] Specific operation: The server uses predefined rules and machine learning models to classify messages as either "work" or "private."

[0533] Step 5:

[0534] Sentiment analysis of messages

[0535] The server analyzes the content of received messages using an emotion engine.

[0536] Input: The body of each message.

[0537] Output: Sentiment score for each message.

[0538] Specific operation: The server calls the sentiment analysis API to obtain the sentiment score of the message.

[0539] Step 6:

[0540] Assessment of emotional intensity

[0541] The server evaluates the intensity of emotions based on the emotion score obtained from the emotion engine.

[0542] Input: Sentiment score for each message.

[0543] Output: Emotional intensity of each message (high, medium, low).

[0544] Specific operation: The server compares the emotion score to a threshold and classifies the intensity of the emotion as "high," "medium," or "low."

[0545] Step 7:

[0546] Message priority settings

[0547] The server prioritizes messages based on the intensity of emotion.

[0548] Input: Emotional intensity of each message.

[0549] Output: Priority of each message (high, medium, low).

[0550] Specific operation: The server sets the message priority to "high," "medium," or "low" depending on the intensity of the emotion.

[0551] Step 8:

[0552] Displaying messages

[0553] The device displays high-priority messages so that they are immediately visible to the user.

[0554] Input: Priority of each message.

[0555] Output: The message displayed to the user.

[0556] Specific action: The device uses its notification function to display high-priority messages as pop-ups.

[0557] Step 9:

[0558] Tasking messages

[0559] The server creates and manages tasks based on the content of the messages.

[0560] Input: The body and priority of each message.

[0561] Output: Messages managed as tasks.

[0562] Specific operation: The server analyzes the message content and registers it in the task management system.

[0563] In this way, the system can automatically categorize messages based on their content, adjust message priorities based on the user's sentiment, and efficiently manage tasks.

[0564] (Application Example 2)

[0565] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0566] In modern brick-and-mortar stores, it is difficult for staff to efficiently manage messages from multiple communication tools. Furthermore, they are required to differentiate between work and personal messages based on their content, and then prioritize them based on emotional factors, but no system exists to automate this process. This increases the risk of important messages being overlooked, potentially leading to a decline in the quality of customer service.

[0567] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0568] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for tasking and managing messages based on their content, means for analyzing the sentiment of messages and adjusting their priority, and means for enabling store staff to efficiently manage messages. This allows staff to respond quickly and appropriately without missing important messages.

[0569] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0570] A "message" refers to information sent and received in various formats, such as text, images, audio, and video.

[0571] "Centralization" refers to the process of consolidating data from multiple sources into a single location and managing it in a unified manner.

[0572] "Display" refers to providing data and information to users visually.

[0573] "Classification" refers to the process of classifying data or information based on specific criteria.

[0574] "Work" refers to activities and tasks related to one's duties or responsibilities.

[0575] "Private" refers to personal activities or tasks.

[0576] "Task-making" refers to converting the content of a message into specific tasks or action items.

[0577] "Management" refers to the efficient organization of data and information, and the manipulation and control of them as needed.

[0578] "Emotions" refers to the user's psychological state as interpreted from the content of the message.

[0579] "Analysis" refers to the process of thoroughly examining data and information to understand its meaning and structure.

[0580] "Priority" is an indicator that shows the importance or urgency of a task or message.

[0581] A "physical store" refers to a place of sale or service provision that exists in a physical location and can be visited directly by customers.

[0582] "Staff" refers to employees or staff who work at a physical store.

[0583] "Efficient" means achieving maximum results with minimum time and effort.

[0584] The following system configuration will be described as an embodiment for carrying out this invention.

[0585] System Configuration

[0586] hardware

[0587] Server: A central processing unit for centralized management and analysis of messages.

[0588] Devices: Devices used by staff, such as smartphones and smart glasses.

[0589] Network: Communication infrastructure used to connect servers and terminals.

[0590] software

[0591] Message Management System: A program that centralizes, categorizes, task-creates, analyzes sentiment, and prioritizes messages.

[0592] Sentiment analysis engine: Sentiment analysis libraries such as TextBlob.

[0593] User Interface: An application for staff to review and respond to messages.

[0594] Processing flow

[0595] 1. Centralized messaging

[0596] The server collects and centralizes messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.).

[0597] This allows staff to view all messages through a single interface.

[0598] 2. Classification of messages

[0599] The server analyzes the source and content of messages and automatically determines whether they are work-related or personal.

[0600] For example, if keywords such as "customer," "order," "complaint," or "inquiry" are included, it will be classified as work-related.

[0601] 3. Task Breakdown and Management

[0602] The server generates and manages tasks based on the classified messages.

[0603] Tasks are prioritized based on the importance and urgency of the message.

[0604] 4. Emotional Analysis and Prioritization

[0605] The server analyzes the sentiment of messages using sentiment analysis engines such as TextBlob.

[0606] Based on the analysis results, messages expressing anger or dissatisfaction are set as having a high priority.

[0607] For example, a message stating, "This is a customer complaint. They are very dissatisfied," will be displayed as a high-priority message.

[0608] 5. User Interface

[0609] Through applications installed on their devices, staff can check messages according to priority and respond quickly.

[0610] Specific example

[0611] For example, if a staff member at a physical store is using a smartphone, the following prompt message will be generated:

[0612] Analyze customer messages to determine whether they are work-related or personal, and use the sentiment engine to adjust their priority. For example, a message saying, "This is a customer complaint. They are very unhappy," would be considered work-related and therefore high-priority.

[0613] Based on this prompt, the server analyzes the message and performs appropriate classification and prioritization. This allows staff to respond quickly and appropriately without missing any important messages.

[0614] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0615] Step 1:

[0616] The server collects and centralizes messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.).

[0617] Input: Message data from various communication tools.

[0618] Data processing: Convert message data into a unified format and save it to the database.

[0619] Output: Centralized message data.

[0620] Specific operation: Use the API to retrieve messages from each communication tool, convert them to a unified format, and save them to the database.

[0621] Step 2:

[0622] The server analyzes the source and content of messages and automatically determines whether they are work-related or personal.

[0623] Input: Centralized message data.

[0624] Data processing: Analyze message content and classify it based on keywords.

[0625] Output: Classified message data (work-related or personal).

[0626] Specific operation: Uses natural language processing (NLP) techniques to analyze message content and detect keywords such as "customer," "order," "complaint," and "inquiry."

[0627] Step 3:

[0628] The server generates and manages tasks based on the classified messages.

[0629] Input: Classified message data.

[0630] Data processing: Convert messages into tasks and prioritize them based on importance and urgency.

[0631] Output: Tasked message data.

[0632] Specific actions: Analyze the message content, register it as a task in the task management system, and set its priority.

[0633] Step 4:

[0634] The server analyzes the sentiment of messages using sentiment analysis engines such as TextBlob.

[0635] Input: Tasked message data.

[0636] Data processing: Analyze the sentiment of the message using an emotion analysis engine and calculate the polarity.

[0637] Output: Sentiment analysis results (polarity value).

[0638] Specific operation: Use the TextBlob library to analyze the sentiment of a message and obtain a polarity value.

[0639] Step 5:

[0640] Based on the analysis results, the server prioritizes messages expressing anger or dissatisfaction.

[0641] Input: Sentiment analysis results (polarity value).

[0642] Data processing: Prioritize based on polarity values.

[0643] Output: Task data with assigned priorities.

[0644] Specific operation: If the polarity value falls below a certain threshold, the priority of that task will be set higher.

[0645] Step 6:

[0646] Through applications installed on their devices, staff members can check messages according to priority and respond quickly.

[0647] Input: Task data with assigned priorities.

[0648] Data processing: Display tasks based on priority.

[0649] Output: A list of tasks that staff can review.

[0650] Specific actions: Through smartphone or smart glasses applications, staff are notified of tasks according to priority and prompted to take action.

[0651] (Example 3)

[0652] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0653] In today's business environment, it is common to use multiple communication methods (email, communication tools, chat, messenger applications, etc.). However, it is difficult to centrally manage messages from these communication methods, separate work and personal messages, and automatically generate and manage tasks based on the content of messages. Furthermore, the lack of a function to adjust task priorities based on user emotions results in inefficient task management.

[0654] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0655] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for analyzing message content and automatically generating tasks, means for analyzing user sentiment and adjusting task priority, and means for adding and displaying generated tasks in a task list. This makes it possible to centrally manage messages from multiple communication means, distinguish between business and personal messages, and further adjust task priority based on user sentiment.

[0656] "Means of communication" refers to the means by which users send and receive messages, such as email, communication tools, chat, and messenger applications.

[0657] "Unification" refers to integrating messages from multiple communication methods and displaying them on a single interface.

[0658] "Work" refers to activities that a user engages in that are related to their job or duties.

[0659] "Private" refers to activities that users undertake for personal purposes.

[0660] "Analyzing the content of a message" refers to analyzing the text of a message using natural language processing techniques to understand its meaning and intent.

[0661] "Automatically generating tasks" refers to automatically creating a list of specific tasks and actions that the user should perform based on the content of the message.

[0662] "Analyzing user emotions" refers to using emotion analysis technology to determine the user's emotional state from the content and expression of a message.

[0663] "Adjusting task priorities" refers to setting the importance and urgency of generated tasks based on the user's emotions or other factors.

[0664] A "task list" refers to a list that displays a list of tasks that a user needs to complete.

[0665] "Displaying" refers to visually showing generated tasks and messages on the user's device.

[0666] This invention is a system that centrally displays messages from multiple communication methods, categorizes messages as either business-related or personal based on their content, automatically generates tasks by analyzing the message content, and adjusts task priorities by analyzing the user's emotions.

[0667] System Configuration

[0668] hardware

[0669] Server: Receives and analyzes messages, generates tasks, performs sentiment analysis, and manages tasks.

[0670] Device: Displays the task list on the device the user is using (PC, smartphone, tablet, etc.).

[0671] software

[0672] Natural Language Processing Engine: Used to analyze the content of messages. Specifically, it utilizes Google Cloud Natural Language API and Microsoft Azure® Text Analytics.

[0673] Sentiment analysis engine: Used to analyze user emotions. Specifically, it utilizes IBM Watson Tone Analyzer or Amazon Comprehend.

[0674] Database: Used to store generated tasks and messages.

[0675] System operation

[0676] Message received

[0677] The server receives messages sent by users. These messages are sent via email, communication tools, chat, messenger applications, etc.

[0678] Analysis of message content

[0679] The server uses a natural language processing engine to analyze the content of received messages. For example, it might use the Google Cloud Natural Language API to analyze messages and extract action phrases.

[0680] Task generation

[0681] The server generates tasks based on action phrases extracted by the NLP engine. For example, if the phrase "prepare for the meeting" is extracted, the server will generate a task called "prepare for the meeting".

[0682] Emotional analysis

[0683] The server uses a sentiment analysis engine to analyze the user's emotions from the message content. For example, it might use IBM Watson Tone Analyzer to analyze the sentiment of a message and determine that the user is excited.

[0684] Task priority setting

[0685] The server prioritizes tasks based on the results of the emotion analysis engine. For example, if a user is agitated, the related task will be given a higher priority.

[0686] Adding and displaying tasks to the task list

[0687] The server saves the generated task to the database and adds it to the task list. The terminal updates the user's task list to display the new task.

[0688] Specific example

[0689] Consider a scenario where a user sends the message, "I need to prepare for next week's meeting." Upon receiving this message, the server uses the Google Cloud Natural Language API to extract the phrase "prepare for the meeting" and generates a task. Then, IBM Watson Tone Analyzer is used to analyze the user's sentiment, and if it determines the user is agitated, this task is given a high priority.

[0690] Examples of prompts to input into a generative AI model:

[0691] You received the message, "I need to prepare for next week's meeting." Based on this message, generate tasks and prioritize them based on the user's sentiment.

[0692] In this way, users can manage tasks appropriately according to the content of the message. The flow of a specific process in Example 3 will be explained using Figure 21.

[0693] Step 1: Receiving a message

[0694] The server receives messages sent by users. These messages are sent via email, communication tools, chat, messenger applications, etc. The input is the message from the user, and the output is the received message data.

[0695] Step 2: Analyze the message content

[0696] The server uses a natural language processing engine to analyze the content of received messages. Specifically, it uses the Google Cloud Natural Language API to analyze messages and extract action phrases. The input is the received message data, and the output is the extracted action phrases.

[0697] Step 3: Task Generation

[0698] The server generates tasks based on action phrases extracted by the NLP engine. For example, if the phrase "prepare for the meeting" is extracted, the server generates the task "prepare for the meeting". The input is the extracted action phrase, and the output is the generated task data.

[0699] Step 4: Emotional Analysis

[0700] The server uses a sentiment analysis engine to analyze the user's emotions from the message content. Specifically, it uses IBM Watson Tone Analyzer to analyze the sentiment of the message and determine if the user is agitated. The input is the received message data, and the output is the analyzed sentiment data.

[0701] Step 5: Prioritizing tasks

[0702] The server prioritizes tasks based on the results of the sentiment analysis engine. For example, if a user is agitated, the associated tasks will be given a higher priority. The input consists of generated task data and analyzed sentiment data, and the output is the task data with the assigned priorities.

[0703] Step 6: Add and display the task list

[0704] The server saves the generated tasks to the database and adds them to the task list. The terminal updates the user's task list to display the new tasks. The input is task data with priority set, and the output is the updated task list.

[0705] (Application Example 3)

[0706] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0707] Traditional task management systems can generate tasks by analyzing message content, but they lack the functionality to adjust task priorities based on user emotions. This makes flexible task management that adapts to user feelings and circumstances difficult, potentially hindering efficient work execution. Furthermore, the inability to centrally manage messages from multiple communication sources leads to information scattering and management cumbersome issues.

[0708] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0709] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for creating and managing tasks based on their content, and means for analyzing the sentiment of messages and adjusting task priorities. This enables flexible task management that responds to the user's emotions and circumstances, thereby achieving efficient work execution.

[0710] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0711] "Unification" refers to the process of integrating data from multiple different sources and consolidating it into a single location.

[0712] "Display" refers to providing data and information to users visually.

[0713] "Classification" refers to the process of classifying data or information based on specific criteria.

[0714] "Work" refers to activities and tasks related to one's duties or job.

[0715] "Private" refers to an individual's private activities or tasks.

[0716] "Tasking" refers to generating specific work items based on the content of a message.

[0717] "Management" refers to the process of organizing, tracking, and completing tasks that have been generated.

[0718] "Emotions" refer to the psychological state or feelings that users express through messages.

[0719] "Analysis" refers to the process of thoroughly examining data and information to understand its meaning and structure.

[0720] "Priority" refers to the criteria used to determine the order of tasks or work based on their importance and urgency.

[0721] "Adjustment" refers to changing settings or states based on specific criteria or conditions.

[0722] The system for implementing this invention centrally displays messages from multiple communication methods, categorizes them as either business or personal based on their content, and automatically generates and manages tasks based on the message content. It also includes a function to analyze the sentiment of the messages and adjust the priority of tasks.

[0723] Hardware and software to use

[0724] Hardware: Robots, servers, and user terminals (smartphones, tablets, PCs, etc.) within the factory.

[0725] Software: Python, TextBlob (sentiment analysis library), messaging APIs (email, chat tools, etc.)

[0726] Data processing and data calculation

[0727] Message centralization and display

[0728] The server collects messages from multiple communication channels, centralizes them, and displays them on the user's terminal. This allows the user to view all messages through a single interface.

[0729] Message sorting

[0730] The server analyzes the message content and automatically distinguishes between work-related and personal messages. For example, if a message contains the phrase "prepare for the meeting," it will be classified as work-related.

[0731] Task automation and management

[0732] The server automatically generates tasks based on the content of messages and adds them to the task list. For example, if a message saying "Prepare for the meeting" is received, a task called "Prepare for the meeting" will be generated based on its content.

[0733] Emotion analysis and prioritization

[0734] The server uses TextBlob to analyze the sentiment of a message and determine whether it is positive or negative. Based on the sentiment analysis, it dynamically adjusts the priority of the generated tasks. For example, if a user sends a positive message such as "I'm really looking forward to today!", tasks related to that message will be given a higher priority.

