system

Abstract

We provide the system. [Solution] A means for the user to input routine tasks in text format, A means of analyzing the entered work content and dividing it into specific tasks, A method for training a machine learning model based on the analyzed task, A means of distributing tasks between users and automated systems using a trained learning model, A means of executing assigned tasks and displaying their progress to the user, A means of obtaining user feedback and updating the learning model. A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In many modern business environments, workers spend a lot of time on routine and repetitive tasks. Such tasks often impede efficiency and prevent concentration on important creative tasks. In addition, long working hours disrupt workers' work-life balance and increase stress. To solve these problems, a method of efficiently automating routine tasks and enabling humans and automated systems to cooperate in performing tasks is needed.

Means for Solving the Problems

[0005] This invention provides a system in which a user inputs routine tasks in text format, and the system analyzes this input to divide it into specific tasks. Furthermore, it trains a machine learning model based on the analyzed tasks and uses this trained model to distribute tasks between the user and an automated system (copy AI). This system includes a dashboard that displays the progress of tasks to the user and provides functions for user task modification and feedback. It also includes a function to update the trained model based on user feedback. As a result, routine tasks are efficiently automated, enabling humans and automated systems to work together, leading to improved work efficiency and work-life balance.

[0006] "Routine tasks" refer to standardized tasks that users perform repeatedly on a daily basis.

[0007] A "user" refers to an individual or organization that uses this system to automate routine tasks.

[0008] "Text format" refers to a format in which users input work details as a string of characters.

[0009] "Analysis" refers to the process of structuring input text-based work content using technologies such as natural language processing, and then dividing it into specific tasks.

[0010] A "task" refers to an individual, specific unit of work within the analyzed business process.

[0011] A "machine learning model" refers to an algorithm or statistical model that learns from analyzed tasks and uses those results to efficiently distribute and execute those tasks.

[0012] "Training" refers to the process of inputting business data into a machine learning model and allowing it to effectively learn patterns.

[0013] An "automation system" refers to hardware and software that automatically executes analyzed and distributed tasks.

[0014] "Distribution" refers to the process of effectively assigning tasks between users and automated systems.

[0015] "Progress" refers to the process and state of a task as it is being executed.

[0016] A "dashboard" refers to an interface that visually displays the progress of a task in real time.

[0017] "Feedback" refers to evaluations and corrections that users provide regarding tasks they have performed.

[0018] "Updating" refers to the process of improving machine learning models by incorporating user feedback. [Brief explanation of the drawing]

[0019] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0021] First, the language used in the following description will be explained.

[0022] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Further, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of the arithmetic unit include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] Understood. The "Modes for Carrying Out the Invention" are shown below.

[0041] This invention is a system designed to enable users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[0042] System program configuration and specific operation

[0043] 1. Collect information about the work from the user.

[0044] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[0045] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[0046] 2. Analyze the work content and generate tasks.

[0047] Terminal: Performs processing to send the work details entered by the user to the server.

[0048] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[0049] 3. Creating and optimizing the learning model

[0050] Server: Trains a machine learning model based on the analyzed task list. The model used here learns the user's work patterns and uses this knowledge to improve future task allocation.

[0051] Terminal: Equipped with a function to visually display the progress and accuracy of the learning model to the user.

[0052] 4. Division and execution of tasks

[0053] Server: Using a learning model, it distributes the generated tasks to "users" and "automation systems (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[0054] Server: Issues instructions to the copy AI to perform specific tasks. The server also uses the Calendar API and Email API to execute tasks.

[0055] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[0056] 5. User Verification and Intervention

[0057] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard.

[0058] User: Review the task results and make corrections or provide feedback as needed. For example, adjust the content of the notification email.

[0059] Terminal: Collects user feedback and sends it to the server.

[0060] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0061] Specific example

[0062] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0063] 1. User: Enter the following text for the job description: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[0064] 2. Terminal: Sends the input content to the server.

[0065] 3. Server: Analyzes the work content and divides it into two tasks: "setting up a meeting" and "sending notification emails".

[0066] 4. Server: Trains machine learning models based on the analysis results.

[0067] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[0068] 6. Server: Automatically schedule meetings using the Calendar API.

[0069] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[0070] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[0071] 9. Terminal: Send feedback to the server.

[0072] 10. Server: Update the learning model based on feedback.

[0073] The above describes a specific embodiment for carrying out this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[0074] The following describes the processing flow.

[0075] Understood. The processing steps are explained in detail below.

[0076] Step 1:

[0077] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and multiple selection options where users can enter details about their tasks.

[0078] Step 2:

[0079] User: Enter task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0080] Step 3:

[0081] Terminal: Retrieves the entered work details and sends them to the server for analysis.

[0082] Step 4:

[0083] Server: Sends the received text data to the natural language processing engine and starts the analysis. The analysis structures the business content and divides it into specific tasks.

[0084] Step 5:

[0085] Server: Based on the analysis results, it generates specific tasks. For example, it might divide the data into two tasks: "Set up a meeting" and "Send a notification email."

[0086] Step 6:

[0087] Server: Inputs the generated task list into a machine learning engine to learn the user's work patterns.

[0088] Step 7:

[0089] Server: Uses a learned model to determine the optimal way to distribute tasks.

[0090] Step 8:

[0091] Server: Distributes tasks between "users" and "automation systems (copy AI)". For example, assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[0092] Step 9:

[0093] Server: Issues task execution instructions to the automation system. For example, it can use the Calendar API to automatically schedule meetings.

[0094] Step 10:

[0095] Terminal: Provides users with a dashboard that displays task progress in real time.

[0096] Step 11:

[0097] User: Check the progress and results of completed tasks through the dashboard.

[0098] Step 12:

[0099] User: Modify the task results as needed and provide feedback.

[0100] Step 13:

[0101] Terminal: Collects user feedback and sends it to the server.

[0102] Step 14:

[0103] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0104] The above outlines the specific processing steps for implementing this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[0105] (Example 1)

[0106] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0107] In today's business environment, routine tasks consume a great deal of time and effort while adding little value, making efficient automation of these tasks essential. However, routine tasks are diverse, and there is a lack of means to accurately analyze each task and automate it appropriately. Furthermore, there are few systems that allow for real-time monitoring of task progress or systems that update models based on user feedback. There is a need for highly practical automation systems to address these challenges.

[0108] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0109] In this invention, the server includes means for users to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, and means for training a machine learning model based on the analyzed tasks. This enables efficient automation of routine tasks, reduces the burden on users, and improves operational efficiency.

[0110] A "user" is an individual or group that uses the system to automate routine tasks.

[0111] "Routine tasks" are work or tasks that are performed repeatedly at regular intervals.

[0112] "Text format" refers to a method of inputting information as a string of characters, allowing users to freely enter text and data.

[0113] "Analysis" is the process of breaking down input data and business operations and classifying them into specific patterns or elements.

[0114] A "task" is an individual work or unit of work performed to achieve a specific objective.

[0115] A "machine learning model" is an algorithm that learns specific patterns based on data and uses them to make predictions and decisions.

[0116] "Training" is the process by which a machine learning model analyzes data and optimizes the model in order to make the best predictions and decisions.

[0117] An "automation platform" is a system or software designed to automatically perform specific tasks.

[0118] A "Calendar API" is a programmatic interface for creating and managing schedules in conjunction with external calendar systems.

[0119] A "mail API" is a programmatic interface for sending and receiving emails in conjunction with external mail servers and services.

[0120] A "dashboard" is a user interface that visually displays the progress of tasks and various metrics.

[0121] "Feedback" refers to the opinions and evaluations provided by users regarding the output results and operation of a system.

[0122] This invention is a system designed to enable users to efficiently automate routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[0123] Program processing

[0124] Collect information about the work performed by the user.

[0125] The terminal first displays an interface for the user to input routine tasks. This interface includes text boxes and selection options.

[0126] Users input routine tasks into the interface in text format. For example, they might enter a specific task such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0127] The terminal validates the entered data and prompts the user to correct any errors.

[0128] Analyze the business process and generate tasks.

[0129] The terminal sends the work details that have passed validation to the server.

[0130] The server analyzes the received business content using a natural language processing engine (e.g., a natural language processing API). As a result of the analysis, the business content is divided into specific tasks. For example, it might be divided into "setting up a meeting" and "sending a notification email."

[0131] The server saves the analysis results to an internal database and generates a task list.

[0132] Creating and optimizing learning models

[0133] The server trains a machine learning model (e.g., a machine learning library) based on the generated task list. The data used here consists of past business data and feedback history.

[0134] The device visualizes and displays training progress and accuracy to the user, using graphs and statistical information.

[0135] The server evaluates the trained model and optimizes it as needed.

[0136] Division and execution of tasks

[0137] The server uses a trained model to distribute tasks between "users" and "automation platforms." For example, it might assign "setting up a meeting" to the automation platform and "sending notification emails" to users.

[0138] The server issues instructions to the automation platform, using the calendar API and email API to perform specific tasks. For example, it might automatically add a new meeting to the calendar.

[0139] The device provides users with a dashboard that displays the progress of tasks in real time.

[0140] User verification and intervention

[0141] The device notifies the user of the results of the completed tasks and displays them on the dashboard.

[0142] Users review the task results and make corrections or provide feedback as needed. For example, they might adjust the content of notification emails.

[0143] The device collects user feedback and sends it to the server.

[0144] The server updates its learning model based on the feedback, optimizing task allocation and execution for the next time.

[0145] Specific example

[0146] For example, to automate the scheduling of a weekly meeting held by a member of the marketing department:

[0147] 1. User: Enter the task description in text format: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[0148] 2. Terminal: Sends the input content to the server.

[0149] 3. Server: Analyze the work content and divide it into two tasks: "Set up a meeting" and "Send notification emails."

[0150] 4. Server: Trains machine learning models based on the analysis results.

[0151] 5. Server: Automate meeting setup to the platform and distribute notification email sending to users.

[0152] 6. Server: Automatically schedule meetings using the Calendar API.

[0153] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[0154] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[0155] 9. Terminal: Send feedback to the server.

[0156] 10. Server: Updates the learning model based on feedback.

[0157] Examples of prompt statements

[0158] For example, input the following prompt message into the AI ​​model:

[0159] "How can I set up a meeting every Monday at 9 AM and automatically send notification emails to participants?"

[0160] "Please suggest the optimal task breakdown method for automating recurring tasks."

[0161] This allows the system to provide specific steps for automating tasks that meet the user's needs.

[0162] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0163] Step 1: Enter details of the work

[0164] Terminal: First, an interface is displayed for the user to input routine tasks. This interface includes text boxes and selection options.

[0165] Input: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0166] Operation: The terminal receives the input data and temporarily stores it in its internal data storage.

[0167] Step 2: Validation of the work content

[0168] Terminal: Start the validation process. Verify that the format and content of the entered data are correct.

[0169] Input: Text data entered by the user.

[0170] Data processing: Perform validation on input data, including grammatical error checks and verification of required fields.

[0171] Output: Generates validation results and notifies the user if there are any errors.

[0172] Action: The terminal displays error messages and correction requests to the user.

[0173] Step 3: Submit the work details

[0174] Terminal: Sends the business details that have passed validation to the server.

[0175] Input: Text data that has passed validation.

[0176] Data processing: Encode data into a format that the server can understand.

[0177] Output: Details of the tasks to be sent to the server.

[0178] Operation: The terminal sends data to the server using methods such as HTTP requests.

[0179] Step 4: Analysis of Business Operations

[0180] Server: Analyzes the received work content using a natural language processing engine.

[0181] Input: Text data sent from the device.

[0182] Data processing: Analyze text using a natural language processing engine and break it down into specific tasks.

[0183] Output: Analyzed task list.

[0184] Operation: The server calls a natural language processing API and saves the analysis results to an internal database.

[0185] Step 5: Generate a task list

[0186] Server: Generates a list of executable tasks based on the analysis results.

[0187] Input: Analyzed business operations.

[0188] Data processing: Set the attributes of the task (e.g., deadline, assignee, importance, etc.).

[0189] Output: Completed task list.

[0190] Operation: The server composes a task list and passes it on to the next processing step.

[0191] Step 6: Training the machine learning model

[0192] Server: Trains machine learning models based on the task list.

[0193] Input: Past business data and analyzed task list.

[0194] Data processing: Input data into the model and run the learning algorithm.

[0195] Output: Trained machine learning model.

[0196] Operation: The server calls machine learning libraries to train the model.

[0197] Step 7: Task Distribution

[0198] Server: Uses trained models to distribute tasks to "users" and "automation platforms".

[0199] Input: Trained model and task list.

[0200] Data processing: Execute algorithms that optimally distribute tasks based on the model.

[0201] Output: Distributed task list.

[0202] Operation: The server issues instructions to the automation platform and assigns tasks.

[0203] Step 8: Execute the task

[0204] Server: Executes the specified task.

[0205] Input: Distributed task list.

[0206] Data calculations: Generate requests to call the Calendar API and Mail API.

[0207] Output: Execution result.

[0208] Operation: The server calls the API to set up meetings and send notification emails.

[0209] Step 9: Displaying Task Progress

[0210] Terminal: Provides a dashboard that displays task progress in real time.

[0211] Input: Execution results and progress data sent from the server.

[0212] Data processing: Convert data into a format that is easy to visualize.

[0213] Output: Visual progress display on the dashboard.

[0214] Operation: The device displays the progress using graphs and charts.

[0215] Step 10: Gathering Feedback and Updating the Model

[0216] Device: Collects user feedback.

[0217] Input: User feedback comments and suggested improvements.

[0218] Output: Feedback data.

[0219] Action: The device sends feedback to the server.

[0220] Server: Updates the learning model based on the feedback received.

[0221] Input: Feedback data.

[0222] Data processing: Retrain the model to improve accuracy.

[0223] Output: Updated machine learning model.

[0224] Operation: The server saves the latest model and applies it to subsequent operations.

[0225] The above outlines the specific processing steps of this system. This system allows users to efficiently automate routine tasks.

[0226] (Application Example 1)

[0227] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0228] In modern factories, manual processing of routine tasks is time-consuming and labor-intensive, reducing production efficiency. Furthermore, there is a need to reduce the burden on workers, improve work-life balance, and minimize human error. However, the problem is that conventional systems lack efficient methods to address these challenges.

[0229] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0230] In this invention, the server includes means for a user to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for sending instructions to the automation robot to execute the distributed tasks, means for displaying the progress to the user, and means for obtaining user feedback and updating the learning model. As a result, routine tasks in the factory are efficiently automated, reducing the burden on workers, improving work efficiency, and reducing errors.

[0231] A "user" is the entity that uses the system to input and manage routine tasks.

[0232] "Routine tasks" refer to standardized tasks or duties that are performed repeatedly.

[0233] "Text format" refers to the format in which information is entered as text characters.

[0234] "Means" refer to the methods or processes used to achieve a specific objective.

[0235] "Analysis" is the process of understanding and breaking down the entered business data.

[0236] A "task" is a division of work content into specific actions or tasks.

[0237] A "machine learning model" is a program that uses algorithms and data to perform pattern recognition and prediction.

[0238] "Training" is the process of using data to allow a machine learning model to learn.

[0239] An "automation system" is a set of hardware and software designed to automate routine tasks.

[0240] "Distribution" is the process of assigning analyzed tasks to users and automated systems.

[0241] An "automation robot" is a machine used to perform routine tasks within a factory.

[0242] "Sending instructions" means sending a command from the server to an automated robot to execute a task.

[0243] "Progress status" refers to information indicating the stage of a task.

[0244] "Displaying" means providing users with a visual representation of the progress or results.

[0245] "Feedback" refers to the process of communicating user opinions and requests for corrections to the system.

[0246] "Updating" is the process of improving a machine learning model based on the feedback received.

[0247] This invention is a system that allows users to efficiently automate routine tasks within a factory, improve productivity, and reduce the burden on workers. The specific configuration and operation of this system are described below.

[0248] System Configuration

[0249] The system consists of the following main components:

[0250] 1. User terminal: Provides an interface for users to input and manage routine tasks. Specifically, smartphones, tablets, PCs, etc., are used.

[0251] 2. Server: Analyzes the business processes, divides them into specific tasks, and trains machine learning models.

[0252] 3. Automation robots: These are automated devices used to perform routine tasks within a factory. Examples include ABB's IRB 6700 and Universal Robots' UR series.

[0253] Operation details

[0254] 1. Entering routine tasks:

[0255] Users input routine tasks in text format via their user terminals. The entered task details are sent to the server. For example, a user might input, "Check the machine oil at 6 PM every day."

[0256] 2. Analysis of business processes and generation of tasks:

[0257] The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "oil check" and "results report."

[0258] 3. Training machine learning models:

[0259] The server trains a machine learning model based on the analyzed task list. This model will then be used to distribute tasks.

[0260] 4. Task distribution and execution:

[0261] The server uses a trained machine learning model to distribute the generated tasks to the user and the automated robot. Specifically, it assigns "oil check" to the automated robot and "results report" to the user. The server sends instructions to the automated robot via an API.

[0262] 5. Display of progress and feedback:

[0263] An automated robot performs a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task's progress and provides corrections and feedback as needed. The server collects user feedback and updates the machine learning model.

[0264] Specific example

[0265] For example, consider automating parts inventory management. Using this system, a robot can check inventory at 8 AM every morning and automatically issue replenishment orders if any parts are missing. This enables rapid inventory management and reduces labor.

[0266] Example of a prompt

[0267] 1. "Check the machine's oil every day at 6 PM and notify us if there are any abnormalities."

[0268] 2. "Check the parts inventory every morning at 8:00 AM and issue replenishment orders if any are missing."

[0269] This invention not only efficiently automates routine tasks within the factory, but is also expected to reduce the burden on workers and improve operational efficiency. The procedure described above enables precise operation in an automated environment.

[0270] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0271] Step 1:

[0272] Entering routine tasks

[0273] Subject: User

[0274] Specific operation: Users access the system using their own devices (smartphones, tablets, PCs, etc.) and input routine tasks in text format.

[0275] Input: Routine task details entered by the user in text format (e.g., "Check the machine oil at 6 PM every day").

[0276] Output: The entered work details are sent to the server via the terminal.

[0277] Step 2:

[0278] Analysis of business processes and task generation

[0279] Subject: Server

[0280] Specific operation: The server analyzes the received business content using a natural language processing (NLP) engine and divides it into specific tasks.

[0281] Input: User-entered details of the work (in text format).

[0282] Data processing: Use an NLP engine to analyze text and break down business content into specific tasks.

