System

Abstract

A system is provided.SOLUTION: This system is provided with a means for collecting the communication data of a user, a means for automatically generating a task by analyzing the collected data, a means for discriminating and reporting the importance of the generated task, and a means for retrieving and providing necessary information from past communication.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In their daily work, businesspeople communicate through numerous emails and chats, resulting in numerous requests and tasks. However, these tasks often get buried or forgotten. This creates the risk of delays in work progress and important requests being overlooked. It is also difficult to find the necessary information among the vast amount of text. Therefore, a system that can solve these issues and improve the efficiency of task management is needed. [Means for solving the problem]

[0005] This invention provides a system that includes a means for collecting user communication data, a means for automatically generating tasks by analyzing the collected data, a means for determining and notifying the user of the importance of the generated tasks, and a means for retrieving and providing necessary information from past interactions. Specifically, a server analyzes email and chat data collected from the user's device and automatically extracts and generates tasks to be done. The system then determines the importance of each task and sets reminders and alerts for high-priority tasks to notify the user. Furthermore, even if the user submits an ambiguous request, the system searches for relevant information from past data and provides appropriate summary information, allowing the user to quickly obtain the necessary information. In this way, the efficiency of task management in business communication is significantly improved, solving problems such as overlooked requests and difficulty in information retrieval.

[0006] "Communication Data" refers to text messages, attachments, and other information sent or received by a user via email or chat.

[0007] "Means of collection" refers to the method or function of acquiring communication data from the user's device and transferring it to the server.

[0008] "Means for analyzing data" refers to AI models and algorithms that analyze received communication data and automatically extract tasks and related information from its contents.

[0009] "Means for automatically generating tasks" refers to the method or function by which the system automatically creates tasks with specific actions and deadlines based on the analyzed data.

[0010] "Means for determining importance" refers to algorithms and rules for assessing the importance and urgency of generated tasks and setting appropriate reminders and alerts.

[0011] "Means of notification" refers to the method or function of sending information to the user's device in the form of push notification, email, etc. about identified important tasks or tasks that require a reminder.

[0012] "Means for searching and providing information" refers to methods and functions for searching for relevant information from past communication data and providing summaries or answers in response to vague requests from users. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention relates to a system for automatically generating and managing tasks from user communication data. The following describes in detail how to implement the program for this system.

[0035] A natural language description of the program's operation

[0036] Collection of communication data

[0037] When users communicate via email or chat, their devices obtain permission to send these communications to the system. The devices are configured to periodically send collected data to the server, ensuring that the latest communication data is always available to the system.

[0038] Data analysis and task generation

[0039] The server analyzes the received data and automatically generates tasks to be done. Using natural language processing technology, the server divides the message content into tokens and extracts specific tasks by analyzing the intent. For example, if a user receives a message saying "Please submit a report by tomorrow," the server analyzes the message, generates a task called "Submit report," and sets the deadline to "tomorrow."

[0040] Determining the importance

[0041] The server evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task content. Depending on the evaluation result, the server classifies the task as high, medium, or low importance.

[0042] Reminders and notifications

[0043] The server sets reminders for tasks with high importance. The reminder settings are configured to send notifications to the user before the task deadline approaches. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user's device.

[0044] Dealing with ambiguous requests

[0045] When a user sends a vague request from their device, for example, "I want to check the details of last week's meeting," the server searches past communication data, summarizes the relevant content, and provides it to the user. This function allows users to quickly obtain the information they need.

[0046] Specific examples

[0047] 1. Task Creation Example

[0048] User: Receives an email saying "Please check with client X about meeting next week."

[0049] Terminal: Send the data of this email to the server.

[0050] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[0051] Server: Set the due date of the generated task to "Next week".

[0052] Server: Rate the importance of the task and set it as high importance.

[0053] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[0054] 2. Examples of Ambiguous Requests

[0055] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[0056] Terminal: Sends the request to the server.

[0057] Server: Searches past communication data and summarizes relevant messages.

[0058] Server: Sends the summarized information to the user's terminal.

[0059] Terminal: Displays the received summary information to the user.

[0060] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Users communicate via email and chat. Users send and receive messages as part of their normal business processes.

[0064] Step 2:

[0065] With user permission, the device collects email and chat data, including information such as message body, sender, recipient, and timestamp.

[0066] Step 3:

[0067] The device periodically sends the collected data to a server, where the data is encrypted and securely transmitted.

[0068] Step 4:

[0069] The server analyzes the received data, and an AI model breaks the message down into tokens and uses natural language processing techniques to understand the content of the message.

[0070] Step 5:

[0071] The server automatically generates tasks based on the analysis results. For example, a message such as "Please submit a report by tomorrow" generates a task called "Submit a report."

[0072] Step 6:

[0073] The server saves the details of the created task (task ID, task content, deadline, importance, etc.) in a database.

[0074] Step 7:

[0075] The server determines the importance of the task, analyzes the deadline and content of the task, and calculates the importance score.

[0076] Step 8:

[0077] The server sets reminders and alerts based on the importance of the task, and for high-priority tasks, it determines the frequency and timing of reminder notifications.

[0078] Step 9:

[0079] The server sends reminders and alerts to the user's device, for example, a notification that "Tomorrow is the deadline for submitting a report."

[0080] Step 10:

[0081] The device will display reminders and alerts to the user, allowing them to review important tasks and take appropriate action.

[0082] Step 11:

[0083] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[0084] Step 12:

[0085] The terminal sends the user's request to the server.

[0086] Step 13:

[0087] The server searches past communication data, extracts relevant information, generates summary information, and prepares it for presentation to the user.

[0088] Step 14:

[0089] The server transmits the generated summary information to the user's terminal.

[0090] Step 15:

[0091] The terminal displays the summary information to the user, allowing the user to quickly obtain the information they need.

[0092] Example 1

[0093] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0094] In today's business environment, many tasks and communications are performed daily, requiring efficient management and tracking. However, many users face challenges such as overlooking important tasks and difficulty responding appropriately to ambiguous requests. This can lead to poor task management efficiency and a decline in the quality of business communications. The present invention aims to solve these challenges by providing a system that enables users to effectively manage tasks and quickly respond to ambiguous requests.

[0095] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0096] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data to automatically generate tasks, means for evaluating the importance of the generated tasks, means for sending a notification to the user's terminal before the task deadline approaches, and means for analyzing the user's ambiguous requests and providing summary information from related past data, thereby preventing the user from overlooking tasks, enabling effective management of important tasks, and prompt response to ambiguous requests.

[0097] "Communication data" refers to data that includes the content of communications that users make electronically, such as by email or chat.

[0098] The "means of collection" is a mechanism for transferring communication data from the user's terminal to a server at regular intervals.

[0099] "Means of analyzing and automatically generating tasks" refers to the process of analyzing communication data using natural language processing technology, extracting specific actions and tasks from it, and automatically generating them.

[0100] The "means for evaluating the importance of a task" is a method for evaluating and ranking the importance of a generated task based on the deadline and urgency of the task's content.

[0101] "Means for sending notifications" refers to the technical means by which reminders and alerts are sent to the user's device when an important task is approaching its deadline.

[0102] "Means for analyzing ambiguous requests and providing summary information from related past data" refers to a method of analyzing ambiguous requests from users using natural language processing technology, searching past communication data to extract relevant information, and providing it in a summarized form.

[0103] "Preventing tasks from being overlooked" means that the system automatically generates tasks and sends reminders based on their importance, preventing users from forgetting important tasks.

[0104] "Effectively managing important tasks" means improving the efficiency of task management by evaluating the priority of tasks generated by the system and notifying the user at the appropriate time.

[0105] "Quick response to ambiguous requests" means enabling users to quickly obtain the information they need by quickly providing relevant information in response to ambiguous instructions or questions.

[0106] This invention relates to a system for automatically generating and managing tasks from user communication data. This system has the function of collecting and analyzing user communication data and sending reminders and notifications based on importance. It can also provide necessary information from related past data in response to vague user requests.

[0107] Hardware and Software

[0108] This system uses the following hardware and software:

[0109] Hardware: Servers, users' PCs and smartphones

[0110] Software: Natural language processing tools (e.g., Google Cloud Natural Language API), reminder and notification systems (e.g., Firebase Cloud Messaging)

[0111] Program processing

[0112] 1. Collection of communication data

[0113] Users: Allow the system to collect data when communicating with them via email or chat.

[0114] Terminal: Periodically transmits authorized communication data to the server.

[0115] 2. Data analysis and task generation

[0116] Server: Analyzes the received communication data using natural language processing technology and extracts specific tasks.

[0117] Server: For example, if a message "Please submit a report by tomorrow" is received, a task called "Submit report" is generated and its deadline is set to "tomorrow."

[0118] 3. Determining the importance

[0119] Server: Evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task.

[0120] 4. Reminders and Notifications

[0121] Server: Sends reminders to users about high-priority tasks before their deadlines approach.

[0122] Device: For example, display a notification saying "Tomorrow is the deadline for submitting your report."

[0123] 5. Dealing with Ambiguous Requests

[0124] User: Sends vague requests to the system (e.g., "I want to see what happened in last week's meetings").

[0125] Server: Searches past communication data, summarizes relevant content, and provides it to the user.

[0126] Specific examples

[0127] 1. Task Creation Example

[0128] User: Receives an email saying "Please check with client X about meeting next week."

[0129] Terminal: Send the data of this email to the server.

[0130] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[0131] Server: Set the due date of the generated task to "Next week".

[0132] Server: Rate the importance of the task and set it as high importance.

[0133] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[0134] 2. Examples of Ambiguous Requests

[0135] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[0136] Terminal: Sends the request to the server.

[0137] Server: Searches past communication data and summarizes relevant messages.

[0138] Server: Sends the summarized information to the user's terminal.

[0139] Terminal: Displays the received summary information to the user.

[0140] Prompt Sentence Examples

[0141] "Please explain a system that automatically generates tasks to be done for the next seven days of work and sets reminders based on their importance. Please provide a specific example that includes a process that collects and analyzes user communication data to generate tasks, evaluates their importance, and sends reminders."

[0142] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] System program processing flow

[0145] Step 1:

[0146] Obtaining permission

[0147] User: The system obtains permission from the user to collect communication data.

[0148] Specific operation: The user selects permission for data collection in the system settings screen.

[0149] Input: A setting change request from the user.

[0150] Output: The data collection permission flag is enabled.

[0151] Step 2:

[0152] Data collection

[0153] Device: Every time a user communicates via email or chat, the communication data is temporarily stored on the device.

[0154] Specific operation: The device stores communication data in local storage and updates it whenever the data is collected.

[0155] Input: Communication data sent and received by users.

[0156] Output: The latest communication data is saved in local storage.

[0157] Step 3:

[0158] Sending data

[0159] Terminal: Sends collected data to the server at regular intervals.

[0160] Specific operation: The terminal executes a batch job every night and sends the collected data to the server.

[0161] Input: Communication data stored in local storage.

[0162] Output: Communication data sent to the server.

[0163] Step 4:

[0164] Receiving data

[0165] Server: Receives communication data sent from the device and stores it in a database.

[0166] Specific operation: The server saves the communication data as a new record in the database.

[0167] Input: Communication data sent from the terminal.

[0168] Output: Communication data stored in a database.

[0169] Step 5:

[0170] Message Parsing

[0171] Server: Uses natural language processing (NLP) techniques to parse the message content and break it down into tokens.

[0172] What happens: The server uses the Google Cloud Natural Language API to split the text into tokens.

[0173] Input: Communication data stored in a database.

[0174] Output: Message data split into tokens.

[0175] Step 6:

[0176] Extracting tasks

[0177] Server: Extracts specific tasks from the analysis results.

[0178] Specific operation: Extract action words such as "submit" and "confirm" and register them as tasks.

[0179] Input: Message data split into tokens.

[0180] Output: Actions extracted as tasks with their details.

[0181] Step 7:

[0182] Task registration

[0183] Server: Register the extracted task as a new task in the database.

[0184] What it does: Adds a record to the database, including the task title, due date, importance, etc.

[0185] Input: Actions extracted as tasks and their details.

[0186] Output: The newly added task record in the database.

[0187] Step 8:

[0188] Initial assessment of task importance

[0189] Server: Initially assesses the importance of the task based on its deadline and content.

[0190] Specific behavior: The shorter the deadline, the higher the importance.

[0191] Input: Task description and deadline.

[0192] Output: Initially assessed task importance.

[0193] Step 9:

[0194] Finalize the importance

[0195] Server: Determines the final priority based on the user's past behavior and task management patterns.

[0196] Specific operation: Automatically classifies the importance of tasks into "high," "medium," or "low" based on the user's past task completion status.

[0197] Input: Initially assessed task importance and user performance data.

[0198] Output: The finalized task importance.

[0199] Step 10:

[0200] Reminder Settings

[0201] Server: Set reminders for high-priority tasks.

[0202] What it does: Adds a new record to the database with the reminder date and time.

[0203] Input: The finalized task importance.

[0204] Output: The reminder settings added to the database.

[0205] Step 11:

[0206] Sending notifications

[0207] Server: Sends a notification to the user's device at the scheduled date and time.

[0208] What it does: Sends a notification using Firebase Cloud Messaging and displays a message with details about the task.

[0209] Input: Reminder settings stored in the database.

[0210] Output: Notification sent to the user's device.

[0211] Step 12:

[0212] Receiving an ambiguous request

[0213] Server: Receives and analyzes ambiguous requests from users.

[0214] Specific behavior: Analyzes the request message using natural language processing to identify intent.

[0215] Input: An ambiguous request sent by the user.

[0216] Output: The parsed request content.

[0217] Step 13:

[0218] Data Search

[0219] Server: Searches past communication data and extracts relevant information.

[0220] What it does: It applies filtering criteria to the database to extract relevant messages.

[0221] Input: The parsed request content.

[0222] Output: Extracted relevant messages.

[0223] Step 14:

[0224] Creating a summary

[0225] Server: Summarizes the extracted information and presents it to the user.

[0226] What it does: Uses a summarization algorithm to extract key points.

[0227] Input: The extracted relevant message.

[0228] Output: Summarized information.

[0229] Step 15:

[0230] Sending a Summary

[0231] Server: Sends the summarized information to the user's terminal.

[0232] Specific behavior: Summary text is sent to the user's device and displayed via notification or email.

[0233] Input: Summarized information.

[0234] Output: Summary information sent to the user's device.

[0235] (Application example 1)

[0236] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0237] The present invention aims to improve productivity and efficiency by providing a means for automatically generating and managing important tasks from a large amount of constantly updated communication data, thereby issuing appropriate instructions to automated equipment and robots used in factories. Furthermore, it aims to support the execution of work by providing relevant information quickly and accurately even when a user makes an ambiguous request.

[0238] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0239] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and automatically generating tasks, means for determining the importance of the generated tasks and notifying the user, means for retrieving and providing necessary information from past communications, and means for issuing instructions to automated equipment used in the factory. This allows users to efficiently manage tasks arising from daily communications, and in particular, enables productivity and work efficiency to be improved while appropriately issuing instructions to automated equipment in the factory.

[0240] "User communication data" refers to information generated through the means of communication that users use on a daily basis, such as email, chat messages, and voice communications.

[0241] A "task" is a specific task or activity that a user must perform, and is automatically generated and managed by the system.

[0242] "Analysis" is the process of breaking down collected data and extracting specific patterns or information.

[0243] "Importance" is an evaluation criterion that indicates the priority of a generated task, and is determined based on the urgency and importance of the task.

[0244] "Notifications" are messages that inform users about task progress and deadlines.

[0245] "Search" is the operation of finding information that matches specific conditions from a database or stored information.

[0246] "Providing" refers to presenting the searched information to the user in an easy-to-view format.

[0247] "Automated equipment used in factories" refers to robots and mechanical devices used on production lines and in workshops.

[0248] "Instruction" is the act of ordering or requesting someone to perform a specific task or work.

[0249] A "system" is an information processing device or a collection of software in which multiple components operate in cooperation with each other.

[0250] The present invention is a system for collecting user communication data and automatically generating and managing tasks. In particular, it is possible to efficiently issue instructions to automated equipment used in factories. Specific embodiments of the present invention will be described below.

[0251] First, the system configuration will be explained. The system includes the following elements:

[0252] 1. User device: A digital device used by a user, such as a smartphone, smart glasses, or computer.

[0253] 2. Server: A computer system that analyzes data, generates tasks, and manages tasks.

[0254] 3. Natural Language Processing (NLP) module: Software for analyzing user communication data using NLP techniques such as SpaCy and BERT.

[0255] 4. Communication protocol: A protocol that uses MQTT or HTTP to communicate data between the user device and the server.

[0256] The user terminal sends communication data via email and chat to the server. With the user's permission, the collected data is periodically sent to the server. This collection process ensures that the system always has the latest communication data available.

[0257] The server analyzes the received data and automatically generates tasks to be done. The server uses an NLP module to divide the message content into tokens, analyze the intent, and extract specific tasks. For example, if a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend," the server analyzes this message, generates a task called "Maintain Machine X," and sets its deadline to "weekend."

[0258] The generated tasks are evaluated for importance using an importance evaluation module. This evaluation is based on the proximity of the task's deadline and the importance of the content. Depending on the task's importance, the server sets a reminder notification and sends it to the user's device when the deadline approaches.

[0259] In addition, if a user sends a vague request such as "I want to check last week's maintenance records," the server searches past communication data, summarizes the relevant information, and provides it to the user. This function allows users to quickly obtain the information they need.

[0260] For example, a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend." This message is sent from the user's device to the server, which analyzes it and generates a "Maintain Machine X" task with a deadline of the weekend. This task is evaluated as being of medium importance, and a reminder is sent the day before the weekend.

[0261] Furthermore, when a user requests, "I want to check last week's maintenance records," the server searches past data, summarizes the relevant records, and provides them to the user. In this way, users can efficiently manage tasks and issue appropriate instructions to automated equipment in the factory.

[0262] Example prompt sentence:

[0263] User message: "Tell Robot A to perform maintenance on Machine X over the weekend"

[0264] Process: Maintenance task generation and deadline setting

[0265]

[0266] User Request: "I want to check last week's maintenance records."

[0267] Process: Searching for and summarizing historical data

[0268] This invention enables users to efficiently manage tasks arising from daily communication, and in particular to give appropriate instructions to automated equipment in factories, thereby improving productivity and business efficiency.

[0269] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0270] Step 1: Collect communication data

[0271] When a user sends a message via email or chat, the device collects this communication data. The input data is the user's message, and the output data is the text data of the collected message. Specifically, the device is configured to capture the message and send it to a server at regular intervals.

[0272] Step 2: Sending data to the server

[0273] The terminal sends the collected text data to the server. The input data is the collected message text data, and the output data is the message data stored on the server. Specifically, data is sent from the terminal to the server using the MQTT or HTTP protocol.

[0274] Step 3: Data analysis and task generation

[0275] The server analyzes the received data and automatically generates tasks to be done. The input data is the text data of the received message, and the output data is the analyzed task information. Specifically, the server uses an NLP module (SpaCy or BERT) to divide the message content into tokens and perform intent analysis. Based on the results of this analysis, it extracts specific tasks and sets task descriptions, deadlines, etc.

[0276] Step 4: Task Importance Rating

[0277] The server evaluates the importance of the generated tasks. The input data is the generated task information, and the output data is the task information with the assigned importance. Specifically, the server evaluates the tasks based on their deadlines and the importance of their contents, and classifies them into high, medium, or low importance.