[0735] Specific example

[0736] Message examples

[0737] Message: "Preparing for the meeting. I'm really looking forward to it today!"

[0738] Task generated: "Prepare for the meeting"

[0739] Priority: High

[0740] Example of a prompt

[0741] Message: "Preparing for the meeting. I'm really looking forward to it today!"

[0742] Task generated: "Prepare for the meeting"

[0743] Priority: High

[0744] In this way, the server analyzes messages, automatically generates tasks, and sets priorities, enabling flexible task management that responds to the user's emotions and circumstances. This allows for efficient work execution.

[0745] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0746] Step 1:

[0747] The server collects messages from multiple communication methods (email, chat tools, etc.).

[0748] Input: Message data from each communication method

[0749] Output: Centralized message list

[0750] Specific operation: The server retrieves messages using the API of each communication method and consolidates them into a single list.

[0751] Step 2:

[0752] The server analyzes the collected messages and distinguishes between work-related and personal messages.

[0753] Input: Centralized message list

[0754] Output: Sorted message list (work-related, personal)

[0755] Specific operation: The server uses natural language processing (NLP) techniques to analyze the content of messages and classify them as either work-related or personal based on specific keywords or phrases.

[0756] Step 3:

[0757] The server automatically generates tasks from business-related messages and adds them to the task list.

[0758] Input: Business-related message

[0759] Output: Generated task list

[0760] Specific operation: The server parses business-related messages, extracts action phrases, generates tasks, and adds them to the task list.

[0761] Step 4:

[0762] The server analyzes the sentiment of messages and adjusts task priorities accordingly.

[0763] Input: Business-related messages, generated task list

[0764] Output: Task list with adjusted priorities

[0765] Specific operation: The server uses sentiment analysis libraries such as TextBlob to analyze the sentiment of a message, prioritizing tasks based on positive sentiment and lowering them based on negative sentiment.

[0766] Step 5:

[0767] The server displays a task list with adjusted priorities on the user's terminal.

[0768] Input: Task list with adjusted priority

[0769] Output: Task list displayed on the user's terminal

[0770] Specific operation: The server sends a task list to the user's terminal and displays it for the user to visually confirm.

[0771] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0772] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0773] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are examples.

[0774] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0775] [Second Embodiment]

[0776] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0777] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0778] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0779] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0780] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0781] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0782] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0783] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0784] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0785] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0786] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0787] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0788] "Example of form 1"

[0789] The system of the present invention has means for centrally displaying messages from multiple communication tools. Specifically, it collects messages from email, communication tools, chat, messenger apps, etc., and displays them in a list on a single interface. This allows the user to see at a glance which tool a message originated from.

[0790] "Example of form 2"

[0791] Furthermore, the system of the present invention has means for distinguishing between work-related and personal messages based on their content. Specifically, it analyzes the sender and content of a message and automatically determines whether it is work-related or personal. For example, if the sender of a message is a work email address, or if the message content contains work-related keywords, the message is determined to be work-related.

[0792] "Example of form 3"

[0793] Furthermore, the system of the present invention has means for creating and managing tasks based on the content of messages. Specifically, it analyzes the content of a message and automatically generates tasks based on it. For example, if the content of a message includes a phrase indicating an action such as "prepare for the meeting," it generates a task based on that phrase and adds it to the task list. This allows the user to manage tasks appropriately according to the content of the message.

[0794] The following describes the processing flow for each example of the form.

[0795] "Example of form 1"

[0796] Step 1: The system collects messages from email, communication tools, chat, messenger apps, etc.

[0797] Step 2: Display the collected messages in a list on a single interface.

[0798] Step 3: Users can see at a glance which tool a message is from by looking at the list of messages.

[0799] "Example of form 2"

[0800] Step 1: The system analyzes the source and content of the message.

[0801] Step 2: Based on the analysis, the system automatically determines whether the message is work-related or personal.

[0802] Step 3: For example, if the message is sent from a work email address or contains work-related keywords, the message is considered work-related.

[0803] "Example of form 3"

[0804] Step 1: The system analyzes the content of the message.

[0805] Step 2: Based on the analysis results, automatically generate tasks based on the messages.

[0806] Step 3: For example, if the message contains a phrase indicating an action, such as "prepare for the meeting," generate a task based on that phrase and add it to the task list.

[0807] Step 4: This allows users to manage tasks appropriately based on the content of the message.

[0808] (Example 1)

[0809] Next, we will describe Embodiment 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0810] In today's business environment, it's common for users to receive messages using multiple communication methods. However, this makes message management cumbersome and increases the risk of missing important messages. Furthermore, there's the challenge of categorizing messages as work-related or personal based on their content, and then managing them as tasks.

[0811] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0812] In this invention, the server includes means for collecting messages from multiple communication means, means for centralizing the collected messages, and means for storing the centralized messages. This allows the user to view messages from multiple communication means through a single interface and manage them efficiently without missing important messages.

[0813] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0814] "Means for collecting messages" refers to a function for obtaining new messages from multiple communication methods.

[0815] "A means of centralizing messages" refers to a function that converts collected messages into a common data format and manages them uniformly.

[0816] "Means of saving messages" refers to a function for storing centralized messages in a storage device such as a database.

[0817] "Means for displaying messages" refers to a function that displays saved messages on the interface so that users can view them.

[0818] "Means of manipulating messages" refer to functions that allow users to click on displayed messages to view details or to reply.

[0819] "Means for distinguishing between work and personal matters" refers to a function that determines whether a message is work-related or personal based on its content.

[0820] "A means of creating and managing tasks" refers to a function that classifies messages into tasks based on their content and manages them according to their importance and urgency.

[0821] Modes for carrying out the invention

[0822] This invention is a system that centrally displays messages from multiple communication methods, further categorizes them as either work-related or personal based on their content, and manages them as tasks. A specific embodiment of this system is described below.

[0823] Server Role

[0824] The server is responsible for collecting messages from multiple communication channels. Specifically, it uses APIs from email servers, communication tools (e.g., Slack, Microsoft Teams), chat apps (e.g., WhatsApp, LINE), and messenger apps (e.g., Facebook Messenger) to retrieve new messages. The server centralizes these messages and converts them into a common data format. The converted messages are then stored in relational databases such as MySQL or PostgreSQL.

[0825] Terminal role

[0826] The device provides an interface for users to view and interact with messages. Specifically, it displays a list of messages retrieved from the server via a web or mobile application. For example, the frontend could be built using React or Vue.js to allow users to visually review messages. Messages are color-coded by tool: emails are displayed in blue, communication tools in green, and chat apps in red.

[0827] User actions

[0828] Users interact with messages using an interface on their device. Specifically, they can click on a particular message to view details or reply to it. Users can also use a filter function to display only messages from specific communication methods. Furthermore, they can categorize messages as work-related or personal based on their content and manage them as tasks. Task creation is based on the importance and urgency of the message.

[0829] Specific example

[0830] For example, consider a scenario where a user receives messages from multiple communication channels while at work. This system allows the user to view messages from email, Slack, WhatsApp, and Facebook Messenger in a single interface. This enables them to quickly identify the source of each message and respond promptly.

[0831] Example of a prompt

[0832] Examples of prompt statements to input into a generative AI model include the following:

[0833] Please describe a system that centralizes and displays messages from multiple communication methods. Specifically, please specify what hardware and software are used, and what kind of data processing and calculations are performed. Also, please provide concrete examples.

[0834] By using this prompt statement, the generative AI model can generate a detailed description of the system.

[0835] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0836] Program processing flow

[0837] Step 1: Collecting Messages

[0838] The server collects messages from multiple communication methods. It uses API endpoints such as email servers, communication tools (e.g., Slack, Microsoft Teams), chat apps (e.g., WhatsApp, LINE), and messenger apps (e.g., Facebook Messenger) as input. The server sends requests to these APIs to retrieve new messages. The output is message data obtained from each communication method.

[0839] Step 2: Centralize messages

[0840] The server centralizes the collected messages. It uses the message data collected in Step 1 as input. Specifically, it converts messages obtained from each communication method into a common data format. For example, an email message has fields such as "sender," "subject," "body," and "received date and time," while a Slack message has fields such as "sender," "channel," "message content," and "sent date and time." The server unifies these fields and converts them into a single data format. The output is the centralized message data.

[0841] Step 3: Save the message

[0842] The server stores the centralized messages in a database. It uses the message data centralized in step 2 as input. Specifically, it uses a relational database such as MySQL or PostgreSQL to store the message data in a table. For example, the message table may have columns such as "Message ID," "Sender," "Content," "Tool Name," and "Received Date and Time," ensuring each message is uniquely identified. The output is the message data stored in the database.

[0843] Step 4: Displaying the message

[0844] The device provides an interface for users to view messages. It uses message data retrieved from the server as input. Specifically, it displays a list of messages through a web or mobile application. For example, the frontend is built using React or Vue.js to allow users to visually view messages. Messages are color-coded by tool: email is displayed in blue, communication tools in green, and chat apps in red. The output is a list of messages viewable by the user.

[0845] Step 5: Message manipulation

[0846] Users interact with messages using an interface on their device. The displayed message list serves as input. Specifically, they can click on a particular message to view details or reply. Users can also use a filter function to display only messages from specific communication methods. Furthermore, they can categorize messages as work-related or personal based on their content and manage them as tasks. The output is the result of the user's actions.

[0847] (Application Example 1)

[0848] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0849] In logistics centers, messages are scattered across multiple communication tools (email, communication tools, chat, messenger apps, etc.), making it difficult for staff to quickly grasp and respond to information. This also reduces operational efficiency and increases the risk of important communications being overlooked.

[0850] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0851] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on their content, means for integrating messages collected from multiple communication tools so that logistics center staff can understand them at a glance on their smartphones, and means for centrally displaying messages from multiple communication tools used within the logistics center. As a result, logistics center staff can quickly understand which tool a message is coming from and respond promptly.

[0852] "Multiple communication tools" refers to different types of messaging methods, such as email, communication tools, chat, and messenger apps.

[0853] "A means of centralized display" refers to a function that collects messages from multiple communication tools and displays them in a list on a single interface.

[0854] "Means of sorting" refers to the function of classifying messages based on their content, determining whether they are work-related or personal.

[0855] "A means of creating and managing tasks" refers to a function that generates tasks based on the content of a message and manages those tasks.

[0856] A "logistics center" refers to a facility that stores, sorts, and distributes goods.

[0857] "Staff" refers to employees working at the logistics center.

[0858] A "smartphone" refers to a mobile phone that is capable of connecting to the internet and using applications.

[0859] "Means of integration" refers to the function of consolidating messages collected from multiple communication tools into a single system.

[0860] "Responding quickly" means taking the necessary action promptly after receiving a message.

[0861] The system for implementing this invention is for centrally displaying messages from multiple communication tools in a logistics center. Specifically, the server includes the following means:

[0862] First, the server collects messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.). This involves using Python's imaplib and email libraries to retrieve emails from an IMAP server, using the slack_sdk library to collect Slack messages, and using the WhatsApp API to collect WhatsApp messages.

[0863] Next, the server uses Flask to provide an API endpoint for centrally displaying the collected messages. This allows logistics center staff to view all messages on a single interface using their smartphones.

[0864] Furthermore, the server categorizes messages based on their content, determining whether they are work-related or personal. This allows staff to quickly identify and respond to important messages.

[0865] Furthermore, the server generates and manages tasks based on the content of the messages. This makes it possible to take appropriate actions based on the importance and urgency of the messages.

[0866] As a concrete example, when a logistics center staff member opens the "Logistics Messaging Integration App" on their smartphone, messages from email, Slack, and WhatsApp are displayed in a single screen. This allows staff to see at a glance which tool a message originated from and respond quickly.

[0867] Examples of prompt statements are as follows:

[0868] When logistics center staff open the "Logistics Messaging Integration App" on their smartphones, messages from email, Slack, and WhatsApp are displayed in a single screen. This allows staff to see at a glance which tool a message is coming from and respond quickly.

[0869] In this way, the efficiency of message management in logistics centers can be significantly improved.

[0870] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0871] Step 1:

[0872] The server retrieves email from the IMAP server. Specifically, it uses the imaplib and email libraries to log in to the specified email account and retrieve all emails from the inbox. The input is the email server's authentication information, and the output is data including the email sender, subject, and body.

[0873] Step 2:

[0874] The server retrieves messages from Slack. Specifically, it uses the slack_sdk library to retrieve messages from a specified Slack channel. The input is the Slack API token and channel ID, and the output is data containing the user ID and message text.

[0875] Step 3:

[0876] The server retrieves messages from WhatsApp. Specifically, it uses the WhatsApp API to retrieve messages from a specified WhatsApp account. The input is a WhatsApp API token, and the output is data containing the sender and message text.

[0877] Step 4:

[0878] The server centralizes all acquired messages. Specifically, it integrates messages from email, Slack, and WhatsApp, and combines them into a single data structure. The input is message data acquired from each communication tool, and the output is an integrated message list.

[0879] Step 5:

[0880] The server will serve the integrated messages from the API endpoint using Flask. Specifically, it will use the Flask framework to build an API that returns an integrated message list in JSON format. The input is the integrated message list, and the output is the JSON data provided from the API endpoint.

[0881] Step 6:

[0882] The user opens the "Logistics Message Integration App" on their smartphone. Specifically, they access the server's API endpoint using their smartphone's browser or a dedicated app. The input is the URL of the API endpoint, and the output is a list of integrated messages.

[0883] Step 7:

[0884] The user reviews the displayed messages and takes action as needed. Specifically, they review the message content and take appropriate action based on its importance and urgency. The input is a list of integrated messages, and the output is the user's actions.

[0885] (Example 2)

[0886] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0887] In today's business environment, there is a need to efficiently manage messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.). However, it is difficult to centralize these messages, further categorize them based on their content as work-related or personal, and manage them appropriately as tasks. In particular, there is a need to accurately analyze the sender and content of messages and quickly notify users of the classification results, but current systems cannot do this efficiently.

[0888] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0889] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for analyzing the source addresses of messages, means for analyzing the content of messages using a generative AI model and distinguishing between work and personal messages, means for creating and managing tasks based on the content of the messages, and means for notifying the user's terminal of the classification results. This makes it possible to efficiently centrally manage messages from multiple communication means, appropriately classify and create tasks based on their content, and quickly notify the user.

[0890] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0891] "Sender address" refers to information such as the email address or user ID of the sender who sent the message.

[0892] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze text data and understand and classify its content.

[0893] "Message content" refers to the main body of text data sent and received through a communication method.

[0894] "Means of centralized display" refers to a function that integrates messages obtained from multiple communication methods into a single interface for display.

[0895] "Means of analysis" refers to a function that analyzes the sender address and content of a message and extracts its characteristics.

[0896] "Means of sorting" refers to a function that automatically classifies whether a message is work-related or personal based on its analyzed content.

[0897] "A means of creating and managing tasks" refers to a function that generates tasks based on categorized messages and manages those tasks.

[0898] "Means for notifying of classification results" refers to a function that informs the user's device of the results of the sorting process.

[0899] This invention relates to a system that centrally displays messages from multiple communication methods, analyzes the source address and content of the messages to distinguish between work and personal messages, and further manages them as tasks based on their content. A specific embodiment of this system is shown below.

[0900] System Configuration

[0901] The server is comprised of the following hardware and software:

[0902] Hardware: A server machine equipped with a high-performance processor, sufficient memory, storage devices, and network interfaces.

[0903] Software: Mail server (supporting IMAP protocol), generative AI model (e.g., OpenAI's GPT-4), natural language processing library (e.g., NLTK and spaCy), notification system (e.g., Pushbullet).

[0904] Message received

[0905] The server receives messages sent by users. Specifically, it retrieves messages through email servers and chat application APIs. For example, it retrieves messages from an email server using the IMAP protocol.

[0906] Source analysis

[0907] The server analyzes the message's sender address. Specifically, it analyzes the message's header information to extract the sender address. For example, if the sender is a business email address like "@company.com", the server determines that the message is work-related.