[0283] Output: Parsed task list (e.g., "Oil check", "Result report").

[0284] Step 3:

[0285] Training of the machine learning model

[0286] Subject: Server

[0287] Specific operation: The server trains a machine learning model based on the parsed task list. It also utilizes past data to improve model performance.

[0288] Input: Parsed task list and past execution data.

[0289] Data operation: Train the model using machine learning algorithms.

[0290] Output: Trained machine learning model.

[0291] Step 4:

[0292] Task assignment and execution

[0293] Subject: Server, automated robot

[0294] Specific operation: The server uses the trained machine learning model to assign each task to a user or an automated robot. The assigned tasks are sent to the robot as instructions.

[0295] Input: Trained machine learning model and parsed task list.

[0296] Data operation: Determine the assignment based on task priority and content.

[0297] Output: Tasks instructed to the robot (e.g., "Instruction to perform an oil check").

[0298] Step 5:

[0299] Display of progress and feedback

[0300] Subject: Automated robot, server, user

[0301] Specific actions: The automated robot executes a task and reports its progress to the server. The server displays the information in real-time on the user terminal dashboard. The user checks the progress of the task and provides corrections or feedback as needed.

[0302] Input: Task progress data from the robot.

[0303] Data processing: Convert the progress data into a dashboard format.

[0304] Output: Progress displayed on the dashboard and feedback from the user. [[ID= twenty-five]]

[0305] Step 6:

[0306] Reflection of feedback and model update

[0307] Subject: Server

[0308] Specific actions: The server collects feedback from the user and updates the machine learning model based on it.

[0309] Input: Feedback data from the user.

[0310] Data calculation: Feed the feedback data into the machine learning algorithm to retrain the model.

[0311] Output: Updated machine learning model.

[0312] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0313] Understood. The "Modes for Carrying Out the Invention" are shown below.

[0314] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[0315] System program configuration and specific operation

[0316] 1. Collect information about the work from the user.

[0317] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[0318] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[0319] 2. Analyze the work content and generate tasks.

[0320] Terminal: Sends the entered work details to the server.

[0321] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[0322] 3. Utilizing the Emotional Engine

[0323] Terminal: When a user inputs work details, the emotion engine collects data to recognize the user's emotions. This includes using text analysis to read emotions from the text and facial recognition technology via a webcam.

[0324] Server: The emotion engine analyzes the user's emotions and determines task priorities based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[0325] 4. Creating and optimizing the learning model

[0326] Server: Trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[0327] Terminal: Visually displays the progress and accuracy of the learning model to the user.

[0328] 5. Division and execution of tasks

[0329] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (copy AI)." For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Task assignments are also adjusted based on the emotion engine.

[0330] Server: Issues instructions to an automated system to perform a specific task. For example, using the Calendar API to schedule a meeting.

[0331] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[0332] 6. User Verification and Intervention

[0333] Terminal: Notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[0334] User: Review the task results and make corrections or provide feedback as needed.

[0335] Terminal: Collects user feedback and sends it to the server.

[0336] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0337] Specific example

[0338] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0339] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[0340] 2. Terminal: Sends the input content to the server.

[0341] 3. Server: Analyzes the work content and divides it into two tasks: "set up a meeting" and "send notification emails." The emotion engine evaluates the user's stress level and adjusts the order of the tasks.

[0342] 4. Server: Trains the learning model based on the analysis results.

[0343] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[0344] 6. Server: Automatically schedule meetings using the Calendar API.

[0345] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[0346] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[0347] 9. Terminal: Send feedback to the server.

[0348] 10. Server: Update the learning model based on feedback.

[0349] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks, but also takes user emotions into consideration, enabling more efficient and less stressful work execution.

[0350] The following describes the processing flow.

[0351] Understood. The processing steps are explained in detail below.

[0352] Step 1:

[0353] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and selection options, allowing users to input details about their tasks. In addition, an emotion engine retrieves emotional data from the user's facial expressions and input patterns.

[0354] Step 2:

[0355] User: Enters specific task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." The emotion engine observes the user's input and recognizes emotions such as stress and anxiety.

[0356] Step 3:

[0357] Terminal: Retrieves the entered work details and sends them to the server. Simultaneously, it also sends the emotion data collected by the emotion engine to the server.

[0358] Step 4:

[0359] Server: The server analyzes the received text data using a natural language processing engine and divides the work content into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[0360] Step 5:

[0361] Server: Analyzes the emotional data provided by the emotion engine and evaluates the user's emotional state. Based on this evaluation, it adjusts the task prioritization and distribution method.

[0362] Step 6:

[0363] Server: Trains a machine learning model based on analysis results and sentiment data to learn user work patterns and sentiment patterns.

[0364] Step 7:

[0365] Server: Using a learning model, it distributes the generated tasks to the "user" and the "automation system (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Here, it utilizes data from the emotion engine to prioritize assigning difficult tasks when stress levels are low and easy tasks when stress levels are high.

[0366] Step 8:

[0367] Server: Issues instructions to an automated system to perform a specific task. For example, it can use a calendar API to automatically schedule meetings.

[0368] Step 9:

[0369] Terminal: Provides users with a dashboard that displays task progress in real time. Here, the sentiment engine also displays support messages and feedback tailored to the user's state.

[0370] Step 10:

[0371] User: Check the progress and results of completed tasks through the dashboard. Modify task results as needed.

[0372] Step 11:

[0373] Terminal: Collects user modifications and feedback and sends them to the server.

[0374] Step 12:

[0375] Server: Updates the learning model based on user feedback to further optimize task distribution and execution for future sessions.

[0376] Specific example

[0377] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0378] Step 1:

[0379] Terminal: "Displays an interface for inputting routine tasks and captures the user's facial expressions using an emotion engine."

[0380] Step 2:

[0381] User: "I typed, 'Set up a meeting every Monday at 9:00 AM and send a notification email to participants,' and my facial expression was recognized."

[0382] Step 3:

[0383] Terminal: "Send input content and sentiment data to the server."

[0384] Step 4:

[0385] Server: "Analyzes the business process and divides it into two tasks. Analyzes emotional data and evaluates the user's emotional state."

[0386] Step 5:

[0387] Server: "Adjust task priorities and distribution methods based on sentiment evaluations."

[0388] Step 6:

[0389] Server: "Train a machine learning model based on analysis results and sentiment data."

[0390] Step 7:

[0391] Server: "Assign the automated system to set up meetings and the users to send notification emails."

[0392] Step 8:

[0393] Server: "Automatically schedule meetings using the Calendar API."

[0394] Step 9:

[0395] Terminal: "Displays execution status in real time on the dashboard and shows sentiment-based messages."

[0396] Step 10:

[0397] User: "Check the task progress on the dashboard and make corrections as needed."

[0398] Step 11:

[0399] Terminal: "Send corrections and feedback to the server."

[0400] Step 12:

[0401] Server: "Update the learning model based on feedback."

[0402] The above outlines the specific processing steps for implementing this invention. This system not only efficiently automates routine tasks but also takes into account the user's emotional state, enabling more efficient and less stressful work execution.

[0403] (Example 2)

[0404] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0405] Traditional business automation systems fail to consider the user's emotional state when allocating or prioritizing tasks, potentially leading to user stress and decreased work efficiency. Furthermore, real-time updates of machine learning models based on user feedback are difficult, resulting in limited system adaptability.

[0406] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0407] In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for collecting user sentiment data based on the analyzed tasks, means for analyzing the collected sentiment data and determining task priorities, means for training a machine learning model based on the analyzed tasks and sentiment data, means for distributing tasks to the user and the automation system using the trained learning model, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables automation of tasks that take user sentiment into consideration and real-time system adaptation based on feedback.

[0408] A "user" refers to a person who uses the system to input data and provide feedback.

[0409] "Routine tasks" refer to repetitive tasks that users need to perform regularly.

[0410] "Text format" refers to a data format represented by strings of characters.

[0411] "Means" refers to the methods or devices used to achieve a specific objective.

[0412] "Job description" refers to the specific tasks and details of work that users input into the system.

[0413] "Analysis" refers to the process of breaking down input data and understanding its meaning and structure.

[0414] "Specific tasks" refer to individual work units that can be executed based on the analyzed business content.

[0415] "Emotional data" refers to information that indicates a user's emotional state. This includes facial expressions, tone of voice, and emotional expressions in text.

[0416] "Collecting emotional data" refers to the process of obtaining a user's emotions and storing them in an analyzable format.

[0417] "Emotional analysis" refers to the process of processing collected emotional data to understand the user's emotional state.

[0418] "Priority" refers to determining the order in which tasks are performed and their importance.

[0419] A "machine learning model" refers to an algorithm that learns specific patterns based on data and uses them to make future predictions and decisions.

[0420] "Training" refers to the process of using data to train a machine learning model to achieve an optimal state.

[0421] An "automation system" refers to a system of software or hardware designed to automatically perform specific tasks.

[0422] "Progress status" refers to information indicating the stage of a task.

[0423] "Feedback" refers to the evaluations and opinions that users provide to a system.

[0424] "Updating" refers to the process of improving existing machine learning models and systems using new information and feedback.

[0425] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks by coordinating various technologies, with terminals, servers, and users as the main components.

[0426] System configuration and operation

[0427] First, the system collects information about routine tasks from the user. In this process, the terminal displays an input interface to the user, who then inputs the task details in text format.

[0428] Specific actions

[0429] 1. Collect information about the work from the user.

[0430] Terminal: The terminal displays an interface for users to input routine tasks. This interface includes text boxes and selection options, allowing users to freely input task details. Software used includes HTML, CSS, and JavaScript (registered trademark).

[0431] User: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0432] 2. Analyze the work content and generate tasks.

[0433] Terminal: Sends the entered work details to the server via an HTTP request.

[0434] Server: The server uses a natural language processing engine (e.g., SpaCy, Transformer) to analyze the received business data. For example, it might break it down into specific tasks such as "setting up a meeting" and "sending notification emails." This clarifies the specific routine tasks that the system will handle.

[0435] 3. Utilizing the Emotional Engine

[0436] Terminal: When a user inputs work details, the terminal uses its camera and microphone to collect user emotion data. This is done using facial recognition technology (e.g., OpenCV, AWS® Rekognition) and speech analysis technology.

[0437] Server: The server analyzes the data collected using the emotion engine to understand the user's emotional state. Based on the collected emotional data, it determines task priorities. For example, if a user is feeling stressed, it adjusts the assignment to prioritize easier tasks.

[0438] 4. Creating and optimizing the learning model

[0439] Server: Trains a machine learning model based on the analyzed task and sentiment data. This training uses Scikit-learn and TENSORFLOW®. The trained model learns the user's work patterns and sentiment patterns and reflects them in subsequent execution.

[0440] Terminal: Use graphs and dashboards (e.g., Plotly, Grafana) to visually display training progress and accuracy to the user.

[0441] 5. Division and execution of tasks

[0442] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (e.g., Zapier or IFTTT)". For example, it might assign "setting up a meeting" to an automation system and "sending notification emails" to a user. The server also uses the Google® Calendar API, etc., to automate meeting setup and other tasks.

[0443] Terminal: Provides a dashboard to display task progress to the user in real time. Users can check the task execution status through the dashboard and intervene or correct as needed.

[0444] 6. User Verification and Intervention

[0445] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[0446] User: Review the task results and make corrections or provide feedback as needed.

[0447] Terminal: Sends collected feedback to the server.

[0448] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0449] Specific example

[0450] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0451] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[0452] 2. Terminal: Sends the input content to the server.

[0453] 3. Server: Analyzes work content and divides it into "meeting scheduling" and "sending notification emails." An emotion engine evaluates the user's stress level.

[0454] 4. Server: Trains the learning model based on the analysis results.

[0455] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[0456] 6. Server: Automatically schedule meetings using the Google Calendar API.

[0457] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[0458] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[0459] 9. Terminal: Send feedback to the server.

[0460] 10. Server: Update the learning model based on feedback.

[0461] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks but also enables appropriate task distribution that takes into account the user's emotions, resulting in more efficient and less stressful work performance.

[0462] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0463] Step 1:

[0464] Collect information about the work performed by the user.

[0465] Terminal: Displays an interface where the user can input work details. This interface includes text boxes and selection options. This allows the user to input details of routine tasks in text format.

[0466] Input: User's job description (e.g., "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants").

[0467] Output: Text data of the work details entered by the user.

[0468] Step 2:

[0469] Sending and analyzing work details

[0470] Terminal: Sends the entered work details to the server. This process is performed via an HTTP request.

[0471] Server: The server analyzes the received text data using a natural language processing engine (e.g., SpaCy, Transformer) and divides it into specific tasks.

[0472] Input: Text data of the work details entered by the user.

[0473] Output: Specific tasks analyzed (e.g., "Set up a meeting", "Send notification email").

[0474] Step 3:

[0475] Collection of emotional data

[0476] Terminal: When users input work details, the system collects emotional data using the camera and microphone. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[0477] Input: User's facial expressions and voice data.

[0478] Output: Collected emotional data (e.g., facial features, voice tone).

[0479] Step 4:

[0480] Analysis of emotional data

[0481] Server: The collected emotional data is analyzed by an emotion engine to understand the user's emotional state. Emotional scores and stress levels are calculated.

[0482] Input: Collected sentiment data.

[0483] Output: Sentiment score and stress level.

[0484] Step 5:

[0485] Training machine learning models

[0486] Server: Trains a machine learning model based on the analyzed task and sentiment data. This uses Scikit-learn or TensorFlow. The model learns the user's work patterns and sentiment patterns.

[0487] Input: Analyzed task and sentiment data.

[0488] Output: Trained machine learning model.

[0489] Step 6:

[0490] Task distribution

[0491] Server: Uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, assigning "setting up a meeting" to the automation system and "sending notification emails" to users.

[0492] Input: A trained machine learning model and the task to be analyzed.

[0493] Output: Distributed tasks.

[0494] Step 7:

[0495] Task execution and progress display

[0496] Server: Issues instructions to the automation system to execute tasks. Specifically, it uses the Google Calendar API to schedule meetings.

[0497] Terminal: Provides a dashboard to display task progress to the user in real time.

[0498] Input: Assigned tasks.

[0499] Output: Tasks performed and their progress.

[0500] Step 8:

[0501] User verification and intervention

[0502] Terminal: Displays the results of completed tasks on the dashboard and notifies the user.

[0503] User: Review the task results and make corrections or provide feedback as needed.

[0504] Terminal: Sends corrections and feedback to the server.

[0505] Server: Updates the machine learning model based on feedback.

[0506] Input: User feedback.

[0507] Output: Updated machine learning model.

[0508] These processing steps enable the system to efficiently automate users' routine tasks and achieve task distribution that takes emotions into account.

[0509] (Application Example 2)

[0510] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0511] Modern factories and logistics centers have numerous routine tasks that must be handled efficiently. In particular, since employee performance fluctuates depending on their emotional state, task allocation that takes emotions into account is crucial. However, current systems often fail to consider user emotions when assigning tasks, limiting efficiency. Furthermore, assigning tasks without considering employee emotions can cause stress, leading to decreased satisfaction and productivity. Therefore, a system is needed that not only streamlines routine tasks but also dynamically reflects user emotions in task allocation.

[0512] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for analyzing emotional data and distributing and adjusting tasks according to the emotional state, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables dynamic task distribution that takes the user's emotions into consideration, making it possible to simultaneously achieve increased work efficiency and reduced stress.

[0513] "Routine tasks" refer to standardized tasks that are performed repeatedly on a daily basis.

[0514] "Text format" refers to a format that uses strings of characters to represent information.

[0515] "Analysis" refers to the process of breaking down input information and understanding its contents in detail.

[0516] A "task" refers to an individual work or activity performed to achieve a specific objective.

[0517] A "machine learning model" refers to the structure of an algorithm that learns from data and performs predictions and classifications.

[0518] "Training" refers to the process of using data to allow a machine learning model to learn.

[0519] An "automation system" refers to a system that performs specific tasks or processes without human intervention.

[0520] "Distribution" refers to the process of allocating specific resources or tasks to multiple targets.

[0521] "Emotional data" refers to data that represents the emotional state of a user.

[0522] "Analysis" refers to the process of examining data in detail and understanding its patterns and meanings.

[0523] "Adjustment" refers to changing the arrangement or content based on specific conditions.

[0524] "Execution" refers to actually carrying out the planned tasks.

[0525] "Progress status" refers to information that indicates the degree of completion during the task's execution process.

[0526] "Display" refers to the visual presentation of information.

[0527] "Feedback" refers to providing information or opinions about a particular action or outcome.

[0528] "Updating" refers to improving or changing existing data or systems based on new information.

[0529] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting the user's emotions in the work process. Specific embodiments are described in detail below.

[0530] System Configuration

[0531] This system automates tasks through the collaboration of terminals, servers, and users. The main hardware used includes smart glasses and factory robots, while the software includes EmotionEngine (emotion recognition engine), TaskParser (task analysis engine), RobotController (robot control API), and SmartGlass®es (smart glasses API).

[0532] Specific actions

[0533] 1. Collect information about the work from the user.

[0534] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, where users can enter specific details about their tasks.

[0535] Users input task details such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0536] 2. Analyze the work content and generate tasks.

[0537] The terminal sends the entered work information to the server.

[0538] The server analyzes the received work content using TaskParser and divides it into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[0539] 3. Utilizing the Emotional Engine

[0540] When a user inputs work details, the terminal collects data for EmotionEngine to recognize the user's emotions. This includes text analysis and facial recognition via the camera.

[0541] The server uses EmotionEngine to analyze the user's emotions and prioritizes tasks based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[0542] 4. Creating and optimizing the learning model

[0543] The server trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[0544] 5. Division and execution of tasks

[0545] The server uses a trained learning model to distribute tasks between "users" and "automation systems." For example, it might assign "setting up a meeting" to the automation system and "sending notification emails" to the user.

[0546] The server issues instructions to the automated system to perform specific tasks. For example, it might use the Calendar API to schedule a meeting.

[0547] 6. User Verification and Intervention

[0548] The device notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[0549] Users review the task results and make corrections or provide feedback as needed.

[0550] Specific example

[0551] For example, in the automation of production operations in a factory:

[0552] 1. The user enters "replenish materials on the packaging line" as their job description, and sentiment data is also collected.

[0553] 2. The terminal sends the input content to the server.

[0554] 3. The server analyzes the work content and divides it into two tasks: "preparing materials" and "replenishing materials." The emotion engine assesses the user's stress level and adjusts the order of the tasks.