[0278] Step 5: Set up reminder notifications

[0279] The server sets reminders and alerts based on the set task importance. The input data is task information with the set importance, and the output data is reminder notification setting information. Specifically, the system is configured to determine the timing of the reminder and send a notification to the user's device when the deadline approaches.

[0280] Step 6: Send reminders

[0281] The server sends the configured reminder notification to the user's device. The input data is the reminder notification setting information, and the output data is the sent notification. Specifically, a notification is sent to the user's device in the form of "Tomorrow is the deadline for the task."

[0282] Step 7: Addressing Ambiguous Requests

[0283] When a user sends an ambiguous request from their device, the server searches past data in response to the request and summarizes the relevant information. The input data is the ambiguous request from the user, and the output data is the summarized information. Specifically, the server searches and analyzes past data, extracts and summarizes the most relevant parts, and sends them to the user's device.

[0284] Step 8: Provide summary information

[0285] The terminal receives the summary information sent from the server and displays it to the user. The input data is the summarized information, and the output data is the displayed summary information. In concrete terms, the terminal displays the information received from the server in a format that is easy for the user to see.

[0286] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0287] The present invention relates to a system that analyzes a user's communication data and emotional state to automatically manage tasks. This system is equipped with an emotion engine that recognizes the user's emotions and adjusts task importance and reminder functions based on the user's emotional state.

[0288] A natural language description of the program's operation

[0289] Collection of communication data

[0290] Users communicate via email and chat, and these communications are collected and sent to the system by the user's device.

[0291] Collecting Emotional Data

[0292] The device collects data to recognize the user's emotions, including emotion analysis from text or emotion data obtained from external devices such as biometric sensors.

[0293] Sending data

[0294] The communication data and emotion data collected by the device are sent to a server. The data is encrypted before transmission, ensuring security.

[0295] Data analysis and task generation

[0296] The server analyzes the received data and automatically generates tasks. Using natural language processing technology, the server extracts tasks to be done from the message content. For example, if a message is received saying "Please submit a report by tomorrow," the server generates a task called "Submit report" and sets a deadline. The server also analyzes the user's emotional state using an emotion engine; if the emotional state is "tense," the task is deemed more important.

[0297] Determining and adjusting importance

[0298] The server determines the importance of the generated tasks. The emotion engine analyzes the user's emotional state and adjusts the importance of the tasks accordingly. For example, if the user is under a high level of stress, tasks with high urgency will be given a higher priority.

[0299] Reminders and notifications

[0300] The server prepares reminders and alerts based on the configured importance. The server determines the timing of the reminder and sends a notification to the user's device. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user.

[0301] Dealing with ambiguous requests

[0302] A user sends a vague request from their device. For example, if the request is "I want to check the contents of last week's meeting," the server searches for relevant information from past communication data, summarizes it, and provides it to the user. The server also takes into account emotional data and provides a summary that is designed to keep the user calm.

[0303] Specific examples

[0304] 1. Task Creation Example

[0305] A user receives an email saying, "Please check with client X about next week's meeting."

[0306] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[0307] The server parses the message and generates a task called "Confirm next week's meeting."

[0308] The server evaluates the importance of the task and sets it as "urgent."

[0309] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[0310] 2. Examples of Ambiguous Requests

[0311] The user sends a request from the terminal saying, "I want to check the contents of last week's meeting."

[0312] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[0313] The server searches past communication data and summarizes relevant content.

[0314] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[0315] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[0316] The processing flow will be explained below.

[0317] Step 1:

[0318] Users communicate via email and chat, including everyday business interactions.

[0319] Step 2:

[0320] With the user's permission, the device collects communication data and emotional data. Communication data includes email text and chat messages, while emotional data includes emotions analyzed from text and biometric signals obtained from external sensors.

[0321] Step 3:

[0322] The communication and emotion data collected by the device is sent to a server, where it is encrypted for enhanced security.

[0323] Step 4:

[0324] The server analyzes the received data.

[0325] 1. Using natural language processing technology, communication data is tokenized and sentence structure is analyzed.

[0326] 2. Conduct intent analysis and extract specific tasks and requests.

[0327] Step 5:

[0328] The server uses an emotion engine to analyze the emotion data.

[0329] 1. Apply sentiment understanding algorithms to extract sentiment from text.

[0330] 2. Analyze data from external sensors to assess the user's stress level and emotional state.

[0331] Step 6:

[0332] The server automatically generates tasks based on the extracted task information and emotion data.

[0333] 1. For example, from the message "Please submit the report by tomorrow," generate a task called "Submit report" and set the deadline to "tomorrow."

[0334] 2. Adjust importance based on sentiment data.

[0335] Step 7:

[0336] The server stores task details (task ID, task content, deadline, importance, etc.) in a database, allowing you to track and manage tasks.

[0337] Step 8:

[0338] The server evaluates the importance of the generated task.

[0339] 1. Consider sentiment data when calculating importance scores.

[0340] 2. If you're stressed, prioritize tasks and set more urgent reminders.

[0341] Step 9:

[0342] The server sets reminders and alerts.

[0343] 1. Determine the timing of the reminder and notify the user at the appropriate time.

[0344] 2. For example, prepare a notice that says, "Tomorrow is the deadline for your report. Relax and get ready."

[0345] Step 10:

[0346] The server sends reminder and alert notifications to the user's device.

[0347] Step 11:

[0348] The device displays any reminders or alerts received to the user, allowing them to review important tasks and take appropriate action.

[0349] Step 12:

[0350] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[0351] Step 13:

[0352] The terminal transmits the user's request and associated emotion data to the server.

[0353] Step 14:

[0354] The server analyzes the ambiguous request and searches for the necessary information from related past communication data.

[0355] 1. Search historical data and extract relevant emails and chats.

[0356] 2. Summarize the extracted information and present it in a user-friendly format.

[0357] Step 15:

[0358] The server takes emotion data into account and generates summary information that takes the user's feelings into consideration. For example, if the user is feeling anxious, the server may add a message saying, "Here are the important points. Please stay calm and check."

[0359] Step 16:

[0360] The server transmits the generated summary information to the user's terminal.

[0361] Step 17:

[0362] The terminal displays the summary information to the user, allowing the user to quickly obtain the necessary information and take appropriate action.

[0363] Example 2

[0364] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0365] In today's business environment, users are often faced with numerous tasks and the associated stress. In particular, there is a need for not only appropriate task management based on communication data, but also task prioritization that takes into account the user's emotional state. However, conventional task management systems are unable to reflect the user's emotional data, resulting in inefficient task management.

[0366] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user communication data, means for automatically generating tasks by analyzing the collected data, means for determining and notifying the importance of the generated tasks, means for collecting user emotion data, means for adjusting the importance of the tasks based on the emotion data, and means for searching for and providing necessary information from past interactions. This enables efficient task management that takes the user's emotional state into consideration.

[0367] "User" means an individual or corporation that uses the system.

[0368] "Communication data" is data generated when a user exchanges information with others, such as through email or chat.

[0369] "Collection means" refers to the functions and devices that the system uses to acquire user communication data and emotional data.

[0370] "Analysis tools" are algorithms and models used to analyze collected data and understand meaning and sentiment.

[0371] A "task" refers to a task or activity that a user must perform.

[0372] The "task generation means" is a function that creates a new task from the analyzed data.

[0373] "Importance" is a criterion for evaluating the urgency and priority of a task.

[0374] The "notification means" refers to a function or protocol for transmitting information about the generated task to the user.

[0375] "Emotional data" refers to information that describes a user's emotional state, and includes data obtained from text analysis and biometric sensors.

[0376] The "importance adjustment means" is a function for changing the importance of a task based on collected emotion data.

[0377] "Search means" is a function for finding necessary information from past communication data and providing it to the user.

[0378] The present invention relates to a system that analyzes a user's communication data and emotional data to automatically manage tasks. This system recognizes the user's emotional state and can adjust task importance and reminder functions based on that information. A specific embodiment of the present invention will be described below.

[0379] Collection of communication data

[0380] Users communicate via email or chat. For example, they exchange information using applications such as Gmail or Slack. These interactions are recorded on the user's device (PC, smartphone, etc.) and sent to the system, where they are collected. The device automatically captures this data.

[0381] Collecting Emotional Data

[0382] The device collects the user's emotional state. To do this, it uses natural language processing technology (e.g., OpenAI's GPT-3) to perform text-based sentiment analysis. In addition, if the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data will also be collected.

[0383] Sending data

[0384] The communication data and emotion data collected by the device are sent to a server, where the data is encrypted using the Transport Layer Security (TLS) protocol to ensure security.

[0385] Data analysis and task generation

[0386] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ, and uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, a "Submit report" task will be generated. An emotion engine (e.g., an emotion analysis model using TensorFlow) analyzes the user's emotional state, and if the emotion is evaluated as "tense," the importance of the task will be increased.

[0387] Determining and adjusting importance

[0388] The server determines the importance of each task. It adjusts the importance of each task based on the user's emotional state, as determined by the emotion engine. For example, if the user's stress level is high, it sets a higher priority to tasks that are more urgent.

[0389] Reminders and notifications

[0390] The server prepares reminders and alerts based on the configured severity level and sends them to the user's device. For example, it uses AWS SES or Google Firebase Cloud Messaging to send emails or push notifications. The user receives a notification that "Tomorrow is the deadline for submitting a report."

[0391] Dealing with ambiguous requests

[0392] A user sends a vague request from their device to the server. For example, if the request is "I want to check the contents of last week's meeting," the server searches past communication data, summarizes the relevant information, and provides it to the user. In this case, too, it is possible to provide a summary that takes into account emotional data so that the user can check it in a calm state.

[0393] Specific examples

[0394] 1. Task Creation Example

[0395] A user receives an email saying, "Please check with your client about next week's meeting."

[0396] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[0397] The server analyzes the message and generates a task called "Confirm Meeting."

[0398] The server evaluates the importance of the task and sets it as "urgent."

[0399] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[0400] 2. Examples of Ambiguous Requests

[0401] The user sends a request from the terminal saying, "I want to check the contents of last week's meeting."

[0402] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[0403] The server searches past communication data and summarizes relevant content.

[0404] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[0405] Prompt Sentence Examples

[0406] "Create a task based on this email and rate its importance."

[0407] Please give me a summary of last week's meeting.

[0408] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[0409] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0410] Step 1:

[0411] When a user communicates via email or chat, the resulting communication data is recorded on the device. Communication data includes text messages, subjects, sender and recipient information. For example, when a user sends an email using Gmail, the content of the email and related information are stored on the device. The input is the communication data sent and received by the user. The output is the communication data stored on the device.

[0412] Step 2:

[0413] The device collects the user's emotional data. It uses natural language processing technology (e.g., OpenAI's GPT-3) to perform sentiment analysis from text. If the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data is also collected. The input is communication data and sensor data. The output is data reflecting the emotional state. For example, an emotional state label such as "high pressure" or "relaxed" is assigned.

[0414] Step 3:

[0415] The communication data and emotion data collected by the device are sent to the server. At this time, the data is encrypted using the TLS (Transport Layer Security) protocol, ensuring security. The input is the encrypted communication data and emotion data. The output is the encrypted data sent to the server.

[0416] Step 4:

[0417] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ. It uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, the task "Submit the report" is generated. The input is the encrypted data sent to the server. The output is the task information analyzed on the server.

[0418] Step 5:

[0419] The server evaluates the importance of the task. Based on the collected emotional data, an emotion analysis model using TensorFlow evaluates the user's emotional state and determines the priority of the task. The input is the analyzed task information and emotional data. The output is the task information with the assigned priority. For example, if the stress level is high, the task is set as "high priority."

[0420] Step 6:

[0421] The server prepares reminders and alerts and sends them to the user's device. It determines the timing of the reminder based on the set priority and sends the notification using AWS SES or Google Firebase Cloud Messaging. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent. The input is high-priority task information. The output is a reminder notification.

[0422] Step 7:

[0423] A user sends a vague request from their device to the server. For example, a request might be, "I want to check the contents of last week's meeting." The server searches past communication data, summarizes the relevant information, and provides it to the user. It is possible to provide a summary that takes into account emotional data and helps the user feel at ease. The input is the user's request and past communication data. The output is summarized information. For example, summary information such as, "At last week's meeting, plans for launching a new product were discussed" is provided.

[0424] This allows users to efficiently manage tasks according to the context, allowing work to proceed smoothly.

[0425] (Application example 2)

[0426] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0427] To improve work efficiency and safety in factories, there is a need for a task management system that takes into account the emotional state of workers. However, current systems do not adequately adjust task priorities or suggest appropriate breaks that reflect the emotional state of workers, resulting in reduced work efficiency and a worsening working environment. Furthermore, there is a lack of ways to respond to ambiguous requests, which can increase worker stress and reduce the quality of work. Furthermore, there is a need for a method to centrally manage the wide variety of data collected by robots and respond appropriately in real time.

[0428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0429] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and emotion data to automatically generate tasks, and means for determining the importance of the generated tasks and adjusting them based on the emotion data, thereby enabling improved work efficiency, stress reduction, and safety.

[0430] "User" refers to an individual or worker who uses this system.

[0431] "Communication data" refers to data including voice, text, and other information sent and received by users.

[0432] "Emotion data" refers to data including biometric information, facial data, etc. that indicates the user's emotional state.

[0433] A "task" refers to a job that includes work or instructions to be performed by a user.

[0434] A "robot" is an automatic machine that operates in a factory and receives and carries out instructions from the user.

[0435] "Server" refers to a central processing unit that analyzes data and notifies the user or robot of the results.

[0436] A "remind" refers to a notification that reminds the user of the existence of a particular task.

[0437] An "alert" refers to an urgent notification or warning given to the user.

[0438] "Priority adjustment" refers to changing the order in which tasks are executed or their importance based on emotional data, etc.

[0439] An "ambiguous request" is a request that is not specific but includes information or instructions the user is looking for.

[0440] "Summary information" refers to information extracted from past data and summarized concisely.

[0441] The present invention relates to a system for managing tasks by analyzing communication data and emotional data in order to improve work efficiency and reduce worker stress in factories. This system collects communication data and emotional data from users (workers), and a server analyzes this data to automatically generate and manage tasks. Specific embodiments are described below.

[0442] System configuration

[0443] 1. Collection of communication data

[0444] Users send and receive instructions and messages via voice and text through factory robots, and an application installed on the robot collects this data and sends it to a server.

[0445] 2. Collecting Emotional Data

[0446] The robot is equipped with biometric sensors and a facial recognition camera that collects real-time emotional data from the user, which is then sent to a server using secure communication methods.

[0447] Hardware and software used

[0448] Hardware

[0449] Factory robot: Collects communication data and executes work instructions.

[0450] Biometric sensors: Measure the user's heart rate and skin temperature and collect emotional data.

[0451] Facial recognition camera: Performs facial expression analysis and analyzes emotional data.

[0452] software

[0453] Natural language processing engine (NLP): Analyzes communication data and extracts tasks from the content of messages.

[0454] Sentiment Analysis Engine: Analyzes emotional data and determines the user's emotional state.

[0455] Data processing and calculation

[0456] Data collection

[0457] The communication and emotion data collected by the robot and sensors is sent to a server, where it is integrated and a dataset is generated for analysis.

[0458] Data analysis

[0459] The server uses a natural language processing engine to extract tasks from the received message. For example, if the message received is "Please start packing the next product," a task called "Pack the product" is generated.

[0460] The emotion analysis engine analyzes the user's emotional state and determines whether the user is feeling stressed based on emotional data (e.g., elevated heart rate and facial expression data obtained through facial recognition).

[0461] Task creation and priority adjustment

[0462] Task importance determination

[0463] The server determines the importance of the generated tasks and adjusts the importance based on the emotional data. For example, if the user is under stress, it will set urgent tasks as high priority and postpone less urgent tasks.

[0464] Reminders and notifications

[0465] The server sends reminders and alerts to the user's device and robot at appropriate times based on task priority, such as notifications to "start the next task" or reminders to "take a break."

[0466] Dealing with ambiguous requests

[0467] Ambiguous Request Analysis

[0468] The server analyzes a user's vague request (e.g., "I want to check the details of last week's meetings") and searches for relevant past communication data. It then generates summary information and provides it to the user, allowing the user to quickly obtain the information they need.

[0469] Specific examples

[0470] 1. Generate work instructions

[0471] A factory robot receives a voice command: "Start packing the next product."

[0472] The robot sends this instruction data and emotional data indicating that the worker is feeling stressed to a central server.

[0473] The server analyzes the data and generates a task called "Start packing the next product."

[0474] The server sets the task's importance as "high."

[0475] The server sends a notification to the worker saying, "Your stress is increasing, so please take a break before starting work."

[0476] 2. Ambiguous requests

[0477] A worker tells the robot a request: "I'd like to review the contents of last week's meeting."

[0478] The robot sends the request and emotional data indicating that the worker is feeling impatient to the server.

[0479] The server searches past communication data and summarizes relevant content.

[0480] The server sends the summary information to the worker along with a message urging them to "please take your time to check, as we are feeling impatient."

[0481] Prompt Sentence Examples

[0482] "Generate work tasks and adjust priorities based on the following work instruction data and emotion data."

[0483] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0484] Step 1:

[0485] Users send instructions and messages via voice or text to factory robots, and these communications data are collected by the robots, sometimes using software that converts voice input into text.

[0486] Input: User voice commands and text messages

[0487] Data processing: converting voice data to text, collecting text data

[0488] Output: Communication data

[0489] Step 2:

[0490] The robot collects user emotional data using biometric sensors and a facial recognition camera, which record heart rate, skin temperature, and facial expression data.

[0491] Input: User's biometric information (heart rate, skin temperature, facial expression, etc.)

[0492] Data processing: collection of biometric information, conversion of data from sensors

[0493] Output: Emotion data

[0494] Step 3:

[0495] The communication and emotion data collected by the robot is sent to a server using a secure communication protocol, and the data is encrypted.

[0496] Input: communication data, emotion data

[0497] Data processing: Data encryption

[0498] Output: Encrypted data (for sending to server)

[0499] Step 4:

[0500] The server uses a natural language processing engine to analyze the communication data it receives and automatically generate tasks. Tasks to be done are extracted from the message content.

[0501] Input: Encrypted data

[0502] Data processing: Decoding data and analyzing it with a natural language processing engine

[0503] Output: The generated tasks

[0504] Step 5:

[0505] The server uses an emotion analysis engine to analyze the collected emotional data, thereby determining the user's emotional state and recognizing conditions such as tension or stress.

[0506] Input: Emotion data

[0507] Data processing: Analysis using a sentiment analysis engine

[0508] Output: User's emotional state

[0509] Step 6:

[0510] The server determines the importance of the generated tasks and adjusts the importance based on emotional data. For example, if the user is under stress, tasks with high urgency are assigned a higher priority.

[0511] Input: Generated task, user's emotional state

[0512] Data processing: Task priority determination and adjustment

[0513] Output: Adjusted task priorities

[0514] Step 7:

[0515] The server sends reminders and alerts to users and robots at appropriate times based on task priority. The server creates notification content so that users can understand it quickly.

[0516] Input: Adjusted task priority

[0517] Data Processing: Creating reminders and alerts

[0518] Output: Reminder and alert notifications

[0519] Step 8:

[0520] The server receives a user's vague request, searches past communication data, and generates summary information, thereby quickly providing the information the user needs.