[0908] Content analysis

[0909] The server analyzes the message content using natural language processing (NLP) techniques. This analysis uses a generative AI model (for example, OpenAI's GPT-4). Specifically, the following prompt sentences are input to the generative AI model.

[0910] Prompt: "Please determine whether the following message is work-related or personal. Message: 'Please prepare the materials for tomorrow's meeting.'"

[0911] The server receives the response from the generated AI model and determines whether the message is work-related or personal.

[0912] Notification of classification results

[0913] The server classifies messages as "work" or "personal" based on the analysis results and notifies the user's device of the result. Specifically, the result is notified via push notification or email. For example, the Pushbullet library is used to send push notifications.

[0914] Specific example

[0915] When a user receives the message "Please prepare the materials for tomorrow's meeting," the server processes it as follows:

[0916] 1. Verify that the message is sent from a business email address ending in "@company.com".

[0917] 2. Analyze the message content to determine if it contains business-related keywords such as "meeting" or "documents."

[0918] 3. Based on this information, categorize the messages as "work."

[0919] 4. Notify the user's device of the classification results.

[0920] In this way, it becomes possible to efficiently centrally manage messages from multiple communication methods, appropriately classify and assign tasks based on their content, and quickly notify users.

[0921] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0922] Step 1:

[0923] Message received

[0924] The server receives messages sent by users. Specifically, it retrieves messages through email servers and chat application APIs. For example, it retrieves messages from an email server using the IMAP protocol.

[0925] Input: Message sent by the user

[0926] Output: Message data stored on the server

[0927] Step 2:

[0928] Source analysis

[0929] The server analyzes the message's sender address. Specifically, it analyzes the message's header information to extract the sender address. For example, if the sender is a business email address like "@company.com", the server determines that the message is work-related.

[0930] Input: Message data stored on the server

[0931] Output: Source address analysis results

[0932] Step 3:

[0933] Content analysis

[0934] The server analyzes the message content using natural language processing (NLP) techniques. This analysis uses a generative AI model (for example, OpenAI's GPT-4). Specifically, the following prompt sentences are input to the generative AI model.

[0935] Prompt: "Please determine whether the following message is work-related or personal. Message: 'Please prepare the materials for tomorrow's meeting.'"

[0936] The server receives the response from the generated AI model and determines whether the message is work-related or personal.

[0937] Input: Message content

[0938] Output: Message classification result (work or personal)

[0939] Step 4:

[0940] Notification of classification results

[0941] The server classifies messages as "work" or "personal" based on the analysis results and notifies the user's device of the result. Specifically, the result is notified via push notification or email. For example, the Pushbullet library is used to send push notifications.

[0942] Input: Message classification result

[0943] Output: Notification sent to the user's device

[0944] Step 5:

[0945] Task creation and management

[0946] The server generates and manages tasks based on classified messages. Specifically, it prioritizes tasks based on the importance and urgency of the messages and notifies users at the appropriate time.

[0947] Input: Classified message

[0948] Output: Tasks registered in the task management system

[0949] The above describes the specific processing flow of this system's program.

[0950] (Application Example 2)

[0951] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0952] Many modern users utilize multiple communication tools, resulting in a mix of work-related and personal messages. This makes message management cumbersome, particularly in determining whether expense-related messages are work-related or personal. Furthermore, improper expense classification can lead to problems with expense reimbursement and personal financial management. Therefore, a system is needed that automatically categorizes expenses based on message content, allowing users to easily review them.

[0953] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for classifying messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for analyzing the source and content of messages to automatically determine whether an expense is work-related or personal, and means for displaying the expense classification results so that the user can confirm them. As a result, the user can centrally manage messages from multiple communication tools and automatically classify and confirm expenses.

[0954] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[0955] A "message" refers to information such as text, images, audio, and video that is sent and received through communication tools.

[0956] "Centralization" refers to consolidating and displaying messages from multiple communication tools into a single interface.

[0957] "Classification" refers to judging and classifying messages based on their content, determining whether they are work-related or personal.

[0958] "Tasking" refers to managing a message by breaking it down into specific work items based on its content.

[0959] "Sender information" refers to the information of the person who sent the message.

[0960] "Analysis" refers to the process of analyzing the source and content of a message and making decisions based on specific criteria.

[0961] "Expenses" refers to information related to monetary payments.

[0962] "Classification result" refers to the result of classifying expenditures based on the content of the message.

[0963] "Display" refers to providing classification results visually so that users can confirm them.

[0964] A system for carrying out this invention includes means for centrally displaying messages from multiple communication tools, means for classifying messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for analyzing the sender and content of messages to automatically determine whether an expense is work-related or personal, and means for displaying the expense classification results so that the user can review them.

[0965] System program

[0966] The program for this system will be implemented using a programming language such as Python. The program will perform the following operations:

[0967] 1. Centralizing messages:

[0968] The server collects messages from email, communication tools, chat, messenger apps, etc., and aggregates them into a single interface. This allows users to view messages from multiple communication tools in one place.

[0969] 2. Message sorting:

[0970] The server analyzes the sender and content of messages to automatically determine whether they are work-related or personal. For example, if the sender is a work email address, or if the message contains work-related keywords such as "meeting expenses" or "travel expenses," the message will be classified as work-related.

[0971] 3. Taskification:

[0972] The server creates tasks based on sorted messages. Task creation is based on the importance and urgency of the messages. This allows users to prioritize and manage important tasks.

[0973] 4. Classification of expenditures:

[0974] The server analyzes the source and content of messages to automatically determine whether an expense is work-related or personal. For example, if a payment notification is sent from a work email address, or if the message contains work-related keywords such as "meeting expenses" or "travel expenses," the expense will be classified as work-related.

[0975] 5. Displaying classification results:

[0976] The server displays the expenditure classification results so that users can easily review and properly manage their spending.

[0977] Hardware and software to be used

[0978] Hardware: Smartphones, servers

[0979] Software: Python, database management systems (e.g., MySQL), messaging APIs (e.g., Gmail API)

[0980] Specific example

[0981] For example, consider a scenario where a user receives the following message.

[0982] Sender: "boss@work-email.com"

[0983] Message: "Regarding the cost of the next meeting"

[0984] In this case, the server classifies this message as "work" and manages the expense as work-related.

[0985] Example of a prompt

[0986] The following are examples of prompts to input into the generating AI model.

[0987] Sender: "boss@work-email.com"

[0988] Message: "Regarding the cost of the next meeting"

[0989] Is this message work-related or personal?

[0990] This prompt can be used to ask a generative AI model to classify a message.

[0991] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0992] Step 1:

[0993] The server collects messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.). It receives message data obtained through the APIs of each communication tool as input. As output, it stores these messages in a centralized database. Specifically, the server calls the API of each communication tool, retrieves the message data, and stores it in the database.

[0994] Step 2:

[0995] The server analyzes the source and content of collected messages and automatically determines whether they are work-related or personal. It receives message data stored in a database as input and generates a classification result (work or personal) for each message as output. Specifically, the server analyzes message content using regular expressions and keyword matching and stores the classification results in the database.

[0996] Step 3:

[0997] The server creates tasks based on the sorted messages. It receives message data, including the classification results, as input. It generates tasked data as output. Specifically, the server evaluates the importance and urgency of messages and saves them as tasks in the database.

[0998] Step 4:

[0999] The server analyzes the source and content of messages to automatically determine whether an expense is work-related or personal. It receives message data stored in a database as input and generates expense classification results as output. Specifically, the server classifies expenses based on message content and saves the results to the database.

[1000] Step 5:

[1001] The server displays the expenditure classification results for the user to review. It receives data containing expenditure classification results as input and generates data to display in the user interface as output. Specifically, the server provides the classification results visually to the user through a web page or mobile application.

[1002] Step 6:

[1003] The user inputs a prompt message into the generative AI model and requests that it classify the message. The input is the prompt message sent to the generative AI model. The output is the classification result received from the generative AI model. Specifically, the user inputs a prompt message like the following:

[1004] Sender: "boss@work-email.com"

[1005] Message: "Regarding the cost of the next meeting"

[1006] Is this message work-related or personal?

[1007] This prompt can be used to ask a generative AI model to classify a message.

[1008] (Example 3)

[1009] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[1010] In today's business environment, it is common to use multiple communication methods (email, communication tools, chat, messenger apps, etc.). However, it is difficult to centrally manage messages from these communication methods, separate work and personal matters, and automatically generate and manage tasks based on the content of the messages. As a result, users have to manually check the content of messages and manually generate tasks, which presents a challenge in efficient task management.

[1011] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1012] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for analyzing the content of messages and automatically generating tasks based on the analysis results, and means for adding the generated tasks to a task list and managing them. This enables users to centrally manage messages from multiple communication means, distinguish between business and personal messages, and automatically generate tasks based on the content of messages, thereby enabling efficient task management.

[1013] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1014] "Centralization" refers to the process of consolidating and displaying messages from multiple communication methods in a single location.

[1015] "Work" refers to activities and tasks related to one's duties or job.

[1016] "Personal business" refers to personal errands or private activities.

[1017] "Distinguishing" refers to distinguishing between business and personal messages based on their content.

[1018] "Analysis" refers to the process of analyzing the content of a message using natural language processing techniques to understand its meaning.

[1019] A "task" refers to a specific action or task, and is a concrete work item generated based on the content of a message.

[1020] A "task list" is a list used to display and manage tasks that have been generated.

[1021] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[1022] This invention is a system that centralizes messages from multiple communication methods, categorizes them as either business or personal based on their content, analyzes the message content to automatically generate tasks, and adds them to a task list for management.

[1023] Hardware and software to be used

[1024] hardware

[1025] User's device (PC, smartphone, etc.)

[1026] software

[1027] Natural language processing technologies (Google Cloud Natural Language API, IBM Watson Natural Language Understanding, etc.)

[1028] Program processing

[1029] Server Processing

[1030] The server analyzes messages received from users. Specifically, the server uses natural language processing techniques to analyze the message content and extract phrases that indicate actions. This analysis utilizes software such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1031] Once the analysis is complete, the server automatically generates tasks based on the extracted phrases. The generated tasks are added to a task list and managed so that the user can review them later. For example, if the message contains the phrase "prepare for the meeting," the server generates a task called "prepare for the meeting" and adds it to the task list.

[1032] Terminal processing

[1033] The terminal's role is to send messages entered by the user to the server. When the user enters a message and presses the send button, the terminal sends that message to the server. For example, if the user enters "I need to prepare for tomorrow's meeting," that message will be sent from the terminal to the server.

[1034] User processing

[1035] Users manage tasks by typing messages using their devices. When a user types a message, it is sent to the server via the device. The server parses the message and generates a task, which the user can then view in their task list. For example, if a user types "Create presentation materials for next week," a task titled "Create presentation materials" will be generated based on that content.

[1036] Specific example

[1037] Example of a prompt

[1038] When you enter the message "I need to prepare for tomorrow's meeting," the server generates a task called "Prepare for meeting" and adds it to your task list.

[1039] This system allows users to automatically generate tasks based on message content and manage tasks efficiently. The flow of a specific process in Example 3 will be explained using Figure 15.

[1040] Step 1: The user enters a message.

[1041] The user enters the message using a device (such as a PC or smartphone). For example, the user might type, "I need to prepare for tomorrow's meeting." This input is saved on the device as a text message.

[1042] Step 2: The device sends the message to the server.

[1043] When a user types a message and presses the send button, the device sends that message to the server. Specifically, the device sends text-formatted message data to the server via the internet connection. The input is the user's message, and the output is the message sent to the server.

[1044] Step 3: The server receives the message.

[1045] The server receives messages sent from the terminal. The received messages are stored on the server as text data. The input is the message data from the terminal, and the output is the message data stored on the server.

[1046] Step 4: The server parses the message.

[1047] The server analyzes the received message. Specifically, the server uses natural language processing technologies (such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding) to analyze the message content and extract action phrases. The input is the message data stored on the server, and the output is the extracted action phrases.

[1048] Step 5: The server generates the task.

[1049] The server automatically generates tasks based on the analysis results. It creates specific tasks based on the extracted phrases. For example, it generates the task "Prepare for the meeting" from the phrase "Prepare for the meeting." The input is the extracted action phrase, and the output is the generated task.

[1050] Step 6: The server updates the task list.

[1051] The server adds the generated tasks to the task list. The task list is stored in a database and managed so that users can review it later. The input is the generated tasks, and the output is the updated task list.

[1052] Step 7: The user checks the task list.

[1053] The user uses a terminal to view the task list. The task list displays tasks generated by the server. This allows the user to view and manage tasks that have been automatically generated based on the content of messages. The input is the updated task list, and the output is the task list displayed on the user's screen.

[1054] (Application Example 3)

[1055] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1056] Conventional message management systems lacked the ability to automatically generate tasks based on message content and issue instructions to machines, resulting in decreased work efficiency within factories. Furthermore, the inability to analyze message content and generate appropriate tasks could lead to delays and errors. This, in turn, compromised factory productivity and safety.

[1057] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1058] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on the message content, means for analyzing the message content, generating specific tasks for a machine based on the analysis results, and adding them to a task list, and means for instructing the machine on the generated tasks. This makes it possible to automatically generate appropriate tasks based on the message content and instruct the machine. As a result, the work efficiency in the factory can be improved and delays and errors in work can be reduced.

[1059] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1060] "Messages" refer to text information and instructions sent and received through communication tools.

[1061] "Centralization" refers to consolidating messages from multiple communication tools into a single platform or interface.

[1062] "Discrimination" refers to distinguishing whether a message is work-related or personal based on its content.

[1063] "Task creation" refers to analyzing the content of a message and generating specific tasks or instructions based on that analysis.

[1064] "Management" refers to adding generated tasks to a list and tracking their progress and completion status.

[1065] "Analysis" refers to understanding the content of a message using techniques such as natural language processing and extracting its meaning.

[1066] "Machinery" refers to robots and automated equipment used within a factory.

[1067] A "task list" refers to a list used to display and manage generated tasks in a list format.

[1068] "Instructions" refer to giving specific commands to a machine based on the generated task.

[1069] The system for carrying out this invention includes an application installed on a robot used in a factory. Specific embodiments of this system are described below.

[1070] System Configuration

[1071] The system consists of the following main components:

[1072] 1. Server: Centralizes and displays messages from multiple communication tools.

[1073] 2. Natural Language Processing (NLP) Engine: Analyzes the content of messages and generates tasks based on the analysis results.

[1074] 3. Task Manager: Add and manage generated tasks in the task list.

[1075] 4. Robot Controller: Instructs the robot on the generated tasks.

[1076] Hardware and software to be used

[1077] Hardware: Robots in factories

[1078] Software: Python, spaCy (natural language processing library), TaskManager (task management system), RobotController (robot control system)

[1079] Processing flow

[1080] 1. Receiving messages: The server receives messages from communication tools such as email, communication tools, chat, and messenger apps.

[1081] 2. Message centralization: Received messages are aggregated and displayed on a single platform.

[1082] 3. Message Analysis: The content of the message is analyzed using a natural language processing engine (spaCy) and its meaning is extracted.

[1083] 4. Task Generation: Based on the analysis results, specific tasks are generated. For example, if the message "Perform maintenance on line 1" is received, a maintenance task is generated.

[1084] 5. Add to task list: Add the generated task to the task list and manage it.

[1085] 6. Instructions to the robot: Instruct the robot to execute the tasks added to the task list.

[1086] Specific example

[1087] For example, consider the case where the following message is received:

[1088] Message: "Performing maintenance on line 1"

[1089] Program processing: Analyzes messages, generates "maintenance" tasks, and issues instructions to the robot.

[1090] Examples of prompts to input into a generative AI model:

[1091] "We have received a message indicating that maintenance will be performed on line 1. Based on this message, generate a maintenance task and issue instructions to the robot."

[1092] In this way, it becomes possible to automatically generate tasks and issue instructions to robots based on messages within the factory. This improves work efficiency within the factory and reduces delays and errors.