[0555] 4. The server trains a learning model based on the analysis results.

[0556] 5. The server distributes the task of "preparing materials" to the automated system and the task of "replenishing materials" to the user.

[0557] 6. The server instructs the robot to "prepare materials," and it executes this automatically.

[0558] 7. The terminal displays the task progress in real time and shows appropriate support messages.

[0559] 8. The user confirms that the task is complete and provides feedback as needed.

[0560] Example of a prompt

[0561] "It seems that worker A is unhappy. Please have them handle the easier tasks first."

[0562] "The next task is 'replenishing materials on the packaging line.' Due to its high stress level, please assign this task to a robot."

[0563] This allows for efficient automation of each process while simultaneously enabling flexible task management that reflects user emotions, resulting in improved overall productivity and satisfaction.

[0564] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0565] Step 1:

[0566] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, allowing users to input specific details about their tasks. The input data here consists of text or voice information describing the user's work. For example, specific tasks such as "replenishing materials on the packaging line" might be entered.

[0567] Step 2:

[0568] The terminal transmits the entered work information to the server. At this time, the entered text or voice data is transferred to the server and prepared for analysis. The role of the terminal is to transmit the collected data to the server quickly and accurately.

[0569] Step 3:

[0570] The server uses TaskParser to analyze the received business information and divides it into specific tasks. For example, it might divide it into tasks such as "prepare materials" and "replenish materials." This process utilizes natural language processing technology to analyze the text data and identify each business task.

[0571] Step 4:

[0572] The terminal uses EmotionEngine to collect emotional data when users input work-related information. The collected data includes emotion determination through text analysis and facial recognition via the camera. The input data represents information about the user's emotional state, such as stress levels and satisfaction levels.

[0573] Step 5:

[0574] The server analyzes emotional data using EmotionEngine and determines task priorities based on the results. For example, if a user's stress level is high, it will assign them easier tasks first. This process involves performing data calculations that prioritize tasks using emotional analysis data.

[0575] Step 6:

[0576] The server trains a machine learning model based on the analyzed task and sentiment data. In this process, it uses a large amount of historical task and sentiment state data to generate a model that will help with future task allocation and sentiment regulation. The input data is the analyzed task and sentiment data, and the output is the updated machine learning model.

[0577] Step 7:

[0578] The server uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, it might assign "preparing materials" to the automation system and "replenishing materials" to the user. This process involves data calculations that use the machine learning model to determine the optimal task distribution.

[0579] Step 8:

[0580] The server issues instructions to the automated system to perform specific tasks. For example, it might use RobotController to instruct a factory robot to prepare materials. In this process, specific operation commands are generated as output data that are sent to the robot.

[0581] Step 9:

[0582] The device displays the task progress to the user in real time. Here, the SmartGlasses API is used to visually display the task progress on smart glasses. The displayed data includes the task's progress and completion status.

[0583] Step 10:

[0584] Users review the results of completed tasks and make corrections or provide feedback as needed. This feedback can include comments such as "Task complete" or "Needs correction." This allows the system to reflect the user's intentions.

[0585] Step 11:

[0586] The terminal sends user feedback to the server. This feedback data is used to further optimize task distribution and execution in the future.

[0587] Step 12:

[0588] The server updates the machine learning model based on the feedback received. This allows the model to reflect the latest data, enabling more accurate task allocation and sentiment adjustment. The output data is the updated machine learning model.

[0589] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0590] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0591] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0592] [Second Embodiment]

[0593] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0594] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0595] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0596] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0597] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0598] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0599] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0600] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0601] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0602] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0603] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0604] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0605] Understood. The "Modes for Carrying Out the Invention" are shown below.

[0606] This invention is a system designed to enable users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[0607] System program configuration and specific operation

[0608] 1. Collect information about the work from the user.

[0609] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[0610] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[0611] 2. Analyze the work content and generate tasks.

[0612] Terminal: Performs processing to send the work details entered by the user to the server.

[0613] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[0614] 3. Creating and optimizing the learning model

[0615] Server: Trains a machine learning model based on the analyzed task list. The model used here learns the user's work patterns and uses this knowledge to improve future task allocation.

[0616] Terminal: Equipped with a function to visually display the progress and accuracy of the learning model to the user.

[0617] 4. Division and execution of tasks

[0618] Server: Using a learning model, it distributes the generated tasks to "users" and "automation systems (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[0619] Server: Issues instructions to the copy AI to perform specific tasks. The server also uses the Calendar API and Email API to execute tasks.

[0620] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[0621] 5. User Verification and Intervention

[0622] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard.

[0623] User: Review the task results and make corrections or provide feedback as needed. For example, adjust the content of the notification email.

[0624] Terminal: Collects user feedback and sends it to the server.

[0625] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0626] Specific example

[0627] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0628] 1. User: Enter the following text for the job description: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[0629] 2. Terminal: Sends the input content to the server.

[0630] 3. Server: Analyzes the work content and divides it into two tasks: "setting up a meeting" and "sending notification emails".

[0631] 4. Server: Trains machine learning models based on the analysis results.

[0632] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[0633] 6. Server: Automatically schedule meetings using the Calendar API.

[0634] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[0635] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[0636] 9. Terminal: Send feedback to the server.

[0637] 10. Server: Update the learning model based on feedback.

[0638] The above describes a specific embodiment for carrying out this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[0639] The following describes the processing flow.

[0640] Understood. The processing steps are explained in detail below.

[0641] Step 1:

[0642] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and multiple selection options where users can enter details about their tasks.

[0643] Step 2:

[0644] User: Enter task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0645] Step 3:

[0646] Terminal: Retrieves the entered work details and sends them to the server for analysis.

[0647] Step 4:

[0648] Server: Sends the received text data to the natural language processing engine and starts the analysis. The analysis structures the business content and divides it into specific tasks.

[0649] Step 5:

[0650] Server: Based on the analysis results, it generates specific tasks. For example, it might divide the data into two tasks: "Set up a meeting" and "Send a notification email."

[0651] Step 6:

[0652] Server: Inputs the generated task list into a machine learning engine to learn the user's work patterns.

[0653] Step 7:

[0654] Server: Uses a learned model to determine the optimal way to distribute tasks.

[0655] Step 8:

[0656] Server: Distributes tasks between "users" and "automation systems (copy AI)". For example, assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[0657] Step 9:

[0658] Server: Issues task execution instructions to the automation system. For example, it can use the Calendar API to automatically schedule meetings.

[0659] Step 10:

[0660] Terminal: Provides users with a dashboard that displays task progress in real time.

[0661] Step 11:

[0662] User: Check the progress and results of completed tasks through the dashboard.

[0663] Step 12:

[0664] User: Modify the task results as needed and provide feedback.

[0665] Step 13:

[0666] Terminal: Collects user feedback and sends it to the server.

[0667] Step 14:

[0668] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0669] The above outlines the specific processing steps for implementing this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[0670] (Example 1)

[0671] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0672] In today's business environment, routine tasks consume a great deal of time and effort while adding little value, making efficient automation of these tasks essential. However, routine tasks are diverse, and there is a lack of means to accurately analyze each task and automate it appropriately. Furthermore, there are few systems that allow for real-time monitoring of task progress or systems that update models based on user feedback. There is a need for highly practical automation systems to address these challenges.

[0673] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0674] In this invention, the server includes means for users to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, and means for training a machine learning model based on the analyzed tasks. This enables efficient automation of routine tasks, reduces the burden on users, and improves operational efficiency.

[0675] A "user" is an individual or group that uses the system to automate routine tasks.

[0676] "Routine tasks" are work or tasks that are performed repeatedly at regular intervals.

[0677] "Text format" refers to a method of inputting information as a string of characters, allowing users to freely enter text and data.

[0678] "Analysis" is the process of breaking down input data and business operations and classifying them into specific patterns or elements.

[0679] A "task" is an individual work or unit of work performed to achieve a specific objective.

[0680] A "machine learning model" is an algorithm that learns specific patterns based on data and uses them to make predictions and decisions.

[0681] "Training" is the process by which a machine learning model analyzes data and optimizes the model in order to make the best predictions and decisions.

[0682] An "automation platform" is a system or software designed to automatically perform specific tasks.

[0683] A "Calendar API" is a programmatic interface for creating and managing schedules in conjunction with external calendar systems.

[0684] A "mail API" is a programmatic interface for sending and receiving emails in conjunction with external mail servers and services.

[0685] A "dashboard" is a user interface that visually displays the progress of tasks and various metrics.

[0686] "Feedback" refers to the opinions and evaluations provided by users regarding the output results and operation of a system.

[0687] This invention is a system designed to enable users to efficiently automate routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[0688] Program processing

[0689] Collect information about the work performed by the user.

[0690] The terminal first displays an interface for the user to input routine tasks. This interface includes text boxes and selection options.

[0691] Users input routine tasks into the interface in text format. For example, they might enter a specific task such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0692] The terminal validates the entered data and prompts the user to correct any errors.

[0693] Analyze the business process and generate tasks.

[0694] The terminal sends the work details that have passed validation to the server.

[0695] The server analyzes the received business content using a natural language processing engine (e.g., a natural language processing API). As a result of the analysis, the business content is divided into specific tasks. For example, it might be divided into "setting up a meeting" and "sending a notification email."

[0696] The server saves the analysis results to an internal database and generates a task list.

[0697] Creating and optimizing learning models

[0698] The server trains a machine learning model (e.g., a machine learning library) based on the generated task list. The data used here consists of past business data and feedback history.

[0699] The device visualizes and displays training progress and accuracy to the user, using graphs and statistical information.

[0700] The server evaluates the trained model and optimizes it as needed.

[0701] Division and execution of tasks

[0702] The server uses a trained model to distribute tasks between "users" and "automation platforms." For example, it might assign "setting up a meeting" to the automation platform and "sending notification emails" to users.

[0703] The server issues instructions to the automation platform, using the calendar API and email API to perform specific tasks. For example, it might automatically add a new meeting to the calendar.

[0704] The device provides users with a dashboard that displays the progress of tasks in real time.

[0705] User verification and intervention

[0706] The device notifies the user of the results of the completed tasks and displays them on the dashboard.

[0707] Users review the task results and make corrections or provide feedback as needed. For example, they might adjust the content of notification emails.

[0708] The device collects user feedback and sends it to the server.

[0709] The server updates its learning model based on the feedback, optimizing task allocation and execution for the next time.

[0710] Specific example

[0711] For example, to automate the scheduling of a weekly meeting held by a member of the marketing department:

[0712] 1. User: Enter the task description in text format: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[0713] 2. Terminal: Sends the input content to the server.

[0714] 3. Server: Analyze the work content and divide it into two tasks: "Set up a meeting" and "Send notification emails."

[0715] 4. Server: Trains machine learning models based on the analysis results.

[0716] 5. Server: Automate meeting setup to the platform and distribute notification email sending to users.

[0717] 6. Server: Automatically schedule meetings using the Calendar API.

[0718] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[0719] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[0720] 9. Terminal: Send feedback to the server.

[0721] 10. Server: Updates the learning model based on feedback.

[0722] Examples of prompt statements

[0723] For example, input the following prompt message into the AI ​​model:

[0724] "How can I set up a meeting every Monday at 9 AM and automatically send notification emails to participants?"

[0725] "Please suggest the optimal task breakdown method for automating recurring tasks."

[0726] This allows the system to provide specific steps for automating tasks that meet the user's needs.

[0727] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0728] Step 1: Enter details of the work

[0729] Terminal: First, an interface is displayed for the user to input routine tasks. This interface includes text boxes and selection options.

[0730] Input: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0731] Operation: The terminal receives the input data and temporarily stores it in its internal data storage.

[0732] Step 2: Validation of the work content

[0733] Terminal: Start the validation process. Verify that the format and content of the entered data are correct.

[0734] Input: Text data entered by the user.

[0735] Data processing: Perform validation on input data, including grammatical error checks and verification of required fields.

[0736] Output: Generates validation results and notifies the user if there are any errors.

[0737] Action: The terminal displays error messages and correction requests to the user.

[0738] Step 3: Submit the work details

[0739] Terminal: Sends the business details that have passed validation to the server.

[0740] Input: Text data that has passed validation.

[0741] Data processing: Encode data into a format that the server can understand.

[0742] Output: Details of the tasks to be sent to the server.

[0743] Operation: The terminal sends data to the server using methods such as HTTP requests.

[0744] Step 4: Analysis of Business Operations

[0745] Server: Analyzes the received work content using a natural language processing engine.

[0746] Input: Text data sent from the device.

[0747] Data processing: Analyze text using a natural language processing engine and break it down into specific tasks.

[0748] Output: Analyzed task list.

[0749] Operation: The server calls a natural language processing API and saves the analysis results to an internal database.

[0750] Step 5: Generate a task list

[0751] Server: Generates a list of executable tasks based on the analysis results.

[0752] Input: Analyzed business operations.

[0753] Data processing: Set the attributes of the task (e.g., deadline, assignee, importance, etc.).

[0754] Output: Completed task list.

[0755] Operation: The server composes a task list and passes it on to the next processing step.

[0756] Step 6: Training the machine learning model

[0757] Server: Trains machine learning models based on the task list.

[0758] Input: Past business data and analyzed task list.

[0759] Data processing: Input data into the model and run the learning algorithm.

[0760] Output: Trained machine learning model.

[0761] Operation: The server calls machine learning libraries to train the model.

[0762] Step 7: Task Distribution

[0763] Server: Uses trained models to distribute tasks to "users" and "automation platforms".

[0764] Input: Trained model and task list.

[0765] Data processing: Execute algorithms that optimally distribute tasks based on the model.

[0766] Output: Distributed task list.

[0767] Operation: The server issues instructions to the automation platform and assigns tasks.

[0768] Step 8: Execute the task

[0769] Server: Executes the specified task.

[0770] Input: Distributed task list.

[0771] Data calculations: Generate requests to call the Calendar API and Mail API.

[0772] Output: Execution result.

[0773] Operation: The server calls the API to set up meetings and send notification emails.

[0774] Step 9: Displaying Task Progress

[0775] Terminal: Provides a dashboard that displays task progress in real time.

[0776] Input: Execution results and progress data sent from the server.

[0777] Data processing: Convert data into a format that is easy to visualize.

[0778] Output: Visual progress display on the dashboard.

[0779] Operation: The device displays the progress using graphs and charts.

[0780] Step 10: Gathering Feedback and Updating the Model

[0781] Device: Collects user feedback.

[0782] Input: User feedback comments and suggested improvements.

[0783] Output: Feedback data.

[0784] Action: The device sends feedback to the server.

[0785] Server: Updates the learning model based on the feedback received.

[0786] Input: Feedback data.

[0787] Data processing: Retrain the model to improve accuracy.

[0788] Output: Updated machine learning model.

[0789] Operation: The server saves the latest model and applies it to subsequent operations.

[0790] The above outlines the specific processing steps of this system. This system allows users to efficiently automate routine tasks.

[0791] (Application Example 1)

[0792] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0793] In modern factories, manual processing of routine tasks is time-consuming and labor-intensive, reducing production efficiency. Furthermore, there is a need to reduce the burden on workers, improve work-life balance, and minimize human error. However, the problem is that conventional systems lack efficient methods to address these challenges.

[0794] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0795] In this invention, the server includes means for a user to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for sending instructions to the automation robot to execute the distributed tasks, means for displaying the progress to the user, and means for obtaining user feedback and updating the learning model. As a result, routine tasks in the factory are efficiently automated, reducing the burden on workers, improving work efficiency, and reducing errors.

[0796] A "user" is the entity that uses the system to input and manage routine tasks.

[0797] "Routine tasks" refer to standardized tasks or duties that are performed repeatedly.

[0798] "Text format" refers to the format in which information is entered as text characters.

[0799] "Means" refer to the methods or processes used to achieve a specific objective.

[0800] "Analysis" is the process of understanding and breaking down the entered business data.

[0801] A "task" is a division of work content into specific actions or tasks.

[0802] A "machine learning model" is a program that uses algorithms and data to perform pattern recognition and prediction.

[0803] "Training" is the process of using data to allow a machine learning model to learn.

[0804] An "automation system" is a set of hardware and software designed to automate routine tasks.

[0805] "Distribution" is the process of assigning analyzed tasks to users and automated systems.

[0806] An "automation robot" is a machine used to perform routine tasks within a factory.

[0807] "Sending instructions" means sending a command from the server to an automated robot to execute a task.

[0808] "Progress status" refers to information indicating the stage of a task.

[0809] "Displaying" means providing users with a visual representation of the progress or results.

[0810] "Feedback" refers to the process of communicating user opinions and requests for corrections to the system.

[0811] "Updating" is the process of improving a machine learning model based on the feedback received.

[0812] This invention is a system that allows users to efficiently automate routine tasks within a factory, improve productivity, and reduce the burden on workers. The specific configuration and operation of this system are described below.

[0813] System Configuration

[0814] The system consists of the following main components:

[0815] 1. User terminal: Provides an interface for users to input and manage routine tasks. Specifically, smartphones, tablets, PCs, etc., are used.

[0816] 2. Server: Analyzes the business processes, divides them into specific tasks, and trains machine learning models.

[0817] 3. Automation robots: These are automated devices used to perform routine tasks within a factory. Examples include ABB's IRB 6700 and Universal Robots' UR series.

[0818] Operation details

[0819] 1. Entering routine tasks:

[0820] Users input routine tasks in text format via their user terminals. The entered task details are sent to the server. For example, a user might input, "Check the machine oil at 6 PM every day."

[0821] 2. Analysis of business processes and generation of tasks:

[0822] The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "oil check" and "results report."

[0823] 3. Training machine learning models:

[0824] The server trains a machine learning model based on the analyzed task list. This model will then be used to distribute tasks.

[0825] 4. Task distribution and execution:

[0826] The server uses a trained machine learning model to distribute the generated tasks to the user and the automated robot. Specifically, it assigns "oil check" to the automated robot and "results report" to the user. The server sends instructions to the automated robot via an API.

[0827] 5. Display of progress and feedback:

[0828] An automated robot performs a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task's progress and provides corrections and feedback as needed. The server collects user feedback and updates the machine learning model.

[0829] Specific example

[0830] For example, consider automating parts inventory management. Using this system, a robot can check inventory at 8 AM every morning and automatically issue replenishment orders if any parts are missing. This enables rapid inventory management and reduces labor.