[0521] Input: Ambiguous request

[0522] Data processing: Searching past data and generating summary information

[0523] Output: Summary information

[0524] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0525] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0526] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0527] [Second embodiment]

[0528] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0529] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0530] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0531] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0532] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0533] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0534] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0535] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0536] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0537] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0538] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0539] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0540] The present invention relates to a system for automatically generating and managing tasks from user communication data. The following describes in detail how to implement the program for this system.

[0541] A natural language description of the program's operation

[0542] Collection of communication data

[0543] When users communicate via email or chat, their devices obtain permission to send these communications to the system. The devices are configured to periodically send collected data to the server, ensuring that the latest communication data is always available to the system.

[0544] Data analysis and task generation

[0545] The server analyzes the received data and automatically generates tasks to be done. Using natural language processing technology, the server divides the message content into tokens and extracts specific tasks by analyzing the intent. For example, if a user receives a message saying "Please submit a report by tomorrow," the server analyzes the message, generates a task called "Submit report," and sets the deadline to "tomorrow."

[0546] Determining the importance

[0547] The server evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task content. Depending on the evaluation result, the server classifies the task as high, medium, or low importance.

[0548] Reminders and notifications

[0549] The server sets reminders for tasks with high importance. The reminder settings are configured to send notifications to the user before the task deadline approaches. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user's device.

[0550] Dealing with ambiguous requests

[0551] When a user sends a vague request from their device, for example, "I want to check the details of last week's meeting," the server searches past communication data, summarizes the relevant content, and provides it to the user. This function allows users to quickly obtain the information they need.

[0552] Specific examples

[0553] 1. Task Creation Example

[0554] User: Receives an email saying "Please check with client X about meeting next week."

[0555] Terminal: Send the data of this email to the server.

[0556] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[0557] Server: Set the due date of the generated task to "Next week".

[0558] Server: Rate the importance of the task and set it as high importance.

[0559] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[0560] 2. Examples of Ambiguous Requests

[0561] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[0562] Terminal: Sends the request to the server.

[0563] Server: Searches past communication data and summarizes relevant messages.

[0564] Server: Sends the summarized information to the user's terminal.

[0565] Terminal: Displays the received summary information to the user.

[0566] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[0567] The processing flow will be explained below.

[0568] Step 1:

[0569] Users communicate via email and chat. Users send and receive messages as part of their normal business processes.

[0570] Step 2:

[0571] With user permission, the device collects email and chat data, including information such as message body, sender, recipient, and timestamp.

[0572] Step 3:

[0573] The device periodically sends the collected data to a server, where the data is encrypted and securely transmitted.

[0574] Step 4:

[0575] The server analyzes the received data, and an AI model breaks the message down into tokens and uses natural language processing techniques to understand the content of the message.

[0576] Step 5:

[0577] The server automatically generates tasks based on the analysis results. For example, a message such as "Please submit a report by tomorrow" generates a task called "Submit a report."

[0578] Step 6:

[0579] The server saves the details of the created task (task ID, task content, deadline, importance, etc.) in a database.

[0580] Step 7:

[0581] The server determines the importance of the task, analyzes the deadline and content of the task, and calculates the importance score.

[0582] Step 8:

[0583] The server sets reminders and alerts based on the importance of the task, and for high-priority tasks, it determines the frequency and timing of reminder notifications.

[0584] Step 9:

[0585] The server sends reminders and alerts to the user's device, for example, a notification that "Tomorrow is the deadline for submitting a report."

[0586] Step 10:

[0587] The device will display reminders and alerts to the user, allowing them to review important tasks and take appropriate action.

[0588] Step 11:

[0589] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[0590] Step 12:

[0591] The terminal sends the user's request to the server.

[0592] Step 13:

[0593] The server searches past communication data, extracts relevant information, generates summary information, and prepares it for presentation to the user.

[0594] Step 14:

[0595] The server transmits the generated summary information to the user's terminal.

[0596] Step 15:

[0597] The terminal displays the summary information to the user, allowing the user to quickly obtain the information they need.

[0598] Example 1

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

[0600] In today's business environment, many tasks and communications are performed daily, requiring efficient management and tracking. However, many users face challenges such as overlooking important tasks and difficulty responding appropriately to ambiguous requests. This can lead to poor task management efficiency and a decline in the quality of business communications. The present invention aims to solve these challenges by providing a system that enables users to effectively manage tasks and quickly respond to ambiguous requests.

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

[0602] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data to automatically generate tasks, means for evaluating the importance of the generated tasks, means for sending a notification to the user's terminal before the task deadline approaches, and means for analyzing the user's ambiguous requests and providing summary information from related past data, thereby preventing the user from overlooking tasks, enabling effective management of important tasks, and prompt response to ambiguous requests.

[0603] "Communication data" refers to data that includes the content of communications that users make electronically, such as by email or chat.

[0604] The "means of collection" is a mechanism for transferring communication data from the user's terminal to a server at regular intervals.

[0605] "Means of analyzing and automatically generating tasks" refers to the process of analyzing communication data using natural language processing technology, extracting specific actions and tasks from it, and automatically generating them.

[0606] The "means for evaluating the importance of a task" is a method for evaluating and ranking the importance of a generated task based on the deadline and urgency of the task's content.

[0607] "Means for sending notifications" refers to the technical means by which reminders and alerts are sent to the user's device when an important task is approaching its deadline.

[0608] "Means for analyzing ambiguous requests and providing summary information from related past data" refers to a method of analyzing ambiguous requests from users using natural language processing technology, searching past communication data to extract relevant information, and providing it in a summarized form.

[0609] "Preventing tasks from being overlooked" means that the system automatically generates tasks and sends reminders based on their importance, preventing users from forgetting important tasks.

[0610] "Effectively managing important tasks" means improving the efficiency of task management by evaluating the priority of tasks generated by the system and notifying the user at the appropriate time.

[0611] "Quick response to ambiguous requests" means enabling users to quickly obtain the information they need by quickly providing relevant information in response to ambiguous instructions or questions.

[0612] This invention relates to a system for automatically generating and managing tasks from user communication data. This system has the function of collecting and analyzing user communication data and sending reminders and notifications based on importance. It can also provide necessary information from related past data in response to vague user requests.

[0613] Hardware and Software

[0614] This system uses the following hardware and software:

[0615] Hardware: Servers, users' PCs and smartphones

[0616] Software: Natural language processing tools (e.g., Google Cloud Natural Language API), reminder and notification systems (e.g., Firebase Cloud Messaging)

[0617] Program processing

[0618] 1. Collection of communication data

[0619] Users: Allow the system to collect data when communicating with them via email or chat.

[0620] Terminal: Periodically transmits authorized communication data to the server.

[0621] 2. Data analysis and task generation

[0622] Server: Analyzes the received communication data using natural language processing technology and extracts specific tasks.

[0623] Server: For example, if a message "Please submit a report by tomorrow" is received, a task called "Submit report" is generated and its deadline is set to "tomorrow."

[0624] 3. Determining the importance

[0625] Server: Evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task.

[0626] 4. Reminders and Notifications

[0627] Server: Sends reminders to users about high-priority tasks before their deadlines approach.

[0628] Device: For example, display a notification saying "Tomorrow is the deadline for submitting your report."

[0629] 5. Dealing with Ambiguous Requests

[0630] User: Sends vague requests to the system (e.g., "I want to see what happened in last week's meetings").

[0631] Server: Searches past communication data, summarizes relevant content, and provides it to the user.

[0632] Specific examples

[0633] 1. Task Creation Example

[0634] User: Receives an email saying "Please check with client X about meeting next week."

[0635] Terminal: Send the data of this email to the server.

[0636] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[0637] Server: Set the due date of the generated task to "Next week".

[0638] Server: Rate the importance of the task and set it as high importance.

[0639] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[0640] 2. Examples of Ambiguous Requests

[0641] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[0642] Terminal: Sends the request to the server.

[0643] Server: Searches past communication data and summarizes relevant messages.

[0644] Server: Sends the summarized information to the user's terminal.

[0645] Terminal: Displays the received summary information to the user.

[0646] Prompt Sentence Examples

[0647] "Please explain a system that automatically generates tasks to be done for the next seven days of work and sets reminders based on their importance. Please provide a specific example that includes a process that collects and analyzes user communication data to generate tasks, evaluates their importance, and sends reminders."

[0648] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[0649] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0650] System program processing flow

[0651] Step 1:

[0652] Obtaining permission

[0653] User: The system obtains permission from the user to collect communication data.

[0654] Specific operation: The user selects permission for data collection in the system settings screen.

[0655] Input: A setting change request from the user.

[0656] Output: The data collection permission flag is enabled.

[0657] Step 2:

[0658] Data collection

[0659] Device: Every time a user communicates via email or chat, the communication data is temporarily stored on the device.

[0660] Specific operation: The device stores communication data in local storage and updates it whenever the data is collected.

[0661] Input: Communication data sent and received by users.

[0662] Output: The latest communication data is saved in local storage.

[0663] Step 3:

[0664] Sending data

[0665] Terminal: Sends collected data to the server at regular intervals.

[0666] Specific operation: The terminal executes a batch job every night and sends the collected data to the server.

[0667] Input: Communication data stored in local storage.

[0668] Output: Communication data sent to the server.

[0669] Step 4:

[0670] Receiving data

[0671] Server: Receives communication data sent from the device and stores it in a database.

[0672] Specific operation: The server saves the communication data as a new record in the database.

[0673] Input: Communication data sent from the terminal.

[0674] Output: Communication data stored in a database.

[0675] Step 5:

[0676] Message Parsing

[0677] Server: Uses natural language processing (NLP) techniques to parse the message content and break it down into tokens.

[0678] What happens: The server uses the Google Cloud Natural Language API to split the text into tokens.

[0679] Input: Communication data stored in a database.

[0680] Output: Message data split into tokens.

[0681] Step 6:

[0682] Extracting tasks

[0683] Server: Extracts specific tasks from the analysis results.

[0684] Specific operation: Extract action words such as "submit" and "confirm" and register them as tasks.

[0685] Input: Message data split into tokens.

[0686] Output: Actions extracted as tasks with their details.

[0687] Step 7:

[0688] Task registration

[0689] Server: Register the extracted task as a new task in the database.

[0690] What it does: Adds a record to the database, including the task title, due date, importance, etc.

[0691] Input: Actions extracted as tasks and their details.

[0692] Output: The newly added task record in the database.

[0693] Step 8:

[0694] Initial assessment of task importance

[0695] Server: Initially assesses the importance of the task based on its deadline and content.

[0696] Specific behavior: The shorter the deadline, the higher the importance.

[0697] Input: Task description and deadline.

[0698] Output: Initially assessed task importance.

[0699] Step 9:

[0700] Finalize the importance

[0701] Server: Determines the final priority based on the user's past behavior and task management patterns.

[0702] Specific operation: Automatically classifies the importance of tasks into "high," "medium," or "low" based on the user's past task completion status.

[0703] Input: Initially assessed task importance and user performance data.

[0704] Output: The finalized task importance.

[0705] Step 10:

[0706] Reminder Settings

[0707] Server: Set reminders for high-priority tasks.

[0708] What it does: Adds a new record to the database with the reminder date and time.

[0709] Input: The finalized task importance.

[0710] Output: The reminder settings added to the database.

[0711] Step 11:

[0712] Sending notifications

[0713] Server: Sends a notification to the user's device at the scheduled date and time.

[0714] What it does: Sends a notification using Firebase Cloud Messaging and displays a message with details about the task.

[0715] Input: Reminder settings stored in the database.

[0716] Output: Notification sent to the user's device.

[0717] Step 12:

[0718] Receiving an ambiguous request

[0719] Server: Receives and analyzes ambiguous requests from users.

[0720] Specific behavior: Analyzes the request message using natural language processing to identify intent.

[0721] Input: An ambiguous request sent by the user.

[0722] Output: The parsed request content.

[0723] Step 13:

[0724] Data Search

[0725] Server: Searches past communication data and extracts relevant information.

[0726] What it does: It applies filtering criteria to the database to extract relevant messages.

[0727] Input: The parsed request content.

[0728] Output: Extracted relevant messages.

[0729] Step 14:

[0730] Creating a summary

[0731] Server: Summarizes the extracted information and presents it to the user.

[0732] What it does: Uses a summarization algorithm to extract key points.

[0733] Input: The extracted relevant message.

[0734] Output: Summarized information.

[0735] Step 15:

[0736] Sending a Summary

[0737] Server: Sends the summarized information to the user's terminal.

[0738] Specific behavior: Summary text is sent to the user's device and displayed via notification or email.

[0739] Input: Summarized information.

[0740] Output: Summary information sent to the user's device.

[0741] (Application example 1)

[0742] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0743] The present invention aims to improve productivity and efficiency by providing a means for automatically generating and managing important tasks from a large amount of constantly updated communication data, thereby issuing appropriate instructions to automated equipment and robots used in factories. Furthermore, it aims to support the execution of work by providing relevant information quickly and accurately even when a user makes an ambiguous request.

[0744] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0745] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and automatically generating tasks, means for determining the importance of the generated tasks and notifying the user, means for retrieving and providing necessary information from past communications, and means for issuing instructions to automated equipment used in the factory. This allows users to efficiently manage tasks arising from daily communications, and in particular, enables productivity and work efficiency to be improved while appropriately issuing instructions to automated equipment in the factory.

[0746] "User communication data" refers to information generated through the means of communication that users use on a daily basis, such as email, chat messages, and voice communications.

[0747] A "task" is a specific task or activity that a user must perform, and is automatically generated and managed by the system.

[0748] "Analysis" is the process of breaking down collected data and extracting specific patterns or information.

[0749] "Importance" is an evaluation criterion that indicates the priority of a generated task, and is determined based on the urgency and importance of the task.

[0750] "Notifications" are messages that inform users about task progress and deadlines.

[0751] "Search" is the operation of finding information that matches specific conditions from a database or stored information.

[0752] "Providing" refers to presenting the searched information to the user in an easy-to-view format.

[0753] "Automated equipment used in factories" refers to robots and mechanical devices used on production lines and in workshops.

[0754] "Instruction" is the act of ordering or requesting someone to perform a specific task or work.

[0755] A "system" is an information processing device or a collection of software in which multiple components operate in cooperation with each other.

[0756] The present invention is a system for collecting user communication data and automatically generating and managing tasks. In particular, it is possible to efficiently issue instructions to automated equipment used in factories. Specific embodiments of the present invention will be described below.

[0757] First, the system configuration will be explained. The system includes the following elements:

[0758] 1. User device: A digital device used by a user, such as a smartphone, smart glasses, or computer.

[0759] 2. Server: A computer system that analyzes data, generates tasks, and manages tasks.

[0760] 3. Natural Language Processing (NLP) module: Software for analyzing user communication data using NLP techniques such as SpaCy and BERT.

[0761] 4. Communication protocol: A protocol that uses MQTT or HTTP to communicate data between the user device and the server.

[0762] The user terminal sends communication data via email and chat to the server. With the user's permission, the collected data is periodically sent to the server. This collection process ensures that the system always has the latest communication data available.

[0763] The server analyzes the received data and automatically generates tasks to be done. The server uses an NLP module to divide the message content into tokens, analyze the intent, and extract specific tasks. For example, if a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend," the server analyzes this message, generates a task called "Maintain Machine X," and sets its deadline to "weekend."

[0764] The generated tasks are evaluated for importance using an importance evaluation module. This evaluation is based on the proximity of the task's deadline and the importance of the content. Depending on the task's importance, the server sets a reminder notification and sends it to the user's device when the deadline approaches.

[0765] In addition, if a user sends a vague request such as "I want to check last week's maintenance records," the server searches past communication data, summarizes the relevant information, and provides it to the user. This function allows users to quickly obtain the information they need.

[0766] For example, a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend." This message is sent from the user's device to the server, which analyzes it and generates a "Maintain Machine X" task with a deadline of the weekend. This task is evaluated as being of medium importance, and a reminder is sent the day before the weekend.

[0767] Furthermore, when a user requests, "I want to check last week's maintenance records," the server searches past data, summarizes the relevant records, and provides them to the user. In this way, users can efficiently manage tasks and issue appropriate instructions to automated equipment in the factory.

[0768] Example prompt sentence:

[0769] User message: "Tell Robot A to perform maintenance on Machine X over the weekend"

[0770] Process: Maintenance task generation and deadline setting

[0771]

[0772] User Request: "I want to check last week's maintenance records."

[0773] Process: Searching for and summarizing historical data

[0774] This invention enables users to efficiently manage tasks arising from daily communication, and in particular to give appropriate instructions to automated equipment in factories, thereby improving productivity and business efficiency.

[0775] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0776] Step 1: Collect communication data

[0777] When a user sends a message via email or chat, the device collects this communication data. The input data is the user's message, and the output data is the text data of the collected message. Specifically, the device is configured to capture the message and send it to a server at regular intervals.

[0778] Step 2: Sending data to the server

[0779] The terminal sends the collected text data to the server. The input data is the collected message text data, and the output data is the message data stored on the server. Specifically, data is sent from the terminal to the server using the MQTT or HTTP protocol.

[0780] Step 3: Data analysis and task generation

[0781] The server analyzes the received data and automatically generates tasks to be done. The input data is the text data of the received message, and the output data is the analyzed task information. Specifically, the server uses an NLP module (SpaCy or BERT) to divide the message content into tokens and perform intent analysis. Based on the results of this analysis, it extracts specific tasks and sets task descriptions, deadlines, etc.

[0782] Step 4: Task Importance Rating

[0783] The server evaluates the importance of the generated tasks. The input data is the generated task information, and the output data is the task information with the assigned importance. Specifically, the server evaluates the tasks based on their deadlines and the importance of their contents, and classifies them into high, medium, or low importance.

[0784] Step 5: Set up reminder notifications

[0785] The server sets reminders and alerts based on the set task importance. The input data is task information with the set importance, and the output data is reminder notification setting information. Specifically, the system is configured to determine the timing of the reminder and send a notification to the user's device when the deadline approaches.

[0786] Step 6: Send reminders

[0787] The server sends the configured reminder notification to the user's device. The input data is the reminder notification setting information, and the output data is the sent notification. Specifically, a notification is sent to the user's device in the form of "Tomorrow is the deadline for the task."

[0788] Step 7: Addressing Ambiguous Requests

[0789] When a user sends an ambiguous request from their device, the server searches past data in response to the request and summarizes the relevant information. The input data is the ambiguous request from the user, and the output data is the summarized information. Specifically, the server searches and analyzes past data, extracts and summarizes the most relevant parts, and sends them to the user's device.

[0790] Step 8: Provide summary information

[0791] The terminal receives the summary information sent from the server and displays it to the user. The input data is the summarized information, and the output data is the displayed summary information. In concrete terms, the terminal displays the information received from the server in a format that is easy for the user to see.

[0792] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0793] The present invention relates to a system that analyzes a user's communication data and emotional state to automatically manage tasks. This system is equipped with an emotion engine that recognizes the user's emotions and adjusts task importance and reminder functions based on the user's emotional state.

[0794] A natural language description of the program's operation

[0795] Collection of communication data

[0796] Users communicate via email and chat, and these communications are collected and sent to the system by the user's device.

[0797] Collecting Emotional Data

[0798] The device collects data to recognize the user's emotions, including emotion analysis from text or emotion data obtained from external devices such as biometric sensors.

[0799] Sending data

[0800] The communication data and emotion data collected by the device are sent to a server. The data is encrypted before transmission, ensuring security.

[0801] Data analysis and task generation

[0802] The server analyzes the received data and automatically generates tasks. Using natural language processing technology, the server extracts tasks to be done from the message content. For example, if a message is received saying "Please submit a report by tomorrow," the server generates a task called "Submit report" and sets a deadline. The server also analyzes the user's emotional state using an emotion engine; if the emotional state is "tense," the task is deemed more important.