[1093] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1094] Step 1:

[1095] The server receives messages from communication tools such as email, communication tools, chat, and messenger apps. The input is messages sent from each communication tool, and the output is centralized message data. Specifically, messages are retrieved using the APIs of each communication tool and stored in a database.

[1096] Step 2:

[1097] The server aggregates and displays received messages on a single platform. The input is centralized message data, and the output is a user-accessible integrated message interface. Specifically, it retrieves messages from a database and displays them on a web interface or application screen.

[1098] Step 3:

[1099] The server uses a natural language processing engine (spaCy) to analyze message content and extract meaning. The input is centralized message data, and the output is the analyzed message content. Specifically, the spaCy model is loaded, and the message text is analyzed to extract important keywords and phrases.

[1100] Step 4:

[1101] The server generates specific tasks based on the analysis results. The input is the analyzed message content, and the output is the generated task. Specifically, it determines the type and details of the task based on the extracted keywords and phrases, and generates a task object.

[1102] Step 5:

[1103] The server adds and manages the generated tasks to a task list. The input is the generated tasks, and the output is the updated task list. Specifically, it saves task objects to the database and updates the task list.

[1104] Step 6:

[1105] The server instructs the robot to execute tasks added to the task list. The input is the updated task list, and the output is the robot's execution status. Specifically, the generated tasks are sent to the robot via the robot controller, and their execution status is monitored.

[1106] In this way, it becomes possible to automatically generate tasks and issue instructions to robots based on messages within the factory. This improves work efficiency within the factory and reduces delays and errors.

[1107] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1108] "Example of form 1"

[1109] One embodiment of the present invention provides a system that combines an emotion engine. This system includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, and an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions, for example, from the user's tone of voice, facial expressions, and the context of the message.

[1110] "Example of form 2"

[1111] As one embodiment of a system using an emotion engine, a function is provided that adjusts the priority of messages based on the user's emotions. For example, if a user receives a message expressing anger or dissatisfaction, that message is determined to have high priority and is displayed so that it is immediately visible to the user.

[1112] "Example of form 3"

[1113] As one embodiment of a system using an emotion engine, a function is provided that adjusts task priorities based on the user's emotions. For example, if a user receives a message indicating joy or excitement, tasks related to that message are determined to have a high priority and are displayed higher up in the task list.

[1114] The following describes the processing flow for each example of the form.

[1115] "Example of form 1"

[1116] Step 1: The system centralizes and displays messages from multiple communication tools.

[1117] Step 2: Next, the system sorts the message into work-related or personal based on its content.

[1118] Step 3: The system then breaks down the message content into tasks and manages them accordingly.

[1119] Step 4: Finally, the emotion engine recognizes the user's emotions based on factors such as the user's tone of voice, facial expressions, and the context of the message.

[1120] "Example of form 2"

[1121] Step 1: The system adjusts message priorities based on the user's emotions.

[1122] Step 2: For example, if a user receives a message expressing anger or dissatisfaction, that message is judged to have high priority.

[1123] Step 3: As a result, the message is displayed so that it is immediately visible to the user. (Example 3)

[1124] Step 1: The system adjusts task priorities based on the user's emotions.

[1125] Step 2: For example, if a user receives a message expressing joy or excitement, the task associated with that message will be judged to have a high priority.

[1126] Step 3: As a result, the task will appear higher up in the task list.

[1127] (Example 1)

[1128] Next, we will describe Embodiment 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[1129] In today's business environment, users utilize multiple communication methods (email, communication tools, chat, messaging applications, etc.), requiring them to individually check messages from each tool. This makes message checking and management cumbersome, increasing the risk of missing important messages. Furthermore, users need to categorize messages as either work-related or personal, and manage them as tasks, but doing this manually is time-consuming and laborious. Additionally, recognizing user emotions and providing appropriate feedback is crucial, but current systems do not adequately address this.

[1130] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1131] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for recognizing the user's emotions, and means for providing feedback based on the recognized emotions. This allows the user to centrally manage messages from multiple communication means, efficiently manage tasks without missing important messages, and improve user satisfaction and productivity by recognizing the user's emotions and providing appropriate feedback.

[1132] "Communication methods" refer to various means that users use to send and receive messages, such as email, communication tools, chat, and messaging applications.

[1133] "Means of centralized display" refers to methods for displaying messages collected from multiple communication methods in a list on a single interface.

[1134] "Means of sorting" refers to methods for analyzing the content of a message and classifying whether it is work-related or personal.

[1135] "Means of task creation and management" refers to methods for generating tasks based on the content of a message and managing those tasks.

[1136] "Means of recognizing emotions" refers to methods for recognizing a user's emotions from their tone of voice, facial expressions, message context, etc.

[1137] "Means of providing feedback" refers to means of providing users with appropriate advice and information based on their perceived emotions.

[1138] This invention is a system that centrally displays messages from multiple communication methods, categorizes them as either work-related or personal based on their content, and further manages them as tasks. It also includes a function to recognize the user's emotions and provide appropriate feedback.

[1139] Message collection and centralized display

[1140] The server collects messages from multiple communication methods used by the user (e.g., email, communication tools, chat, messaging applications). This is done by utilizing the APIs of each communication method. For example, the email API is used to collect emails, the communication API for communication tools, the chat API for chats, and the messaging API for messaging applications. The collected messages are stored in a database, and the terminal displays an interface accessible to the user, showing the collected messages in a list format.

[1141] Message Classification

[1142] The server analyzes the content of the collected messages and distinguishes between work-related and personal matters. This is done using natural language processing (NLP) techniques. Specifically, it uses a natural language processing API to analyze the message content and determine the category. For example, a message like "Please prepare the materials for tomorrow's meeting" is classified as work-related, while a message like "Let's go see a movie this weekend" is classified as personal.

[1143] Task creation and management

[1144] The server generates tasks based on classified messages and adds them to the task management tool. Task management uses a task management API. For example, a new task can be generated using the task management tool's API and added to the user's task management board. Users can then view the generated tasks and manage their progress.

[1145] Emotional Recognition and Feedback

[1146] The server uses an emotion engine to recognize the user's emotions. This involves using speech recognition and facial recognition technologies. For example, it uses a speech recognition API to analyze the tone of the user's voice and a facial recognition API to analyze the user's facial expressions. Based on the recognized emotions, the server provides appropriate feedback to the user. For example, if the user sends the message "I'm very tired today," the emotion engine recognizes the user's fatigue and provides advice on how to relax.

[1147] Specific example

[1148] When users are using email, communication tools, chat, and messaging applications, the server collects messages from these tools and displays them in a single interface. Users can see at a glance which tool a message originated from. They can also categorize messages as work-related or personal based on their content, and generate and manage tasks accordingly. Furthermore, by recognizing user emotions and providing appropriate feedback, the system can improve user satisfaction and productivity.

[1149] Example of a prompt

[1150] "Collect messages from email, communication tools, chat, and messaging applications and display them in a single interface. Furthermore, categorize messages as either work-related or personal based on their content, generate and manage tasks accordingly, and recognize user sentiment to provide appropriate feedback."

[1151] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1152] Step 1:

[1153] The server collects messages from multiple communication methods.

[1154] Input: Message data from email, communication tools, chat, and messaging application APIs.

[1155] Specific operation: The server retrieves new messages by calling the API for each communication method. For example, it uses the email API to retrieve new emails and the communication tool API to retrieve new chat messages.

[1156] Output: The collected message data is saved to the database.

[1157] Step 2:

[1158] The server retrieves messages from the database in order to centrally display the collected messages.

[1159] Input: Message data stored in the database.

[1160] Specific operation: The server retrieves messages collected from the database and sends them to the interface accessed by the user.

[1161] Output: A centralized list of messages displayed on the terminal.

[1162] Step 3:

[1163] The server analyzes the content of the collected messages and distinguishes between work-related and personal messages.

[1164] Input: Message data retrieved from the database.

[1165] Specific operation: The server calls a natural language processing API to analyze the message content and determine its category. For example, the message "Please prepare the materials for tomorrow's meeting" is classified as work-related, while the message "Let's go see a movie this weekend" is classified as personal.

[1166] Output: Classified message data.

[1167] Step 4:

[1168] The server generates tasks based on the classified messages and adds them to the task management tool.

[1169] Input: Classified message data.

[1170] Specific operation: The server calls the task management API to generate a new task and adds it to the user's task management board. For example, it uses the task management tool's API to generate a task called "Prepare meeting materials" and adds it to the user's task management board.

[1171] Output: A new task added to the task management tool.

[1172] Step 5:

[1173] The server uses an emotion engine to recognize the user's emotions.

[1174] Input: User's tone of voice, facial expression, and message context.

[1175] Specific operation: The server calls a speech recognition API to analyze the tone of the user's voice and a facial recognition API to analyze the user's facial expressions. For example, if the user sends the message "I'm very tired today," the emotion engine recognizes the user's level of fatigue.

[1176] Output: Sentiment data of recognized users.

[1177] Step 6:

[1178] The server provides appropriate feedback to the user based on the emotions it perceives.

[1179] Input: Sentiment data of the recognized user.

[1180] Specific operation: The server provides the user with advice and information to help them relax based on the emotions it perceives. For example, if the server perceives the user as tired, it will suggest relaxing music or taking a break.

[1181] Output: Feedback provided to the user.

[1182] (Application Example 1)

[1183] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1184] Traditional factory robots lacked features such as the ability to centrally display messages from multiple communication tools, differentiate between work-related and personal messages based on their content, and manage tasks based on message content. Furthermore, they lacked the ability to recognize the emotions of factory staff and prompt appropriate responses, making efficient communication and appropriate responses based on staff emotions difficult.

[1185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on their content, means including an emotion engine that recognizes the user's emotions, and means for recognizing the emotions of factory staff and prompting appropriate responses. This enables more efficient communication within the factory and appropriate responses based on the emotions of the staff.

[1186] "Multiple communication tools" refers to different types of communication methods such as email, communication tools, chat, and messenger apps.

[1187] "A means of centralized display" refers to a function that integrates and displays messages from multiple communication tools on a single interface.

[1188] "Means of sorting" refers to a function that automatically categorizes messages based on their content, determining whether they are work-related or personal.

[1189] "A means of creating and managing tasks" refers to a function that generates tasks based on the content of a message and manages those tasks.

[1190] An "emotion engine" refers to technology that recognizes a user's emotions based on factors such as the tone of their voice, facial expressions, and the context of their message.

[1191] "Means of recognizing the emotions of factory staff and prompting appropriate responses" refers to a function that uses an emotion engine to recognize the emotions of staff working in the factory and takes appropriate action based on those emotions.

[1192] The system for carrying out this invention is configured as an application installed on a factory robot. A specific embodiment is shown below.

[1193] System Configuration

[1194] The server includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means including an emotion engine for recognizing user emotions, and means for recognizing the emotions of factory staff and prompting appropriate responses.

[1195] Hardware and software to be used

[1196] Hardware: Factory robots (e.g., KUKA, Fanuc)

[1197] Software: Python, smtplib, imaplib, email library, TextBlob, json

[1198] Data processing and data calculation

[1199] The server performs the following data processing and calculations:

[1200] 1. Retrieve emails:

[1201] The server retrieves email from the IMAP server. This is done using the imaplib library.

[1202] 2. Message analysis:

[1203] The server analyzes the content of the retrieved emails and performs sentiment analysis. This is done using the TextBlob library.

[1204] 3. Centralizing messages:

[1205] The server centralizes the analysis results and displays them on an integrated interface. This is done using the JSON library.

[1206] 4. Emotional Engine:

[1207] The server recognizes the user's emotions based on factors such as the user's tone of voice, facial expressions, and the context of the message. This is done using emotion recognition technology.

[1208] 5. Facilitating appropriate responses:

[1209] The server recognizes the emotions of the staff in the factory and takes appropriate action based on those emotions.

[1210] Specific example

[1211] For example, if a staff member in a factory tells a robot that "the production line is behind schedule today," the robot registers that message as a task and notifies the manager. Also, if the robot detects that a staff member is tired, it sends a message encouraging them to take a break.

[1212] Example of a prompt

[1213] Design a system where, when a staff member speaks to a robot in a factory, the robot recognizes the staff member's emotions and responds appropriately. For example, if a staff member says, "The production line is behind schedule today," the robot should register that message as a task and notify the manager.

[1214] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1215] Step 1:

[1216] The server retrieves emails from the IMAP server. Specifically, it connects to the mail server using the imaplib library and logs into the user's email account. Next, it searches all emails in the inbox and obtains the ID of each email. This results in a list containing the email's metadata (sender, subject, date and time, etc.).

[1217] Input: IMAP server connection information, user's email account information

[1218] Output: Email metadata list

[1219] Step 2:

[1220] The server analyzes the content of the retrieved emails and performs sentiment analysis. Specifically, it uses the email library to extract the body of each email and the TextBlob library to perform sentiment analysis. As a result of the sentiment analysis, a sentiment score (positive, negative, neutral) is obtained for each email.

[1221] Input: Email metadata list

[1222] Output: Email data with sentiment scores

[1223] Step 3:

[1224] The server centralizes the analysis results and displays them on an integrated interface. Specifically, it converts email data with sentiment scores into JSON format using a JSON library and displays it on an interface accessible to users. This interface can be accessed via a web browser or a dedicated application.

[1225] Input: Email data with sentiment scores

[1226] Output: Display data on the integrated interface

[1227] Step 4:

[1228] The server recognizes the user's emotions from factors such as the tone of their voice, facial expressions, and the context of their messages. Specifically, it uses emotion recognition technology to analyze audio and video data to identify the user's emotional state. This allows the server to understand the user's emotional state in real time.

[1229] Input: Audio data, video data

[1230] Output: User emotional state data

[1231] Step 5:

[1232] The server recognizes the emotions of the factory staff and takes appropriate action based on those emotions. Specifically, based on emotional state data, it sends messages encouraging staff to take breaks if they are feeling stressed. It also notifies managers if important tasks are behind schedule.

[1233] Input: User's emotional state data

[1234] Output: Appropriate response message, notification to administrator

[1235] (Example 2)

[1236] Next, we will describe Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[1237] In today's business environment, efficiently managing messages from multiple communication channels (email, communication tools, chat, messenger apps, etc.) is essential. However, it is difficult to centrally display these messages, differentiate between work and personal content, and adjust priorities based on emotions. Furthermore, while it is important to create and manage tasks based on message content, current systems cannot provide these functions in an integrated manner. This leads to problems such as users missing important messages and task management becoming cumbersome.

[1238] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1239] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between work and personal messages based on their content, means for analyzing message content and adjusting message priority based on sentiment, and means for creating and managing tasks based on message content. This enables users to centrally manage messages from multiple communication means, avoid missing important messages, and efficiently manage tasks.

[1240] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1241] A "message" refers to information such as text, images, audio, and video that is sent and received through communication methods.

[1242] "Unification" refers to integrating messages from multiple communication methods and displaying and managing them through a single interface.

[1243] "Classification" refers to the automatic categorization of messages based on their content and sender, determining whether they are work-related or personal.

[1244] "Emotional analysis" is the process of analyzing the content of a message and detecting the emotions contained within it (for example, joy, anger, sadness, etc.).

[1245] "Priority adjustment" refers to changing the display order and notification methods of messages based on the results of sentiment analysis.

[1246] "Tasking" refers to managing a message by breaking it down into specific work items based on its content.

[1247] "Management" refers to tracking task-based work items, checking their progress, and updating or correcting them as needed.

[1248] This invention is a system that centrally displays messages from multiple communication methods, categorizes messages as either work-related or personal based on their content, adjusts message priority based on emotions, and manages them as tasks based on their content.

[1249] Hardware and software to be used

[1250] Hardware: Servers, terminals (PCs, smartphones)

[1251] Software: Message analysis engine, emotion engine, generative AI model

[1252] System Overview

[1253] Message centralization

[1254] The server retrieves messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.) and displays them in a centralized manner. This allows users to view all messages in a single interface.