[0831] Example of a prompt

[0832] 1. "Check the machine's oil every day at 6 PM and notify us if there are any abnormalities."

[0833] 2. "Check the parts inventory every morning at 8:00 AM and issue replenishment orders if any are missing."

[0834] This invention not only efficiently automates routine tasks within the factory, but is also expected to reduce the burden on workers and improve operational efficiency. The procedure described above enables precise operation in an automated environment.

[0835] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0836] Step 1:

[0837] Entering routine tasks

[0838] Subject: User

[0839] Specific operation: Users access the system using their own devices (smartphones, tablets, PCs, etc.) and input routine tasks in text format.

[0840] Input: Routine task details entered by the user in text format (e.g., "Check the machine oil at 6 PM every day").

[0841] Output: The entered work details are sent to the server via the terminal.

[0842] Step 2:

[0843] Analysis of business processes and task generation

[0844] Subject: Server

[0845] Specific operation: The server analyzes the received business content using a natural language processing (NLP) engine and divides it into specific tasks.

[0846] Input: User-entered details of the work (in text format).

[0847] Data processing: Use an NLP engine to analyze text and break down business content into specific tasks.

[0848] Output: Analyzed task list (e.g., "Oil check", "Result report").

[0849] Step 3:

[0850] Training machine learning models

[0851] Subject: Server

[0852] Specific operation: The server trains a machine learning model based on the analyzed task list. It also utilizes historical data to improve model performance.

[0853] Input: Analyzed task list and past execution data.

[0854] Data processing: Train the model using machine learning algorithms.

[0855] Output: Trained machine learning model.

[0856] Step 4:

[0857] Task distribution and execution

[0858] Subject: Server, automation robot

[0859] Specific operation: The server uses a trained machine learning model to distribute each task to a user or an automated robot. The distributed tasks are then sent to the robot as instructions.

[0860] Input: Trained machine learning model and analyzed task list.

[0861] Data processing: Allocation is determined based on the priority and content of the tasks.

[0862] Output: The task instructed to the robot (e.g., "Instruction to perform an oil check").

[0863] Step 5:

[0864] Display of progress and feedback

[0865] Subject: Automation robot, server, user

[0866] Specific operation: An automated robot executes a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task progress and provides corrections and feedback as needed.

[0867] Input: Task progress data from the robot.

[0868] Data processing: Convert progress data into a dashboard format.

[0869] Output: Progress displayed on the dashboard, and user feedback.

[0870] Step 6:

[0871] Incorporating feedback and updating the model

[0872] Subject: Server

[0873] Specific operation: The server collects user feedback and updates the machine learning model based on it.

[0874] Input: User feedback data.

[0875] Data processing: Feed feedback data into a machine learning algorithm and retrain the model.

[0876] Output: Updated machine learning model.

[0877] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0878] Understood. The "Modes for Carrying Out the Invention" are shown below.

[0879] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[0880] System program configuration and specific operation

[0881] 1. Collect information about the work from the user.

[0882] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[0883] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[0884] 2. Analyze the work content and generate tasks.

[0885] Terminal: Sends the entered work details to the server.

[0886] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[0887] 3. Utilizing the Emotional Engine

[0888] Terminal: When a user inputs work details, the emotion engine collects data to recognize the user's emotions. This includes using text analysis to read emotions from the text and facial recognition technology via a webcam.

[0889] Server: The emotion engine analyzes the user's emotions and determines task priorities based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[0890] 4. Creating and optimizing the learning model

[0891] Server: Trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[0892] Terminal: Visually displays the progress and accuracy of the learning model to the user.

[0893] 5. Division and execution of tasks

[0894] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (copy AI)." For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Task assignments are also adjusted based on the emotion engine.

[0895] Server: Issues instructions to an automated system to perform a specific task. For example, using the Calendar API to schedule a meeting.

[0896] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[0897] 6. User Verification and Intervention

[0898] Terminal: Notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[0899] User: Review the task results and make corrections or provide feedback as needed.

[0900] Terminal: Collects user feedback and sends it to the server.

[0901] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[0902] Specific example

[0903] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0904] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[0905] 2. Terminal: Sends the input content to the server.

[0906] 3. Server: Analyzes the work content and divides it into two tasks: "set up a meeting" and "send notification emails." The emotion engine evaluates the user's stress level and adjusts the order of the tasks.

[0907] 4. Server: Trains the learning model based on the analysis results.

[0908] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[0909] 6. Server: Automatically schedule meetings using the Calendar API.

[0910] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[0911] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[0912] 9. Terminal: Send feedback to the server.

[0913] 10. Server: Update the learning model based on feedback.

[0914] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks, but also takes user emotions into consideration, enabling more efficient and less stressful work execution.

[0915] The following describes the processing flow.

[0916] Understood. The processing steps are explained in detail below.

[0917] Step 1:

[0918] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and selection options, allowing users to input details about their tasks. In addition, an emotion engine retrieves emotional data from the user's facial expressions and input patterns.

[0919] Step 2:

[0920] User: Enters specific task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." The emotion engine observes the user's input and recognizes emotions such as stress and anxiety.

[0921] Step 3:

[0922] Terminal: Retrieves the entered work details and sends them to the server. Simultaneously, it also sends the emotion data collected by the emotion engine to the server.

[0923] Step 4:

[0924] Server: The server analyzes the received text data using a natural language processing engine and divides the work content into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[0925] Step 5:

[0926] Server: Analyzes the emotional data provided by the emotion engine and evaluates the user's emotional state. Based on this evaluation, it adjusts the task prioritization and distribution method.

[0927] Step 6:

[0928] Server: Trains a machine learning model based on analysis results and sentiment data to learn user work patterns and sentiment patterns.

[0929] Step 7:

[0930] Server: Using a learning model, it distributes the generated tasks to the "user" and the "automation system (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Here, it utilizes data from the emotion engine to prioritize assigning difficult tasks when stress levels are low and easy tasks when stress levels are high.

[0931] Step 8:

[0932] Server: Issues instructions to an automated system to perform a specific task. For example, it can use a calendar API to automatically schedule meetings.

[0933] Step 9:

[0934] Terminal: Provides users with a dashboard that displays task progress in real time. Here, the sentiment engine also displays support messages and feedback tailored to the user's state.

[0935] Step 10:

[0936] User: Check the progress and results of completed tasks through the dashboard. Modify task results as needed.

[0937] Step 11:

[0938] Terminal: Collects user modifications and feedback and sends them to the server.

[0939] Step 12:

[0940] Server: Updates the learning model based on user feedback to further optimize task distribution and execution for future sessions.

[0941] Specific example

[0942] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[0943] Step 1:

[0944] Terminal: "Displays an interface for inputting routine tasks and captures the user's facial expressions using an emotion engine."

[0945] Step 2:

[0946] User: "I typed, 'Set up a meeting every Monday at 9:00 AM and send a notification email to participants,' and my facial expression was recognized."

[0947] Step 3:

[0948] Terminal: "Send input content and sentiment data to the server."

[0949] Step 4:

[0950] Server: "Analyzes the business process and divides it into two tasks. Analyzes emotional data and evaluates the user's emotional state."

[0951] Step 5:

[0952] Server: "Adjust task priorities and distribution methods based on sentiment evaluations."

[0953] Step 6:

[0954] Server: "Train a machine learning model based on analysis results and sentiment data."

[0955] Step 7:

[0956] Server: "Assign the automated system to set up meetings and the users to send notification emails."

[0957] Step 8:

[0958] Server: "Automatically schedule meetings using the Calendar API."

[0959] Step 9:

[0960] Terminal: "Displays execution status in real time on the dashboard and shows sentiment-based messages."

[0961] Step 10:

[0962] User: "Check the task progress on the dashboard and make corrections as needed."

[0963] Step 11:

[0964] Terminal: "Send corrections and feedback to the server."

[0965] Step 12:

[0966] Server: "Update the learning model based on feedback."

[0967] The above outlines the specific processing steps for implementing this invention. This system not only efficiently automates routine tasks but also takes into account the user's emotional state, enabling more efficient and less stressful work execution.

[0968] (Example 2)

[0969] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0970] Traditional business automation systems fail to consider the user's emotional state when allocating or prioritizing tasks, potentially leading to user stress and decreased work efficiency. Furthermore, real-time updates of machine learning models based on user feedback are difficult, resulting in limited system adaptability.

[0971] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0972] In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for collecting user sentiment data based on the analyzed tasks, means for analyzing the collected sentiment data and determining task priorities, means for training a machine learning model based on the analyzed tasks and sentiment data, means for distributing tasks to the user and the automation system using the trained learning model, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables automation of tasks that take user sentiment into consideration and real-time system adaptation based on feedback.

[0973] A "user" refers to a person who uses the system to input data and provide feedback.

[0974] "Routine tasks" refer to repetitive tasks that users need to perform regularly.

[0975] "Text format" refers to a data format represented by strings of characters.

[0976] "Means" refers to the methods or devices used to achieve a specific objective.

[0977] "Job description" refers to the specific tasks and details of work that users input into the system.

[0978] "Analysis" refers to the process of breaking down input data and understanding its meaning and structure.

[0979] "Specific tasks" refer to individual work units that can be executed based on the analyzed business content.

[0980] "Emotional data" refers to information that indicates a user's emotional state. This includes facial expressions, tone of voice, and emotional expressions in text.

[0981] "Collecting emotional data" refers to the process of obtaining a user's emotions and storing them in an analyzable format.

[0982] "Emotional analysis" refers to the process of processing collected emotional data to understand the user's emotional state.

[0983] "Priority" refers to determining the order in which tasks are performed and their importance.

[0984] A "machine learning model" refers to an algorithm that learns specific patterns based on data and uses them to make future predictions and decisions.

[0985] "Training" refers to the process of using data to train a machine learning model to achieve an optimal state.

[0986] An "automation system" refers to a system of software or hardware designed to automatically perform specific tasks.

[0987] "Progress status" refers to information indicating the stage of a task.

[0988] "Feedback" refers to the evaluations and opinions that users provide to a system.

[0989] "Updating" refers to the process of improving existing machine learning models and systems using new information and feedback.

[0990] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks by coordinating various technologies, with terminals, servers, and users as the main components.

[0991] System configuration and operation

[0992] First, the system collects information about routine tasks from the user. In this process, the terminal displays an input interface to the user, who then inputs the task details in text format.

[0993] Specific actions

[0994] 1. Collect information about the work from the user.

[0995] Terminal: The terminal displays an interface for users to input routine tasks. This interface includes text boxes and selection options, allowing users to freely input task details. Software used includes HTML, CSS, and JavaScript.

[0996] User: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[0997] 2. Analyze the work content and generate tasks.

[0998] Terminal: Sends the entered work details to the server via an HTTP request.

[0999] Server: The server uses a natural language processing engine (e.g., SpaCy, Transformer) to analyze the received business data. For example, it might break it down into specific tasks such as "setting up a meeting" and "sending notification emails." This clarifies the specific routine tasks that the system will handle.

[1000] 3. Utilizing the Emotional Engine

[1001] Terminal: When a user inputs work details, the terminal uses its camera and microphone to collect user emotion data. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[1002] Server: The server analyzes the data collected using the emotion engine to understand the user's emotional state. Based on the collected emotional data, it determines task priorities. For example, if a user is feeling stressed, it adjusts the assignment to prioritize easier tasks.

[1003] 4. Creating and optimizing the learning model

[1004] Server: Trains a machine learning model based on the analyzed task and sentiment data. This training uses Scikit-learn or TensorFlow. The trained model learns the user's work patterns and sentiment patterns and reflects them in subsequent execution.

[1005] Terminal: Use graphs and dashboards (e.g., Plotly, Grafana) to visually display training progress and accuracy to the user.

[1006] 5. Division and execution of tasks

[1007] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (e.g., Zapier or IFTTT)." For example, it might assign "setting up a meeting" to an automation system and "sending notification emails" to a user. The server also uses the Google Calendar API, etc., to automate tasks such as setting up meetings.

[1008] Terminal: Provides a dashboard to display task progress to the user in real time. Users can check the task execution status through the dashboard and intervene or correct as needed.

[1009] 6. User Verification and Intervention

[1010] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[1011] User: Review the task results and make corrections or provide feedback as needed.

[1012] Terminal: Sends collected feedback to the server.

[1013] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1014] Specific example

[1015] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[1016] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[1017] 2. Terminal: Sends the input content to the server.

[1018] 3. Server: Analyzes work content and divides it into "meeting scheduling" and "sending notification emails." An emotion engine evaluates the user's stress level.

[1019] 4. Server: Trains the learning model based on the analysis results.

[1020] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[1021] 6. Server: Automatically schedule meetings using the Google Calendar API.

[1022] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[1023] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[1024] 9. Terminal: Send feedback to the server.

[1025] 10. Server: Update the learning model based on feedback.

[1026] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks but also enables appropriate task distribution that takes into account the user's emotions, resulting in more efficient and less stressful work performance.

[1027] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1028] Step 1:

[1029] Collect information about the work performed by the user.

[1030] Terminal: Displays an interface where the user can input work details. This interface includes text boxes and selection options. This allows the user to input details of routine tasks in text format.

[1031] Input: User's job description (e.g., "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants").

[1032] Output: Text data of the work details entered by the user.

[1033] Step 2:

[1034] Sending and analyzing work details

[1035] Terminal: Sends the entered work details to the server. This process is performed via an HTTP request.

[1036] Server: The server analyzes the received text data using a natural language processing engine (e.g., SpaCy, Transformer) and divides it into specific tasks.

[1037] Input: Text data of the work details entered by the user.

[1038] Output: Specific tasks analyzed (e.g., "Set up a meeting", "Send notification email").

[1039] Step 3:

[1040] Collection of emotional data

[1041] Terminal: When users input work details, the system collects emotional data using the camera and microphone. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[1042] Input: User's facial expressions and voice data.

[1043] Output: Collected emotional data (e.g., facial features, voice tone).

[1044] Step 4:

[1045] Analysis of emotional data

[1046] Server: The collected emotional data is analyzed by an emotion engine to understand the user's emotional state. Emotional scores and stress levels are calculated.

[1047] Input: Collected sentiment data.

[1048] Output: Sentiment score and stress level.

[1049] Step 5:

[1050] Training machine learning models

[1051] Server: Trains a machine learning model based on the analyzed task and sentiment data. This uses Scikit-learn or TensorFlow. The model learns the user's work patterns and sentiment patterns.

[1052] Input: Analyzed task and sentiment data.

[1053] Output: Trained machine learning model.

[1054] Step 6:

[1055] Task distribution

[1056] Server: Uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, assigning "setting up a meeting" to the automation system and "sending notification emails" to users.

[1057] Input: A trained machine learning model and the task to be analyzed.

[1058] Output: Distributed tasks.

[1059] Step 7:

[1060] Task execution and progress display

[1061] Server: Issues instructions to the automation system to execute tasks. Specifically, it uses the Google Calendar API to schedule meetings.

[1062] Terminal: Provides a dashboard to display task progress to the user in real time.

[1063] Input: Assigned tasks.

[1064] Output: Tasks performed and their progress.

[1065] Step 8:

[1066] User verification and intervention

[1067] Terminal: Displays the results of completed tasks on the dashboard and notifies the user.

[1068] User: Review the task results and make corrections or provide feedback as needed.

[1069] Terminal: Sends corrections and feedback to the server.

[1070] Server: Updates the machine learning model based on feedback.

[1071] Input: User feedback.

[1072] Output: Updated machine learning model.

[1073] These processing steps enable the system to efficiently automate users' routine tasks and achieve task distribution that takes emotions into account.

[1074] (Application Example 2)

[1075] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1076] Modern factories and logistics centers have numerous routine tasks that must be handled efficiently. In particular, since employee performance fluctuates depending on their emotional state, task allocation that takes emotions into account is crucial. However, current systems often fail to consider user emotions when assigning tasks, limiting efficiency. Furthermore, assigning tasks without considering employee emotions can cause stress, leading to decreased satisfaction and productivity. Therefore, a system is needed that not only streamlines routine tasks but also dynamically reflects user emotions in task allocation.

[1077] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for analyzing emotional data and distributing and adjusting tasks according to the emotional state, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables dynamic task distribution that takes the user's emotions into consideration, making it possible to simultaneously achieve increased work efficiency and reduced stress.

[1078] "Routine tasks" refer to standardized tasks that are performed repeatedly on a daily basis.

[1079] "Text format" refers to a format that uses strings of characters to represent information.

[1080] "Analysis" refers to the process of breaking down input information and understanding its contents in detail.

[1081] A "task" refers to an individual work or activity performed to achieve a specific objective.

[1082] A "machine learning model" refers to the structure of an algorithm that learns from data and performs predictions and classifications.

[1083] "Training" refers to the process of using data to allow a machine learning model to learn.

[1084] An "automation system" refers to a system that performs specific tasks or processes without human intervention.

[1085] "Distribution" refers to the process of allocating specific resources or tasks to multiple targets.

[1086] "Emotional data" refers to data that represents the emotional state of a user.

[1087] "Analysis" refers to the process of examining data in detail and understanding its patterns and meanings.

[1088] "Adjustment" refers to changing the arrangement or content based on specific conditions.

[1089] "Execution" refers to actually carrying out the planned tasks.

[1090] "Progress status" refers to information that indicates the degree of completion during the task's execution process.

[1091] "Display" refers to the visual presentation of information.

[1092] "Feedback" refers to providing information or opinions about a particular action or outcome.

[1093] "Updating" refers to improving or changing existing data or systems based on new information.

[1094] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting the user's emotions in the work process. Specific embodiments are described in detail below.

[1095] System Configuration

[1096] This system automates tasks through the collaboration of terminals, servers, and users. The main hardware used includes smart glasses and factory robots, while the software includes EmotionEngine (emotion recognition engine), TaskParser (task analysis engine), RobotController (robot control API), and SmartGlasses (smart glasses API).

[1097] Specific actions

[1098] 1. Collect information about the work from the user.

[1099] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, where users can enter specific details about their tasks.

[1100] Users input task details such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1101] 2. Analyze the work content and generate tasks.

[1102] The terminal sends the entered work information to the server.

[1103] The server analyzes the received work content using TaskParser and divides it into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[1104] 3. Utilizing the Emotional Engine

[1105] When a user inputs work details, the terminal collects data for EmotionEngine to recognize the user's emotions. This includes text analysis and facial recognition via the camera.