[0803] Determining and adjusting importance

[0804] The server determines the importance of the generated tasks. The emotion engine analyzes the user's emotional state and adjusts the importance of the tasks accordingly. For example, if the user is under a high level of stress, tasks with high urgency will be given a higher priority.

[0805] Reminders and notifications

[0806] The server prepares reminders and alerts based on the configured importance. The server determines the timing of the reminder and sends a notification to the user's device. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user.

[0807] Dealing with ambiguous requests

[0808] A user sends a vague request from their device. For example, if the request is "I want to check the contents of last week's meeting," the server searches for relevant information from past communication data, summarizes it, and provides it to the user. The server also takes into account emotional data and provides a summary that is designed to keep the user calm.

[0809] Specific examples

[0810] 1. Task Creation Example

[0811] A user receives an email saying, "Please check with client X about next week's meeting."

[0812] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[0813] The server parses the message and generates a task called "Confirm next week's meeting."

[0814] The server evaluates the importance of the task and sets it as "urgent."

[0815] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[0816] 2. Examples of Ambiguous Requests

[0817] The user sends a request from the terminal saying, "I want to check the contents of last week's meeting."

[0818] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[0819] The server searches past communication data and summarizes relevant content.

[0820] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[0821] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[0822] The processing flow will be explained below.

[0823] Step 1:

[0824] Users communicate via email and chat, including everyday business interactions.

[0825] Step 2:

[0826] With the user's permission, the device collects communication data and emotional data. Communication data includes email text and chat messages, while emotional data includes emotions analyzed from text and biometric signals obtained from external sensors.

[0827] Step 3:

[0828] The communication and emotion data collected by the device is sent to a server, where it is encrypted for enhanced security.

[0829] Step 4:

[0830] The server analyzes the received data.

[0831] 1. Using natural language processing technology, communication data is tokenized and sentence structure is analyzed.

[0832] 2. Conduct intent analysis and extract specific tasks and requests.

[0833] Step 5:

[0834] The server uses an emotion engine to analyze the emotion data.

[0835] 1. Apply sentiment understanding algorithms to extract sentiment from text.

[0836] 2. Analyze data from external sensors to assess the user's stress level and emotional state.

[0837] Step 6:

[0838] The server automatically generates tasks based on the extracted task information and emotion data.

[0839] 1. For example, from the message "Please submit the report by tomorrow," generate a task called "Submit report" and set the deadline to "tomorrow."

[0840] 2. Adjust importance based on sentiment data.

[0841] Step 7:

[0842] The server stores task details (task ID, task content, deadline, importance, etc.) in a database, allowing you to track and manage tasks.

[0843] Step 8:

[0844] The server evaluates the importance of the generated task.

[0845] 1. Consider sentiment data when calculating importance scores.

[0846] 2. If you're stressed, prioritize tasks and set more urgent reminders.

[0847] Step 9:

[0848] The server sets reminders and alerts.

[0849] 1. Determine the timing of the reminder and notify the user at the appropriate time.

[0850] 2. For example, prepare a notice that says, "Tomorrow is the deadline for your report. Relax and get ready."

[0851] Step 10:

[0852] The server sends reminder and alert notifications to the user's device.

[0853] Step 11:

[0854] The device displays any reminders or alerts received to the user, allowing them to review important tasks and take appropriate action.

[0855] Step 12:

[0856] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[0857] Step 13:

[0858] The terminal transmits the user's request and associated emotion data to the server.

[0859] Step 14:

[0860] The server analyzes the ambiguous request and searches for the necessary information from related past communication data.

[0861] 1. Search historical data and extract relevant emails and chats.

[0862] 2. Summarize the extracted information and present it in a user-friendly format.

[0863] Step 15:

[0864] The server takes emotion data into account and generates summary information that takes the user's feelings into consideration. For example, if the user is feeling anxious, the server may add a message saying, "Here are the important points. Please stay calm and check."

[0865] Step 16:

[0866] The server transmits the generated summary information to the user's terminal.

[0867] Step 17:

[0868] The terminal displays the summary information to the user, allowing the user to quickly obtain the necessary information and take appropriate action.

[0869] Example 2

[0870] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0871] In today's business environment, users are often faced with numerous tasks and the associated stress. In particular, there is a need for not only appropriate task management based on communication data, but also task prioritization that takes into account the user's emotional state. However, conventional task management systems are unable to reflect the user's emotional data, resulting in inefficient task management.

[0872] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user communication data, means for automatically generating tasks by analyzing the collected data, means for determining and notifying the importance of the generated tasks, means for collecting user emotion data, means for adjusting the importance of the tasks based on the emotion data, and means for searching for and providing necessary information from past interactions. This enables efficient task management that takes the user's emotional state into consideration.

[0873] "User" means an individual or corporation that uses the system.

[0874] "Communication data" is data generated when a user exchanges information with others, such as through email or chat.

[0875] "Collection means" refers to the functions and devices that the system uses to acquire user communication data and emotional data.

[0876] "Analysis tools" are algorithms and models used to analyze collected data and understand meaning and sentiment.

[0877] A "task" refers to a task or activity that a user must perform.

[0878] The "task generation means" is a function that creates a new task from the analyzed data.

[0879] "Importance" is a criterion for evaluating the urgency and priority of a task.

[0880] The "notification means" refers to a function or protocol for transmitting information about the generated task to the user.

[0881] "Emotional data" refers to information that describes a user's emotional state, and includes data obtained from text analysis and biometric sensors.

[0882] The "importance adjustment means" is a function for changing the importance of a task based on collected emotion data.

[0883] "Search means" is a function for finding necessary information from past communication data and providing it to the user.

[0884] The present invention relates to a system that analyzes a user's communication data and emotional data to automatically manage tasks. This system recognizes the user's emotional state and can adjust task importance and reminder functions based on that information. A specific embodiment of the present invention will be described below.

[0885] Collection of communication data

[0886] Users communicate via email or chat. For example, they exchange information using applications such as Gmail or Slack. These interactions are recorded on the user's device (PC, smartphone, etc.) and sent to the system, where they are collected. The device automatically captures this data.

[0887] Collecting Emotional Data

[0888] The device collects the user's emotional state. To do this, it uses natural language processing technology (e.g., OpenAI's GPT-3) to perform text-based sentiment analysis. In addition, if the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data will also be collected.

[0889] Sending data

[0890] The communication data and emotion data collected by the device are sent to a server, where the data is encrypted using the Transport Layer Security (TLS) protocol to ensure security.

[0891] Data analysis and task generation

[0892] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ, and uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, a "Submit report" task will be generated. An emotion engine (e.g., an emotion analysis model using TensorFlow) analyzes the user's emotional state, and if the emotion is evaluated as "tense," the importance of the task will be increased.

[0893] Determining and adjusting importance

[0894] The server determines the importance of each task. It adjusts the importance of each task based on the user's emotional state, as determined by the emotion engine. For example, if the user's stress level is high, tasks with high urgency will be given a higher priority.

[0895] Reminders and notifications

[0896] The server prepares reminders and alerts based on the configured severity level and sends them to the user's device. For example, it uses AWS SES or Google Firebase Cloud Messaging to send emails or push notifications. The user receives a notification that "Tomorrow is the deadline for submitting a report."

[0897] Dealing with ambiguous requests

[0898] A user sends a vague request from their device to the server. For example, if the request is "I want to check the contents of last week's meeting," the server searches past communication data, summarizes the relevant information, and provides it to the user. In this case, too, it is possible to provide a summary that takes into account emotional data so that the user can check it in a calm state.

[0899] Specific examples

[0900] 1. Task Creation Example

[0901] A user receives an email saying, "Please check with your client about next week's meeting."

[0902] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[0903] The server analyzes the message and generates a task called "Confirm Meeting."

[0904] The server evaluates the importance of the task and sets it as "urgent."

[0905] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[0906] 2. Examples of Ambiguous Requests

[0907] The user sends a request from the terminal saying, "I want to check the contents of last week's meeting."

[0908] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[0909] The server searches past communication data and summarizes relevant content.

[0910] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[0911] Prompt Sentence Examples

[0912] "Create a task based on this email and rate its importance."

[0913] Please give me a summary of last week's meeting.

[0914] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[0915] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0916] Step 1:

[0917] When a user communicates via email or chat, the resulting communication data is recorded on the device. Communication data includes text messages, subjects, sender and recipient information. For example, when a user sends an email using Gmail, the content of the email and related information are stored on the device. The input is the communication data sent and received by the user. The output is the communication data stored on the device.

[0918] Step 2:

[0919] The device collects the user's emotional data. It uses natural language processing technology (e.g., OpenAI's GPT-3) to perform sentiment analysis from text. If the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data is also collected. The input is communication data and sensor data. The output is data reflecting the emotional state. For example, an emotional state label such as "high pressure" or "relaxed" is assigned.

[0920] Step 3:

[0921] The communication data and emotion data collected by the device are sent to the server. At this time, the data is encrypted using the TLS (Transport Layer Security) protocol, ensuring security. The input is the encrypted communication data and emotion data. The output is the encrypted data sent to the server.

[0922] Step 4:

[0923] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ. It uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, the task "Submit the report" is generated. The input is the encrypted data sent to the server. The output is the task information analyzed on the server.

[0924] Step 5:

[0925] The server evaluates the importance of the task. Based on the collected emotional data, an emotion analysis model using TensorFlow evaluates the user's emotional state and determines the priority of the task. The input is the analyzed task information and emotional data. The output is the task information with the assigned priority. For example, if the stress level is high, the task is set as "high priority."

[0926] Step 6:

[0927] The server prepares reminders and alerts and sends them to the user's device. The timing of the reminder is determined based on the configured priority, and notifications are sent using AWS SES or Google Firebase Cloud Messaging. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent. The input is high-priority task information. The output is a reminder notification.

[0928] Step 7:

[0929] A user sends a vague request from their device to the server. For example, a request might be, "I want to check the contents of last week's meeting." The server searches past communication data, summarizes the relevant information, and provides it to the user. It is possible to provide a summary that takes into account emotional data and helps the user feel at ease. The input is the user's request and past communication data. The output is summarized information. For example, summary information such as, "At last week's meeting, plans for launching a new product were discussed" is provided.

[0930] This allows users to efficiently manage tasks according to the context, allowing work to proceed smoothly.

[0931] (Application example 2)

[0932] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0933] To improve work efficiency and safety in factories, there is a need for a task management system that takes into account the emotional state of workers. However, current systems do not adequately adjust task priorities or suggest appropriate breaks that reflect the emotional state of workers, resulting in reduced work efficiency and a worsening working environment. Furthermore, there is a lack of ways to respond to ambiguous requests, which can increase worker stress and reduce the quality of work. Furthermore, there is a need for a method to centrally manage the wide variety of data collected by robots and respond appropriately in real time.

[0934] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0935] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and emotion data to automatically generate tasks, and means for determining the importance of the generated tasks and adjusting them based on the emotion data, thereby enabling improved work efficiency, stress reduction, and safety.

[0936] "User" refers to an individual or worker who uses this system.

[0937] "Communication data" refers to data including voice, text, and other information sent and received by users.

[0938] "Emotion data" refers to data including biometric information, facial data, etc. that indicates the user's emotional state.

[0939] A "task" refers to a job that includes work or instructions to be performed by a user.

[0940] A "robot" is an automatic machine that operates in a factory and receives and carries out instructions from the user.

[0941] "Server" refers to a central processing unit that analyzes data and notifies the user or robot of the results.

[0942] A "remind" refers to a notification that reminds the user of the existence of a particular task.

[0943] An "alert" refers to an urgent notification or warning given to the user.

[0944] "Priority adjustment" refers to changing the order in which tasks are executed or their importance based on emotional data, etc.

[0945] An "ambiguous request" is a request that is not specific but includes information or instructions the user is looking for.

[0946] "Summary information" refers to information extracted from past data and summarized concisely.

[0947] The present invention relates to a system for managing tasks by analyzing communication data and emotional data in order to improve work efficiency and reduce worker stress in factories. This system collects communication data and emotional data from users (workers), and a server analyzes this data to automatically generate and manage tasks. Specific embodiments are described below.

[0948] System configuration

[0949] 1. Collection of communication data

[0950] Users send and receive instructions and messages via voice and text through factory robots, and an application installed on the robot collects this data and sends it to a server.

[0951] 2. Collecting Emotional Data

[0952] The robot is equipped with biometric sensors and a facial recognition camera that collects real-time emotional data from the user, which is then sent to a server using secure communication methods.

[0953] Hardware and software used

[0954] Hardware

[0955] Factory robot: Collects communication data and executes work instructions.

[0956] Biometric sensors: Measure the user's heart rate and skin temperature and collect emotional data.

[0957] Facial recognition camera: Performs facial expression analysis and analyzes emotional data.

[0958] software

[0959] Natural language processing engine (NLP): Analyzes communication data and extracts tasks from the content of messages.

[0960] Sentiment Analysis Engine: Analyzes emotional data and determines the user's emotional state.

[0961] Data processing and calculation

[0962] Data collection

[0963] The communication and emotion data collected by the robot and sensors is sent to a server, where it is integrated and a dataset is generated for analysis.

[0964] Data analysis

[0965] The server uses a natural language processing engine to extract tasks from the received message. For example, if the message received is "Please start packing the next product," a task called "Pack the product" is generated.

[0966] The emotion analysis engine analyzes the user's emotional state and determines whether the user is feeling stressed based on emotional data (e.g., elevated heart rate and facial expression data obtained through facial recognition).

[0967] Task creation and priority adjustment

[0968] Task importance determination

[0969] The server determines the importance of the generated tasks and adjusts the importance based on the emotional data. For example, if the user is under stress, it will set urgent tasks as high priority and postpone less urgent tasks.

[0970] Reminders and notifications

[0971] The server sends reminders and alerts to the user's device and robot at appropriate times based on task priority, such as notifications to "start the next task" or reminders to "take a break."

[0972] Dealing with ambiguous requests

[0973] Ambiguous Request Analysis

[0974] The server analyzes a user's vague request (e.g., "I want to check the details of last week's meetings") and searches for relevant past communication data. It then generates summary information and provides it to the user, allowing the user to quickly obtain the information they need.

[0975] Specific examples

[0976] 1. Generate work instructions

[0977] A factory robot receives a voice command: "Start packing the next product."

[0978] The robot sends this instruction data and emotional data indicating that the worker is feeling stressed to a central server.

[0979] The server analyzes the data and generates a task called "Start packing the next product."

[0980] The server sets the task's importance as "high."

[0981] The server sends a notification to the worker saying, "Your stress is increasing, so please take a break before starting work."

[0982] 2. Ambiguous requests

[0983] A worker tells the robot a request: "I'd like to review the contents of last week's meeting."

[0984] The robot sends the request and emotional data indicating that the worker is feeling impatient to the server.

[0985] The server searches past communication data and summarizes relevant content.

[0986] The server sends the summary information to the worker along with a message urging them to "please take your time to check, as we are feeling impatient."

[0987] Prompt Sentence Examples

[0988] "Generate work tasks and adjust priorities based on the following work instruction data and emotion data."

[0989] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0990] Step 1:

[0991] Users send instructions and messages via voice or text to factory robots, and these communications data are collected by the robots, sometimes using software that converts voice input into text.

[0992] Input: User voice commands and text messages

[0993] Data processing: converting voice data to text, collecting text data

[0994] Output: Communication data

[0995] Step 2:

[0996] The robot collects user emotional data using biometric sensors and a facial recognition camera, which record heart rate, skin temperature, and facial expression data.

[0997] Input: User's biometric information (heart rate, skin temperature, facial expression, etc.)

[0998] Data processing: collection of biometric information, conversion of data from sensors

[0999] Output: Emotion data

[1000] Step 3:

[1001] The communication and emotion data collected by the robot is sent to a server using a secure communication protocol, and the data is encrypted.

[1002] Input: communication data, emotion data

[1003] Data processing: Data encryption

[1004] Output: Encrypted data (for sending to server)

[1005] Step 4:

[1006] The server uses a natural language processing engine to analyze the communication data it receives and automatically generate tasks. Tasks to be done are extracted from the message content.

[1007] Input: Encrypted data

[1008] Data processing: Decoding data and analyzing it with a natural language processing engine

[1009] Output: The generated tasks

[1010] Step 5:

[1011] The server uses an emotion analysis engine to analyze the collected emotional data, thereby determining the user's emotional state and recognizing conditions such as tension or stress.

[1012] Input: Emotion data

[1013] Data processing: Analysis using a sentiment analysis engine

[1014] Output: User's emotional state

[1015] Step 6:

[1016] The server determines the importance of the generated tasks and adjusts the importance based on emotional data. For example, if the user is under stress, tasks with high urgency are assigned a higher priority.

[1017] Input: Generated task, user's emotional state

[1018] Data processing: Task priority determination and adjustment

[1019] Output: Adjusted task priorities

[1020] Step 7:

[1021] The server sends reminders and alerts to users and robots at appropriate times based on task priority. The server creates notification content so that users can understand it quickly.

[1022] Input: Adjusted task priority

[1023] Data Processing: Creating reminders and alerts

[1024] Output: Reminder and alert notifications

[1025] Step 8:

[1026] The server receives a user's vague request, searches past communication data, and generates summary information, thereby quickly providing the information the user needs.

[1027] Input: Ambiguous request

[1028] Data processing: Searching past data and generating summary information

[1029] Output: Summary information

[1030] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1031] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1032] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1033] [Third embodiment]

[1034] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1035] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1036] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1037] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1038] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1039] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1040] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1041] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1042] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1043] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1044] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1045] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1046] The present invention relates to a system for automatically generating and managing tasks from user communication data. The following describes in detail how to implement the program for this system.

[1047] A natural language description of the program's operation

[1048] Collection of communication data

[1049] When users communicate via email or chat, their devices obtain permission to send these communications to the system. The devices are configured to periodically send collected data to the server, ensuring that the latest communication data is always available to the system.

[1050] Data analysis and task generation

[1051] The server analyzes the received data and automatically generates tasks to be done. Using natural language processing technology, the server divides the message content into tokens and extracts specific tasks by analyzing the intent. For example, if a user receives a message saying "Please submit a report by tomorrow," the server analyzes the message, generates a task called "Submit report," and sets the deadline to "tomorrow."

[1052] Determining the importance

[1053] The server evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task content. Depending on the evaluation result, the server classifies the task as high, medium, or low importance.

[1054] Reminders and notifications

[1055] The server sets reminders for tasks with high importance. The reminder settings are configured to send notifications to the user before the task deadline approaches. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user's device.

[1056] Dealing with ambiguous requests

[1057] When a user sends a vague request from their device, for example, "I want to check the details of last week's meeting," the server searches past communication data, summarizes the relevant content, and provides it to the user. This function allows users to quickly obtain the information they need.

[1058] Specific examples

[1059] 1. Task Creation Example

[1060] User: Receives an email saying "Please check with client X about meeting next week."

[1061] Terminal: Send the data of this email to the server.

[1062] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[1063] Server: Set the due date of the generated task to "Next week".

[1064] Server: Rate the importance of the task and set it as high importance.

[1065] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[1066] 2. Examples of Ambiguous Requests

[1067] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[1068] Terminal: Sends the request to the server.

[1069] Server: Searches past communication data and summarizes relevant messages.

[1070] Server: Sends the summarized information to the user's terminal.