[1255] Message sorting

[1256] The server analyzes the sender address and content of received messages and automatically determines whether they are work-related or personal. Specifically, it makes this determination based on work email addresses and work-related keywords.

[1257] Prioritizing messages

[1258] The server uses an emotion engine to analyze the message content and detect the user's emotions (e.g., anger, frustration). Based on the intensity of the emotion, the server prioritizes the messages, and the terminal displays high-priority messages so that they are immediately visible to the user.

[1259] Tasking messages

[1260] The server creates and manages tasks based on the content of the messages. Task creation is based on the importance and urgency of the messages.

[1261] Specific example

[1262] Message sorting

[1263] Example: If a user receives a message from "boss@company.com" with the subject "Project Progress Report," the server will determine that the message is work-related. The server recognizes "boss@company.com" as a work email address and determines that the keyword "Project Progress Report" is work-related.

[1264] Prioritizing messages

[1265] Example: If a user receives the message "This project isn't progressing at all!", the emotion engine detects "anger" and sets the message as a high priority. The device then displays the message as a pop-up notification.

[1266] Example of a prompt

[1267] Prompt: "Analyze the following message and determine whether it is work-related or personal. Also, prioritize the message based on the user's sentiment. Message: 'This project is not progressing at all!'"

[1268] In this way, the system can automatically categorize messages based on their content, adjust message priorities based on the user's sentiment, and efficiently manage tasks.

[1269] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1270] Step 1:

[1271] Message received

[1272] The server retrieves new messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.).

[1273] Input: Message data from each communication method.

[1274] Output: List of retrieved messages.

[1275] Specific operation: The server calls the API of each communication method and polls to retrieve new messages.

[1276] Step 2:

[1277] Checking the sender address of the message

[1278] The server checks the sender address of the received message.

[1279] Input: A list of received messages.

[1280] Output: The source address of each message.

[1281] Specific operation: The server analyzes the message header information and extracts the source address.

[1282] Step 3:

[1283] Analysis of message content

[1284] The server analyzes the message body and checks if it contains business-related keywords.

[1285] Input: The body of each message.

[1286] Output: Analysis results for each message (presence or absence of keywords).

[1287] Specific operation: The server uses a natural language processing (NLP) engine to extract keywords from the message body.

[1288] Step 4:

[1289] Message Classification

[1290] The server automatically determines whether a message is work-related or personal based on the sender's address and content.

[1291] Input: The sender address and parsing result for each message.

[1292] Output: Classification result for each message (work-related or personal).

[1293] Specific operation: The server uses predefined rules and machine learning models to classify messages as either "work" or "private."

[1294] Step 5:

[1295] Sentiment analysis of messages

[1296] The server analyzes the content of received messages using an emotion engine.

[1297] Input: The body of each message.

[1298] Output: Sentiment score for each message.

[1299] Specific operation: The server calls the sentiment analysis API to obtain the sentiment score of the message.

[1300] Step 6:

[1301] Assessment of emotional intensity

[1302] The server evaluates the intensity of emotions based on the emotion score obtained from the emotion engine.

[1303] Input: Sentiment score for each message.

[1304] Output: Emotional intensity of each message (high, medium, low).

[1305] Specific operation: The server compares the emotion score to a threshold and classifies the intensity of the emotion as "high," "medium," or "low."

[1306] Step 7:

[1307] Message priority settings

[1308] The server prioritizes messages based on the intensity of emotion.

[1309] Input: Emotional intensity of each message.

[1310] Output: Priority of each message (high, medium, low).

[1311] Specific operation: The server sets the message priority to "high," "medium," or "low" depending on the intensity of the emotion.

[1312] Step 8:

[1313] Displaying messages

[1314] The device displays high-priority messages so that they are immediately visible to the user.

[1315] Input: Priority of each message.

[1316] Output: The message displayed to the user.

[1317] Specific action: The device uses its notification function to display high-priority messages as pop-ups.

[1318] Step 9:

[1319] Tasking messages

[1320] The server creates and manages tasks based on the content of the messages.

[1321] Input: The body and priority of each message.

[1322] Output: Messages managed as tasks.

[1323] Specific operation: The server analyzes the message content and registers it in the task management system.

[1324] In this way, the system can automatically categorize messages based on their content, adjust message priorities based on the user's sentiment, and efficiently manage tasks.

[1325] (Application Example 2)

[1326] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1327] In modern brick-and-mortar stores, it is difficult for staff to efficiently manage messages from multiple communication tools. Furthermore, they are required to differentiate between work and personal messages based on their content, and then prioritize them based on emotional factors, but no system exists to automate this process. This increases the risk of important messages being overlooked, potentially leading to a decline in the quality of customer service.

[1328] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1329] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for tasking and managing messages based on their content, means for analyzing the sentiment of messages and adjusting their priority, and means for enabling store staff to efficiently manage messages. This allows staff to respond quickly and appropriately without missing important messages.

[1330] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1331] A "message" refers to information sent and received in various formats, such as text, images, audio, and video.

[1332] "Centralization" refers to the process of consolidating data from multiple sources into a single location and managing it in a unified manner.

[1333] "Display" refers to providing data and information to users visually.

[1334] "Classification" refers to the process of classifying data or information based on specific criteria.

[1335] "Work" refers to activities and tasks related to one's duties or responsibilities.

[1336] "Private" refers to personal activities or tasks.

[1337] "Task-making" refers to converting the content of a message into specific tasks or action items.

[1338] "Management" refers to the efficient organization of data and information, and the manipulation and control of them as needed.

[1339] "Emotions" refers to the user's psychological state as interpreted from the content of the message.

[1340] "Analysis" refers to the process of thoroughly examining data and information to understand its meaning and structure.

[1341] "Priority" is an indicator that shows the importance or urgency of a task or message.

[1342] A "physical store" refers to a place of sale or service provision that exists in a physical location and can be visited directly by customers.

[1343] "Staff" refers to employees or staff who work at a physical store.

[1344] "Efficient" means achieving maximum results with minimum time and effort.

[1345] The following system configuration will be described as an embodiment for carrying out this invention.

[1346] System Configuration

[1347] hardware

[1348] Server: A central processing unit for centralized management and analysis of messages.

[1349] Devices: Devices used by staff, such as smartphones and smart glasses.

[1350] Network: Communication infrastructure used to connect servers and terminals.

[1351] software

[1352] Message Management System: A program that centralizes, categorizes, task-creates, analyzes sentiment, and prioritizes messages.

[1353] Sentiment analysis engine: Sentiment analysis libraries such as TextBlob.

[1354] User Interface: An application for staff to review and respond to messages.

[1355] Processing flow

[1356] 1. Centralized messaging

[1357] The server collects and centralizes messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.).

[1358] This allows staff to view all messages through a single interface.

[1359] 2. Classification of messages

[1360] The server analyzes the source and content of messages and automatically determines whether they are work-related or personal.

[1361] For example, if keywords such as "customer," "order," "complaint," or "inquiry" are included, it will be classified as work-related.

[1362] 3. Task Breakdown and Management

[1363] The server generates and manages tasks based on the classified messages.

[1364] Tasks are prioritized based on the importance and urgency of the message.

[1365] 4. Emotional Analysis and Prioritization

[1366] The server analyzes the sentiment of messages using sentiment analysis engines such as TextBlob.

[1367] Based on the analysis results, messages expressing anger or dissatisfaction are set as having a high priority.

[1368] For example, a message stating, "This is a customer complaint. They are very dissatisfied," will be displayed as a high-priority message.

[1369] 5. User Interface

[1370] Through applications installed on their devices, staff can check messages according to priority and respond quickly.

[1371] Specific example

[1372] For example, if a staff member at a physical store is using a smartphone, the following prompt message will be generated:

[1373] Analyze customer messages to determine whether they are work-related or personal, and use the sentiment engine to adjust their priority. For example, a message saying, "This is a customer complaint. They are very unhappy," would be considered work-related and therefore high-priority.

[1374] Based on this prompt, the server analyzes the message and performs appropriate classification and prioritization. This allows staff to respond quickly and appropriately without missing any important messages.

[1375] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1376] Step 1:

[1377] The server collects and centralizes messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.).

[1378] Input: Message data from various communication tools.

[1379] Data processing: Convert message data into a unified format and save it to the database.

[1380] Output: Centralized message data.

[1381] Specific operation: Use the API to retrieve messages from each communication tool, convert them to a unified format, and save them to the database.

[1382] Step 2:

[1383] The server analyzes the source and content of messages and automatically determines whether they are work-related or personal.

[1384] Input: Centralized message data.

[1385] Data processing: Analyze message content and classify it based on keywords.

[1386] Output: Classified message data (work-related or personal).

[1387] Specific operation: Uses natural language processing (NLP) techniques to analyze message content and detect keywords such as "customer," "order," "complaint," and "inquiry."

[1388] Step 3:

[1389] The server generates and manages tasks based on the classified messages.

[1390] Input: Classified message data.

[1391] Data processing: Convert messages into tasks and prioritize them based on importance and urgency.

[1392] Output: Tasked message data.

[1393] Specific actions: Analyze the message content, register it as a task in the task management system, and set its priority.

[1394] Step 4:

[1395] The server analyzes the sentiment of messages using sentiment analysis engines such as TextBlob.

[1396] Input: Tasked message data.

[1397] Data processing: Analyze the sentiment of the message using an emotion analysis engine and calculate the polarity.

[1398] Output: Sentiment analysis results (polarity value).

[1399] Specific operation: Use the TextBlob library to analyze the sentiment of a message and obtain a polarity value.

[1400] Step 5:

[1401] Based on the analysis results, the server prioritizes messages expressing anger or dissatisfaction.

[1402] Input: Sentiment analysis results (polarity value).

[1403] Data processing: Prioritize based on polarity values.

[1404] Output: Task data with assigned priorities.

[1405] Specific operation: If the polarity value falls below a certain threshold, the priority of that task will be set higher.

[1406] Step 6:

[1407] Through applications installed on their devices, staff members can check messages according to priority and respond quickly.

[1408] Input: Task data with assigned priorities.

[1409] Data processing: Display tasks based on priority.

[1410] Output: A list of tasks that staff can review.

[1411] Specific actions: Through smartphone or smart glasses applications, staff are notified of tasks according to priority and prompted to take action.

[1412] (Example 3)

[1413] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[1414] In today's business environment, it is common to use multiple communication methods (email, communication tools, chat, messenger applications, etc.). However, it is difficult to centrally manage messages from these communication methods, separate work and personal messages, and automatically generate and manage tasks based on the content of messages. Furthermore, the lack of a function to adjust task priorities based on user emotions results in inefficient task management.

[1415] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1416] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for analyzing message content and automatically generating tasks, means for analyzing user sentiment and adjusting task priority, and means for adding and displaying generated tasks in a task list. This makes it possible to centrally manage messages from multiple communication means, distinguish between business and personal messages, and further adjust task priority based on user sentiment.

[1417] "Means of communication" refers to the means by which users send and receive messages, such as email, communication tools, chat, and messenger applications.

[1418] "Unification" refers to integrating messages from multiple communication methods and displaying them on a single interface.

[1419] "Work" refers to activities that a user engages in that are related to their job or duties.

[1420] "Private" refers to activities that users undertake for personal purposes.

[1421] "Analyzing the content of a message" refers to analyzing the text of a message using natural language processing techniques to understand its meaning and intent.

[1422] "Automatically generating tasks" refers to automatically creating a list of specific tasks and actions that the user should perform based on the content of the message.

[1423] "Analyzing user emotions" refers to using emotion analysis technology to determine the user's emotional state from the content and expression of a message.

[1424] "Adjusting task priorities" refers to setting the importance and urgency of generated tasks based on the user's emotions or other factors.

[1425] A "task list" refers to a list that displays a list of tasks that a user needs to complete.

[1426] "Displaying" refers to visually showing generated tasks and messages on the user's device.

[1427] This invention is a system that centrally displays messages from multiple communication methods, categorizes messages as either business-related or personal based on their content, automatically generates tasks by analyzing the message content, and adjusts task priorities by analyzing the user's emotions.

[1428] System Configuration

[1429] hardware

[1430] Server: Receives and analyzes messages, generates tasks, performs sentiment analysis, and manages tasks.

[1431] Device: Displays the task list on the device the user is using (PC, smartphone, tablet, etc.).

[1432] software

[1433] Natural Language Processing Engine: Used to analyze the content of messages. Specifically, it utilizes Google Cloud Natural Language API and Microsoft Azure Text Analytics.

[1434] Sentiment analysis engine: Used to analyze user emotions. Specifically, it utilizes IBM Watson Tone Analyzer or Amazon Comprehend.

[1435] Database: Used to store generated tasks and messages.

[1436] System operation

[1437] Message received

[1438] The server receives messages sent by users. These messages are sent via email, communication tools, chat, messenger applications, etc.

[1439] Analysis of message content

[1440] The server uses a natural language processing engine to analyze the content of received messages. For example, it might use the Google Cloud Natural Language API to analyze messages and extract action phrases.

[1441] Task generation

[1442] The server generates tasks based on action phrases extracted by the NLP engine. For example, if the phrase "prepare for the meeting" is extracted, the server will generate a task called "prepare for the meeting".

[1443] Emotional analysis

[1444] The server uses a sentiment analysis engine to analyze the user's emotions from the message content. For example, it might use IBM Watson Tone Analyzer to analyze the sentiment of a message and determine that the user is excited.

[1445] Task priority setting

[1446] The server prioritizes tasks based on the results of the emotion analysis engine. For example, if a user is agitated, the related task will be given a higher priority.

[1447] Adding and displaying tasks to the task list

[1448] The server saves the generated task to the database and adds it to the task list. The terminal updates the user's task list to display the new task.

[1449] Specific example

[1450] Consider a scenario where a user sends the message, "I need to prepare for next week's meeting." Upon receiving this message, the server uses the Google Cloud Natural Language API to extract the phrase "prepare for the meeting" and generates a task. Then, IBM Watson Tone Analyzer is used to analyze the user's sentiment, and if it determines the user is agitated, this task is given a high priority.

[1451] Examples of prompts to input into a generative AI model:

[1452] You received the message, "I need to prepare for next week's meeting." Based on this message, generate tasks and prioritize them based on the user's sentiment.

[1453] In this way, users can manage tasks appropriately according to the content of the message. The flow of a specific process in Example 3 will be explained using Figure 21.

[1454] Step 1: Receiving a message

[1455] The server receives messages sent by users. These messages are sent via email, communication tools, chat, messenger applications, etc. The input is the message from the user, and the output is the received message data.

[1456] Step 2: Analyze the message content

[1457] The server uses a natural language processing engine to analyze the content of received messages. Specifically, it uses the Google Cloud Natural Language API to analyze messages and extract action phrases. The input is the received message data, and the output is the extracted action phrases.

[1458] Step 3: Task Generation

[1459] The server generates tasks based on action phrases extracted by the NLP engine. For example, if the phrase "prepare for the meeting" is extracted, the server generates the task "prepare for the meeting". The input is the extracted action phrase, and the output is the generated task data.

[1460] Step 4: Emotional Analysis

[1461] The server uses a sentiment analysis engine to analyze the user's emotions from the message content. Specifically, it uses IBM Watson Tone Analyzer to analyze the sentiment of the message and determine if the user is agitated. The input is the received message data, and the output is the analyzed sentiment data.

[1462] Step 5: Prioritizing tasks

[1463] The server prioritizes tasks based on the results of the sentiment analysis engine. For example, if a user is agitated, the associated tasks will be given a higher priority. The input consists of generated task data and analyzed sentiment data, and the output is the task data with the assigned priorities.

[1464] Step 6: Add and display the task list

[1465] The server saves the generated tasks to the database and adds them to the task list. The terminal updates the user's task list to display the new tasks. The input is task data with priority set, and the output is the updated task list.

[1466] (Application Example 3)

[1467] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[1468] Traditional task management systems can generate tasks by analyzing message content, but they lack the functionality to adjust task priorities based on user emotions. This makes flexible task management that adapts to user feelings and circumstances difficult, potentially hindering efficient work execution. Furthermore, the inability to centrally manage messages from multiple communication sources leads to information scattering and management cumbersome issues.