[1106] The server uses EmotionEngine to analyze the user's emotions and prioritizes tasks based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[1107] 4. Creating and optimizing the learning model

[1108] The server trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[1109] 5. Division and execution of tasks

[1110] The server uses a trained learning model to distribute tasks between "users" and "automation systems." For example, it might assign "setting up a meeting" to the automation system and "sending notification emails" to the user.

[1111] The server issues instructions to the automated system to perform specific tasks. For example, it might use the Calendar API to schedule a meeting.

[1112] 6. User Verification and Intervention

[1113] The device notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[1114] Users review the task results and make corrections or provide feedback as needed.

[1115] Specific example

[1116] For example, in the automation of production operations in a factory:

[1117] 1. The user enters "replenish materials on the packaging line" as their job description, and sentiment data is also collected.

[1118] 2. The terminal sends the input content to the server.

[1119] 3. The server analyzes the work content and divides it into two tasks: "preparing materials" and "replenishing materials." The emotion engine assesses the user's stress level and adjusts the order of the tasks.

[1120] 4. The server trains a learning model based on the analysis results.

[1121] 5. The server distributes the task of "preparing materials" to the automated system and the task of "replenishing materials" to the user.

[1122] 6. The server instructs the robot to "prepare materials," and it executes this automatically.

[1123] 7. The terminal displays the task progress in real time and shows appropriate support messages.

[1124] 8. The user confirms that the task is complete and provides feedback as needed.

[1125] Example of a prompt

[1126] "It seems that worker A is unhappy. Please have them handle the easier tasks first."

[1127] "The next task is 'replenishing materials on the packaging line.' Due to its high stress level, please assign this task to a robot."

[1128] This allows for efficient automation of each process while simultaneously enabling flexible task management that reflects user emotions, resulting in improved overall productivity and satisfaction.

[1129] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1130] Step 1:

[1131] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, allowing users to input specific details about their tasks. The input data here consists of text or voice information describing the user's work. For example, specific tasks such as "replenishing materials on the packaging line" might be entered.

[1132] Step 2:

[1133] The terminal transmits the entered work information to the server. At this time, the entered text or voice data is transferred to the server and prepared for analysis. The role of the terminal is to transmit the collected data to the server quickly and accurately.

[1134] Step 3:

[1135] The server uses TaskParser to analyze the received business information and divides it into specific tasks. For example, it might divide it into tasks such as "prepare materials" and "replenish materials." This process utilizes natural language processing technology to analyze the text data and identify each business task.

[1136] Step 4:

[1137] The terminal uses EmotionEngine to collect emotional data when users input work-related information. The collected data includes emotion determination through text analysis and facial recognition via the camera. The input data represents information about the user's emotional state, such as stress levels and satisfaction levels.

[1138] Step 5:

[1139] The server analyzes emotional data using EmotionEngine and determines task priorities based on the results. For example, if a user's stress level is high, it will assign them easier tasks first. This process involves performing data calculations that prioritize tasks using emotional analysis data.

[1140] Step 6:

[1141] The server trains a machine learning model based on the analyzed task and sentiment data. In this process, it uses a large amount of historical task and sentiment state data to generate a model that will help with future task allocation and sentiment regulation. The input data is the analyzed task and sentiment data, and the output is the updated machine learning model.

[1142] Step 7:

[1143] The server uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, it might assign "preparing materials" to the automation system and "replenishing materials" to the user. This process involves data calculations that use the machine learning model to determine the optimal task distribution.

[1144] Step 8:

[1145] The server issues instructions to the automated system to perform specific tasks. For example, it might use RobotController to instruct a factory robot to prepare materials. In this process, specific operation commands are generated as output data that are sent to the robot.

[1146] Step 9:

[1147] The device displays the task progress to the user in real time. Here, the SmartGlasses API is used to visually display the task progress on smart glasses. The displayed data includes the task's progress and completion status.

[1148] Step 10:

[1149] Users review the results of completed tasks and make corrections or provide feedback as needed. This feedback can include comments such as "Task complete" or "Needs correction." This allows the system to reflect the user's intentions.

[1150] Step 11:

[1151] The terminal sends user feedback to the server. This feedback data is used to further optimize task distribution and execution in the future.

[1152] Step 12:

[1153] The server updates the machine learning model based on the feedback received. This allows the model to reflect the latest data, enabling more accurate task allocation and sentiment adjustment. The output data is the updated machine learning model.

[1154] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1155] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1156] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1157] [Third Embodiment]

[1158] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1159] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1160] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1161] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1162] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1164] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1165] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1166] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1167] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1168] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1169] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1170] Understood. The "Modes for Carrying Out the Invention" are shown below.

[1171] This invention is a system designed to enable users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[1172] System program configuration and specific operation

[1173] 1. Collect information about the work from the user.

[1174] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[1175] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[1176] 2. Analyze the work content and generate tasks.

[1177] Terminal: Performs processing to send the work details entered by the user to the server.

[1178] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[1179] 3. Creating and optimizing the learning model

[1180] Server: Trains a machine learning model based on the analyzed task list. The model used here learns the user's work patterns and uses this knowledge to improve future task allocation.

[1181] Terminal: Equipped with a function to visually display the progress and accuracy of the learning model to the user.

[1182] 4. Division and execution of tasks

[1183] Server: Using a learning model, it distributes the generated tasks to "users" and "automation systems (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[1184] Server: Issues instructions to the copy AI to perform specific tasks. The server also uses the Calendar API and Email API to execute tasks.

[1185] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[1186] 5. User Verification and Intervention

[1187] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard.

[1188] User: Review the task results and make corrections or provide feedback as needed. For example, adjust the content of the notification email.

[1189] Terminal: Collects user feedback and sends it to the server.

[1190] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1191] Specific example

[1192] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[1193] 1. User: Enter the following text for the job description: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[1194] 2. Terminal: Sends the input content to the server.

[1195] 3. Server: Analyzes the work content and divides it into two tasks: "setting up a meeting" and "sending notification emails".

[1196] 4. Server: Trains machine learning models based on the analysis results.

[1197] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[1198] 6. Server: Automatically schedule meetings using the Calendar API.

[1199] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[1200] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[1201] 9. Terminal: Send feedback to the server.

[1202] 10. Server: Update the learning model based on feedback.

[1203] The above describes a specific embodiment for carrying out this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[1204] The following describes the processing flow.

[1205] Understood. The processing steps are explained in detail below.

[1206] Step 1:

[1207] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and multiple selection options where users can enter details about their tasks.

[1208] Step 2:

[1209] User: Enter task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1210] Step 3:

[1211] Terminal: Retrieves the entered work details and sends them to the server for analysis.

[1212] Step 4:

[1213] Server: Sends the received text data to the natural language processing engine and starts the analysis. The analysis structures the business content and divides it into specific tasks.

[1214] Step 5:

[1215] Server: Based on the analysis results, it generates specific tasks. For example, it might divide the data into two tasks: "Set up a meeting" and "Send a notification email."

[1216] Step 6:

[1217] Server: Inputs the generated task list into a machine learning engine to learn the user's work patterns.

[1218] Step 7:

[1219] Server: Uses a learned model to determine the optimal way to distribute tasks.

[1220] Step 8:

[1221] Server: Distributes tasks between "users" and "automation systems (copy AI)". For example, assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[1222] Step 9:

[1223] Server: Issues task execution instructions to the automation system. For example, it can use the Calendar API to automatically schedule meetings.

[1224] Step 10:

[1225] Terminal: Provides users with a dashboard that displays task progress in real time.

[1226] Step 11:

[1227] User: Check the progress and results of completed tasks through the dashboard.

[1228] Step 12:

[1229] User: Modify the task results as needed and provide feedback.

[1230] Step 13:

[1231] Terminal: Collects user feedback and sends it to the server.

[1232] Step 14:

[1233] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1234] The above outlines the specific processing steps for implementing this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[1235] (Example 1)

[1236] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1237] In today's business environment, routine tasks consume a great deal of time and effort while adding little value, making efficient automation of these tasks essential. However, routine tasks are diverse, and there is a lack of means to accurately analyze each task and automate it appropriately. Furthermore, there are few systems that allow for real-time monitoring of task progress or systems that update models based on user feedback. There is a need for highly practical automation systems to address these challenges.

[1238] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1239] In this invention, the server includes means for users to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, and means for training a machine learning model based on the analyzed tasks. This enables efficient automation of routine tasks, reduces the burden on users, and improves operational efficiency.

[1240] A "user" is an individual or group that uses the system to automate routine tasks.

[1241] "Routine tasks" are work or tasks that are performed repeatedly at regular intervals.

[1242] "Text format" refers to a method of inputting information as a string of characters, allowing users to freely enter text and data.

[1243] "Analysis" is the process of breaking down input data and business operations and classifying them into specific patterns or elements.

[1244] A "task" is an individual work or unit of work performed to achieve a specific objective.

[1245] A "machine learning model" is an algorithm that learns specific patterns based on data and uses them to make predictions and decisions.

[1246] "Training" is the process by which a machine learning model analyzes data and optimizes the model in order to make the best predictions and decisions.

[1247] An "automation platform" is a system or software designed to automatically perform specific tasks.

[1248] A "Calendar API" is a programmatic interface for creating and managing schedules in conjunction with external calendar systems.

[1249] A "mail API" is a programmatic interface for sending and receiving emails in conjunction with external mail servers and services.

[1250] A "dashboard" is a user interface that visually displays the progress of tasks and various metrics.

[1251] "Feedback" refers to the opinions and evaluations provided by users regarding the output results and operation of a system.

[1252] This invention is a system designed to enable users to efficiently automate routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[1253] Program processing

[1254] Collect information about the work performed by the user.

[1255] The terminal first displays an interface for the user to input routine tasks. This interface includes text boxes and selection options.

[1256] Users input routine tasks into the interface in text format. For example, they might enter a specific task such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1257] The terminal validates the entered data and prompts the user to correct any errors.

[1258] Analyze the business process and generate tasks.

[1259] The terminal sends the work details that have passed validation to the server.

[1260] The server analyzes the received business content using a natural language processing engine (e.g., a natural language processing API). As a result of the analysis, the business content is divided into specific tasks. For example, it might be divided into "setting up a meeting" and "sending a notification email."

[1261] The server saves the analysis results to an internal database and generates a task list.

[1262] Creating and optimizing learning models

[1263] The server trains a machine learning model (e.g., a machine learning library) based on the generated task list. The data used here consists of past business data and feedback history.

[1264] The device visualizes and displays training progress and accuracy to the user, using graphs and statistical information.

[1265] The server evaluates the trained model and optimizes it as needed.

[1266] Division and execution of tasks

[1267] The server uses a trained model to distribute tasks between "users" and "automation platforms." For example, it might assign "setting up a meeting" to the automation platform and "sending notification emails" to users.

[1268] The server issues instructions to the automation platform, using the calendar API and email API to perform specific tasks. For example, it might automatically add a new meeting to the calendar.

[1269] The device provides users with a dashboard that displays the progress of tasks in real time.

[1270] User verification and intervention

[1271] The device notifies the user of the results of the completed tasks and displays them on the dashboard.

[1272] Users review the task results and make corrections or provide feedback as needed. For example, they might adjust the content of notification emails.

[1273] The device collects user feedback and sends it to the server.

[1274] The server updates its learning model based on the feedback, optimizing task allocation and execution for the next time.

[1275] Specific example

[1276] For example, to automate the scheduling of a weekly meeting held by a member of the marketing department:

[1277] 1. User: Enter the task description in text format: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[1278] 2. Terminal: Sends the input content to the server.

[1279] 3. Server: Analyze the work content and divide it into two tasks: "Set up a meeting" and "Send notification emails."

[1280] 4. Server: Trains machine learning models based on the analysis results.

[1281] 5. Server: Automate meeting setup to the platform and distribute notification email sending to users.

[1282] 6. Server: Automatically schedule meetings using the Calendar API.

[1283] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[1284] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[1285] 9. Terminal: Send feedback to the server.

[1286] 10. Server: Updates the learning model based on feedback.

[1287] Examples of prompt statements

[1288] For example, input the following prompt message into the AI ​​model:

[1289] "How can I set up a meeting every Monday at 9 AM and automatically send notification emails to participants?"

[1290] "Please suggest the optimal task breakdown method for automating recurring tasks."

[1291] This allows the system to provide specific steps for automating tasks that meet the user's needs.

[1292] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1293] Step 1: Enter details of the work

[1294] Terminal: First, an interface is displayed for the user to input routine tasks. This interface includes text boxes and selection options.

[1295] Input: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1296] Operation: The terminal receives the input data and temporarily stores it in its internal data storage.

[1297] Step 2: Validation of the work content

[1298] Terminal: Start the validation process. Verify that the format and content of the entered data are correct.

[1299] Input: Text data entered by the user.

[1300] Data processing: Perform validation on input data, including grammatical error checks and verification of required fields.

[1301] Output: Generates validation results and notifies the user if there are any errors.

[1302] Action: The terminal displays error messages and correction requests to the user.

[1303] Step 3: Submit the work details

[1304] Terminal: Sends the business details that have passed validation to the server.

[1305] Input: Text data that has passed validation.

[1306] Data processing: Encode data into a format that the server can understand.

[1307] Output: Details of the tasks to be sent to the server.

[1308] Operation: The terminal sends data to the server using methods such as HTTP requests.

[1309] Step 4: Analysis of Business Operations

[1310] Server: Analyzes the received work content using a natural language processing engine.

[1311] Input: Text data sent from the device.

[1312] Data processing: Analyze text using a natural language processing engine and break it down into specific tasks.

[1313] Output: Analyzed task list.

[1314] Operation: The server calls a natural language processing API and saves the analysis results to an internal database.

[1315] Step 5: Generate a task list

[1316] Server: Generates a list of executable tasks based on the analysis results.

[1317] Input: Analyzed business operations.

[1318] Data processing: Set the attributes of the task (e.g., deadline, assignee, importance, etc.).

[1319] Output: Completed task list.

[1320] Operation: The server composes a task list and passes it on to the next processing step.

[1321] Step 6: Training the machine learning model

[1322] Server: Trains machine learning models based on the task list.

[1323] Input: Past business data and analyzed task list.

[1324] Data processing: Input data into the model and run the learning algorithm.

[1325] Output: Trained machine learning model.

[1326] Operation: The server calls machine learning libraries to train the model.

[1327] Step 7: Task Distribution

[1328] Server: Uses trained models to distribute tasks to "users" and "automation platforms".

[1329] Input: Trained model and task list.

[1330] Data processing: Execute algorithms that optimally distribute tasks based on the model.

[1331] Output: Distributed task list.

[1332] Operation: The server issues instructions to the automation platform and assigns tasks.

[1333] Step 8: Execute the task

[1334] Server: Executes the specified task.

[1335] Input: Distributed task list.

[1336] Data calculations: Generate requests to call the Calendar API and Mail API.

[1337] Output: Execution result.

[1338] Operation: The server calls the API to set up meetings and send notification emails.

[1339] Step 9: Displaying Task Progress

[1340] Terminal: Provides a dashboard that displays task progress in real time.

[1341] Input: Execution results and progress data sent from the server.

[1342] Data processing: Convert data into a format that is easy to visualize.

[1343] Output: Visual progress display on the dashboard.

[1344] Operation: The device displays the progress using graphs and charts.

[1345] Step 10: Gathering Feedback and Updating the Model

[1346] Device: Collects user feedback.

[1347] Input: User feedback comments and suggested improvements.

[1348] Output: Feedback data.

[1349] Action: The device sends feedback to the server.

[1350] Server: Updates the learning model based on the feedback received.

[1351] Input: Feedback data.

[1352] Data processing: Retrain the model to improve accuracy.

[1353] Output: Updated machine learning model.

[1354] Operation: The server saves the latest model and applies it to subsequent operations.

[1355] The above outlines the specific processing steps of this system. This system allows users to efficiently automate routine tasks.

[1356] (Application Example 1)

[1357] Next, we will explain Application Example 1. In the following explanation, 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."

[1358] In modern factories, manual processing of routine tasks is time-consuming and labor-intensive, reducing production efficiency. Furthermore, there is a need to reduce the burden on workers, improve work-life balance, and minimize human error. However, the problem is that conventional systems lack efficient methods to address these challenges.

[1359] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1360] In this invention, the server includes means for a user to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for sending instructions to the automation robot to execute the distributed tasks, means for displaying the progress to the user, and means for obtaining user feedback and updating the learning model. As a result, routine tasks in the factory are efficiently automated, reducing the burden on workers, improving work efficiency, and reducing errors.

[1361] A "user" is the entity that uses the system to input and manage routine tasks.

[1362] "Routine tasks" refer to standardized tasks or duties that are performed repeatedly.

[1363] "Text format" refers to the format in which information is entered as text characters.

[1364] "Means" refer to the methods or processes used to achieve a specific objective.

[1365] "Analysis" is the process of understanding and breaking down the entered business data.

[1366] A "task" is a division of work content into specific actions or tasks.

[1367] A "machine learning model" is a program that uses algorithms and data to perform pattern recognition and prediction.

[1368] "Training" is the process of using data to allow a machine learning model to learn.

[1369] An "automation system" is a set of hardware and software designed to automate routine tasks.

[1370] "Distribution" is the process of assigning analyzed tasks to users and automated systems.

[1371] An "automation robot" is a machine used to perform routine tasks within a factory.

[1372] "Sending instructions" means sending a command from the server to an automated robot to execute a task.

[1373] "Progress status" refers to information indicating the stage of a task.

[1374] "Displaying" means providing users with a visual representation of the progress or results.

[1375] "Feedback" refers to the process of communicating user opinions and requests for corrections to the system.

[1376] "Updating" is the process of improving a machine learning model based on the feedback received.

[1377] This invention is a system that allows users to efficiently automate routine tasks within a factory, improve productivity, and reduce the burden on workers. The specific configuration and operation of this system are described below.

[1378] System Configuration

[1379] The system consists of the following main components:

[1380] 1. User terminal: Provides an interface for users to input and manage routine tasks. Specifically, smartphones, tablets, PCs, etc., are used.

[1381] 2. Server: Analyzes the business processes, divides them into specific tasks, and trains machine learning models.

[1382] 3. Automation robots: These are automated devices used to perform routine tasks within a factory. Examples include ABB's IRB 6700 and Universal Robots' UR series.

[1383] Operation details

[1384] 1. Entering routine tasks:

[1385] Users input routine tasks in text format via their user terminals. The entered task details are sent to the server. For example, a user might input, "Check the machine oil at 6 PM every day."