[1071] Terminal: Displays the received summary information to the user.

[1072] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[1073] The processing flow will be explained below.

[1074] Step 1:

[1075] Users communicate via email and chat. Users send and receive messages as part of their normal business processes.

[1076] Step 2:

[1077] With user permission, the device collects email and chat data, including information such as message body, sender, recipient, and timestamp.

[1078] Step 3:

[1079] The device periodically sends the collected data to a server, where the data is encrypted and securely transmitted.

[1080] Step 4:

[1081] The server analyzes the received data, and an AI model breaks the message down into tokens and uses natural language processing techniques to understand the content of the message.

[1082] Step 5:

[1083] The server automatically generates tasks based on the analysis results. For example, a message such as "Please submit a report by tomorrow" generates a task called "Submit a report."

[1084] Step 6:

[1085] The server saves the details of the created task (task ID, task content, deadline, importance, etc.) in a database.

[1086] Step 7:

[1087] The server determines the importance of the task, analyzes the deadline and content of the task, and calculates the importance score.

[1088] Step 8:

[1089] The server sets reminders and alerts based on the importance of the task, and for high-priority tasks, it determines the frequency and timing of reminder notifications.

[1090] Step 9:

[1091] The server sends reminders and alerts to the user's device, for example, a notification that "Tomorrow is the deadline for submitting a report."

[1092] Step 10:

[1093] The device will display reminders and alerts to the user, allowing them to review important tasks and take appropriate action.

[1094] Step 11:

[1095] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[1096] Step 12:

[1097] The terminal sends the user's request to the server.

[1098] Step 13:

[1099] The server searches past communication data, extracts relevant information, generates summary information, and prepares it for presentation to the user.

[1100] Step 14:

[1101] The server transmits the generated summary information to the user's terminal.

[1102] Step 15:

[1103] The terminal displays the summary information to the user, allowing the user to quickly obtain the information they need.

[1104] Example 1

[1105] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1106] In today's business environment, many tasks and communications are performed daily, requiring efficient management and tracking. However, many users face challenges such as overlooking important tasks and difficulty responding appropriately to ambiguous requests. This can lead to poor task management efficiency and a decline in the quality of business communications. The present invention aims to solve these challenges by providing a system that enables users to effectively manage tasks and quickly respond to ambiguous requests.

[1107] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1108] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data to automatically generate tasks, means for evaluating the importance of the generated tasks, means for sending a notification to the user's terminal before the task deadline approaches, and means for analyzing the user's ambiguous requests and providing summary information from related past data, thereby preventing the user from overlooking tasks, enabling effective management of important tasks, and prompt response to ambiguous requests.

[1109] "Communication data" refers to data that includes the content of communications that users make electronically, such as by email or chat.

[1110] The "means of collection" is a mechanism for transferring communication data from the user's terminal to a server at regular intervals.

[1111] "Means of analyzing and automatically generating tasks" refers to the process of analyzing communication data using natural language processing technology, extracting specific actions and tasks from it, and automatically generating them.

[1112] The "means for evaluating the importance of a task" is a method for evaluating and ranking the importance of a generated task based on the deadline and urgency of the task's content.

[1113] "Means for sending notifications" refers to the technical means by which reminders and alerts are sent to the user's device when an important task is approaching its deadline.

[1114] "Means for analyzing ambiguous requests and providing summary information from related past data" refers to a method of analyzing ambiguous requests from users using natural language processing technology, searching past communication data to extract relevant information, and providing it in a summarized form.

[1115] "Preventing tasks from being overlooked" means that the system automatically generates tasks and sends reminders based on their importance, preventing users from forgetting important tasks.

[1116] "Effectively managing important tasks" means improving the efficiency of task management by evaluating the priority of tasks generated by the system and notifying the user at the appropriate time.

[1117] "Quick response to ambiguous requests" means enabling users to quickly obtain the information they need by quickly providing relevant information in response to ambiguous instructions or questions.

[1118] This invention relates to a system for automatically generating and managing tasks from user communication data. This system has the function of collecting and analyzing user communication data and sending reminders and notifications based on importance. It can also provide necessary information from related past data in response to vague user requests.

[1119] Hardware and Software

[1120] This system uses the following hardware and software:

[1121] Hardware: Servers, users' PCs and smartphones

[1122] Software: Natural language processing tools (e.g., Google Cloud Natural Language API), reminder and notification systems (e.g., Firebase Cloud Messaging)

[1123] Program processing

[1124] 1. Collection of communication data

[1125] Users: Allow the system to collect data when communicating with them via email or chat.

[1126] Terminal: Periodically transmits authorized communication data to the server.

[1127] 2. Data analysis and task generation

[1128] Server: Analyzes the received communication data using natural language processing technology and extracts specific tasks.

[1129] Server: For example, if a message "Please submit a report by tomorrow" is received, a task called "Submit report" is generated and its deadline is set to "tomorrow."

[1130] 3. Determining the importance

[1131] Server: Evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task.

[1132] 4. Reminders and Notifications

[1133] Server: Sends reminders to users about high-priority tasks before their deadlines approach.

[1134] Device: For example, display a notification saying "Tomorrow is the deadline for submitting your report."

[1135] 5. Dealing with Ambiguous Requests

[1136] User: Sends vague requests to the system (e.g., "I want to see what happened in last week's meetings").

[1137] Server: Searches past communication data, summarizes relevant content, and provides it to the user.

[1138] Specific examples

[1139] 1. Task Creation Example

[1140] User: Receives an email saying "Please check with client X about meeting next week."

[1141] Terminal: Send the data of this email to the server.

[1142] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[1143] Server: Set the due date of the generated task to "Next week".

[1144] Server: Rate the importance of the task and set it as high importance.

[1145] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[1146] 2. Examples of Ambiguous Requests

[1147] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[1148] Terminal: Sends the request to the server.

[1149] Server: Searches past communication data and summarizes relevant messages.

[1150] Server: Sends the summarized information to the user's terminal.

[1151] Terminal: Displays the received summary information to the user.

[1152] Prompt Sentence Examples

[1153] "Please explain a system that automatically generates tasks to be done for the next seven days of work and sets reminders based on their importance. Please provide a specific example that includes a process that collects and analyzes user communication data to generate tasks, evaluates their importance, and sends reminders."

[1154] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[1155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1156] System program processing flow

[1157] Step 1:

[1158] Obtaining permission

[1159] User: The system obtains permission from the user to collect communication data.

[1160] Specific operation: The user selects permission for data collection in the system settings screen.

[1161] Input: A setting change request from the user.

[1162] Output: The data collection permission flag is enabled.

[1163] Step 2:

[1164] Data collection

[1165] Device: Every time a user communicates via email or chat, the communication data is temporarily stored on the device.

[1166] Specific operation: The device stores communication data in local storage and updates it whenever the data is collected.

[1167] Input: Communication data sent and received by users.

[1168] Output: The latest communication data is saved in local storage.

[1169] Step 3:

[1170] Sending data

[1171] Terminal: Sends collected data to the server at regular intervals.

[1172] Specific operation: The terminal executes a batch job every night and sends the collected data to the server.

[1173] Input: Communication data stored in local storage.

[1174] Output: Communication data sent to the server.

[1175] Step 4:

[1176] Receiving data

[1177] Server: Receives communication data sent from the device and stores it in a database.

[1178] Specific operation: The server saves the communication data as a new record in the database.

[1179] Input: Communication data sent from the terminal.

[1180] Output: Communication data stored in a database.

[1181] Step 5:

[1182] Message Parsing

[1183] Server: Uses natural language processing (NLP) techniques to parse the message content and break it down into tokens.

[1184] What happens: The server uses the Google Cloud Natural Language API to split the text into tokens.

[1185] Input: Communication data stored in a database.

[1186] Output: Message data split into tokens.

[1187] Step 6:

[1188] Extracting tasks

[1189] Server: Extracts specific tasks from the analysis results.

[1190] Specific operation: Extract action words such as "submit" and "confirm" and register them as tasks.

[1191] Input: Message data split into tokens.

[1192] Output: Actions extracted as tasks with their details.

[1193] Step 7:

[1194] Task registration

[1195] Server: Register the extracted task as a new task in the database.

[1196] What it does: Adds a record to the database, including the task title, due date, importance, etc.

[1197] Input: Actions extracted as tasks and their details.

[1198] Output: The newly added task record in the database.

[1199] Step 8:

[1200] Initial assessment of task importance

[1201] Server: Initially assesses the importance of the task based on its deadline and content.

[1202] Specific behavior: The shorter the deadline, the higher the importance.

[1203] Input: Task description and deadline.

[1204] Output: Initially assessed task importance.

[1205] Step 9:

[1206] Finalize the importance

[1207] Server: Determines the final priority based on the user's past behavior and task management patterns.

[1208] Specific operation: Automatically classifies the importance of tasks into "high," "medium," or "low" based on the user's past task completion status.

[1209] Input: Initially assessed task importance and user performance data.

[1210] Output: The finalized task importance.

[1211] Step 10:

[1212] Reminder Settings

[1213] Server: Set reminders for high-priority tasks.

[1214] What it does: Adds a new record to the database with the reminder date and time.

[1215] Input: The finalized task importance.

[1216] Output: The reminder settings added to the database.

[1217] Step 11:

[1218] Sending notifications

[1219] Server: Sends a notification to the user's device at the scheduled date and time.

[1220] What it does: Sends a notification using Firebase Cloud Messaging and displays a message with details about the task.

[1221] Input: Reminder settings stored in the database.

[1222] Output: Notification sent to the user's device.

[1223] Step 12:

[1224] Receiving an ambiguous request

[1225] Server: Receives and analyzes ambiguous requests from users.

[1226] Specific behavior: Analyzes the request message using natural language processing to identify intent.

[1227] Input: An ambiguous request sent by the user.

[1228] Output: The parsed request content.

[1229] Step 13:

[1230] Data Search

[1231] Server: Searches past communication data and extracts relevant information.

[1232] What it does: It applies filtering criteria to the database to extract relevant messages.

[1233] Input: The parsed request content.

[1234] Output: Extracted relevant messages.

[1235] Step 14:

[1236] Creating a summary

[1237] Server: Summarizes the extracted information and presents it to the user.

[1238] What it does: Uses a summarization algorithm to extract key points.

[1239] Input: The extracted relevant message.

[1240] Output: Summarized information.

[1241] Step 15:

[1242] Sending a Summary

[1243] Server: Sends the summarized information to the user's terminal.

[1244] Specific behavior: Summary text is sent to the user's device and displayed via notification or email.

[1245] Input: Summarized information.

[1246] Output: Summary information sent to the user's device.

[1247] (Application example 1)

[1248] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1249] The present invention aims to improve productivity and efficiency by providing a means for automatically generating and managing important tasks from a large amount of constantly updated communication data, thereby issuing appropriate instructions to automated equipment and robots used in factories. Furthermore, it aims to support the execution of work by providing relevant information quickly and accurately even when a user makes an ambiguous request.

[1250] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1251] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and automatically generating tasks, means for determining the importance of the generated tasks and notifying the user, means for retrieving and providing necessary information from past communications, and means for issuing instructions to automated equipment used in the factory. This allows users to efficiently manage tasks arising from daily communications, and in particular, enables productivity and work efficiency to be improved while appropriately issuing instructions to automated equipment in the factory.

[1252] "User communication data" refers to information generated through the means of communication that users use on a daily basis, such as email, chat messages, and voice communications.

[1253] A "task" is a specific task or activity that a user must perform, and is automatically generated and managed by the system.

[1254] "Analysis" is the process of breaking down collected data and extracting specific patterns or information.

[1255] "Importance" is an evaluation criterion that indicates the priority of a generated task, and is determined based on the urgency and importance of the task.

[1256] "Notifications" are messages that inform users about task progress and deadlines.

[1257] "Search" is the operation of finding information that matches specific conditions from a database or stored information.

[1258] "Providing" refers to presenting the searched information to the user in an easy-to-view format.

[1259] "Automated equipment used in factories" refers to robots and mechanical devices used on production lines and in workshops.

[1260] "Instruction" is the act of ordering or requesting someone to perform a specific task or work.

[1261] A "system" is an information processing device or a collection of software in which multiple components operate in cooperation with each other.

[1262] The present invention is a system for collecting user communication data and automatically generating and managing tasks. In particular, it is possible to efficiently issue instructions to automated equipment used in factories. Specific embodiments of the present invention will be described below.

[1263] First, the system configuration will be explained. The system includes the following elements:

[1264] 1. User device: A digital device used by a user, such as a smartphone, smart glasses, or computer.

[1265] 2. Server: A computer system that analyzes data, generates tasks, and manages tasks.

[1266] 3. Natural Language Processing (NLP) module: Software for analyzing user communication data using NLP techniques such as SpaCy and BERT.

[1267] 4. Communication protocol: A protocol that uses MQTT or HTTP to communicate data between the user device and the server.

[1268] The user terminal sends communication data via email and chat to the server. With the user's permission, the collected data is periodically sent to the server. This collection process ensures that the system always has the latest communication data available.

[1269] The server analyzes the received data and automatically generates tasks to be done. The server uses an NLP module to divide the message content into tokens, analyze the intent, and extract specific tasks. For example, if a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend," the server analyzes this message, generates a task called "Maintain Machine X," and sets its deadline to "weekend."

[1270] The generated tasks are evaluated for importance using an importance evaluation module. This evaluation is based on the proximity of the task's deadline and the importance of the content. Depending on the task's importance, the server sets a reminder notification and sends it to the user's device when the deadline approaches.

[1271] In addition, if a user sends a vague request such as "I want to check last week's maintenance records," the server searches past communication data, summarizes the relevant information, and provides it to the user. This function allows users to quickly obtain the information they need.

[1272] For example, a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend." This message is sent from the user's device to the server, which analyzes it and generates a "Maintain Machine X" task with a deadline of the weekend. This task is evaluated as being of medium importance, and a reminder is sent the day before the weekend.

[1273] Furthermore, when a user requests, "I want to check last week's maintenance records," the server searches past data, summarizes the relevant records, and provides them to the user. In this way, users can efficiently manage tasks and issue appropriate instructions to automated equipment in the factory.

[1274] Example prompt sentence:

[1275] User message: "Tell Robot A to perform maintenance on Machine X over the weekend"

[1276] Process: Maintenance task generation and deadline setting

[1277]

[1278] User Request: "I want to check last week's maintenance records."

[1279] Process: Searching for and summarizing historical data

[1280] This invention enables users to efficiently manage tasks arising from daily communication, and in particular to give appropriate instructions to automated equipment in factories, thereby improving productivity and business efficiency.

[1281] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1282] Step 1: Collect communication data

[1283] When a user sends a message via email or chat, the device collects this communication data. The input data is the user's message, and the output data is the text data of the collected message. Specifically, the device is configured to capture the message and send it to a server at regular intervals.

[1284] Step 2: Sending data to the server

[1285] The terminal sends the collected text data to the server. The input data is the collected message text data, and the output data is the message data stored on the server. Specifically, data is sent from the terminal to the server using the MQTT or HTTP protocol.

[1286] Step 3: Data analysis and task generation

[1287] The server analyzes the received data and automatically generates tasks to be done. The input data is the text data of the received message, and the output data is the analyzed task information. Specifically, the server uses an NLP module (SpaCy or BERT) to divide the message content into tokens and perform intent analysis. Based on the results of this analysis, it extracts specific tasks and sets task descriptions, deadlines, etc.

[1288] Step 4: Task Importance Rating

[1289] The server evaluates the importance of the generated tasks. The input data is the generated task information, and the output data is the task information with the assigned importance. Specifically, the server evaluates the tasks based on their deadlines and the importance of their contents, and classifies them into high, medium, or low importance.

[1290] Step 5: Set up reminder notifications

[1291] The server sets reminders and alerts based on the set task importance. The input data is task information with the set importance, and the output data is reminder notification setting information. Specifically, the system is configured to determine the timing of the reminder and send a notification to the user's device when the deadline approaches.

[1292] Step 6: Send reminders

[1293] The server sends the configured reminder notification to the user's device. The input data is the reminder notification setting information, and the output data is the sent notification. Specifically, a notification is sent to the user's device in the form of "Tomorrow is the deadline for the task."

[1294] Step 7: Addressing Ambiguous Requests

[1295] When a user sends an ambiguous request from their device, the server searches past data in response to the request and summarizes the relevant information. The input data is the ambiguous request from the user, and the output data is the summarized information. Specifically, the server searches and analyzes past data, extracts and summarizes the most relevant parts, and sends them to the user's device.

[1296] Step 8: Provide summary information

[1297] The terminal receives the summary information sent from the server and displays it to the user. The input data is the summarized information, and the output data is the displayed summary information. In concrete terms, the terminal displays the information received from the server in a format that is easy for the user to see.

[1298] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1299] The present invention relates to a system that analyzes a user's communication data and emotional state to automatically manage tasks. This system is equipped with an emotion engine that recognizes the user's emotions and adjusts task importance and reminder functions based on the user's emotional state.

[1300] A natural language description of the program's operation

[1301] Collection of communication data

[1302] Users communicate via email and chat, and these communications are collected and sent to the system by the user's device.

[1303] Collecting Emotional Data

[1304] The device collects data to recognize the user's emotions, including emotion analysis from text or emotion data obtained from external devices such as biometric sensors.

[1305] Sending data

[1306] The communication data and emotion data collected by the device are sent to a server. The data is encrypted before transmission, ensuring security.

[1307] Data analysis and task generation

[1308] The server analyzes the received data and automatically generates tasks. Using natural language processing technology, the server extracts tasks to be done from the message content. For example, if a message is received saying "Please submit a report by tomorrow," the server generates a task called "Submit report" and sets a deadline. The server also analyzes the user's emotional state using an emotion engine; if the emotional state is "tense," the task is deemed more important.

[1309] Determining and adjusting importance

[1310] The server determines the importance of the generated tasks. The emotion engine analyzes the user's emotional state and adjusts the importance of the tasks accordingly. For example, if the user is under a high level of stress, tasks with high urgency will be given a higher priority.

[1311] Reminders and notifications

[1312] The server prepares reminders and alerts based on the configured importance. The server determines the timing of the reminder and sends a notification to the user's device. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user.

[1313] Dealing with ambiguous requests

[1314] A user sends a vague request from their device. For example, if the request is "I want to check the contents of last week's meeting," the server searches for relevant information from past communication data, summarizes it, and provides it to the user. The server also takes into account emotional data and provides a summary that is designed to keep the user calm.

[1315] Specific examples

[1316] 1. Task Creation Example

[1317] A user receives an email saying, "Please check with client X about next week's meeting."

[1318] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[1319] The server parses the message and generates a task called "Confirm next week's meeting."

[1320] The server evaluates the importance of the task and sets it as "urgent."

[1321] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[1322] 2. Examples of Ambiguous Requests

[1323] The user sends a request from the terminal saying, "I want to check the contents of last week's meeting."

[1324] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[1325] The server searches past communication data and summarizes relevant content.

[1326] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[1327] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[1328] The processing flow will be explained below.

[1329] Step 1:

[1330] Users communicate via email and chat, including everyday business interactions.

[1331] Step 2:

[1332] With the user's permission, the device collects communication data and emotional data. Communication data includes email text and chat messages, while emotional data includes emotions analyzed from text and biometric signals obtained from external sensors.

[1333] Step 3:

[1334] The communication and emotion data collected by the device is sent to a server, where it is encrypted for enhanced security.

[1335] Step 4:

[1336] The server analyzes the received data.