[1469] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1470] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for creating and managing tasks based on their content, and means for analyzing the sentiment of messages and adjusting task priorities. This enables flexible task management that responds to the user's emotions and circumstances, thereby achieving efficient work execution.

[1471] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1472] "Unification" refers to the process of integrating data from multiple different sources and consolidating it into a single location.

[1473] "Display" refers to providing data and information to users visually.

[1474] "Classification" refers to the process of classifying data or information based on specific criteria.

[1475] "Work" refers to activities and tasks related to one's duties or job.

[1476] "Private" refers to an individual's private activities or tasks.

[1477] "Tasking" refers to generating specific work items based on the content of a message.

[1478] "Management" refers to the process of organizing, tracking, and completing tasks that have been generated.

[1479] "Emotions" refer to the psychological state or feelings that users express through messages.

[1480] "Analysis" refers to the process of thoroughly examining data and information to understand its meaning and structure.

[1481] "Priority" refers to the criteria used to determine the order of tasks or work based on their importance and urgency.

[1482] "Adjustment" refers to changing settings or states based on specific criteria or conditions.

[1483] The system for implementing this invention centrally displays messages from multiple communication methods, categorizes them as either business or personal based on their content, and automatically generates and manages tasks based on the message content. It also includes a function to analyze the sentiment of the messages and adjust the priority of tasks.

[1484] Hardware and software to use

[1485] Hardware: Robots, servers, and user terminals (smartphones, tablets, PCs, etc.) within the factory.

[1486] Software: Python, TextBlob (sentiment analysis library), messaging APIs (email, chat tools, etc.)

[1487] Data processing and data calculation

[1488] Message centralization and display

[1489] The server collects messages from multiple communication channels, centralizes them, and displays them on the user's terminal. This allows the user to view all messages through a single interface.

[1490] Message sorting

[1491] The server analyzes the message content and automatically distinguishes between work-related and personal messages. For example, if a message contains the phrase "prepare for the meeting," it will be classified as work-related.

[1492] Task automation and management

[1493] The server automatically generates tasks based on the content of messages and adds them to the task list. For example, if a message saying "Prepare for the meeting" is received, a task called "Prepare for the meeting" will be generated based on its content.

[1494] Emotion analysis and prioritization

[1495] The server uses TextBlob to analyze the sentiment of a message and determine whether it is positive or negative. Based on the sentiment analysis, it dynamically adjusts the priority of the generated tasks. For example, if a user sends a positive message such as "I'm really looking forward to today!", tasks related to that message will be given a higher priority.

[1496] Specific example

[1497] Message examples

[1498] Message: "Preparing for the meeting. I'm really looking forward to it today!"

[1499] Task generated: "Prepare for the meeting"

[1500] Priority: High

[1501] Example of a prompt

[1502] Message: "Preparing for the meeting. I'm really looking forward to it today!"

[1503] Task generated: "Prepare for the meeting"

[1504] Priority: High

[1505] In this way, the server analyzes messages, automatically generates tasks, and sets priorities, enabling flexible task management that responds to the user's emotions and circumstances. This allows for efficient work execution.

[1506] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1507] Step 1:

[1508] The server collects messages from multiple communication methods (email, chat tools, etc.).

[1509] Input: Message data from each communication method

[1510] Output: Centralized message list

[1511] Specific operation: The server retrieves messages using the API of each communication method and consolidates them into a single list.

[1512] Step 2:

[1513] The server analyzes the collected messages and distinguishes between work-related and personal messages.

[1514] Input: Centralized message list

[1515] Output: Sorted message list (work-related, personal)

[1516] Specific operation: The server uses natural language processing (NLP) techniques to analyze the content of messages and classify them as either work-related or personal based on specific keywords or phrases.

[1517] Step 3:

[1518] The server automatically generates tasks from business-related messages and adds them to the task list.

[1519] Input: Business-related message

[1520] Output: Generated task list

[1521] Specific operation: The server parses business-related messages, extracts action phrases, generates tasks, and adds them to the task list.

[1522] Step 4:

[1523] The server analyzes the sentiment of messages and adjusts task priorities accordingly.

[1524] Input: Business-related messages, generated task list

[1525] Output: Task list with adjusted priorities

[1526] Specific operation: The server uses sentiment analysis libraries such as TextBlob to analyze the sentiment of a message, prioritizing tasks based on positive sentiment and lowering them based on negative sentiment.

[1527] Step 5:

[1528] The server displays a task list with adjusted priorities on the user's terminal.

[1529] Input: Task list with adjusted priority

[1530] Output: Task list displayed on the user's terminal

[1531] Specific operation: The server sends a task list to the user's terminal and displays it for the user to visually confirm.

[1532] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1533] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1534] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are examples.

[1535] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1536] [Third Embodiment]

[1537] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1538] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1539] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1540] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1541] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1542] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1543] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1544] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1545] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1546] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1547] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1548] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1549] "Example of form 1"

[1550] The system of the present invention has means for centrally displaying messages from multiple communication tools. Specifically, it collects messages from email, communication tools, chat, messenger apps, etc., and displays them in a list on a single interface. This allows the user to see at a glance which tool a message originated from.

[1551] "Example of form 2"

[1552] Furthermore, the system of the present invention has means for distinguishing between work-related and personal messages based on their content. Specifically, it analyzes the sender and content of a message and automatically determines whether it is work-related or personal. For example, if the sender of a message is a work email address, or if the message content contains work-related keywords, the message is determined to be work-related.

[1553] "Example of form 3"

[1554] Furthermore, the system of the present invention has means for creating and managing tasks based on the content of messages. Specifically, it analyzes the content of a message and automatically generates tasks based on it. For example, if the content of a message includes a phrase indicating an action such as "prepare for the meeting," it generates a task based on that phrase and adds it to the task list. This allows the user to manage tasks appropriately according to the content of the message.

[1555] The following describes the processing flow for each example of the form.

[1556] "Example of form 1"

[1557] Step 1: The system collects messages from email, communication tools, chat, messenger apps, etc.

[1558] Step 2: Display the collected messages in a list on a single interface.

[1559] Step 3: Users can see at a glance which tool a message is from by looking at the list of messages.

[1560] "Example of form 2"

[1561] Step 1: The system analyzes the source and content of the message.

[1562] Step 2: Based on the analysis, the system automatically determines whether the message is work-related or personal.

[1563] Step 3: For example, if the message is sent from a work email address or contains work-related keywords, the message is considered work-related.

[1564] "Example of form 3"

[1565] Step 1: The system analyzes the content of the message.

[1566] Step 2: Based on the analysis results, automatically generate tasks based on the messages.

[1567] Step 3: For example, if the message contains a phrase indicating an action, such as "prepare for the meeting," generate a task based on that phrase and add it to the task list.

[1568] Step 4: This allows users to manage tasks appropriately based on the content of the message.

[1569] (Example 1)

[1570] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1571] In today's business environment, it's common for users to receive messages using multiple communication methods. However, this makes message management cumbersome and increases the risk of missing important messages. Furthermore, there's the challenge of categorizing messages as work-related or personal based on their content, and then managing them as tasks.

[1572] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1573] In this invention, the server includes means for collecting messages from multiple communication means, means for centralizing the collected messages, and means for storing the centralized messages. This allows the user to view messages from multiple communication means through a single interface and manage them efficiently without missing important messages.

[1574] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1575] "Means for collecting messages" refers to a function for obtaining new messages from multiple communication methods.

[1576] "A means of centralizing messages" refers to a function that converts collected messages into a common data format and manages them uniformly.

[1577] "Means of saving messages" refers to a function for storing centralized messages in a storage device such as a database.

[1578] "Means for displaying messages" refers to a function that displays saved messages on the interface so that users can view them.

[1579] "Means of manipulating messages" refer to functions that allow users to click on displayed messages to view details or to reply.

[1580] "Means for distinguishing between work and personal matters" refers to a function that determines whether a message is work-related or personal based on its content.

[1581] "A means of creating and managing tasks" refers to a function that classifies messages into tasks based on their content and manages them according to their importance and urgency.

[1582] Modes for carrying out the invention

[1583] This invention is a system that centrally displays messages from multiple communication methods, further categorizes them as either work-related or personal based on their content, and manages them as tasks. A specific embodiment of this system is described below.

[1584] Server Role

[1585] The server is responsible for collecting messages from multiple communication channels. Specifically, it uses APIs from email servers, communication tools (e.g., Slack, Microsoft Teams), chat apps (e.g., WhatsApp, LINE), and messenger apps (e.g., Facebook Messenger) to retrieve new messages. The server centralizes these messages and converts them into a common data format. The converted messages are then stored in relational databases such as MySQL or PostgreSQL.

[1586] Terminal role

[1587] The device provides an interface for users to view and interact with messages. Specifically, it displays a list of messages retrieved from the server via a web or mobile application. For example, the frontend could be built using React or Vue.js to allow users to visually review messages. Messages are color-coded by tool: emails are displayed in blue, communication tools in green, and chat apps in red.

[1588] User actions

[1589] Users interact with messages using an interface on their device. Specifically, they can click on a particular message to view details or reply to it. Users can also use a filter function to display only messages from specific communication methods. Furthermore, they can categorize messages as work-related or personal based on their content and manage them as tasks. Task creation is based on the importance and urgency of the message.

[1590] Specific example

[1591] For example, consider a scenario where a user receives messages from multiple communication channels while at work. This system allows the user to view messages from email, Slack, WhatsApp, and Facebook Messenger in a single interface. This enables them to quickly identify the source of each message and respond promptly.

[1592] Example of a prompt

[1593] Examples of prompt statements to input into a generative AI model include the following:

[1594] Please describe a system that centralizes and displays messages from multiple communication methods. Specifically, please specify what hardware and software are used, and what kind of data processing and calculations are performed. Also, please provide concrete examples.

[1595] By using this prompt statement, the generative AI model can generate a detailed description of the system.

[1596] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1597] Program processing flow

[1598] Step 1: Collecting Messages

[1599] The server collects messages from multiple communication methods. It uses API endpoints such as email servers, communication tools (e.g., Slack, Microsoft Teams), chat apps (e.g., WhatsApp, LINE), and messenger apps (e.g., Facebook Messenger) as input. The server sends requests to these APIs to retrieve new messages. The output is message data obtained from each communication method.

[1600] Step 2: Centralize messages

[1601] The server centralizes the collected messages. It uses the message data collected in Step 1 as input. Specifically, it converts messages obtained from each communication method into a common data format. For example, an email message has fields such as "sender," "subject," "body," and "received date and time," while a Slack message has fields such as "sender," "channel," "message content," and "sent date and time." The server unifies these fields and converts them into a single data format. The output is the centralized message data.

[1602] Step 3: Save the message

[1603] The server stores the centralized messages in a database. It uses the message data centralized in step 2 as input. Specifically, it uses a relational database such as MySQL or PostgreSQL to store the message data in a table. For example, the message table may have columns such as "Message ID," "Sender," "Content," "Tool Name," and "Received Date and Time," ensuring each message is uniquely identified. The output is the message data stored in the database.

[1604] Step 4: Displaying the message

[1605] The device provides an interface for users to view messages. It uses message data retrieved from the server as input. Specifically, it displays a list of messages through a web or mobile application. For example, the frontend is built using React or Vue.js to allow users to visually view messages. Messages are color-coded by tool: email is displayed in blue, communication tools in green, and chat apps in red. The output is a list of messages viewable by the user.

[1606] Step 5: Message manipulation

[1607] Users interact with messages using an interface on their device. The displayed message list serves as input. Specifically, they can click on a particular message to view details or reply. Users can also use a filter function to display only messages from specific communication methods. Furthermore, they can categorize messages as work-related or personal based on their content and manage them as tasks. The output is the result of the user's actions.

[1608] (Application Example 1)

[1609] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1610] In logistics centers, messages are scattered across multiple communication tools (email, communication tools, chat, messenger apps, etc.), making it difficult for staff to quickly grasp and respond to information. This also reduces operational efficiency and increases the risk of important communications being overlooked.

[1611] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1612] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on their content, means for integrating messages collected from multiple communication tools so that logistics center staff can understand them at a glance on their smartphones, and means for centrally displaying messages from multiple communication tools used within the logistics center. As a result, logistics center staff can quickly understand which tool a message is coming from and respond promptly.

[1613] "Multiple communication tools" refers to different types of messaging methods, such as email, communication tools, chat, and messenger apps.

[1614] "A means of centralized display" refers to a function that collects messages from multiple communication tools and displays them in a list on a single interface.

[1615] "Means of sorting" refers to the function of classifying messages based on their content, determining whether they are work-related or personal.

[1616] "A means of creating and managing tasks" refers to a function that generates tasks based on the content of a message and manages those tasks.

[1617] A "logistics center" refers to a facility that stores, sorts, and distributes goods.

[1618] "Staff" refers to employees working at the logistics center.

[1619] A "smartphone" refers to a mobile phone that is capable of connecting to the internet and using applications.

[1620] "Means of integration" refers to the function of consolidating messages collected from multiple communication tools into a single system.

[1621] "Responding quickly" means taking the necessary action promptly after receiving a message.

[1622] The system for implementing this invention is for centrally displaying messages from multiple communication tools in a logistics center. Specifically, the server includes the following means:

[1623] First, the server collects messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.). This involves using Python's imaplib and email libraries to retrieve emails from an IMAP server, using the slack_sdk library to collect Slack messages, and using the WhatsApp API to collect WhatsApp messages.

[1624] Next, the server uses Flask to provide an API endpoint for centrally displaying the collected messages. This allows logistics center staff to view all messages on a single interface using their smartphones.

[1625] Furthermore, the server categorizes messages based on their content, determining whether they are work-related or personal. This allows staff to quickly identify and respond to important messages.

[1626] Furthermore, the server generates and manages tasks based on the content of the messages. This makes it possible to take appropriate actions based on the importance and urgency of the messages.

[1627] As a concrete example, when a logistics center staff member opens the "Logistics Messaging Integration App" on their smartphone, messages from email, Slack, and WhatsApp are displayed in a single screen. This allows staff to see at a glance which tool a message originated from and respond quickly.

[1628] Examples of prompt statements are as follows:

[1629] When logistics center staff open the "Logistics Messaging Integration App" on their smartphones, messages from email, Slack, and WhatsApp are displayed in a single screen. This allows staff to see at a glance which tool a message is coming from and respond quickly.

[1630] In this way, the efficiency of message management in logistics centers can be significantly improved.

[1631] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1632] Step 1:

[1633] The server retrieves email from the IMAP server. Specifically, it uses the imaplib and email libraries to log in to the specified email account and retrieve all emails from the inbox. The input is the email server's authentication information, and the output is data including the email sender, subject, and body.

[1634] Step 2:

[1635] The server retrieves messages from Slack. Specifically, it uses the slack_sdk library to retrieve messages from a specified Slack channel. The input is the Slack API token and channel ID, and the output is data containing the user ID and message text.

[1636] Step 3:

[1637] The server retrieves messages from WhatsApp. Specifically, it uses the WhatsApp API to retrieve messages from a specified WhatsApp account. The input is a WhatsApp API token, and the output is data containing the sender and message text.

[1638] Step 4:

[1639] The server centralizes all acquired messages. Specifically, it integrates messages from email, Slack, and WhatsApp, and combines them into a single data structure. The input is message data acquired from each communication tool, and the output is an integrated message list.

[1640] Step 5:

[1641] The server will serve the integrated messages from the API endpoint using Flask. Specifically, it will use the Flask framework to build an API that returns an integrated message list in JSON format. The input is the integrated message list, and the output is the JSON data provided from the API endpoint.

[1642] Step 6:

[1643] The user opens the "Logistics Message Integration App" on their smartphone. Specifically, they access the server's API endpoint using their smartphone's browser or a dedicated app. The input is the URL of the API endpoint, and the output is a list of integrated messages.

[1644] Step 7:

[1645] The user reviews the displayed messages and takes action as needed. Specifically, they review the message content and take appropriate action based on its importance and urgency. The input is a list of integrated messages, and the output is the user's actions.