[1386] 2. Analysis of business processes and generation of tasks:

[1387] The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "oil check" and "results report."

[1388] 3. Training machine learning models:

[1389] The server trains a machine learning model based on the analyzed task list. This model will then be used to distribute tasks.

[1390] 4. Task distribution and execution:

[1391] The server uses a trained machine learning model to distribute the generated tasks to the user and the automated robot. Specifically, it assigns "oil check" to the automated robot and "results report" to the user. The server sends instructions to the automated robot via an API.

[1392] 5. Display of progress and feedback:

[1393] An automated robot performs a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task's progress and provides corrections and feedback as needed. The server collects user feedback and updates the machine learning model.

[1394] Specific example

[1395] For example, consider automating parts inventory management. Using this system, a robot can check inventory at 8 AM every morning and automatically issue replenishment orders if any parts are missing. This enables rapid inventory management and reduces labor.

[1396] Example of a prompt

[1397] 1. "Check the machine's oil every day at 6 PM and notify us if there are any abnormalities."

[1398] 2. "Check the parts inventory every morning at 8:00 AM and issue replenishment orders if any are missing."

[1399] This invention not only efficiently automates routine tasks within the factory, but is also expected to reduce the burden on workers and improve operational efficiency. The procedure described above enables precise operation in an automated environment.

[1400] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1401] Step 1:

[1402] Entering routine tasks

[1403] Subject: User

[1404] Specific operation: Users access the system using their own devices (smartphones, tablets, PCs, etc.) and input routine tasks in text format.

[1405] Input: Routine task details entered by the user in text format (e.g., "Check the machine oil at 6 PM every day").

[1406] Output: The entered work details are sent to the server via the terminal.

[1407] Step 2:

[1408] Analysis of business processes and task generation

[1409] Subject: Server

[1410] Specific operation: The server analyzes the received business content using a natural language processing (NLP) engine and divides it into specific tasks.

[1411] Input: User-entered details of the work (in text format).

[1412] Data processing: Use an NLP engine to analyze text and break down business content into specific tasks.

[1413] Output: Analyzed task list (e.g., "Oil check", "Result report").

[1414] Step 3:

[1415] Training machine learning models

[1416] Subject: Server

[1417] Specific operation: The server trains a machine learning model based on the analyzed task list. It also utilizes historical data to improve model performance.

[1418] Input: Analyzed task list and past execution data.

[1419] Data processing: Train the model using machine learning algorithms.

[1420] Output: Trained machine learning model.

[1421] Step 4:

[1422] Task distribution and execution

[1423] Subject: Server, automation robot

[1424] Specific operation: The server uses a trained machine learning model to distribute each task to a user or an automated robot. The distributed tasks are then sent to the robot as instructions.

[1425] Input: Trained machine learning model and analyzed task list.

[1426] Data processing: Allocation is determined based on the priority and content of the tasks.

[1427] Output: The task instructed to the robot (e.g., "Instruction to perform an oil check").

[1428] Step 5:

[1429] Display of progress and feedback

[1430] Subject: Automation robot, server, user

[1431] Specific operation: An automated robot executes a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task progress and provides corrections and feedback as needed.

[1432] Input: Task progress data from the robot.

[1433] Data processing: Convert progress data into a dashboard format.

[1434] Output: Progress displayed on the dashboard, and user feedback.

[1435] Step 6:

[1436] Incorporating feedback and updating the model

[1437] Subject: Server

[1438] Specific operation: The server collects user feedback and updates the machine learning model based on it.

[1439] Input: User feedback data.

[1440] Data processing: Feed feedback data into a machine learning algorithm and retrain the model.

[1441] Output: Updated machine learning model.

[1442] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1443] Understood. The "Modes for Carrying Out the Invention" are shown below.

[1444] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[1445] System program configuration and specific operation

[1446] 1. Collect information about the work from the user.

[1447] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[1448] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[1449] 2. Analyze the work content and generate tasks.

[1450] Terminal: Sends the entered work details to the server.

[1451] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[1452] 3. Utilizing the Emotional Engine

[1453] Terminal: When a user inputs work details, the emotion engine collects data to recognize the user's emotions. This includes using text analysis to read emotions from the text and facial recognition technology via a webcam.

[1454] Server: The emotion engine analyzes the user's emotions and determines task priorities based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[1455] 4. Creating and optimizing the learning model

[1456] Server: Trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[1457] Terminal: Visually displays the progress and accuracy of the learning model to the user.

[1458] 5. Division and execution of tasks

[1459] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (copy AI)." For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Task assignments are also adjusted based on the emotion engine.

[1460] Server: Issues instructions to an automated system to perform a specific task. For example, using the Calendar API to schedule a meeting.

[1461] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[1462] 6. User Verification and Intervention

[1463] Terminal: Notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[1464] User: Review the task results and make corrections or provide feedback as needed.

[1465] Terminal: Collects user feedback and sends it to the server.

[1466] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1467] Specific example

[1468] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[1469] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[1470] 2. Terminal: Sends the input content to the server.

[1471] 3. Server: Analyzes the work content and divides it into two tasks: "set up a meeting" and "send notification emails." The emotion engine evaluates the user's stress level and adjusts the order of the tasks.

[1472] 4. Server: Trains the learning model based on the analysis results.

[1473] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[1474] 6. Server: Automatically schedule meetings using the Calendar API.

[1475] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[1476] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[1477] 9. Terminal: Send feedback to the server.

[1478] 10. Server: Update the learning model based on feedback.

[1479] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks, but also takes user emotions into consideration, enabling more efficient and less stressful work execution.

[1480] The following describes the processing flow.

[1481] Understood. The processing steps are explained in detail below.

[1482] Step 1:

[1483] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and selection options, allowing users to input details about their tasks. In addition, an emotion engine retrieves emotional data from the user's facial expressions and input patterns.

[1484] Step 2:

[1485] User: Enters specific task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." The emotion engine observes the user's input and recognizes emotions such as stress and anxiety.

[1486] Step 3:

[1487] Terminal: Retrieves the entered work details and sends them to the server. Simultaneously, it also sends the emotion data collected by the emotion engine to the server.

[1488] Step 4:

[1489] Server: The server analyzes the received text data using a natural language processing engine and divides the work content into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[1490] Step 5:

[1491] Server: Analyzes the emotional data provided by the emotion engine and evaluates the user's emotional state. Based on this evaluation, it adjusts the task prioritization and distribution method.

[1492] Step 6:

[1493] Server: Trains a machine learning model based on analysis results and sentiment data to learn user work patterns and sentiment patterns.

[1494] Step 7:

[1495] Server: Using a learning model, it distributes the generated tasks to the "user" and the "automation system (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Here, it utilizes data from the emotion engine to prioritize assigning difficult tasks when stress levels are low and easy tasks when stress levels are high.

[1496] Step 8:

[1497] Server: Issues instructions to an automated system to perform a specific task. For example, it can use a calendar API to automatically schedule meetings.

[1498] Step 9:

[1499] Terminal: Provides users with a dashboard that displays task progress in real time. Here, the sentiment engine also displays support messages and feedback tailored to the user's state.

[1500] Step 10:

[1501] User: Check the progress and results of completed tasks through the dashboard. Modify task results as needed.

[1502] Step 11:

[1503] Terminal: Collects user modifications and feedback and sends them to the server.

[1504] Step 12:

[1505] Server: Updates the learning model based on user feedback to further optimize task distribution and execution for future sessions.

[1506] Specific example

[1507] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[1508] Step 1:

[1509] Terminal: "Displays an interface for inputting routine tasks and captures the user's facial expressions using an emotion engine."

[1510] Step 2:

[1511] User: "I typed, 'Set up a meeting every Monday at 9:00 AM and send a notification email to participants,' and my facial expression was recognized."

[1512] Step 3:

[1513] Terminal: "Send input content and sentiment data to the server."

[1514] Step 4:

[1515] Server: "Analyzes the business process and divides it into two tasks. Analyzes emotional data and evaluates the user's emotional state."

[1516] Step 5:

[1517] Server: "Adjust task priorities and distribution methods based on sentiment evaluations."

[1518] Step 6:

[1519] Server: "Train a machine learning model based on analysis results and sentiment data."

[1520] Step 7:

[1521] Server: "Assign the automated system to set up meetings and the users to send notification emails."

[1522] Step 8:

[1523] Server: "Automatically schedule meetings using the Calendar API."

[1524] Step 9:

[1525] Terminal: "Displays execution status in real time on the dashboard and shows sentiment-based messages."

[1526] Step 10:

[1527] User: "Check the task progress on the dashboard and make corrections as needed."

[1528] Step 11:

[1529] Terminal: "Send corrections and feedback to the server."

[1530] Step 12:

[1531] Server: "Update the learning model based on feedback."

[1532] The above outlines the specific processing steps for implementing this invention. This system not only efficiently automates routine tasks but also takes into account the user's emotional state, enabling more efficient and less stressful work execution.

[1533] (Example 2)

[1534] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1535] Traditional business automation systems fail to consider the user's emotional state when allocating or prioritizing tasks, potentially leading to user stress and decreased work efficiency. Furthermore, real-time updates of machine learning models based on user feedback are difficult, resulting in limited system adaptability.

[1536] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1537] In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for collecting user sentiment data based on the analyzed tasks, means for analyzing the collected sentiment data and determining task priorities, means for training a machine learning model based on the analyzed tasks and sentiment data, means for distributing tasks to the user and the automation system using the trained learning model, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables automation of tasks that take user sentiment into consideration and real-time system adaptation based on feedback.

[1538] A "user" refers to a person who uses the system to input data and provide feedback.

[1539] "Routine tasks" refer to repetitive tasks that users need to perform regularly.

[1540] "Text format" refers to a data format represented by strings of characters.

[1541] "Means" refers to the methods or devices used to achieve a specific objective.

[1542] "Job description" refers to the specific tasks and details of work that users input into the system.

[1543] "Analysis" refers to the process of breaking down input data and understanding its meaning and structure.

[1544] "Specific tasks" refer to individual work units that can be executed based on the analyzed business content.

[1545] "Emotional data" refers to information that indicates a user's emotional state. This includes facial expressions, tone of voice, and emotional expressions in text.

[1546] "Collecting emotional data" refers to the process of obtaining a user's emotions and storing them in an analyzable format.

[1547] "Emotional analysis" refers to the process of processing collected emotional data to understand the user's emotional state.

[1548] "Priority" refers to determining the order in which tasks are performed and their importance.

[1549] A "machine learning model" refers to an algorithm that learns specific patterns based on data and uses them to make future predictions and decisions.

[1550] "Training" refers to the process of using data to train a machine learning model to achieve an optimal state.

[1551] An "automation system" refers to a system of software or hardware designed to automatically perform specific tasks.

[1552] "Progress status" refers to information indicating the stage of a task.

[1553] "Feedback" refers to the evaluations and opinions that users provide to a system.

[1554] "Updating" refers to the process of improving existing machine learning models and systems using new information and feedback.

[1555] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks by coordinating various technologies, with terminals, servers, and users as the main components.

[1556] System configuration and operation

[1557] First, the system collects information about routine tasks from the user. In this process, the terminal displays an input interface to the user, who then inputs the task details in text format.

[1558] Specific actions

[1559] 1. Collect information about the work from the user.

[1560] Terminal: The terminal displays an interface for users to input routine tasks. This interface includes text boxes and selection options, allowing users to freely input task details. Software used includes HTML, CSS, and JavaScript.

[1561] User: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1562] 2. Analyze the work content and generate tasks.

[1563] Terminal: Sends the entered work details to the server via an HTTP request.

[1564] Server: The server uses a natural language processing engine (e.g., SpaCy, Transformer) to analyze the received business data. For example, it might break it down into specific tasks such as "setting up a meeting" and "sending notification emails." This clarifies the specific routine tasks that the system will handle.

[1565] 3. Utilizing the Emotional Engine

[1566] Terminal: When a user inputs work details, the terminal uses its camera and microphone to collect user emotion data. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[1567] Server: The server analyzes the data collected using the emotion engine to understand the user's emotional state. Based on the collected emotional data, it determines task priorities. For example, if a user is feeling stressed, it adjusts the assignment to prioritize easier tasks.

[1568] 4. Creating and optimizing the learning model

[1569] Server: Trains a machine learning model based on the analyzed task and sentiment data. This training uses Scikit-learn or TensorFlow. The trained model learns the user's work patterns and sentiment patterns and reflects them in subsequent execution.

[1570] Terminal: Use graphs and dashboards (e.g., Plotly, Grafana) to visually display training progress and accuracy to the user.

[1571] 5. Division and execution of tasks

[1572] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (e.g., Zapier or IFTTT)." For example, it might assign "setting up a meeting" to an automation system and "sending notification emails" to a user. The server also uses the Google Calendar API, etc., to automate tasks such as setting up meetings.

[1573] Terminal: Provides a dashboard to display task progress to the user in real time. Users can check the task execution status through the dashboard and intervene or correct as needed.

[1574] 6. User Verification and Intervention

[1575] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[1576] User: Review the task results and make corrections or provide feedback as needed.

[1577] Terminal: Sends collected feedback to the server.

[1578] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1579] Specific example

[1580] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[1581] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[1582] 2. Terminal: Sends the input content to the server.

[1583] 3. Server: Analyzes work content and divides it into "meeting scheduling" and "sending notification emails." An emotion engine evaluates the user's stress level.

[1584] 4. Server: Trains the learning model based on the analysis results.

[1585] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[1586] 6. Server: Automatically schedule meetings using the Google Calendar API.

[1587] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[1588] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[1589] 9. Terminal: Send feedback to the server.

[1590] 10. Server: Update the learning model based on feedback.

[1591] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks but also enables appropriate task distribution that takes into account the user's emotions, resulting in more efficient and less stressful work performance.

[1592] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1593] Step 1:

[1594] Collect information about the work performed by the user.

[1595] Terminal: Displays an interface where the user can input work details. This interface includes text boxes and selection options. This allows the user to input details of routine tasks in text format.

[1596] Input: User's job description (e.g., "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants").

[1597] Output: Text data of the work details entered by the user.

[1598] Step 2:

[1599] Sending and analyzing work details

[1600] Terminal: Sends the entered work details to the server. This process is performed via an HTTP request.

[1601] Server: The server analyzes the received text data using a natural language processing engine (e.g., SpaCy, Transformer) and divides it into specific tasks.

[1602] Input: Text data of the work details entered by the user.

[1603] Output: Specific tasks analyzed (e.g., "Set up a meeting", "Send notification email").

[1604] Step 3:

[1605] Collection of emotional data

[1606] Terminal: When users input work details, the system collects emotional data using the camera and microphone. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[1607] Input: User's facial expressions and voice data.

[1608] Output: Collected emotional data (e.g., facial features, voice tone).

[1609] Step 4:

[1610] Analysis of emotional data

[1611] Server: The collected emotional data is analyzed by an emotion engine to understand the user's emotional state. Emotional scores and stress levels are calculated.

[1612] Input: Collected sentiment data.

[1613] Output: Sentiment score and stress level.

[1614] Step 5:

[1615] Training machine learning models

[1616] Server: Trains a machine learning model based on the analyzed task and sentiment data. This uses Scikit-learn or TensorFlow. The model learns the user's work patterns and sentiment patterns.

[1617] Input: Analyzed task and sentiment data.

[1618] Output: Trained machine learning model.

[1619] Step 6:

[1620] Task distribution

[1621] Server: Uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, assigning "setting up a meeting" to the automation system and "sending notification emails" to users.

[1622] Input: A trained machine learning model and the task to be analyzed.

[1623] Output: Distributed tasks.

[1624] Step 7:

[1625] Task execution and progress display

[1626] Server: Issues instructions to the automation system to execute tasks. Specifically, it uses the Google Calendar API to schedule meetings.

[1627] Terminal: Provides a dashboard to display task progress to the user in real time.

[1628] Input: Assigned tasks.

[1629] Output: Tasks performed and their progress.

[1630] Step 8:

[1631] User verification and intervention

[1632] Terminal: Displays the results of completed tasks on the dashboard and notifies the user.

[1633] User: Review the task results and make corrections or provide feedback as needed.

[1634] Terminal: Sends corrections and feedback to the server.

[1635] Server: Updates the machine learning model based on feedback.

[1636] Input: User feedback.

[1637] Output: Updated machine learning model.

[1638] These processing steps enable the system to efficiently automate users' routine tasks and achieve task distribution that takes emotions into account.

[1639] (Application Example 2)

[1640] Next, we will explain application example 2. In the following explanation, 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."

[1641] Modern factories and logistics centers have numerous routine tasks that must be handled efficiently. In particular, since employee performance fluctuates depending on their emotional state, task allocation that takes emotions into account is crucial. However, current systems often fail to consider user emotions when assigning tasks, limiting efficiency. Furthermore, assigning tasks without considering employee emotions can cause stress, leading to decreased satisfaction and productivity. Therefore, a system is needed that not only streamlines routine tasks but also dynamically reflects user emotions in task allocation.

[1642] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for analyzing emotional data and distributing and adjusting tasks according to the emotional state, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables dynamic task distribution that takes the user's emotions into consideration, making it possible to simultaneously achieve increased work efficiency and reduced stress.

[1643] "Routine tasks" refer to standardized tasks that are performed repeatedly on a daily basis.

[1644] "Text format" refers to a format that uses strings of characters to represent information.

[1645] "Analysis" refers to the process of breaking down input information and understanding its contents in detail.

[1646] A "task" refers to an individual work or activity performed to achieve a specific objective.

[1647] A "machine learning model" refers to the structure of an algorithm that learns from data and performs predictions and classifications.

[1648] "Training" refers to the process of using data to allow a machine learning model to learn.

[1649] An "automation system" refers to a system that performs specific tasks or processes without human intervention.

[1650] "Distribution" refers to the process of allocating specific resources or tasks to multiple targets.

[1651] "Emotional data" refers to data that represents the emotional state of a user.

[1652] "Analysis" refers to the process of examining data in detail and understanding its patterns and meanings.

[1653] "Adjustment" refers to changing the arrangement or content based on specific conditions.

[1654] "Execution" refers to actually carrying out the planned tasks.

[1655] "Progress status" refers to information that indicates the degree of completion during the task's execution process.

[1656] "Display" refers to the visual presentation of information.

[1657] "Feedback" refers to providing information or opinions about a particular action or outcome.

[1658] "Updating" refers to improving or changing existing data or systems based on new information.

[1659] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting the user's emotions in the work process. Specific embodiments are described in detail below.