[1337] 1. Using natural language processing technology, communication data is tokenized and sentence structure is analyzed.

[1338] 2. Conduct intent analysis and extract specific tasks and requests.

[1339] Step 5:

[1340] The server uses an emotion engine to analyze the emotion data.

[1341] 1. Apply sentiment understanding algorithms to extract sentiment from text.

[1342] 2. Analyze data from external sensors to assess the user's stress level and emotional state.

[1343] Step 6:

[1344] The server automatically generates tasks based on the extracted task information and emotion data.

[1345] 1. For example, from the message "Please submit the report by tomorrow," generate a task called "Submit report" and set the deadline to "tomorrow."

[1346] 2. Adjust importance based on sentiment data.

[1347] Step 7:

[1348] The server stores task details (task ID, task content, deadline, importance, etc.) in a database, allowing you to track and manage tasks.

[1349] Step 8:

[1350] The server evaluates the importance of the generated task.

[1351] 1. Consider sentiment data when calculating importance scores.

[1352] 2. If you're stressed, prioritize tasks and set urgent reminders.

[1353] Step 9:

[1354] The server sets reminders and alerts.

[1355] 1. Determine the timing of the reminder and notify the user at the appropriate time.

[1356] 2. For example, prepare a notice that says, "Tomorrow is the deadline for your report. Relax and get ready."

[1357] Step 10:

[1358] The server sends reminder and alert notifications to the user's device.

[1359] Step 11:

[1360] The device displays any reminders or alerts received to the user, allowing them to review important tasks and take appropriate action.

[1361] Step 12:

[1362] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[1363] Step 13:

[1364] The terminal transmits the user's request and associated emotion data to the server.

[1365] Step 14:

[1366] The server analyzes the ambiguous request and searches for the necessary information from related past communication data.

[1367] 1. Search historical data and extract relevant emails and chats.

[1368] 2. Summarize the extracted information and present it in a user-friendly format.

[1369] Step 15:

[1370] The server takes emotion data into account and generates summary information that takes the user's feelings into consideration. For example, if the user is feeling anxious, the server may add a message saying, "Here are the important points. Please stay calm and check."

[1371] Step 16:

[1372] The server transmits the generated summary information to the user's terminal.

[1373] Step 17:

[1374] The terminal displays the summary information to the user, allowing the user to quickly obtain the necessary information and take appropriate action.

[1375] Example 2

[1376] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1377] In today's business environment, users are often faced with numerous tasks and the associated stress. In particular, there is a need for not only appropriate task management based on communication data, but also task prioritization that takes into account the user's emotional state. However, conventional task management systems are unable to reflect the user's emotional data, resulting in inefficient task management.

[1378] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user communication data, means for automatically generating tasks by analyzing the collected data, means for determining and notifying the importance of the generated tasks, means for collecting user emotion data, means for adjusting the importance of the tasks based on the emotion data, and means for searching for and providing necessary information from past interactions. This enables efficient task management that takes the user's emotional state into consideration.

[1379] "User" means an individual or corporation that uses the system.

[1380] "Communication data" is data generated when a user exchanges information with others, such as through email or chat.

[1381] "Collection means" refers to the functions and devices that the system uses to acquire user communication data and emotional data.

[1382] "Analysis tools" are algorithms and models used to analyze collected data and understand meaning and sentiment.

[1383] A "task" refers to a task or activity that a user must perform.

[1384] The "task generation means" is a function that creates a new task from the analyzed data.

[1385] "Importance" is a criterion for evaluating the urgency and priority of a task.

[1386] The "notification means" refers to a function or protocol for transmitting information about the generated task to the user.

[1387] "Emotional data" refers to information that describes a user's emotional state, and includes data obtained from text analysis and biometric sensors.

[1388] The "importance adjustment means" is a function for changing the importance of a task based on collected emotion data.

[1389] "Search means" is a function for finding necessary information from past communication data and providing it to the user.

[1390] The present invention relates to a system that analyzes a user's communication data and emotional data to automatically manage tasks. This system recognizes the user's emotional state and can adjust task importance and reminder functions based on that information. A specific embodiment of the present invention will be described below.

[1391] Collection of communication data

[1392] Users communicate via email or chat. For example, they exchange information using applications such as Gmail or Slack. These interactions are recorded on the user's device (PC, smartphone, etc.) and sent to the system, where they are collected. The device automatically captures this data.

[1393] Collecting Emotional Data

[1394] The device collects the user's emotional state. To do this, it uses natural language processing technology (e.g., OpenAI's GPT-3) to perform text-based sentiment analysis. In addition, if the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data will also be collected.

[1395] Sending data

[1396] The communication data and emotion data collected by the device are sent to a server, where the data is encrypted using the Transport Layer Security (TLS) protocol to ensure security.

[1397] Data analysis and task generation

[1398] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ, and uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, a "Submit report" task will be generated. An emotion engine (e.g., an emotion analysis model using TensorFlow) analyzes the user's emotional state, and if the emotion is evaluated as "tense," the importance of the task will be increased.

[1399] Determining and adjusting importance

[1400] The server determines the importance of each task. It adjusts the importance of each task based on the user's emotional state, as determined by the emotion engine. For example, if the user's stress level is high, it sets a higher priority to tasks that are more urgent.

[1401] Reminders and notifications

[1402] The server prepares reminders and alerts based on the configured severity level and sends them to the user's device. For example, it uses AWS SES or Google Firebase Cloud Messaging to send emails or push notifications. The user receives a notification that "Tomorrow is the deadline for submitting a report."

[1403] Dealing with ambiguous requests

[1404] A user sends a vague request from their device to the server. For example, if the request is "I want to check the contents of last week's meeting," the server searches past communication data, summarizes the relevant information, and provides it to the user. In this case, too, it is possible to provide a summary that takes into account emotional data so that the user can check it in a calm state.

[1405] Specific examples

[1406] 1. Task Creation Example

[1407] A user receives an email saying, "Please check with your client about next week's meeting."

[1408] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[1409] The server analyzes the message and generates a task called "Confirm Meeting."

[1410] The server evaluates the importance of the task and sets it as "urgent."

[1411] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[1412] 2. Examples of Ambiguous Requests

[1413] The user sends a request from the terminal saying, "I want to check the contents of last week's meeting."

[1414] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[1415] The server searches past communication data and summarizes relevant content.

[1416] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[1417] Prompt Sentence Examples

[1418] "Create a task based on this email and rate its importance."

[1419] Please give me a summary of last week's meeting.

[1420] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[1421] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1422] Step 1:

[1423] When a user communicates via email or chat, the resulting communication data is recorded on the device. Communication data includes text messages, subjects, sender and recipient information. For example, when a user sends an email using Gmail, the content of the email and related information are stored on the device. The input is the communication data sent and received by the user. The output is the communication data stored on the device.

[1424] Step 2:

[1425] The device collects the user's emotional data. It uses natural language processing technology (e.g., OpenAI's GPT-3) to perform sentiment analysis from text. If the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data is also collected. The input is communication data and sensor data. The output is data reflecting the emotional state. For example, an emotional state label such as "high pressure" or "relaxed" is assigned.

[1426] Step 3:

[1427] The communication data and emotion data collected by the device are sent to the server. At this time, the data is encrypted using the TLS (Transport Layer Security) protocol, ensuring security. The input is the encrypted communication data and emotion data. The output is the encrypted data sent to the server.

[1428] Step 4:

[1429] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ. It uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, the task "Submit the report" is generated. The input is the encrypted data sent to the server. The output is the task information analyzed on the server.

[1430] Step 5:

[1431] The server evaluates the importance of the task. Based on the collected emotional data, an emotion analysis model using TensorFlow evaluates the user's emotional state and determines the priority of the task. The input is the analyzed task information and emotional data. The output is the task information with the assigned priority. For example, if the stress level is high, the task is set as "high priority."

[1432] Step 6:

[1433] The server prepares reminders and alerts and sends them to the user's device. The timing of the reminder is determined based on the configured priority, and notifications are sent using AWS SES or Google Firebase Cloud Messaging. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent. The input is high-priority task information. The output is a reminder notification.

[1434] Step 7:

[1435] A user sends a vague request from their device to the server. For example, a request might be, "I want to check the contents of last week's meeting." The server searches past communication data, summarizes the relevant information, and provides it to the user. It is possible to provide a summary that takes into account emotional data and helps the user feel at ease. The input is the user's request and past communication data. The output is summarized information. For example, summary information such as, "At last week's meeting, plans for launching a new product were discussed" is provided.

[1436] This allows users to efficiently manage tasks according to the context, allowing work to proceed smoothly.

[1437] (Application example 2)

[1438] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1439] To improve work efficiency and safety in factories, there is a need for a task management system that takes into account the emotional state of workers. However, current systems do not adequately adjust task priorities or suggest appropriate breaks that reflect the emotional state of workers, resulting in reduced work efficiency and a worsening working environment. Furthermore, there is a lack of ways to respond to ambiguous requests, which can increase worker stress and reduce the quality of work. Furthermore, there is a need for a method to centrally manage the wide variety of data collected by robots and respond appropriately in real time.

[1440] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1441] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and emotion data to automatically generate tasks, and means for determining the importance of the generated tasks and adjusting them based on the emotion data, thereby enabling improved work efficiency, stress reduction, and safety.

[1442] "User" refers to an individual or worker who uses this system.

[1443] "Communication data" refers to data including voice, text, and other information sent and received by users.

[1444] "Emotion data" refers to data including biometric information, facial data, etc. that indicates the user's emotional state.

[1445] A "task" refers to a job that includes work or instructions to be performed by a user.

[1446] A "robot" is an automatic machine that operates in a factory and receives and carries out instructions from the user.

[1447] "Server" refers to a central processing unit that analyzes data and notifies the user or robot of the results.

[1448] A "remind" refers to a notification that reminds the user of the existence of a particular task.

[1449] An "alert" refers to an urgent notification or warning given to the user.

[1450] "Priority adjustment" refers to changing the order in which tasks are executed or their importance based on emotional data, etc.

[1451] An "ambiguous request" is a request that is not specific but includes information or instructions the user is looking for.

[1452] "Summary information" refers to information extracted from past data and summarized concisely.

[1453] The present invention relates to a system for managing tasks by analyzing communication data and emotional data in order to improve work efficiency and reduce worker stress in factories. This system collects communication data and emotional data from users (workers), and a server analyzes this data to automatically generate and manage tasks. Specific embodiments are described below.

[1454] System configuration

[1455] 1. Collection of communication data

[1456] Users send and receive instructions and messages via voice and text through factory robots, and an application installed on the robot collects this data and sends it to a server.

[1457] 2. Collecting Emotional Data

[1458] The robot is equipped with biometric sensors and a facial recognition camera that collects real-time emotional data from the user, which is then sent to a server using secure communication methods.

[1459] Hardware and software used

[1460] Hardware

[1461] Factory robot: Collects communication data and executes work instructions.

[1462] Biometric sensors: Measure the user's heart rate and skin temperature and collect emotional data.

[1463] Facial recognition camera: Performs facial expression analysis and analyzes emotional data.

[1464] software

[1465] Natural language processing engine (NLP): Analyzes communication data and extracts tasks from the content of messages.

[1466] Sentiment Analysis Engine: Analyzes emotional data and determines the user's emotional state.

[1467] Data processing and calculation

[1468] Data collection

[1469] The communication and emotion data collected by the robot and sensors is sent to a server, where it is integrated and a dataset is generated for analysis.

[1470] Data analysis

[1471] The server uses a natural language processing engine to extract tasks from the received message. For example, if the message received is "Please start packing the next product," a task called "Pack the product" is generated.

[1472] The emotion analysis engine analyzes the user's emotional state and determines whether the user is feeling stressed based on emotional data (e.g., elevated heart rate and facial expression data obtained through facial recognition).

[1473] Task creation and priority adjustment

[1474] Task importance determination

[1475] The server determines the importance of the generated tasks and adjusts the importance based on the emotional data. For example, if the user is under stress, it will set urgent tasks as high priority and postpone less urgent tasks.

[1476] Reminders and notifications

[1477] The server sends reminders and alerts to the user's device and robot at appropriate times based on task priority, such as notifications to "start the next task" or reminders to "take a break."

[1478] Dealing with ambiguous requests

[1479] Ambiguous Request Analysis

[1480] The server analyzes a user's vague request (e.g., "I want to check the details of last week's meetings") and searches for relevant past communication data. It then generates summary information and provides it to the user, allowing the user to quickly obtain the information they need.

[1481] Specific examples

[1482] 1. Generate work instructions

[1483] A factory robot receives a voice command: "Start packing the next product."

[1484] The robot sends this instruction data and emotional data indicating that the worker is feeling stressed to a central server.

[1485] The server analyzes the data and generates a task called "Start packing the next product."

[1486] The server sets the task's importance as "high."

[1487] The server sends a notification to the worker saying, "Your stress is increasing, so please take a break before starting work."

[1488] 2. Ambiguous requests

[1489] A worker tells the robot a request: "I'd like to review the contents of last week's meeting."

[1490] The robot sends the request and emotional data indicating that the worker is feeling impatient to the server.

[1491] The server searches past communication data and summarizes relevant content.

[1492] The server sends the summary information to the worker along with a message urging them to "please take your time to check, as we are feeling impatient."

[1493] Prompt Sentence Examples

[1494] "Generate work tasks and adjust priorities based on the following work instruction data and emotion data."

[1495] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1496] Step 1:

[1497] Users send instructions and messages via voice or text to factory robots, and these communications data are collected by the robots, sometimes using software that converts voice input into text.

[1498] Input: User voice commands and text messages

[1499] Data processing: converting voice data to text, collecting text data

[1500] Output: Communication data

[1501] Step 2:

[1502] The robot collects user emotional data using biometric sensors and a facial recognition camera, which record heart rate, skin temperature, and facial expression data.

[1503] Input: User's biometric information (heart rate, skin temperature, facial expression, etc.)

[1504] Data processing: collection of biometric information, conversion of data from sensors

[1505] Output: Emotion data

[1506] Step 3:

[1507] The communication and emotion data collected by the robot is sent to a server using a secure communication protocol, and the data is encrypted.

[1508] Input: communication data, emotion data

[1509] Data processing: Data encryption

[1510] Output: Encrypted data (for sending to server)

[1511] Step 4:

[1512] The server uses a natural language processing engine to analyze the communication data it receives and automatically generate tasks. Tasks to be done are extracted from the message content.

[1513] Input: Encrypted data

[1514] Data processing: Decoding data and analyzing it with a natural language processing engine

[1515] Output: The generated tasks

[1516] Step 5:

[1517] The server uses an emotion analysis engine to analyze the collected emotional data, thereby determining the user's emotional state and recognizing conditions such as tension or stress.

[1518] Input: Emotion data

[1519] Data processing: Analysis using a sentiment analysis engine

[1520] Output: User's emotional state

[1521] Step 6:

[1522] The server determines the importance of the generated tasks and adjusts the importance based on emotional data. For example, if the user is under stress, tasks with high urgency are assigned a higher priority.

[1523] Input: Generated task, user's emotional state

[1524] Data processing: Task priority determination and adjustment

[1525] Output: Adjusted task priorities

[1526] Step 7:

[1527] The server sends reminders and alerts to users and robots at appropriate times based on task priority. The server creates notification content so that users can understand it quickly.

[1528] Input: Adjusted task priority

[1529] Data Processing: Creating reminders and alerts

[1530] Output: Reminder and alert notifications

[1531] Step 8:

[1532] The server receives a user's vague request, searches past communication data, and generates summary information, thereby quickly providing the information the user needs.

[1533] Input: Ambiguous request

[1534] Data processing: Searching past data and generating summary information

[1535] Output: Summary information

[1536] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1537] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1538] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1539] [Fourth embodiment]

[1540] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1541] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1542] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1543] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1544] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1545] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1546] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1547] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1548] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1549] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1550] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1551] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1552] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1553] The present invention relates to a system for automatically generating and managing tasks from user communication data. The following describes in detail how to implement the program for this system.

[1554] A natural language description of the program's operation

[1555] Collection of communication data

[1556] When users communicate via email or chat, their devices obtain permission to send these communications to the system. The devices are configured to periodically send collected data to the server, ensuring that the latest communication data is always available to the system.

[1557] Data analysis and task generation

[1558] The server analyzes the received data and automatically generates tasks to be done. Using natural language processing technology, the server divides the message content into tokens and extracts specific tasks by analyzing the intent. For example, if a user receives a message saying "Please submit a report by tomorrow," the server analyzes the message, generates a task called "Submit report," and sets the deadline to "tomorrow."

[1559] Determining the importance

[1560] The server evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task content. Depending on the evaluation result, the server classifies the task as high, medium, or low importance.

[1561] Reminders and notifications

[1562] The server sets reminders for tasks with high importance. The reminder settings are configured to send notifications to users before the task deadline approaches. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user's device.

[1563] Dealing with ambiguous requests

[1564] When a user sends a vague request from their device, for example, "I want to check the details of last week's meeting," the server searches past communication data, summarizes the relevant content, and provides it to the user. This function allows users to quickly obtain the information they need.

[1565] Specific examples

[1566] 1. Task Creation Example

[1567] User: Receives an email saying "Please check with client X about meeting next week."

[1568] Terminal: Send the data of this email to the server.

[1569] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[1570] Server: Set the due date of the generated task to "Next week".

[1571] Server: Rate the importance of the task and set it as high importance.

[1572] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[1573] 2. Examples of Ambiguous Requests

[1574] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[1575] Terminal: Sends the request to the server.

[1576] Server: Searches past communication data and summarizes relevant messages.

[1577] Server: Sends the summarized information to the user's terminal.

[1578] Terminal: Displays the received summary information to the user.

[1579] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[1580] The processing flow will be explained below.

[1581] Step 1:

[1582] Users communicate via email and chat. Users send and receive messages as part of their normal business processes.

[1583] Step 2:

[1584] With user permission, the device collects email and chat data, including information such as message body, sender, recipient, and timestamp.

[1585] Step 3:

[1586] The device periodically sends the collected data to a server, where the data is encrypted and securely transmitted.

[1587] Step 4:

[1588] The server analyzes the received data, and an AI model breaks the message down into tokens and uses natural language processing techniques to understand the content of the message.

[1589] Step 5:

[1590] The server automatically generates tasks based on the analysis results. For example, a message such as "Please submit a report by tomorrow" generates a task called "Submit a report."

[1591] Step 6:

[1592] The server saves the details of the created task (task ID, task content, deadline, importance, etc.) in a database.

[1593] Step 7:

[1594] The server determines the importance of the task, analyzes the deadline and content of the task, and calculates the importance score.

[1595] Step 8:

[1596] The server sets reminders and alerts based on the importance of the task, and for high-priority tasks, it determines the frequency and timing of reminder notifications.

[1597] Step 9:

[1598] The server sends reminders and alerts to the user's device, for example, a notification that "Tomorrow is the deadline for submitting a report."

[1599] Step 10:

[1600] The device will display reminders and alerts to the user, allowing them to review important tasks and take appropriate action.

[1601] Step 11:

[1602] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[1603] Step 12:

[1604] The terminal sends the user's request to the server.

[1605] Step 13:

[1606] The server searches past communication data, extracts relevant information, generates summary information, and prepares it for presentation to the user.

[1607] Step 14:

[1608] The server transmits the generated summary information to the user's terminal.

[1609] Step 15:

[1610] The terminal displays the summary information to the user, allowing the user to quickly obtain the information they need.