[1646] (Example 2)

[1647] Next, we will describe Example 2 of the morphological example. 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."

[1648] In today's business environment, there is a need to efficiently manage messages from multiple communication methods (email, communication tools, chat, messenger apps, etc.). However, it is difficult to centralize these messages, further categorize them based on their content as work-related or personal, and manage them appropriately as tasks. In particular, there is a need to accurately analyze the sender and content of messages and quickly notify users of the classification results, but current systems cannot do this efficiently.

[1649] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1650] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for analyzing the source addresses of messages, means for analyzing the content of messages using a generative AI model and distinguishing between work and personal messages, means for creating and managing tasks based on the content of the messages, and means for notifying the user's terminal of the classification results. This makes it possible to efficiently centrally manage messages from multiple communication means, appropriately classify and create tasks based on their content, and quickly notify the user.

[1651] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1652] "Sender address" refers to information such as the email address or user ID of the sender who sent the message.

[1653] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze text data and understand and classify its content.

[1654] "Message content" refers to the main body of text data sent and received through a communication method.

[1655] "Means of centralized display" refers to a function that integrates messages obtained from multiple communication methods into a single interface for display.

[1656] "Means of analysis" refers to a function that analyzes the sender address and content of a message and extracts its characteristics.

[1657] "Means of sorting" refers to a function that automatically classifies whether a message is work-related or personal based on its analyzed content.

[1658] "A means of creating and managing tasks" refers to a function that generates tasks based on categorized messages and manages those tasks.

[1659] "Means for notifying of classification results" refers to a function that informs the user's device of the results of the sorting process.

[1660] This invention relates to a system that centrally displays messages from multiple communication methods, analyzes the source address and content of the messages to distinguish between work and personal messages, and further manages them as tasks based on their content. A specific embodiment of this system is shown below.

[1661] System Configuration

[1662] The server is comprised of the following hardware and software:

[1663] Hardware: A server machine equipped with a high-performance processor, sufficient memory, storage devices, and network interfaces.

[1664] Software: Mail server (supporting IMAP protocol), generative AI model (e.g., OpenAI's GPT-4), natural language processing library (e.g., NLTK and spaCy), notification system (e.g., Pushbullet).

[1665] Message received

[1666] The server receives messages sent by users. Specifically, it retrieves messages through email servers and chat application APIs. For example, it retrieves messages from an email server using the IMAP protocol.

[1667] Source analysis

[1668] The server analyzes the message's sender address. Specifically, it analyzes the message's header information to extract the sender address. For example, if the sender is a business email address like "@company.com", the server determines that the message is work-related.

[1669] Content analysis

[1670] The server analyzes the message content using natural language processing (NLP) techniques. This analysis uses a generative AI model (for example, OpenAI's GPT-4). Specifically, the following prompt sentences are input to the generative AI model.

[1671] Prompt: "Please determine whether the following message is work-related or personal. Message: 'Please prepare the materials for tomorrow's meeting.'"

[1672] The server receives the response from the generated AI model and determines whether the message is work-related or personal.

[1673] Notification of classification results

[1674] The server classifies messages as "work" or "personal" based on the analysis results and notifies the user's device of the result. Specifically, the result is notified via push notification or email. For example, the Pushbullet library is used to send push notifications.

[1675] Specific example

[1676] When a user receives the message "Please prepare the materials for tomorrow's meeting," the server processes it as follows:

[1677] 1. Verify that the message is sent from a business email address ending in "@company.com".

[1678] 2. Analyze the message content to determine if it contains business-related keywords such as "meeting" or "documents."

[1679] 3. Based on this information, categorize the messages as "work."

[1680] 4. Notify the user's device of the classification results.

[1681] In this way, it becomes possible to efficiently centrally manage messages from multiple communication methods, appropriately classify and assign tasks based on their content, and quickly notify users.

[1682] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1683] Step 1:

[1684] Message received

[1685] The server receives messages sent by users. Specifically, it retrieves messages through email servers and chat application APIs. For example, it retrieves messages from an email server using the IMAP protocol.

[1686] Input: Message sent by the user

[1687] Output: Message data stored on the server

[1688] Step 2:

[1689] Source analysis

[1690] The server analyzes the message's sender address. Specifically, it analyzes the message's header information to extract the sender address. For example, if the sender is a business email address like "@company.com", the server determines that the message is work-related.

[1691] Input: Message data stored on the server

[1692] Output: Source address analysis results

[1693] Step 3:

[1694] Content analysis

[1695] The server analyzes the message content using natural language processing (NLP) techniques. This analysis uses a generative AI model (for example, OpenAI's GPT-4). Specifically, the following prompt sentences are input to the generative AI model.

[1696] Prompt: "Please determine whether the following message is work-related or personal. Message: 'Please prepare the materials for tomorrow's meeting.'"

[1697] The server receives the response from the generated AI model and determines whether the message is work-related or personal.

[1698] Input: Message content

[1699] Output: Message classification result (work or personal)

[1700] Step 4:

[1701] Notification of classification results

[1702] The server classifies messages as "work" or "personal" based on the analysis results and notifies the user's device of the result. Specifically, the result is notified via push notification or email. For example, the Pushbullet library is used to send push notifications.

[1703] Input: Message classification result

[1704] Output: Notification sent to the user's device

[1705] Step 5:

[1706] Task creation and management

[1707] The server generates and manages tasks based on classified messages. Specifically, it prioritizes tasks based on the importance and urgency of the messages and notifies users at the appropriate time.

[1708] Input: Classified message

[1709] Output: Tasks registered in the task management system

[1710] The above describes the specific processing flow of this system's program.

[1711] (Application Example 2)

[1712] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1713] Many modern users utilize multiple communication tools, resulting in a mix of work-related and personal messages. This makes message management cumbersome, particularly in determining whether expense-related messages are work-related or personal. Furthermore, improper expense classification can lead to problems with expense reimbursement and personal financial management. Therefore, a system is needed that automatically categorizes expenses based on message content, allowing users to easily review them.

[1714] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for classifying messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for analyzing the source and content of messages to automatically determine whether an expense is work-related or personal, and means for displaying the expense classification results so that the user can confirm them. As a result, the user can centrally manage messages from multiple communication tools and automatically classify and confirm expenses.

[1715] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1716] A "message" refers to information such as text, images, audio, and video that is sent and received through communication tools.

[1717] "Centralization" refers to consolidating and displaying messages from multiple communication tools into a single interface.

[1718] "Classification" refers to judging and classifying messages based on their content, determining whether they are work-related or personal.

[1719] "Tasking" refers to managing a message by breaking it down into specific work items based on its content.

[1720] "Sender information" refers to the information of the person who sent the message.

[1721] "Analysis" refers to the process of analyzing the source and content of a message and making decisions based on specific criteria.

[1722] "Expenses" refers to information related to monetary payments.

[1723] "Classification result" refers to the result of classifying expenditures based on the content of the message.

[1724] "Display" refers to providing classification results visually so that users can confirm them.

[1725] A system for carrying out this invention includes means for centrally displaying messages from multiple communication tools, means for classifying messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for analyzing the sender and content of messages to automatically determine whether an expense is work-related or personal, and means for displaying the expense classification results so that the user can review them.

[1726] System program

[1727] The program for this system will be implemented using a programming language such as Python. The program will perform the following operations:

[1728] 1. Centralizing messages:

[1729] The server collects messages from email, communication tools, chat, messenger apps, etc., and aggregates them into a single interface. This allows users to view messages from multiple communication tools in one place.

[1730] 2. Message sorting:

[1731] The server analyzes the sender and content of messages to automatically determine whether they are work-related or personal. For example, if the sender is a work email address, or if the message contains work-related keywords such as "meeting expenses" or "travel expenses," the message will be classified as work-related.

[1732] 3. Taskification:

[1733] The server creates tasks based on sorted messages. Task creation is based on the importance and urgency of the messages. This allows users to prioritize and manage important tasks.

[1734] 4. Classification of expenditures:

[1735] The server analyzes the source and content of messages to automatically determine whether an expense is work-related or personal. For example, if a payment notification is sent from a work email address, or if the message contains work-related keywords such as "meeting expenses" or "travel expenses," the expense will be classified as work-related.

[1736] 5. Displaying classification results:

[1737] The server displays the expenditure classification results so that users can easily review and properly manage their spending.

[1738] Hardware and software to be used

[1739] Hardware: Smartphones, servers

[1740] Software: Python, database management systems (e.g., MySQL), messaging APIs (e.g., Gmail API)

[1741] Specific example

[1742] For example, consider a scenario where a user receives the following message.

[1743] Sender: "boss@work-email.com"

[1744] Message: "Regarding the cost of the next meeting"

[1745] In this case, the server classifies this message as "work" and manages the expense as work-related.

[1746] Example of a prompt

[1747] The following are examples of prompts to input into the generating AI model.

[1748] Sender: "boss@work-email.com"

[1749] Message: "Regarding the cost of the next meeting"

[1750] Is this message work-related or personal?

[1751] This prompt can be used to ask a generative AI model to classify a message.

[1752] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1753] Step 1:

[1754] The server collects messages from multiple communication tools (email, communication tools, chat, messenger apps, etc.). It receives message data obtained through the APIs of each communication tool as input. As output, it stores these messages in a centralized database. Specifically, the server calls the API of each communication tool, retrieves the message data, and stores it in the database.

[1755] Step 2:

[1756] The server analyzes the source and content of collected messages and automatically determines whether they are work-related or personal. It receives message data stored in a database as input and generates a classification result (work or personal) for each message as output. Specifically, the server analyzes message content using regular expressions and keyword matching and stores the classification results in the database.

[1757] Step 3:

[1758] The server creates tasks based on the sorted messages. It receives message data, including the classification results, as input. It generates tasked data as output. Specifically, the server evaluates the importance and urgency of messages and saves them as tasks in the database.

[1759] Step 4:

[1760] The server analyzes the source and content of messages to automatically determine whether an expense is work-related or personal. It receives message data stored in a database as input and generates expense classification results as output. Specifically, the server classifies expenses based on message content and saves the results to the database.

[1761] Step 5:

[1762] The server displays the expenditure classification results for the user to review. It receives data containing expenditure classification results as input and generates data to display in the user interface as output. Specifically, the server provides the classification results visually to the user through a web page or mobile application.

[1763] Step 6:

[1764] The user inputs a prompt message into the generative AI model and requests that it classify the message. The input is the prompt message sent to the generative AI model. The output is the classification result received from the generative AI model. Specifically, the user inputs a prompt message like the following:

[1765] Sender: "boss@work-email.com"

[1766] Message: "Regarding the cost of the next meeting"

[1767] Is this message work-related or personal?

[1768] This prompt can be used to ask a generative AI model to classify a message.

[1769] (Example 3)

[1770] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1771] In today's business environment, it is common to use multiple communication methods (email, communication tools, chat, messenger apps, etc.). However, it is difficult to centrally manage messages from these communication methods, separate work and personal matters, and automatically generate and manage tasks based on the content of the messages. As a result, users have to manually check the content of messages and manually generate tasks, which presents a challenge in efficient task management.

[1772] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1773] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for distinguishing between business and personal messages based on their content, means for analyzing the content of messages and automatically generating tasks based on the analysis results, and means for adding the generated tasks to a task list and managing them. This enables users to centrally manage messages from multiple communication means, distinguish between business and personal messages, and automatically generate tasks based on the content of messages, thereby enabling efficient task management.

[1774] "Means of communication" refers to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1775] "Centralization" refers to the process of consolidating and displaying messages from multiple communication methods in a single location.

[1776] "Work" refers to activities and tasks related to one's duties or job.

[1777] "Personal business" refers to personal errands or private activities.

[1778] "Distinguishing" refers to distinguishing between business and personal messages based on their content.

[1779] "Analysis" refers to the process of analyzing the content of a message using natural language processing techniques to understand its meaning.

[1780] A "task" refers to a specific action or task, and is a concrete work item generated based on the content of a message.

[1781] A "task list" is a list used to display and manage tasks that have been generated.

[1782] "Natural language processing technology" is a technology that enables computers to understand and analyze human language.

[1783] This invention is a system that centralizes messages from multiple communication methods, categorizes them as either business or personal based on their content, analyzes the message content to automatically generate tasks, and adds them to a task list for management.

[1784] Hardware and software to be used

[1785] hardware

[1786] User's device (PC, smartphone, etc.)

[1787] software

[1788] Natural language processing technologies (Google Cloud Natural Language API, IBM Watson Natural Language Understanding, etc.)

[1789] Program processing

[1790] Server Processing

[1791] The server analyzes messages received from users. Specifically, the server uses natural language processing techniques to analyze the message content and extract phrases that indicate actions. This analysis utilizes software such as Google Cloud Natural Language API and IBM Watson Natural Language Understanding.

[1792] Once the analysis is complete, the server automatically generates tasks based on the extracted phrases. The generated tasks are added to a task list and managed so that the user can review them later. For example, if the message contains the phrase "prepare for the meeting," the server generates a task called "prepare for the meeting" and adds it to the task list.

[1793] Terminal processing

[1794] The terminal's role is to send messages entered by the user to the server. When the user enters a message and presses the send button, the terminal sends that message to the server. For example, if the user enters "I need to prepare for tomorrow's meeting," that message will be sent from the terminal to the server.

[1795] User processing

[1796] Users manage tasks by typing messages using their devices. When a user types a message, it is sent to the server via the device. The server parses the message and generates a task, which the user can then view in their task list. For example, if a user types "Create presentation materials for next week," a task titled "Create presentation materials" will be generated based on that content.

[1797] Specific example

[1798] Example of a prompt

[1799] When you enter the message "I need to prepare for tomorrow's meeting," the server generates a task called "Prepare for meeting" and adds it to your task list.

[1800] This system allows users to automatically generate tasks based on message content and manage tasks efficiently. The flow of a specific process in Example 3 will be explained using Figure 15.

[1801] Step 1: The user enters a message.

[1802] The user enters the message using a device (such as a PC or smartphone). For example, the user might type, "I need to prepare for tomorrow's meeting." This input is saved on the device as a text message.

[1803] Step 2: The device sends the message to the server.

[1804] When a user types a message and presses the send button, the device sends that message to the server. Specifically, the device sends text-formatted message data to the server via the internet connection. The input is the user's message, and the output is the message sent to the server.

[1805] Step 3: The server receives the message.

[1806] The server receives messages sent from the terminal. The received messages are stored on the server as text data. The input is the message data from the terminal, and the output is the message data stored on the server.

[1807] Step 4: The server parses the message.

[1808] The server analyzes the received message. Specifically, the server uses natural language processing technologies (such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding) to analyze the message content and extract action phrases. The input is the message data stored on the server, and the output is the extracted action phrases.

[1809] Step 5: The server generates the task.

[1810] The server automatically generates tasks based on the analysis results. It creates specific tasks based on the extracted phrases. For example, it generates the task "Prepare for the meeting" from the phrase "Prepare for the meeting." The input is the extracted action phrase, and the output is the generated task.

[1811] Step 6: The server updates the task list.

[1812] The server adds the generated tasks to the task list. The task list is stored in a database and managed so that users can review it later. The input is the generated tasks, and the output is the updated task list.

[1813] Step 7: The user checks the task list.

[1814] The user uses a terminal to view the task list. The task list displays tasks generated by the server. This allows the user to view and manage tasks that have been automatically generated based on the content of messages. The input is the updated task list, and the output is the task list displayed on the user's screen.

[1815] (Application Example 3)

[1816] Next, we will describe application example 3 of form example 3. 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."

[1817] Conventional message management systems lacked the ability to automatically generate tasks based on message content and issue instructions to machines, resulting in decreased work efficiency within factories. Furthermore, the inability to analyze message content and generate appropriate tasks could lead to delays and errors. This, in turn, compromised factory productivity and safety.

[1818] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1819] In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on the message content, means for analyzing the message content, generating specific tasks for a machine based on the analysis results, and adding them to a task list, and means for instructing the machine on the generated tasks. This makes it possible to automatically generate appropriate tasks based on the message content and instruct the machine. As a result, the work efficiency in the factory can be improved and delays and errors in work can be reduced.