[1660] System Configuration

[1661] This system automates tasks through the collaboration of terminals, servers, and users. The main hardware used includes smart glasses and factory robots, while the software includes EmotionEngine (emotion recognition engine), TaskParser (task analysis engine), RobotController (robot control API), and SmartGlasses (smart glasses API).

[1662] Specific actions

[1663] 1. Collect information about the work from the user.

[1664] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, where users can enter specific details about their tasks.

[1665] Users input task details such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1666] 2. Analyze the work content and generate tasks.

[1667] The terminal sends the entered work information to the server.

[1668] The server analyzes the received work content using TaskParser and divides it into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[1669] 3. Utilizing the Emotional Engine

[1670] When a user inputs work details, the terminal collects data for EmotionEngine to recognize the user's emotions. This includes text analysis and facial recognition via the camera.

[1671] The server uses EmotionEngine to analyze the user's emotions and prioritizes tasks based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[1672] 4. Creating and optimizing the learning model

[1673] The server trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[1674] 5. Division and execution of tasks

[1675] The server uses a trained learning model to distribute tasks between "users" and "automation systems." For example, it might assign "setting up a meeting" to the automation system and "sending notification emails" to the user.

[1676] The server issues instructions to the automated system to perform specific tasks. For example, it might use the Calendar API to schedule a meeting.

[1677] 6. User Verification and Intervention

[1678] The device notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[1679] Users review the task results and make corrections or provide feedback as needed.

[1680] Specific example

[1681] For example, in the automation of production operations in a factory:

[1682] 1. The user enters "replenish materials on the packaging line" as their job description, and sentiment data is also collected.

[1683] 2. The terminal sends the input content to the server.

[1684] 3. The server analyzes the work content and divides it into two tasks: "preparing materials" and "replenishing materials." The emotion engine assesses the user's stress level and adjusts the order of the tasks.

[1685] 4. The server trains a learning model based on the analysis results.

[1686] 5. The server distributes the task of "preparing materials" to the automated system and the task of "replenishing materials" to the user.

[1687] 6. The server instructs the robot to "prepare materials," and it executes this automatically.

[1688] 7. The terminal displays the task progress in real time and shows appropriate support messages.

[1689] 8. The user confirms that the task is complete and provides feedback as needed.

[1690] Example of a prompt

[1691] "It seems that worker A is unhappy. Please have them handle the easier tasks first."

[1692] "The next task is 'replenishing materials on the packaging line.' Due to its high stress level, please assign this task to a robot."

[1693] This allows for efficient automation of each process while simultaneously enabling flexible task management that reflects user emotions, resulting in improved overall productivity and satisfaction.

[1694] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1695] Step 1:

[1696] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, allowing users to input specific details about their tasks. The input data here consists of text or voice information describing the user's work. For example, specific tasks such as "replenishing materials on the packaging line" might be entered.

[1697] Step 2:

[1698] The terminal transmits the entered work information to the server. At this time, the entered text or voice data is transferred to the server and prepared for analysis. The role of the terminal is to transmit the collected data to the server quickly and accurately.

[1699] Step 3:

[1700] The server uses TaskParser to analyze the received business information and divides it into specific tasks. For example, it might divide it into tasks such as "prepare materials" and "replenish materials." This process utilizes natural language processing technology to analyze the text data and identify each business task.

[1701] Step 4:

[1702] The terminal uses EmotionEngine to collect emotional data when users input work-related information. The collected data includes emotion determination through text analysis and facial recognition via the camera. The input data represents information about the user's emotional state, such as stress levels and satisfaction levels.

[1703] Step 5:

[1704] The server analyzes emotional data using EmotionEngine and determines task priorities based on the results. For example, if a user's stress level is high, it will assign them easier tasks first. This process involves performing data calculations that prioritize tasks using emotional analysis data.

[1705] Step 6:

[1706] The server trains a machine learning model based on the analyzed task and sentiment data. In this process, it uses a large amount of historical task and sentiment state data to generate a model that will help with future task allocation and sentiment regulation. The input data is the analyzed task and sentiment data, and the output is the updated machine learning model.

[1707] Step 7:

[1708] The server uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, it might assign "preparing materials" to the automation system and "replenishing materials" to the user. This process involves data calculations that use the machine learning model to determine the optimal task distribution.

[1709] Step 8:

[1710] The server issues instructions to the automated system to perform specific tasks. For example, it might use RobotController to instruct a factory robot to prepare materials. In this process, specific operation commands are generated as output data that are sent to the robot.

[1711] Step 9:

[1712] The device displays the task progress to the user in real time. Here, the SmartGlasses API is used to visually display the task progress on smart glasses. The displayed data includes the task's progress and completion status.

[1713] Step 10:

[1714] Users review the results of completed tasks and make corrections or provide feedback as needed. This feedback can include comments such as "Task complete" or "Needs correction." This allows the system to reflect the user's intentions.

[1715] Step 11:

[1716] The terminal sends user feedback to the server. This feedback data is used to further optimize task distribution and execution in the future.

[1717] Step 12:

[1718] The server updates the machine learning model based on the feedback received. This allows the model to reflect the latest data, enabling more accurate task allocation and sentiment adjustment. The output data is the updated machine learning model.

[1719] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1720] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1721] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1722] [Fourth Embodiment]

[1723] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1724] As shown in Figure 7, the 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.

[1725] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1726] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1727] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1728] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1729] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1730] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1731] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1732] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1733] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1734] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1735] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1736] Understood. The "Modes for Carrying Out the Invention" are shown below.

[1737] This invention is a system designed to enable users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[1738] System program configuration and specific operation

[1739] 1. Collect information about the work from the user.

[1740] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[1741] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[1742] 2. Analyze the work content and generate tasks.

[1743] Terminal: Performs processing to send the work details entered by the user to the server.

[1744] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[1745] 3. Creating and optimizing the learning model

[1746] Server: Trains a machine learning model based on the analyzed task list. The model used here learns the user's work patterns and uses this knowledge to improve future task allocation.

[1747] Terminal: Equipped with a function to visually display the progress and accuracy of the learning model to the user.

[1748] 4. Division and execution of tasks

[1749] Server: Using a learning model, it distributes the generated tasks to "users" and "automation systems (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[1750] Server: Issues instructions to the copy AI to perform specific tasks. The server also uses the Calendar API and Email API to execute tasks.

[1751] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[1752] 5. User Verification and Intervention

[1753] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard.

[1754] User: Review the task results and make corrections or provide feedback as needed. For example, adjust the content of the notification email.

[1755] Terminal: Collects user feedback and sends it to the server.

[1756] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1757] Specific example

[1758] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[1759] 1. User: Enter the following text for the job description: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[1760] 2. Terminal: Sends the input content to the server.

[1761] 3. Server: Analyzes the work content and divides it into two tasks: "setting up a meeting" and "sending notification emails".

[1762] 4. Server: Trains machine learning models based on the analysis results.

[1763] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[1764] 6. Server: Automatically schedule meetings using the Calendar API.

[1765] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[1766] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[1767] 9. Terminal: Send feedback to the server.

[1768] 10. Server: Update the learning model based on feedback.

[1769] The above describes a specific embodiment for carrying out this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[1770] The following describes the processing flow.

[1771] Understood. The processing steps are explained in detail below.

[1772] Step 1:

[1773] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and multiple selection options where users can enter details about their tasks.

[1774] Step 2:

[1775] User: Enter task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1776] Step 3:

[1777] Terminal: Retrieves the entered work details and sends them to the server for analysis.

[1778] Step 4:

[1779] Server: Sends the received text data to the natural language processing engine and starts the analysis. The analysis structures the business content and divides it into specific tasks.

[1780] Step 5:

[1781] Server: Based on the analysis results, it generates specific tasks. For example, it might divide the data into two tasks: "Set up a meeting" and "Send a notification email."

[1782] Step 6:

[1783] Server: Inputs the generated task list into a machine learning engine to learn the user's work patterns.

[1784] Step 7:

[1785] Server: Uses a learned model to determine the optimal way to distribute tasks.

[1786] Step 8:

[1787] Server: Distributes tasks between "users" and "automation systems (copy AI)". For example, assigns "setting up a meeting" to the automation system and "sending notification emails" to users.

[1788] Step 9:

[1789] Server: Issues task execution instructions to the automation system. For example, it can use the Calendar API to automatically schedule meetings.

[1790] Step 10:

[1791] Terminal: Provides users with a dashboard that displays task progress in real time.

[1792] Step 11:

[1793] User: Check the progress and results of completed tasks through the dashboard.

[1794] Step 12:

[1795] User: Modify the task results as needed and provide feedback.

[1796] Step 13:

[1797] Terminal: Collects user feedback and sends it to the server.

[1798] Step 14:

[1799] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[1800] The above outlines the specific processing steps for implementing this invention. This system efficiently automates routine tasks, allowing users to focus on important tasks.

[1801] (Example 1)

[1802] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1803] In today's business environment, routine tasks consume a great deal of time and effort while adding little value, making efficient automation of these tasks essential. However, routine tasks are diverse, and there is a lack of means to accurately analyze each task and automate it appropriately. Furthermore, there are few systems that allow for real-time monitoring of task progress or systems that update models based on user feedback. There is a need for highly practical automation systems to address these challenges.

[1804] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1805] In this invention, the server includes means for users to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, and means for training a machine learning model based on the analyzed tasks. This enables efficient automation of routine tasks, reduces the burden on users, and improves operational efficiency.

[1806] A "user" is an individual or group that uses the system to automate routine tasks.

[1807] "Routine tasks" are work or tasks that are performed repeatedly at regular intervals.

[1808] "Text format" refers to a method of inputting information as a string of characters, allowing users to freely enter text and data.

[1809] "Analysis" is the process of breaking down input data and business operations and classifying them into specific patterns or elements.

[1810] A "task" is an individual work or unit of work performed to achieve a specific objective.

[1811] A "machine learning model" is an algorithm that learns specific patterns based on data and uses them to make predictions and decisions.

[1812] "Training" is the process by which a machine learning model analyzes data and optimizes the model in order to make the best predictions and decisions.

[1813] An "automation platform" is a system or software designed to automatically perform specific tasks.

[1814] A "Calendar API" is a programmatic interface for creating and managing schedules in conjunction with external calendar systems.

[1815] A "mail API" is a programmatic interface for sending and receiving emails in conjunction with external mail servers and services.

[1816] A "dashboard" is a user interface that visually displays the progress of tasks and various metrics.

[1817] "Feedback" refers to the opinions and evaluations provided by users regarding the output results and operation of a system.

[1818] This invention is a system designed to enable users to efficiently automate routine tasks, thereby improving work efficiency and work-life balance. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[1819] Program processing

[1820] Collect information about the work performed by the user.

[1821] The terminal first displays an interface for the user to input routine tasks. This interface includes text boxes and selection options.

[1822] Users input routine tasks into the interface in text format. For example, they might enter a specific task such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1823] The terminal validates the entered data and prompts the user to correct any errors.

[1824] Analyze the business process and generate tasks.

[1825] The terminal sends the work details that have passed validation to the server.

[1826] The server analyzes the received business content using a natural language processing engine (e.g., a natural language processing API). As a result of the analysis, the business content is divided into specific tasks. For example, it might be divided into "setting up a meeting" and "sending a notification email."

[1827] The server saves the analysis results to an internal database and generates a task list.

[1828] Creating and optimizing learning models

[1829] The server trains a machine learning model (e.g., a machine learning library) based on the generated task list. The data used here consists of past business data and feedback history.

[1830] The device visualizes and displays training progress and accuracy to the user, using graphs and statistical information.

[1831] The server evaluates the trained model and optimizes it as needed.

[1832] Division and execution of tasks

[1833] The server uses a trained model to distribute tasks between "users" and "automation platforms." For example, it might assign "setting up a meeting" to the automation platform and "sending notification emails" to users.

[1834] The server issues instructions to the automation platform, using the calendar API and email API to perform specific tasks. For example, it might automatically add a new meeting to the calendar.

[1835] The device provides users with a dashboard that displays the progress of tasks in real time.

[1836] User verification and intervention

[1837] The device notifies the user of the results of the completed tasks and displays them on the dashboard.

[1838] Users review the task results and make corrections or provide feedback as needed. For example, they might adjust the content of notification emails.

[1839] The device collects user feedback and sends it to the server.

[1840] The server updates its learning model based on the feedback, optimizing task allocation and execution for the next time.

[1841] Specific example

[1842] For example, to automate the scheduling of a weekly meeting held by a member of the marketing department:

[1843] 1. User: Enter the task description in text format: "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants."

[1844] 2. Terminal: Sends the input content to the server.

[1845] 3. Server: Analyze the work content and divide it into two tasks: "Set up a meeting" and "Send notification emails."

[1846] 4. Server: Trains machine learning models based on the analysis results.

[1847] 5. Server: Automate meeting setup to the platform and distribute notification email sending to users.

[1848] 6. Server: Automatically schedule meetings using the Calendar API.

[1849] 7. Terminal: Displays the execution status to the user in real time via a dashboard.

[1850] 8. User: Confirm that the meeting has been set up and modify the notification email content if necessary.

[1851] 9. Terminal: Send feedback to the server.

[1852] 10. Server: Updates the learning model based on feedback.

[1853] Examples of prompt statements

[1854] For example, input the following prompt message into the AI ​​model:

[1855] "How can I set up a meeting every Monday at 9 AM and automatically send notification emails to participants?"

[1856] "Please suggest the optimal task breakdown method for automating recurring tasks."

[1857] This allows the system to provide specific steps for automating tasks that meet the user's needs.

[1858] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1859] Step 1: Enter details of the work

[1860] Terminal: First, an interface is displayed for the user to input routine tasks. This interface includes text boxes and selection options.

[1861] Input: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[1862] Operation: The terminal receives the input data and temporarily stores it in its internal data storage.

[1863] Step 2: Validation of the work content

[1864] Terminal: Start the validation process. Verify that the format and content of the entered data are correct.

[1865] Input: Text data entered by the user.

[1866] Data processing: Perform validation on input data, including grammatical error checks and verification of required fields.

[1867] Output: Generates validation results and notifies the user if there are any errors.

[1868] Action: The terminal displays error messages and correction requests to the user.

[1869] Step 3: Submit the work details

[1870] Terminal: Sends the business details that have passed validation to the server.

[1871] Input: Text data that has passed validation.

[1872] Data processing: Encode data into a format that the server can understand.

[1873] Output: Details of the tasks to be sent to the server.

[1874] Operation: The terminal sends data to the server using methods such as HTTP requests.

[1875] Step 4: Analysis of Business Operations

[1876] Server: Analyzes the received work content using a natural language processing engine.

[1877] Input: Text data sent from the device.

[1878] Data processing: Analyze text using a natural language processing engine and break it down into specific tasks.

[1879] Output: Analyzed task list.

[1880] Operation: The server calls a natural language processing API and saves the analysis results to an internal database.

[1881] Step 5: Generate a task list

[1882] Server: Generates a list of executable tasks based on the analysis results.

[1883] Input: Analyzed business operations.

[1884] Data processing: Set the attributes of the task (e.g., deadline, assignee, importance, etc.).

[1885] Output: Completed task list.

[1886] Operation: The server composes a task list and passes it on to the next processing step.

[1887] Step 6: Training the machine learning model

[1888] Server: Trains machine learning models based on the task list.

[1889] Input: Past business data and analyzed task list.

[1890] Data processing: Input data into the model and run the learning algorithm.

[1891] Output: Trained machine learning model.

[1892] Operation: The server calls machine learning libraries to train the model.

[1893] Step 7: Task Distribution

[1894] Server: Uses trained models to distribute tasks to "users" and "automation platforms".

[1895] Input: Trained model and task list.

[1896] Data processing: Execute algorithms that optimally distribute tasks based on the model.

[1897] Output: Distributed task list.

[1898] Operation: The server issues instructions to the automation platform and assigns tasks.

[1899] Step 8: Execute the task

[1900] Server: Executes the specified task.

[1901] Input: Distributed task list.

[1902] Data calculations: Generate requests to call the Calendar API and Mail API.

[1903] Output: Execution result.

[1904] Operation: The server calls the API to set up meetings and send notification emails.

[1905] Step 9: Displaying Task Progress

[1906] Terminal: Provides a dashboard that displays task progress in real time.

[1907] Input: Execution results and progress data sent from the server.

[1908] Data processing: Convert data into a format that is easy to visualize.

[1909] Output: Visual progress display on the dashboard.

[1910] Operation: The device displays the progress using graphs and charts.

[1911] Step 10: Gathering Feedback and Updating the Model

[1912] Device: Collects user feedback.

[1913] Input: User feedback comments and suggested improvements.

[1914] Output: Feedback data.

[1915] Action: The device sends feedback to the server.

[1916] Server: Updates the learning model based on the feedback received.

[1917] Input: Feedback data.

[1918] Data processing: Retrain the model to improve accuracy.

[1919] Output: Updated machine learning model.

[1920] Operation: The server saves the latest model and applies it to subsequent operations.

[1921] The above outlines the specific processing steps of this system. This system allows users to efficiently automate routine tasks.

[1922] (Application Example 1)

[1923] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1924] In modern factories, manual processing of routine tasks is time-consuming and labor-intensive, reducing production efficiency. Furthermore, there is a need to reduce the burden on workers, improve work-life balance, and minimize human error. However, the problem is that conventional systems lack efficient methods to address these challenges.

[1925] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1926] In this invention, the server includes means for a user to input routine tasks in text format, means for analyzing the input tasks and dividing them into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for sending instructions to the automation robot to execute the distributed tasks, means for displaying the progress to the user, and means for obtaining user feedback and updating the learning model. As a result, routine tasks in the factory are efficiently automated, reducing the burden on workers, improving work efficiency, and reducing errors.

[1927] A "user" is the entity that uses the system to input and manage routine tasks.

[1928] "Routine tasks" refer to standardized tasks or duties that are performed repeatedly.

[1929] "Text format" refers to the format in which information is entered as text characters.

[1930] "Means" refer to the methods or processes used to achieve a specific objective.

[1931] "Analysis" is the process of understanding and breaking down the entered business data.

[1932] A "task" is a division of work content into specific actions or tasks.

[1933] A "machine learning model" is a program that uses algorithms and data to perform pattern recognition and prediction.

[1934] "Training" is the process of using data to allow a machine learning model to learn.

[1935] An "automation system" is a set of hardware and software designed to automate routine tasks.

[1936] "Distribution" is the process of assigning analyzed tasks to users and automated systems.