[1611] Example 1

[1612] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1613] In today's business environment, many tasks and communications are performed daily, requiring efficient management and tracking. However, many users face challenges such as overlooking important tasks and difficulty responding appropriately to ambiguous requests. This can lead to poor task management efficiency and a decline in the quality of business communications. The present invention aims to solve these challenges by providing a system that enables users to effectively manage tasks and quickly respond to ambiguous requests.

[1614] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1615] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data to automatically generate tasks, means for evaluating the importance of the generated tasks, means for sending a notification to the user's terminal before the task deadline approaches, and means for analyzing the user's ambiguous requests and providing summary information from related past data, thereby preventing the user from overlooking tasks, enabling effective management of important tasks, and prompt response to ambiguous requests.

[1616] "Communication data" refers to data that includes the content of communications that users make electronically, such as by email or chat.

[1617] The "means of collection" is a mechanism for transferring communication data from the user's terminal to a server at regular intervals.

[1618] "Means of analyzing and automatically generating tasks" refers to the process of analyzing communication data using natural language processing technology, extracting specific actions and tasks from it, and automatically generating them.

[1619] The "means for evaluating the importance of a task" is a method for evaluating and ranking the importance of a generated task based on the deadline and urgency of the task's content.

[1620] "Means for sending notifications" refers to the technical means by which reminders and alerts are sent to the user's device when an important task is approaching its deadline.

[1621] "Means for analyzing ambiguous requests and providing summary information from related past data" refers to a method of analyzing ambiguous requests from users using natural language processing technology, searching past communication data to extract relevant information, and providing it in a summarized form.

[1622] "Preventing tasks from being overlooked" means that the system automatically generates tasks and sends reminders based on their importance, preventing users from forgetting important tasks.

[1623] "Effectively managing important tasks" means improving the efficiency of task management by evaluating the priority of tasks generated by the system and notifying the user at the appropriate time.

[1624] "Quick response to ambiguous requests" means enabling users to quickly obtain the information they need by quickly providing relevant information in response to ambiguous instructions or questions.

[1625] This invention relates to a system for automatically generating and managing tasks from user communication data. This system has the function of collecting and analyzing user communication data and sending reminders and notifications based on importance. It can also provide necessary information from related past data in response to vague user requests.

[1626] Hardware and Software

[1627] This system uses the following hardware and software:

[1628] Hardware: Servers, users' PCs and smartphones

[1629] Software: Natural language processing tools (e.g., Google Cloud Natural Language API), reminder and notification systems (e.g., Firebase Cloud Messaging)

[1630] Program processing

[1631] 1. Collection of communication data

[1632] Users: Allow the system to collect data when communicating with them via email or chat.

[1633] Terminal: Periodically transmits authorized communication data to the server.

[1634] 2. Data analysis and task generation

[1635] Server: Analyzes the received communication data using natural language processing technology and extracts specific tasks.

[1636] Server: For example, if a message "Please submit a report by tomorrow" is received, a task called "Submit report" is generated and its deadline is set to "tomorrow."

[1637] 3. Determining the importance

[1638] Server: Evaluates the importance of the generated tasks based on the proximity of the deadline and the importance of the task.

[1639] 4. Reminders and Notifications

[1640] Server: Sends reminders to users about high-priority tasks before their deadlines approach.

[1641] Device: For example, display a notification saying "Tomorrow is the deadline for submitting your report."

[1642] 5. Dealing with Ambiguous Requests

[1643] User: Sends vague requests to the system (e.g., "I want to see what happened in last week's meetings").

[1644] Server: Searches past communication data, summarizes relevant content, and provides it to the user.

[1645] Specific examples

[1646] 1. Task Creation Example

[1647] User: Receives an email saying "Please check with client X about meeting next week."

[1648] Terminal: Send the data of this email to the server.

[1649] Server: The AI ​​model analyzes the message and generates a task such as "Confirm next week's meeting."

[1650] Server: Set the due date of the generated task to "Next week".

[1651] Server: Rate the importance of the task and set it as high importance.

[1652] Server: The day before the meeting, send a reminder to the user's device saying, "Please confirm the meeting with client X tomorrow."

[1653] 2. Examples of Ambiguous Requests

[1654] User: Sends a request from the device saying, "I want to review the details of last week's meetings."

[1655] Terminal: Sends the request to the server.

[1656] Server: Searches past communication data and summarizes relevant messages.

[1657] Server: Sends the summarized information to the user's terminal.

[1658] Terminal: Displays the received summary information to the user.

[1659] Prompt Sentence Examples

[1660] "Please explain a system that automatically generates tasks to be done for the next seven days of work and sets reminders based on their importance. Please provide a specific example that includes a process that collects and analyzes user communication data to generate tasks, evaluates their importance, and sends reminders."

[1661] The system of the present invention allows users to efficiently manage important tasks, eliminating overlooked requests and difficulty in finding information, thereby significantly improving the quality and efficiency of business communication.

[1662] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1663] System program processing flow

[1664] Step 1:

[1665] Obtaining permission

[1666] User: The system obtains permission from the user to collect communication data.

[1667] Specific operation: The user selects permission for data collection in the settings screen within the system.

[1668] Input: A setting change request from the user.

[1669] Output: The data collection permission flag is enabled.

[1670] Step 2:

[1671] Data collection

[1672] Device: Every time a user communicates via email or chat, the communication data is temporarily stored on the device.

[1673] Specific operation: The device stores communication data in local storage and updates it whenever the data is collected.

[1674] Input: Communication data sent and received by users.

[1675] Output: The latest communication data is saved in local storage.

[1676] Step 3:

[1677] Sending data

[1678] Terminal: Sends collected data to the server at regular intervals.

[1679] Specific operation: The terminal executes a batch job every night and sends the collected data to the server.

[1680] Input: Communication data stored in local storage.

[1681] Output: Communication data sent to the server.

[1682] Step 4:

[1683] Receiving data

[1684] Server: Receives communication data sent from the device and stores it in a database.

[1685] Specific operation: The server saves the communication data as a new record in the database.

[1686] Input: Communication data sent from the terminal.

[1687] Output: Communication data stored in a database.

[1688] Step 5:

[1689] Message Parsing

[1690] Server: Uses natural language processing (NLP) techniques to parse the message content and break it down into tokens.

[1691] What happens: The server uses the Google Cloud Natural Language API to split the text into tokens.

[1692] Input: Communication data stored in a database.

[1693] Output: Message data split into tokens.

[1694] Step 6:

[1695] Extracting tasks

[1696] Server: Extracts specific tasks from the analysis results.

[1697] Specific operation: Extract action words such as "submit" and "confirm" and register them as tasks.

[1698] Input: Message data split into tokens.

[1699] Output: Actions extracted as tasks with their details.

[1700] Step 7:

[1701] Task registration

[1702] Server: Register the extracted task as a new task in the database.

[1703] What it does: Adds a record to the database, including the task title, due date, importance, etc.

[1704] Input: Actions extracted as tasks and their details.

[1705] Output: The newly added task record in the database.

[1706] Step 8:

[1707] Initial assessment of task importance

[1708] Server: Initially assesses the importance of the task based on its deadline and content.

[1709] Specific behavior: The shorter the deadline, the higher the importance.

[1710] Input: Task description and deadline.

[1711] Output: Initially assessed task importance.

[1712] Step 9:

[1713] Finalize the importance

[1714] Server: Determines the final priority based on the user's past behavior and task management patterns.

[1715] Specific operation: Automatically classifies the importance of tasks into "high," "medium," or "low" based on the user's past task completion status.

[1716] Input: Initially assessed task importance and user performance data.

[1717] Output: The finalized task importance.

[1718] Step 10:

[1719] Reminder Settings

[1720] Server: Set reminders for high-priority tasks.

[1721] What it does: Adds a new record to the database with the reminder date and time.

[1722] Input: The finalized task importance.

[1723] Output: The reminder settings added to the database.

[1724] Step 11:

[1725] Sending notifications

[1726] Server: Sends a notification to the user's device at the scheduled date and time.

[1727] What it does: Sends a notification using Firebase Cloud Messaging and displays a message with details about the task.

[1728] Input: Reminder settings stored in the database.

[1729] Output: Notification sent to the user's device.

[1730] Step 12:

[1731] Receiving an ambiguous request

[1732] Server: Receives and analyzes ambiguous requests from users.

[1733] Specific behavior: Analyzes the request message using natural language processing to identify intent.

[1734] Input: An ambiguous request sent by the user.

[1735] Output: The parsed request content.

[1736] Step 13:

[1737] Data Search

[1738] Server: Searches past communication data and extracts relevant information.

[1739] What it does: It applies filtering criteria to the database to extract relevant messages.

[1740] Input: The parsed request content.

[1741] Output: Extracted relevant messages.

[1742] Step 14:

[1743] Creating a summary

[1744] Server: Summarizes the extracted information and presents it to the user.

[1745] What it does: Uses a summarization algorithm to extract key points.

[1746] Input: The extracted relevant message.

[1747] Output: Summarized information.

[1748] Step 15:

[1749] Sending a Summary

[1750] Server: Sends the summarized information to the user's terminal.

[1751] Specific behavior: Summary text is sent to the user's device and displayed via notification or email.

[1752] Input: Summarized information.

[1753] Output: Summary information sent to the user's device.

[1754] (Application example 1)

[1755] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1756] The present invention aims to improve productivity and efficiency by providing a means for automatically generating and managing important tasks from a large amount of constantly updated communication data, thereby issuing appropriate instructions to automated equipment and robots used in factories. Furthermore, it aims to support the execution of work by providing relevant information quickly and accurately even when a user makes an ambiguous request.

[1757] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1758] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and automatically generating tasks, means for determining the importance of the generated tasks and notifying the user, means for retrieving and providing necessary information from past communications, and means for issuing instructions to automated equipment used in the factory. This allows users to efficiently manage tasks arising from daily communications, and in particular, enables productivity and work efficiency to be improved while appropriately issuing instructions to automated equipment in the factory.

[1759] "User communication data" refers to information generated through the means of communication that users use on a daily basis, such as email, chat messages, and voice communications.

[1760] A "task" is a specific task or activity that a user must perform, and is automatically generated and managed by the system.

[1761] "Analysis" is the process of breaking down collected data and extracting specific patterns or information.

[1762] "Importance" is an evaluation criterion that indicates the priority of a generated task, and is determined based on the urgency and importance of the task.

[1763] "Notifications" are messages that inform users about task progress and deadlines.

[1764] "Search" is the operation of finding information that matches specific conditions from a database or stored information.

[1765] "Providing" refers to presenting the searched information to the user in an easy-to-view format.

[1766] "Automated equipment used in factories" refers to robots and mechanical devices used on production lines and in workshops.

[1767] "Instruction" is the act of ordering or requesting someone to perform a specific task or work.

[1768] A "system" is an information processing device or a collection of software in which multiple components operate in cooperation with each other.

[1769] The present invention is a system for collecting user communication data and automatically generating and managing tasks. In particular, it is possible to efficiently issue instructions to automated equipment used in factories. Specific embodiments of the present invention will be described below.

[1770] First, the system configuration will be explained. The system includes the following elements:

[1771] 1. User device: A digital device used by a user, such as a smartphone, smart glasses, or computer.

[1772] 2. Server: A computer system that analyzes data, generates tasks, and manages tasks.

[1773] 3. Natural Language Processing (NLP) module: Software for analyzing user communication data using NLP techniques such as SpaCy and BERT.

[1774] 4. Communication protocol: A protocol that uses MQTT or HTTP to communicate data between the user device and the server.

[1775] The user terminal sends communication data via email and chat to the server. With the user's permission, the collected data is periodically sent to the server. This collection process ensures that the system always has the latest communication data available.

[1776] The server analyzes the received data and automatically generates tasks to be done. The server uses an NLP module to divide the message content into tokens, analyze the intent, and extract specific tasks. For example, if a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend," the server analyzes this message, generates a task called "Maintain Machine X," and sets its deadline to "weekend."

[1777] The generated tasks are evaluated for importance using an importance evaluation module. This evaluation is based on the proximity of the task's deadline and the importance of the content. Depending on the task's importance, the server sets a reminder notification and sends it to the user's device when the deadline approaches.

[1778] In addition, if a user sends a vague request such as "I want to check last week's maintenance records," the server searches past communication data, summarizes the relevant information, and provides it to the user. This function allows users to quickly obtain the information they need.

[1779] For example, a user sends a message saying, "Please instruct Robot A to perform maintenance on Machine X over the weekend." This message is sent from the user's device to the server, which analyzes it and generates a "Maintain Machine X" task with a deadline of the weekend. This task is evaluated as being of medium importance, and a reminder is sent the day before the weekend.

[1780] Furthermore, when a user requests, "I want to check last week's maintenance records," the server searches past data, summarizes the relevant records, and provides them to the user. In this way, users can efficiently manage tasks and issue appropriate instructions to automated equipment in the factory.

[1781] Example prompt sentence:

[1782] User message: "Tell Robot A to perform maintenance on Machine X over the weekend"

[1783] Process: Maintenance task generation and deadline setting

[1784]

[1785] User Request: "I want to check last week's maintenance records."

[1786] Process: Searching for and summarizing historical data

[1787] This invention enables users to efficiently manage tasks arising from daily communication, and in particular to give appropriate instructions to automated equipment in factories, thereby improving productivity and business efficiency.

[1788] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1789] Step 1: Collect communication data

[1790] When a user sends a message via email or chat, the device collects this communication data. The input data is the user's message, and the output data is the text data of the collected message. Specifically, the device is configured to capture the message and send it to a server at regular intervals.

[1791] Step 2: Sending data to the server

[1792] The terminal sends the collected text data to the server. The input data is the collected message text data, and the output data is the message data stored on the server. Specifically, data is sent from the terminal to the server using the MQTT or HTTP protocol.

[1793] Step 3: Data analysis and task generation

[1794] The server analyzes the received data and automatically generates tasks to be done. The input data is the text data of the received message, and the output data is the analyzed task information. Specifically, the server uses an NLP module (SpaCy or BERT) to divide the message content into tokens and perform intent analysis. Based on the results of this analysis, it extracts specific tasks and sets task descriptions, deadlines, etc.

[1795] Step 4: Task Importance Rating

[1796] The server evaluates the importance of the generated tasks. The input data is the generated task information, and the output data is the task information with the assigned importance. Specifically, the server evaluates the tasks based on their deadlines and the importance of their contents, and classifies them into high, medium, or low importance.

[1797] Step 5: Set up reminder notifications

[1798] The server sets reminders and alerts based on the set task importance. The input data is task information with the set importance, and the output data is reminder notification setting information. Specifically, the system is configured to determine the timing of the reminder and send a notification to the user's device when the deadline approaches.

[1799] Step 6: Send reminders

[1800] The server sends the configured reminder notification to the user's device. The input data is the reminder notification setting information, and the output data is the sent notification. Specifically, a notification is sent to the user's device in the form of "Tomorrow is the deadline for the task."

[1801] Step 7: Addressing Ambiguous Requests

[1802] When a user sends an ambiguous request from their device, the server searches past data in response to the request and summarizes the relevant information. The input data is the ambiguous request from the user, and the output data is the summarized information. Specifically, the server searches and analyzes past data, extracts and summarizes the most relevant parts, and sends them to the user's device.

[1803] Step 8: Provide summary information

[1804] The terminal receives the summary information sent from the server and displays it to the user. The input data is the summarized information, and the output data is the displayed summary information. In concrete terms, the terminal displays the information received from the server in a format that is easy for the user to see.

[1805] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1806] The present invention relates to a system that analyzes a user's communication data and emotional state to automatically manage tasks. This system is equipped with an emotion engine that recognizes the user's emotions and adjusts task importance and reminder functions based on the user's emotional state.

[1807] A natural language description of the program's operation

[1808] Collection of communication data

[1809] Users communicate via email and chat, and these communications are collected and sent to the system by the user's device.

[1810] Collecting Emotional Data

[1811] The device collects data to recognize the user's emotions, including emotion analysis from text or emotion data obtained from external devices such as biometric sensors.

[1812] Sending data

[1813] The communication data and emotion data collected by the device are sent to a server. The data is encrypted before transmission, ensuring security.

[1814] Data analysis and task generation

[1815] The server analyzes the received data and automatically generates tasks. Using natural language processing technology, the server extracts tasks to be done from the message content. For example, if a message is received saying "Please submit a report by tomorrow," the server generates a task called "Submit report" and sets a deadline. The server also analyzes the user's emotional state using an emotion engine; if the emotional state is "tense," the task is deemed more important.

[1816] Determining and adjusting importance

[1817] The server determines the importance of the generated tasks. The emotion engine analyzes the user's emotional state and adjusts the importance of the tasks accordingly. For example, if the user is under a high level of stress, tasks with high urgency will be given a higher priority.

[1818] Reminders and notifications

[1819] The server prepares reminders and alerts based on the configured importance. The server determines the timing of the reminder and sends a notification to the user's device. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent to the user.

[1820] Dealing with ambiguous requests

[1821] A user sends a vague request from their device. For example, if the request is "I want to check the contents of last week's meeting," the server searches for relevant information from past communication data, summarizes it, and provides it to the user. The server also takes into account emotional data and provides a summary that is designed to keep the user calm.

[1822] Specific examples

[1823] 1. Task Creation Example

[1824] A user receives an email saying, "Please check with client X about next week's meeting."

[1825] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[1826] The server parses the message and generates a task called "Confirm next week's meeting."

[1827] The server evaluates the importance of the task and sets it as "urgent."

[1828] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[1829] 2. Examples of Ambiguous Requests

[1830] The user sends a request from the terminal saying, "I want to check the details of last week's meeting."

[1831] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[1832] The server searches past communication data and summarizes relevant content.

[1833] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[1834] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[1835] The processing flow will be explained below.

[1836] Step 1:

[1837] Users communicate via email and chat, including everyday business interactions.

[1838] Step 2:

[1839] With the user's permission, the device collects communication data and emotional data. Communication data includes email text and chat messages, while emotional data includes emotions analyzed from text and biometric signals obtained from external sensors.

[1840] Step 3:

[1841] The communication and emotion data collected by the device is sent to a server, where it is encrypted for enhanced security.

[1842] Step 4:

[1843] The server analyzes the received data.

[1844] 1. Using natural language processing technology, communication data is tokenized and sentence structure is analyzed.

[1845] 2. Conduct intent analysis and extract specific tasks and requests.

[1846] Step 5:

[1847] The server uses an emotion engine to analyze the emotion data.

[1848] 1. Apply sentiment understanding algorithms to extract sentiment from text.

[1849] 2. Analyze data from external sensors to assess the user's stress level and emotional state.

[1850] Step 6:

[1851] The server automatically generates tasks based on the extracted task information and emotion data.

[1852] 1. For example, from the message "Please submit the report by tomorrow," generate a task called "Submit report" and set the deadline to "tomorrow."

[1853] 2. Adjust importance based on sentiment data.

[1854] Step 7:

[1855] The server stores task details (task ID, task content, deadline, importance, etc.) in a database, allowing you to track and manage tasks.

[1856] Step 8:

[1857] The server evaluates the importance of the generated task.

[1858] 1. Consider sentiment data when calculating importance scores.

[1859] 2. If you're stressed, prioritize tasks and set more urgent reminders.

[1860] Step 9:

[1861] The server sets reminders and alerts.

[1862] 1. Determine the timing of the reminder and notify the user at the appropriate time.

[1863] 2. For example, prepare a notice that says, "Tomorrow is the deadline for your report. Relax and get ready."

[1864] Step 10:

[1865] The server sends reminder and alert notifications to the user's device.