[1820] "Communication tools" refer to means of sending and receiving messages, such as email, communication tools, chat, and messenger apps.

[1821] "Messages" refer to text information and instructions sent and received through communication tools.

[1822] "Centralization" refers to consolidating messages from multiple communication tools into a single platform or interface.

[1823] "Discrimination" refers to distinguishing whether a message is work-related or personal based on its content.

[1824] "Task creation" refers to analyzing the content of a message and generating specific tasks or instructions based on that analysis.

[1825] "Management" refers to adding generated tasks to a list and tracking their progress and completion status.

[1826] "Analysis" refers to understanding the content of a message using techniques such as natural language processing and extracting its meaning.

[1827] "Machinery" refers to robots and automated equipment used within a factory.

[1828] A "task list" refers to a list used to display and manage generated tasks in a list format.

[1829] "Instructions" refer to giving specific commands to a machine based on the generated task.

[1830] The system for carrying out this invention includes an application installed on a robot used in a factory. Specific embodiments of this system are described below.

[1831] System Configuration

[1832] The system consists of the following main components:

[1833] 1. Server: Centralizes and displays messages from multiple communication tools.

[1834] 2. Natural Language Processing (NLP) Engine: Analyzes the content of messages and generates tasks based on the analysis results.

[1835] 3. Task Manager: Add and manage generated tasks in the task list.

[1836] 4. Robot Controller: Instructs the robot on the generated tasks.

[1837] Hardware and software to be used

[1838] Hardware: Robots in factories

[1839] Software: Python, spaCy (natural language processing library), TaskManager (task management system), RobotController (robot control system)

[1840] Processing flow

[1841] 1. Receiving messages: The server receives messages from communication tools such as email, communication tools, chat, and messenger apps.

[1842] 2. Message centralization: Received messages are aggregated and displayed on a single platform.

[1843] 3. Message Analysis: The content of the message is analyzed using a natural language processing engine (spaCy) and its meaning is extracted.

[1844] 4. Task Generation: Based on the analysis results, specific tasks are generated. For example, if the message "Perform maintenance on line 1" is received, a maintenance task is generated.

[1845] 5. Add to task list: Add the generated task to the task list and manage it.

[1846] 6. Instructions to the robot: Instruct the robot to execute the tasks added to the task list.

[1847] Specific example

[1848] For example, consider the case where the following message is received:

[1849] Message: "Performing maintenance on line 1"

[1850] Program processing: Analyzes messages, generates "maintenance" tasks, and issues instructions to the robot.

[1851] Examples of prompts to input into a generative AI model:

[1852] "We have received a message indicating that maintenance will be performed on line 1. Based on this message, generate a maintenance task and issue instructions to the robot."

[1853] In this way, it becomes possible to automatically generate tasks and issue instructions to robots based on messages within the factory. This improves work efficiency within the factory and reduces delays and errors.

[1854] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1855] Step 1:

[1856] The server receives messages from communication tools such as email, communication tools, chat, and messenger apps. The input is messages sent from each communication tool, and the output is centralized message data. Specifically, messages are retrieved using the APIs of each communication tool and stored in a database.

[1857] Step 2:

[1858] The server aggregates and displays received messages on a single platform. The input is centralized message data, and the output is a user-accessible integrated message interface. Specifically, it retrieves messages from a database and displays them on a web interface or application screen.

[1859] Step 3:

[1860] The server uses a natural language processing engine (spaCy) to analyze message content and extract meaning. The input is centralized message data, and the output is the analyzed message content. Specifically, the spaCy model is loaded, and the message text is analyzed to extract important keywords and phrases.

[1861] Step 4:

[1862] The server generates specific tasks based on the analysis results. The input is the analyzed message content, and the output is the generated task. Specifically, it determines the type and details of the task based on the extracted keywords and phrases, and generates a task object.

[1863] Step 5:

[1864] The server adds and manages the generated tasks to a task list. The input is the generated tasks, and the output is the updated task list. Specifically, it saves task objects to the database and updates the task list.

[1865] Step 6:

[1866] The server instructs the robot to execute tasks added to the task list. The input is the updated task list, and the output is the robot's execution status. Specifically, the generated tasks are sent to the robot via the robot controller, and their execution status is monitored.

[1867] In this way, it becomes possible to automatically generate tasks and issue instructions to robots based on messages within the factory. This improves work efficiency within the factory and reduces delays and errors.

[1868] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1869] "Example of form 1"

[1870] One embodiment of the present invention provides a system that combines an emotion engine. This system includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, and an emotion engine that recognizes the user's emotions. The emotion engine recognizes the user's emotions, for example, from the user's tone of voice, facial expressions, and the context of the message.

[1871] "Example of form 2"

[1872] As one embodiment of a system using an emotion engine, a function is provided that adjusts the priority of messages based on the user's emotions. For example, if a user receives a message expressing anger or dissatisfaction, that message is determined to have high priority and is displayed so that it is immediately visible to the user.

[1873] "Example of form 3"

[1874] As one embodiment of a system using an emotion engine, a function is provided that adjusts task priorities based on the user's emotions. For example, if a user receives a message indicating joy or excitement, tasks related to that message are determined to have a high priority and are displayed higher up in the task list.

[1875] The following describes the processing flow for each example of the form.

[1876] "Example of form 1"

[1877] Step 1: The system centralizes and displays messages from multiple communication tools.

[1878] Step 2: Next, the system sorts the message into work-related or personal based on its content.

[1879] Step 3: The system then breaks down the message content into tasks and manages them accordingly.

[1880] Step 4: Finally, the emotion engine recognizes the user's emotions based on factors such as the user's tone of voice, facial expressions, and the context of the message.

[1881] "Example of form 2"

[1882] Step 1: The system adjusts message priorities based on the user's emotions.

[1883] Step 2: For example, if a user receives a message expressing anger or dissatisfaction, that message is judged to have high priority.

[1884] Step 3: As a result, the message is displayed so that it is immediately visible to the user. (Example 3)

[1885] Step 1: The system adjusts task priorities based on the user's emotions.

[1886] Step 2: For example, if a user receives a message expressing joy or excitement, the task associated with that message will be judged to have a high priority.

[1887] Step 3: As a result, the task will appear higher up in the task list.

[1888] (Example 1)

[1889] Next, we will describe Embodiment 1 of Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1890] In today's business environment, users utilize multiple communication methods (email, communication tools, chat, messaging applications, etc.), requiring them to individually check messages from each tool. This makes message checking and management cumbersome, increasing the risk of missing important messages. Furthermore, users need to categorize messages as either work-related or personal, and manage them as tasks, but doing this manually is time-consuming and laborious. Additionally, recognizing user emotions and providing appropriate feedback is crucial, but current systems do not adequately address this.

[1891] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1892] In this invention, the server includes means for centrally displaying messages from multiple communication means, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means for recognizing the user's emotions, and means for providing feedback based on the recognized emotions. This allows the user to centrally manage messages from multiple communication means, efficiently manage tasks without missing important messages, and improve user satisfaction and productivity by recognizing the user's emotions and providing appropriate feedback.

[1893] "Communication methods" refer to various means that users use to send and receive messages, such as email, communication tools, chat, and messaging applications.

[1894] "Means of centralized display" refers to methods for displaying messages collected from multiple communication methods in a list on a single interface.

[1895] "Means of sorting" refers to methods for analyzing the content of a message and classifying whether it is work-related or personal.

[1896] "Means of task creation and management" refers to methods for generating tasks based on the content of a message and managing those tasks.

[1897] "Means of recognizing emotions" refers to methods for recognizing a user's emotions from their tone of voice, facial expressions, message context, etc.

[1898] "Means of providing feedback" refers to means of providing users with appropriate advice and information based on their perceived emotions.

[1899] This invention is a system that centrally displays messages from multiple communication methods, categorizes them as either work-related or personal based on their content, and further manages them as tasks. It also includes a function to recognize the user's emotions and provide appropriate feedback.

[1900] Message collection and centralized display

[1901] The server collects messages from multiple communication methods used by the user (e.g., email, communication tools, chat, messaging applications). This is done by utilizing the APIs of each communication method. For example, the email API is used to collect emails, the communication API for communication tools, the chat API for chats, and the messaging API for messaging applications. The collected messages are stored in a database, and the terminal displays an interface accessible to the user, showing the collected messages in a list format.

[1902] Message Classification

[1903] The server analyzes the content of the collected messages and distinguishes between work-related and personal matters. This is done using natural language processing (NLP) techniques. Specifically, it uses a natural language processing API to analyze the message content and determine the category. For example, a message like "Please prepare the materials for tomorrow's meeting" is classified as work-related, while a message like "Let's go see a movie this weekend" is classified as personal.

[1904] Task creation and management

[1905] The server generates tasks based on classified messages and adds them to the task management tool. Task management uses a task management API. For example, a new task can be generated using the task management tool's API and added to the user's task management board. Users can then view the generated tasks and manage their progress.

[1906] Emotional Recognition and Feedback

[1907] The server uses an emotion engine to recognize the user's emotions. This involves using speech recognition and facial recognition technologies. For example, it uses a speech recognition API to analyze the tone of the user's voice and a facial recognition API to analyze the user's facial expressions. Based on the recognized emotions, the server provides appropriate feedback to the user. For example, if the user sends the message "I'm very tired today," the emotion engine recognizes the user's fatigue and provides advice on how to relax.

[1908] Specific example

[1909] When users are using email, communication tools, chat, and messaging applications, the server collects messages from these tools and displays them in a single interface. Users can see at a glance which tool a message originated from. They can also categorize messages as work-related or personal based on their content, and generate and manage tasks accordingly. Furthermore, by recognizing user emotions and providing appropriate feedback, the system can improve user satisfaction and productivity.

[1910] Example of a prompt

[1911] "Collect messages from email, communication tools, chat, and messaging applications and display them in a single interface. Furthermore, categorize messages as either work-related or personal based on their content, generate and manage tasks accordingly, and recognize user sentiment to provide appropriate feedback."

[1912] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1913] Step 1:

[1914] The server collects messages from multiple communication methods.

[1915] Input: Message data from email, communication tools, chat, and messaging application APIs.

[1916] Specific operation: The server retrieves new messages by calling the API for each communication method. For example, it uses the email API to retrieve new emails and the communication tool API to retrieve new chat messages.

[1917] Output: The collected message data is saved to the database.

[1918] Step 2:

[1919] The server retrieves messages from the database in order to centrally display the collected messages.

[1920] Input: Message data stored in the database.

[1921] Specific operation: The server retrieves messages collected from the database and sends them to the interface accessed by the user.

[1922] Output: A centralized list of messages displayed on the terminal.

[1923] Step 3:

[1924] The server analyzes the content of the collected messages and distinguishes between work-related and personal messages.

[1925] Input: Message data retrieved from the database.

[1926] Specific operation: The server calls a natural language processing API to analyze the message content and determine its category. For example, the message "Please prepare the materials for tomorrow's meeting" is classified as work-related, while the message "Let's go see a movie this weekend" is classified as personal.

[1927] Output: Classified message data.

[1928] Step 4:

[1929] The server generates tasks based on the classified messages and adds them to the task management tool.

[1930] Input: Classified message data.

[1931] Specific operation: The server calls the task management API to generate a new task and adds it to the user's task management board. For example, it uses the task management tool's API to generate a task called "Prepare meeting materials" and adds it to the user's task management board.

[1932] Output: A new task added to the task management tool.

[1933] Step 5:

[1934] The server uses an emotion engine to recognize the user's emotions.

[1935] Input: User's tone of voice, facial expression, and message context.

[1936] Specific operation: The server calls a speech recognition API to analyze the tone of the user's voice and a facial recognition API to analyze the user's facial expressions. For example, if the user sends the message "I'm very tired today," the emotion engine recognizes the user's level of fatigue.

[1937] Output: Sentiment data of recognized users.

[1938] Step 6:

[1939] The server provides appropriate feedback to the user based on the emotions it perceives.

[1940] Input: Sentiment data of the recognized user.

[1941] Specific operation: The server provides the user with advice and information to help them relax based on the emotions it perceives. For example, if the server perceives the user as tired, it will suggest relaxing music or taking a break.

[1942] Output: Feedback provided to the user.

[1943] (Application Example 1)

[1944] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1945] Traditional factory robots lacked features such as the ability to centrally display messages from multiple communication tools, differentiate between work-related and personal messages based on their content, and manage tasks based on message content. Furthermore, they lacked the ability to recognize the emotions of factory staff and prompt appropriate responses, making efficient communication and appropriate responses based on staff emotions difficult.

[1946] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for centrally displaying messages from multiple communication tools, means for distinguishing between work and personal messages based on their content, means for creating and managing tasks based on their content, means including an emotion engine that recognizes the user's emotions, and means for recognizing the emotions of factory staff and prompting appropriate responses. This enables more efficient communication within the factory and appropriate responses based on the emotions of the staff.

[1947] "Multiple communication tools" refers to different types of communication methods such as email, communication tools, chat, and messenger apps.

[1948] "A means of centralized display" refers to a function that integrates and displays messages from multiple communication tools on a single interface.

[1949] "Means of sorting" refers to a function that automatically categorizes messages based on their content, determining whether they are work-related or personal.

[1950] "A means of creating and managing tasks" refers to a function that generates tasks based on the content of a message and manages those tasks.

[1951] An "emotion engine" refers to technology that recognizes a user's emotions based on factors such as the tone of their voice, facial expressions, and the context of their message.

[1952] "Means of recognizing the emotions of factory staff and prompting appropriate responses" refers to a function that uses an emotion engine to recognize the emotions of staff working in the factory and takes appropriate action based on those emotions.

[1953] The system for carrying out this invention is configured as an application installed on a factory robot. A specific embodiment is shown below.

[1954] System Configuration

[1955] The server includes means for centrally displaying messages from multiple communication tools, means for categorizing messages as either work-related or personal based on their content, means for creating and managing tasks based on their content, means including an emotion engine for recognizing user emotions, and means for recognizing the emotions of factory staff and prompting appropriate responses.

[1956] Hardware and software to be used

[1957] Hardware: Factory robots (e.g., KUKA, Fanuc)

[1958] Software: Python, smtplib, imaplib, email library, TextBlob, json

[1959] Data processing and data calculation

[1960] The server performs the following data processing and calculations:

[1961] 1. Retrieve emails:

[1962] The server retrieves email from the IMAP server. This is done using the imaplib library.

[1963] 2. Message analysis:

[1964] The server analyzes the content of the retrieved emails and performs sentiment analysis. This is done using the TextBlob library.

[1965] 3. Centralizing messages:

[1966] The server centralizes the analysis results and displays them on an integrated interface. This is done using the JSON library.

[1967] 4. Emotional Engine:

[1968] The server recognizes the user's emotions based on factors such as the user's tone of voice, facial expressions, and the context of the message. This is done using emotion recognition technology.

[1969] 5. Facilitating appropriate responses:

[1970] The server recognizes the emotions of the staff in the factory and takes appropriate action based on those emotions.

[1971] Specific example

[1972] For example, if a staff member in a factory tells a robot that "the production line is behind schedule today," the robot registers that message as a task and notifies the manager. Also, if the robot detects that a staff member is tired, it sends a message encouraging them to take a break.

[1973] Example of a prompt

[1974] Design a system where, when a staff member speaks to a robot in a factory, the robot recognizes the staff member's emotions and responds appropriately. For example, if a staff m...

Claims

[Claim 1] A means for collecting messages received in multiple different means of communication, including at least two or more of the following: email, communication tools, chat, and messenger apps. A means of centralizing collected messages by converting them into a common data format, A means for storing centralized messages in a database, associated with identification information indicating the type of communication method, A means for analyzing the content of the message stored in the database using an emotion engine to obtain an emotion score, A means for determining the intensity of emotion by comparing the aforementioned emotion score with a threshold, Means for setting the priority of the message based on the emotional intensity, A means for displaying the message with the aforementioned high priority setting as a pop-up, A system that includes this.

Images