[1866] Step 11:

[1867] The device displays any reminders or alerts received to the user, allowing them to review important tasks and take appropriate action.

[1868] Step 12:

[1869] A user sends a vague request from a terminal, for example, "I want to check the details of last week's meeting."

[1870] Step 13:

[1871] The terminal transmits the user's request and associated emotion data to the server.

[1872] Step 14:

[1873] The server analyzes the ambiguous request and searches for the necessary information from related past communication data.

[1874] 1. Search historical data and extract relevant emails and chats.

[1875] 2. Summarize the extracted information and present it in a user-friendly format.

[1876] Step 15:

[1877] The server takes emotion data into account and generates summary information that takes the user's feelings into consideration. For example, if the user is feeling anxious, the server may add a message saying, "Here are the important points. Please stay calm and check."

[1878] Step 16:

[1879] The server transmits the generated summary information to the user's terminal.

[1880] Step 17:

[1881] The terminal displays the summary information to the user, allowing the user to quickly obtain the necessary information and take appropriate action.

[1882] Example 2

[1883] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1884] In today's business environment, users are often faced with numerous tasks and the associated stress. In particular, there is a need for not only appropriate task management based on communication data, but also task prioritization that takes into account the user's emotional state. However, conventional task management systems are unable to reflect the user's emotional data, resulting in inefficient task management.

[1885] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user communication data, means for automatically generating tasks by analyzing the collected data, means for determining and notifying the importance of the generated tasks, means for collecting user emotion data, means for adjusting the importance of the tasks based on the emotion data, and means for searching for and providing necessary information from past interactions. This enables efficient task management that takes the user's emotional state into consideration.

[1886] "User" means an individual or corporation that uses the system.

[1887] "Communication data" is data generated when a user exchanges information with others, such as through email or chat.

[1888] "Collection means" refers to the functions and devices that the system uses to acquire user communication data and emotional data.

[1889] "Analysis tools" are algorithms and models used to analyze collected data and understand meaning and sentiment.

[1890] A "task" refers to a task or activity that a user must perform.

[1891] The "task generation means" is a function that creates a new task from the analyzed data.

[1892] "Importance" is a criterion for evaluating the urgency and priority of a task.

[1893] The "notification means" refers to a function or protocol for transmitting information about the generated task to the user.

[1894] "Emotional data" refers to information that describes a user's emotional state, and includes data obtained from text analysis and biometric sensors.

[1895] The "importance adjustment means" is a function for changing the importance of a task based on collected emotion data.

[1896] "Search means" is a function for finding necessary information from past communication data and providing it to the user.

[1897] The present invention relates to a system that analyzes a user's communication data and emotional data to automatically manage tasks. This system recognizes the user's emotional state and can adjust task importance and reminder functions based on that information. A specific embodiment of the present invention will be described below.

[1898] Collection of communication data

[1899] Users communicate via email or chat. For example, they exchange information using applications such as Gmail or Slack. These interactions are recorded on the user's device (PC, smartphone, etc.) and collected for transmission to the system. The device automatically captures this data.

[1900] Collecting Emotional Data

[1901] The device collects the user's emotional state. To do this, it uses natural language processing technology (e.g., OpenAI's GPT-3) to perform text-based sentiment analysis. In addition, if the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data will also be collected.

[1902] Sending data

[1903] The communication data and emotion data collected by the device are sent to a server, where the data is encrypted using the Transport Layer Security (TLS) protocol to ensure security.

[1904] Data analysis and task generation

[1905] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ, and uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, a "Submit report" task will be generated. An emotion engine (e.g., an emotion analysis model using TensorFlow) analyzes the user's emotional state, and if the emotion is evaluated as "tense," the importance of the task will be increased.

[1906] Determining and adjusting importance

[1907] The server determines the importance of each task. It adjusts the importance of each task based on the user's emotional state, as determined by the emotion engine. For example, if the user's stress level is high, it sets a higher priority to tasks that are more urgent.

[1908] Reminders and notifications

[1909] The server prepares reminders and alerts based on the configured severity level and sends them to the user's device. For example, it uses AWS SES or Google Firebase Cloud Messaging to send emails or push notifications. The user receives a notification that "Tomorrow is the deadline for submitting a report."

[1910] Dealing with ambiguous requests

[1911] A user sends a vague request from their device to the server. For example, if the request is "I want to check the contents of last week's meeting," the server searches past communication data, summarizes the relevant information, and provides it to the user. In this case, too, it is possible to provide a summary that takes into account emotional data so that the user can check it in a calm state.

[1912] Specific examples

[1913] 1. Task Creation Example

[1914] A user receives an email saying, "Please check with your client about next week's meeting."

[1915] The device sends the email data and emotional data indicating that the user is feeling stressed to the server.

[1916] The server analyzes the message and generates a task called "Confirm Meeting."

[1917] The server evaluates the importance of the task and sets it as "urgent."

[1918] The server sends a reminder to the user the day before the meeting saying, "You are under high stress, please check after your break."

[1919] 2. Examples of Ambiguous Requests

[1920] The user sends a request from the terminal saying, "I want to check the details of last week's meeting."

[1921] The terminal transmits the request and emotional data indicating that "the user is feeling impatient" to the server.

[1922] The server searches past communication data and summarizes relevant content.

[1923] The server takes into account the emotion data and sends summary information to the user along with a message urging them to "check in a calm state."

[1924] Prompt Sentence Examples

[1925] "Create a task based on this email and rate its importance."

[1926] Please give me a summary of last week's meeting.

[1927] The system of the present invention allows users to centrally manage communication data and emotional states, and adjust task importance and reminders, enabling them to carry out their work efficiently and with less stress.

[1928] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1929] Step 1:

[1930] When a user communicates via email or chat, the resulting communication data is recorded on the device. Communication data includes text messages, subjects, sender and recipient information. For example, when a user sends an email using Gmail, the content of the email and related information are stored on the device. The input is the communication data sent and received by the user. The output is the communication data stored on the device.

[1931] Step 2:

[1932] The device collects the user's emotional data. It uses natural language processing technology (e.g., OpenAI's GPT-3) to perform sentiment analysis from text. If the user is wearing a biometric sensor (e.g., MEASURE or Empathy), that data is also collected. The input is communication data and sensor data. The output is data reflecting the emotional state. For example, an emotional state label such as "high pressure" or "relaxed" is assigned.

[1933] Step 3:

[1934] The communication data and emotion data collected by the device are sent to the server. At this time, the data is encrypted using the TLS (Transport Layer Security) protocol, ensuring security. The input is the encrypted communication data and emotion data. The output is the encrypted data sent to the server.

[1935] Step 4:

[1936] The server analyzes the data it receives. It processes the data sequentially using a message broker such as Apache Kafka or RabbitMQ. It uses natural language processing technology (e.g., Google's BERT model) to extract tasks from the message content. For example, if the message "Please submit the report by tomorrow" is analyzed, the task "Submit the report" is generated. The input is the encrypted data sent to the server. The output is the task information analyzed on the server.

[1937] Step 5:

[1938] The server evaluates the importance of the task. Based on the collected emotional data, an emotion analysis model using TensorFlow evaluates the user's emotional state and determines the priority of the task. The input is the analyzed task information and emotional data. The output is the task information with the assigned priority. For example, if the stress level is high, the task is set as "high priority."

[1939] Step 6:

[1940] The server prepares reminders and alerts and sends them to the user's device. The timing of the reminder is determined based on the configured priority, and notifications are sent using AWS SES or Google Firebase Cloud Messaging. For example, a notification saying "Tomorrow is the deadline for submitting a report" is sent. The input is high-priority task information. The output is a reminder notification.

[1941] Step 7:

[1942] A user sends a vague request from their device to the server. For example, a request might be, "I want to check the contents of last week's meeting." The server searches past communication data, summarizes the relevant information, and provides it to the user. It is possible to provide a summary that takes into account emotional data and helps the user feel at ease. The input is the user's request and past communication data. The output is summarized information. For example, summary information such as, "At last week's meeting, plans for launching a new product were discussed" is provided.

[1943] This allows users to efficiently manage tasks according to the context, allowing work to proceed smoothly.

[1944] (Application example 2)

[1945] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1946] To improve work efficiency and safety in factories, there is a need for a task management system that takes into account the emotional state of workers. However, current systems do not adequately adjust task priorities or suggest appropriate breaks that reflect the emotional state of workers, resulting in reduced work efficiency and a worsening working environment. Furthermore, there is a lack of ways to respond to ambiguous requests, which can increase worker stress and reduce the quality of work. Furthermore, there is a need for a method to centrally manage the wide variety of data collected by robots and respond appropriately in real time.

[1947] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1948] In this invention, the server includes means for collecting user communication data, means for analyzing the collected data and emotion data to automatically generate tasks, and means for determining the importance of the generated tasks and adjusting them based on the emotion data, thereby enabling improved work efficiency, stress reduction, and safety.

[1949] "User" refers to an individual or worker who uses this system.

[1950] "Communication data" refers to data including voice, text, and other information sent and received by users.

[1951] "Emotion data" refers to data including biometric information, facial data, etc. that indicates the user's emotional state.

[1952] A "task" refers to a job that includes work or instructions to be performed by a user.

[1953] A "robot" is an automatic machine that operates in a factory and receives and carries out instructions from the user.

[1954] "Server" refers to a central processing unit that analyzes data and notifies the user or robot of the results.

[1955] A "remind" refers to a notification that reminds the user of the existence of a particular task.

[1956] An "alert" refers to an urgent notification or warning given to the user.

[1957] "Priority adjustment" refers to changing the order in which tasks are executed or their importance based on emotional data, etc.

[1958] An "ambiguous request" is a request that is not specific but includes information or instructions the user is looking for.

[1959] "Summary information" refers to information extracted from past data and summarized concisely.

[1960] The present invention relates to a system for managing tasks by analyzing communication data and emotional data in order to improve work efficiency and reduce worker stress in factories. This system collects communication data and emotional data from users (workers), and a server analyzes this data to automatically generate and manage tasks. Specific embodiments are described below.

[1961] System configuration

[1962] 1. Collection of communication data

[1963] Users send and receive instructions and messages via voice and text through factory robots, and an application installed on the robot collects this data and sends it to a server.

[1964] 2. Collecting Emotional Data

[1965] The robot is equipped with biometric sensors and a facial recognition camera that collects real-time emotional data from the user, which is then sent to a server using secure communication methods.

[1966] Hardware and software used

[1967] Hardware

[1968] Factory robot: Collects communication data and executes work instructions.

[1969] Biometric sensors: Measure the user's heart rate and skin temperature and collect emotional data.

[1970] Facial recognition camera: Performs facial expression analysis and analyzes emotional data.

[1971] software

[1972] Natural language processing engine (NLP): Analyzes communication data and extracts tasks from the content of messages.

[1973] Sentiment Analysis Engine: Analyzes emotional data and determines the user's emotional state.

[1974] Data processing and calculation

[1975] Data collection

[1976] The communication and emotion data collected by the robot and sensors is sent to a server, where it is integrated and a dataset is generated for analysis.

[1977] Data analysis

[1978] The server uses a natural language processing engine to extract tasks from the received message. For example, if the message received is "Please start packing the next product," a task called "Pack the product" is generated.

[1979] The emotion analysis engine analyzes the user's emotional state and determines whether the user is feeling stressed based on emotional data (e.g., elevated heart rate and facial expression data obtained through facial recognition).

[1980] Task creation and priority adjustment

[1981] Task importance determination

[1982] The server determines the importance of the generated tasks and adjusts the importance based on the emotional data. For example, if the user is under stress, it will set urgent tasks as high priority and postpone less urgent tasks.

[1983] Reminders and notifications

[1984] The server sends reminders and alerts to the user's device and robot at appropriate times based on task priority, such as notifications to "start the next task" or reminders to "take a break."

[1985] Dealing with ambiguous requests

[1986] Ambiguous Request Analysis

[1987] The server analyzes a user's vague request (e.g., "I want to check the details of last week's meetings") and searches for relevant past communication data. It then generates summary information and provides it to the user, allowing the user to quickly obtain the information they need.

[1988] Specific examples

[1989] 1. Generate work instructions

[1990] A factory robot receives a voice command: "Start packing the next product."

[1991] The robot sends this instruction data and emotional data indicating that the worker is feeling stressed to a central server.

[1992] The server analyzes the data and generates a task called "Start packing the next product."

[1993] The server sets the task's importance as "high."

[1994] The server sends a notification to the worker saying, "Your stress is increasing, so please take a break before starting work."

[1995] 2. Ambiguous requests

[1996] A worker tells the robot a request: "I'd like to review the contents of last week's meeting."

[1997] The robot sends the request and emotional data indicating that the worker is feeling impatient to the server.

[1998] The server searches past communication data and summarizes relevant content.

[1999] The server sends the summary information to the worker along with a message urging them to "please take your time to check, as we are feeling impatient."

[2000] Prompt Sentence Examples

[2001] "Generate work tasks and adjust priorities based on the following work instruction data and emotion data."

[2002] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2003] Step 1:

[2004] Users send instructions and messages via voice or text to factory robots, and these communications data are collected by the robots, sometimes using software that converts voice input into text.

[2005] Input: User voice commands and text messages

[2006] Data processing: converting voice data to text, collecting text data

[2007] Output: Communication data

[2008] Step 2:

[2009] The robot collects user emotional data using biometric sensors and a facial recognition camera, which record heart rate, skin temperature, and facial expression data.

[2010] Input: User's biometric information (heart rate, skin temperature, facial expression, etc.)

[2011] Data processing: collection of biometric information, conversion of data from sensors

[2012] Output: Emotion data

[2013] Step 3:

[2014] The communication and emotion data collected by the robot is sent to a server using a secure communication protocol, and the data is encrypted.

[2015] Input: communication data, emotion data

[2016] Data processing: Data encryption

[2017] Output: Encrypted data (for sending to server)

[2018] Step 4:

[2019] The server uses a natural language processing engine to analyze the communication data it receives and automatically generate tasks. Tasks to be done are extracted from the message content.

[2020] Input: Encrypted data

[2021] Data processing: Decoding data and analyzing it with a natural language processing engine

[2022] Output: The generated tasks

[2023] Step 5:

[2024] The server uses an emotion analysis engine to analyze the collected emotional data, thereby determining the user's emotional state and recognizing conditions such as tension or stress.

[2025] Input: Emotion data

[2026] Data processing: Analysis using a sentiment analysis engine

[2027] Output: User's emotional state

[2028] Step 6:

[2029] The server determines the importance of the generated tasks and adjusts the importance based on emotional data. For example, if the user is under stress, tasks with high urgency are assigned a higher priority.

[2030] Input: Generated task, user's emotional state

[2031] Data processing: Task priority determination and adjustment

[2032] Output: Adjusted task priorities

[2033] Step 7:

[2034] The server sends reminders and alerts to users and robots at appropriate times based on task priority. The server creates notification content so that users can understand it quickly.

[2035] Input: Adjusted task priority

[2036] Data Processing: Creating reminders and alerts

[2037] Output: Reminder and alert notifications

[2038] Step 8:

[2039] The server receives a user's vague request, searches past communication data, and generates summary information, thereby quickly providing the information the user needs.

[2040] Input: Ambiguous request

[2041] Data processing: Searching past data and generating summary information

[2042] Output: Summary information

[2043] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2044] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2045] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2046] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2047] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2048] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2049] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2050] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2051] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2052] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2053] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2054] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2055] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2056] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2057] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2058] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2059] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2060] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2061] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2062] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2063] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2064] The following is further disclosed regarding the above embodiment.

[2065] (Claim 1)

[2066] A means for collecting user communication data;

[2067] A means for analyzing the collected data and automatically generating tasks;

[2068] a means for determining and notifying the importance of the generated task;

[2069] A means to search and provide necessary information from past interactions,

[2070] A system including:

[2071] (Claim 2)

[2072] 10. The system according to claim 1, further comprising means for setting reminders or alerts based on the importance of the task and notifying the user of the reminders or alerts on the user's terminal.

[2073] (Claim 3)

[2074] 10. The system of claim 1, further comprising means for analyzing the user's ambiguous request and providing summary information from relevant historical data.

[2075] "Example 1"

[2076] (Claim 1)

[2077] means for collecting user communication data;

[2078] A means for analyzing the collected data and automatically generating tasks;

[2079] a means for evaluating the importance of the generated tasks;

[2080] a means for sending a notification to a user's terminal before the task deadline approaches;

[2081] a means for analyzing a user's ambiguous request and providing summary information from relevant historical data;

[2082] A system including:

[2083] (Claim 2)

[2084] 10. The system according to claim 1, further comprising means for setting reminders or alerts based on the importance of the task and notifying the user of the reminders or alerts on the user's terminal.

[2085] (Claim 3)

[2086] 10. The system of claim 1, further comprising means for searching past communication data and providing a summary of required information.

[2087] "Application Example 1"

[2088] (Claim 1)

[2089] A means for collecting user communication data;

[2090] A means for analyzing the collected data and automatically generating tasks;

[2091] a means for determining and notifying the importance of the generated task;

[2092] A means to search and provide necessary information from past interactions,

[2093] a means for issuing instructions to automated equipment used in the factory;

[2094] A system including:

[2095] (Claim 2)

[2096] 10. The system according to claim 1, further comprising means for setting reminders or alerts based on the importance of the task and notifying the user of the reminders or alerts on the user's terminal.

[2097] (Claim 3)

[2098] 10. The system of claim 1, further comprising means for analyzing the user's ambiguous request and providing summary information from relevant historical data.

[2099] "Example 2: Combining Emotion Engines"

[2100] (Claim 1)

[2101] A means for collecting user communication data;

[2102] A means for analyzing the collected data and automatically generating tasks;

[2103] a means for determining and notifying the importance of the generated task;

[2104] means for collecting user emotion data;

[2105] a means for adjusting task importance based on the emotion data;

[2106] A means to search and provide necessary information from past interactions,

[2107] A system including:

[2108] (Claim 2)

[2109] 10. The system according to claim 1, further comprising means for setting reminders or alerts based on the importance of the task and notifying the user of the reminders or alerts on the user's terminal.

[2110] (Claim 3)

[2111] 10. The system of claim 1, further comprising means for analyzing the user's ambiguous request and providing summary information from relevant historical data.

[2112] "Application example 2 when combining emotion engines"

[2113] (Claim 1)

[2114] A means for collecting user communication data;

[2115] A means for automatically generating tasks by analyzing the collected data and emotion data;

[2116] a means for determining the importance of the generated tasks and adjusting it based on emotion data;

[2117] A means to search for necessary information from past interactions and provide it taking into account emotional data, and

[2118] means for transmitting the data collected by the robot to a server;

[2119] A means of sending reminders and alerts to the user's device;

[2120] A system including:

[2121] (Claim 2)

[2122] 10. The system of claim 1, further comprising means for setting reminders and alerts based on task importance and notifying the user and the robot.

[2123] (Claim 3)

[2124] 10. The system of claim 1, further comprising means for analyzing the user's ambiguous request and providing summary information from relevant historical data. [Explanation of symbols]

[2125] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting user communication data; A means for analyzing the collected data and automatically generating tasks; a means for determining and notifying the importance of the generated task; A means to search and provide necessary information from past interactions, A system including:

2. The system according to claim 1 , further comprising means for setting reminders and alerts based on the importance of the tasks and notifying the user of the reminders and alerts on the user's terminal.

3. The system of claim 1 further comprising means for analyzing a user's ambiguous request and providing summary information from relevant historical data.

Images