[1937] An "automation robot" is a machine used to perform routine tasks within a factory.

[1938] "Sending instructions" means sending a command from the server to an automated robot to execute a task.

[1939] "Progress status" refers to information indicating the stage of a task.

[1940] "Displaying" means providing users with a visual representation of the progress or results.

[1941] "Feedback" refers to the process of communicating user opinions and requests for corrections to the system.

[1942] "Updating" is the process of improving a machine learning model based on the feedback received.

[1943] This invention is a system that allows users to efficiently automate routine tasks within a factory, improve productivity, and reduce the burden on workers. The specific configuration and operation of this system are described below.

[1944] System Configuration

[1945] The system consists of the following main components:

[1946] 1. User terminal: Provides an interface for users to input and manage routine tasks. Specifically, smartphones, tablets, PCs, etc., are used.

[1947] 2. Server: Analyzes the business processes, divides them into specific tasks, and trains machine learning models.

[1948] 3. Automation robots: These are automated devices used to perform routine tasks within a factory. Examples include ABB's IRB 6700 and Universal Robots' UR series.

[1949] Operation details

[1950] 1. Entering routine tasks:

[1951] Users input routine tasks in text format via their user terminals. The entered task details are sent to the server. For example, a user might input, "Check the machine oil at 6 PM every day."

[1952] 2. Analysis of business processes and generation of tasks:

[1953] The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "oil check" and "results report."

[1954] 3. Training machine learning models:

[1955] The server trains a machine learning model based on the analyzed task list. This model will then be used to distribute tasks.

[1956] 4. Task distribution and execution:

[1957] The server uses a trained machine learning model to distribute the generated tasks to the user and the automated robot. Specifically, it assigns "oil check" to the automated robot and "results report" to the user. The server sends instructions to the automated robot via an API.

[1958] 5. Display of progress and feedback:

[1959] An automated robot performs a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task's progress and provides corrections and feedback as needed. The server collects user feedback and updates the machine learning model.

[1960] Specific example

[1961] For example, consider automating parts inventory management. Using this system, a robot can check inventory at 8 AM every morning and automatically issue replenishment orders if any parts are missing. This enables rapid inventory management and reduces labor.

[1962] Example of a prompt

[1963] 1. "Check the machine's oil every day at 6 PM and notify us if there are any abnormalities."

[1964] 2. "Check the parts inventory every morning at 8:00 AM and issue replenishment orders if any are missing."

[1965] This invention not only efficiently automates routine tasks within the factory, but is also expected to reduce the burden on workers and improve operational efficiency. The procedure described above enables precise operation in an automated environment.

[1966] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1967] Step 1:

[1968] Entering routine tasks

[1969] Subject: User

[1970] Specific operation: Users access the system using their own devices (smartphones, tablets, PCs, etc.) and input routine tasks in text format.

[1971] Input: Routine task details entered by the user in text format (e.g., "Check the machine oil at 6 PM every day").

[1972] Output: The entered work details are sent to the server via the terminal.

[1973] Step 2:

[1974] Analysis of business processes and task generation

[1975] Subject: Server

[1976] Specific operation: The server analyzes the received business content using a natural language processing (NLP) engine and divides it into specific tasks.

[1977] Input: User-entered details of the work (in text format).

[1978] Data processing: Use an NLP engine to analyze text and break down business content into specific tasks.

[1979] Output: Analyzed task list (e.g., "Oil check", "Result report").

[1980] Step 3:

[1981] Training machine learning models

[1982] Subject: Server

[1983] Specific operation: The server trains a machine learning model based on the analyzed task list. It also utilizes historical data to improve model performance.

[1984] Input: Analyzed task list and past execution data.

[1985] Data processing: Train the model using machine learning algorithms.

[1986] Output: Trained machine learning model.

[1987] Step 4:

[1988] Task distribution and execution

[1989] Subject: Server, automation robot

[1990] Specific operation: The server uses a trained machine learning model to distribute each task to a user or an automated robot. The distributed tasks are then sent to the robot as instructions.

[1991] Input: Trained machine learning model and analyzed task list.

[1992] Data processing: Allocation is determined based on the priority and content of the tasks.

[1993] Output: The task instructed to the robot (e.g., "Instruction to perform an oil check").

[1994] Step 5:

[1995] Display of progress and feedback

[1996] Subject: Automation robot, server, user

[1997] Specific operation: An automated robot executes a task and reports its progress to the server. The server displays this information in real time on a dashboard on the user's terminal. The user checks the task progress and provides corrections and feedback as needed.

[1998] Input: Task progress data from the robot.

[1999] Data processing: Convert progress data into a dashboard format.

[2000] Output: Progress displayed on the dashboard, and user feedback.

[2001] Step 6:

[2002] Incorporating feedback and updating the model

[2003] Subject: Server

[2004] Specific operation: The server collects user feedback and updates the machine learning model based on it.

[2005] Input: User feedback data.

[2006] Data processing: Feed feedback data into a machine learning algorithm and retrain the model.

[2007] Output: Updated machine learning model.

[2008] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[2009] Understood. The "Modes for Carrying Out the Invention" are shown below.

[2010] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks through the coordinated efforts of terminals, servers, and users.

[2011] System program configuration and specific operation

[2012] 1. Collect information about the work from the user.

[2013] Terminal: First, the terminal displays an interface for the user to input routine tasks. The interface includes text boxes and selection options where the user enters specific details about the tasks.

[2014] User: Users input task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." This determines the specific routine tasks that the system will handle.

[2015] 2. Analyze the work content and generate tasks.

[2016] Terminal: Sends the entered work details to the server.

[2017] Server: The server analyzes the received business data using a natural language processing engine and divides it into specific tasks. For example, it might divide it into two tasks: "set up a meeting" and "send a notification email."

[2018] 3. Utilizing the Emotional Engine

[2019] Terminal: When a user inputs work details, the emotion engine collects data to recognize the user's emotions. This includes using text analysis to read emotions from the text and facial recognition technology via a webcam.

[2020] Server: The emotion engine analyzes the user's emotions and determines task priorities based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[2021] 4. Creating and optimizing the learning model

[2022] Server: Trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[2023] Terminal: Visually displays the progress and accuracy of the learning model to the user.

[2024] 5. Division and execution of tasks

[2025] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (copy AI)." For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Task assignments are also adjusted based on the emotion engine.

[2026] Server: Issues instructions to an automated system to perform a specific task. For example, using the Calendar API to schedule a meeting.

[2027] Terminal: Provides users with a dashboard that displays task progress in real time. Users can check the execution status through the dashboard and intervene or correct as needed.

[2028] 6. User Verification and Intervention

[2029] Terminal: Notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[2030] User: Review the task results and make corrections or provide feedback as needed.

[2031] Terminal: Collects user feedback and sends it to the server.

[2032] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[2033] Specific example

[2034] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[2035] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[2036] 2. Terminal: Sends the input content to the server.

[2037] 3. Server: Analyzes the work content and divides it into two tasks: "set up a meeting" and "send notification emails." The emotion engine evaluates the user's stress level and adjusts the order of the tasks.

[2038] 4. Server: Trains the learning model based on the analysis results.

[2039] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[2040] 6. Server: Automatically schedule meetings using the Calendar API.

[2041] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[2042] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[2043] 9. Terminal: Send feedback to the server.

[2044] 10. Server: Update the learning model based on feedback.

[2045] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks, but also takes user emotions into consideration, enabling more efficient and less stressful work execution.

[2046] The following describes the processing flow.

[2047] Understood. The processing steps are explained in detail below.

[2048] Step 1:

[2049] Terminal: Displays an interface for users to input routine tasks. The interface includes text boxes and selection options, allowing users to input details about their tasks. In addition, an emotion engine retrieves emotional data from the user's facial expressions and input patterns.

[2050] Step 2:

[2051] User: Enters specific task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send notification emails to participants." The emotion engine observes the user's input and recognizes emotions such as stress and anxiety.

[2052] Step 3:

[2053] Terminal: Retrieves the entered work details and sends them to the server. Simultaneously, it also sends the emotion data collected by the emotion engine to the server.

[2054] Step 4:

[2055] Server: The server analyzes the received text data using a natural language processing engine and divides the work content into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[2056] Step 5:

[2057] Server: Analyzes the emotional data provided by the emotion engine and evaluates the user's emotional state. Based on this evaluation, it adjusts the task prioritization and distribution method.

[2058] Step 6:

[2059] Server: Trains a machine learning model based on analysis results and sentiment data to learn user work patterns and sentiment patterns.

[2060] Step 7:

[2061] Server: Using a learning model, it distributes the generated tasks to the "user" and the "automation system (copy AI)". For example, it assigns "setting up a meeting" to the automation system and "sending notification emails" to the user. Here, it utilizes data from the emotion engine to prioritize assigning difficult tasks when stress levels are low and easy tasks when stress levels are high.

[2062] Step 8:

[2063] Server: Issues instructions to an automated system to perform a specific task. For example, it can use a calendar API to automatically schedule meetings.

[2064] Step 9:

[2065] Terminal: Provides users with a dashboard that displays task progress in real time. Here, the sentiment engine also displays support messages and feedback tailored to the user's state.

[2066] Step 10:

[2067] User: Check the progress and results of completed tasks through the dashboard. Modify task results as needed.

[2068] Step 11:

[2069] Terminal: Collects user modifications and feedback and sends them to the server.

[2070] Step 12:

[2071] Server: Updates the learning model based on user feedback to further optimize task distribution and execution for future sessions.

[2072] Specific example

[2073] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[2074] Step 1:

[2075] Terminal: "Displays an interface for inputting routine tasks and captures the user's facial expressions using an emotion engine."

[2076] Step 2:

[2077] User: "I typed, 'Set up a meeting every Monday at 9:00 AM and send a notification email to participants,' and my facial expression was recognized."

[2078] Step 3:

[2079] Terminal: "Send input content and sentiment data to the server."

[2080] Step 4:

[2081] Server: "Analyzes the business process and divides it into two tasks. Analyzes emotional data and evaluates the user's emotional state."

[2082] Step 5:

[2083] Server: "Adjust task priorities and distribution methods based on sentiment evaluations."

[2084] Step 6:

[2085] Server: "Train a machine learning model based on analysis results and sentiment data."

[2086] Step 7:

[2087] Server: "Assign the automated system to set up meetings and the users to send notification emails."

[2088] Step 8:

[2089] Server: "Automatically schedule meetings using the Calendar API."

[2090] Step 9:

[2091] Terminal: "Displays execution status in real time on the dashboard and shows sentiment-based messages."

[2092] Step 10:

[2093] User: "Check the task progress on the dashboard and make corrections as needed."

[2094] Step 11:

[2095] Terminal: "Send corrections and feedback to the server."

[2096] Step 12:

[2097] Server: "Update the learning model based on feedback."

[2098] The above outlines the specific processing steps for implementing this invention. This system not only efficiently automates routine tasks but also takes into account the user's emotional state, enabling more efficient and less stressful work execution.

[2099] (Example 2)

[2100] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2101] Traditional business automation systems fail to consider the user's emotional state when allocating or prioritizing tasks, potentially leading to user stress and decreased work efficiency. Furthermore, real-time updates of machine learning models based on user feedback are difficult, resulting in limited system adaptability.

[2102] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[2103] In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for collecting user sentiment data based on the analyzed tasks, means for analyzing the collected sentiment data and determining task priorities, means for training a machine learning model based on the analyzed tasks and sentiment data, means for distributing tasks to the user and the automation system using the trained learning model, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables automation of tasks that take user sentiment into consideration and real-time system adaptation based on feedback.

[2104] A "user" refers to a person who uses the system to input data and provide feedback.

[2105] "Routine tasks" refer to repetitive tasks that users need to perform regularly.

[2106] "Text format" refers to a data format represented by strings of characters.

[2107] "Means" refers to the methods or devices used to achieve a specific objective.

[2108] "Job description" refers to the specific tasks and details of work that users input into the system.

[2109] "Analysis" refers to the process of breaking down input data and understanding its meaning and structure.

[2110] "Specific tasks" refer to individual work units that can be executed based on the analyzed business content.

[2111] "Emotional data" refers to information that indicates a user's emotional state. This includes facial expressions, tone of voice, and emotional expressions in text.

[2112] "Collecting emotional data" refers to the process of obtaining a user's emotions and storing them in an analyzable format.

[2113] "Emotional analysis" refers to the process of processing collected emotional data to understand the user's emotional state.

[2114] "Priority" refers to determining the order in which tasks are performed and their importance.

[2115] A "machine learning model" refers to an algorithm that learns specific patterns based on data and uses them to make future predictions and decisions.

[2116] "Training" refers to the process of using data to train a machine learning model to achieve an optimal state.

[2117] An "automation system" refers to a system of software or hardware designed to automatically perform specific tasks.

[2118] "Progress status" refers to information indicating the stage of a task.

[2119] "Feedback" refers to the evaluations and opinions that users provide to a system.

[2120] "Updating" refers to the process of improving existing machine learning models and systems using new information and feedback.

[2121] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting user emotions in the work process. Specifically, it automates tasks by coordinating various technologies, with terminals, servers, and users as the main components.

[2122] System configuration and operation

[2123] First, the system collects information about routine tasks from the user. In this process, the terminal displays an input interface to the user, who then inputs the task details in text format.

[2124] Specific actions

[2125] 1. Collect information about the work from the user.

[2126] Terminal: The terminal displays an interface for users to input routine tasks. This interface includes text boxes and selection options, allowing users to freely input task details. Software used includes HTML, CSS, and JavaScript.

[2127] User: The user enters their task details in text format, such as "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[2128] 2. Analyze the work content and generate tasks.

[2129] Terminal: Sends the entered work details to the server via an HTTP request.

[2130] Server: The server uses a natural language processing engine (e.g., SpaCy, Transformer) to analyze the received business data. For example, it might break it down into specific tasks such as "setting up a meeting" and "sending notification emails." This clarifies the specific routine tasks that the system will handle.

[2131] 3. Utilizing the Emotional Engine

[2132] Terminal: When a user inputs work details, the terminal uses its camera and microphone to collect user emotion data. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[2133] Server: The server analyzes the data collected using the emotion engine to understand the user's emotional state. Based on the collected emotional data, it determines task priorities. For example, if a user is feeling stressed, it adjusts the assignment to prioritize easier tasks.

[2134] 4. Creating and optimizing the learning model

[2135] Server: Trains a machine learning model based on the analyzed task and sentiment data. This training uses Scikit-learn or TensorFlow. The trained model learns the user's work patterns and sentiment patterns and reflects them in subsequent execution.

[2136] Terminal: Use graphs and dashboards (e.g., Plotly, Grafana) to visually display training progress and accuracy to the user.

[2137] 5. Division and execution of tasks

[2138] Server: Using a trained learning model, it distributes tasks between "users" and "automation systems (e.g., Zapier or IFTTT)." For example, it might assign "setting up a meeting" to an automation system and "sending notification emails" to a user. The server also uses the Google Calendar API, etc., to automate tasks such as setting up meetings.

[2139] Terminal: Provides a dashboard to display task progress to the user in real time. Users can check the task execution status through the dashboard and intervene or correct as needed.

[2140] 6. User Verification and Intervention

[2141] Terminal: Notifies the user of the results of completed tasks and displays them on the dashboard. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[2142] User: Review the task results and make corrections or provide feedback as needed.

[2143] Terminal: Sends collected feedback to the server.

[2144] Server: Updates the learning model based on feedback to further optimize task distribution and execution in subsequent sessions.

[2145] Specific example

[2146] For example, to automate the scheduling of a regular weekly meeting held by a marketing department member:

[2147] 1. User: Enters "Schedule a meeting every Monday at 9:00 AM and send a pre-meeting notification email to participants" as their job description, and sentiment data is collected.

[2148] 2. Terminal: Sends the input content to the server.

[2149] 3. Server: Analyzes work content and divides it into "meeting scheduling" and "sending notification emails." An emotion engine evaluates the user's stress level.

[2150] 4. Server: Trains the learning model based on the analysis results.

[2151] 5. Server: The system handles meeting setup, and the sending of notification emails is distributed to users.

[2152] 6. Server: Automatically schedule meetings using the Google Calendar API.

[2153] 7. Terminal: Displays the execution status to the user in real time via a dashboard and shows appropriate support messages.

[2154] 8. User: Confirm that the meeting has been set up and correct the content of the notification email.

[2155] 9. Terminal: Send feedback to the server.

[2156] 10. Server: Update the learning model based on feedback.

[2157] The above describes a specific embodiment for carrying out this invention. This system not only efficiently automates routine tasks but also enables appropriate task distribution that takes into account the user's emotions, resulting in more efficient and less stressful work performance.

[2158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2159] Step 1:

[2160] Collect information about the work performed by the user.

[2161] Terminal: Displays an interface where the user can input work details. This interface includes text boxes and selection options. This allows the user to input details of routine tasks in text format.

[2162] Input: User's job description (e.g., "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants").

[2163] Output: Text data of the work details entered by the user.

[2164] Step 2:

[2165] Sending and analyzing work details

[2166] Terminal: Sends the entered work details to the server. This process is performed via an HTTP request.

[2167] Server: The server analyzes the received text data using a natural language processing engine (e.g., SpaCy, Transformer) and divides it into specific tasks.

[2168] Input: Text data of the work details entered by the user.

[2169] Output: Specific tasks analyzed (e.g., "Set up a meeting", "Send notification email").

[2170] Step 3:

[2171] Collection of emotional data

[2172] Terminal: When users input work details, the system collects emotional data using the camera and microphone. This is done using facial recognition technology (e.g., OpenCV, AWS Rekognition) and speech analysis technology.

[2173] Input: User's facial expressions and voice data.

[2174] Output: Collected emotional data (e.g., facial features, voice tone).

[2175] Step 4:

[2176] Analysis of emotional data

[2177] Server: The collected emotional data is analyzed by an emotion engine to understand the user's emotional state. Emotional scores and stress levels are calculated.

[2178] Input: Collected sentiment data.

[2179] Output: Sentiment score and stress level.

[2180] Step 5:

[2181] Training machine learning models

[2182] Server: Trains a machine learning model based on the analyzed task and sentiment data. This uses Scikit-learn or TensorFlow. The model learns the user's work patterns and sentiment patterns.

[2183] Input: Analyzed task and sentiment data.

[2184] Output: Trained machine learning model.

[2185] Step 6:

[2186] Task distribution

[2187] Server: Uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, assigning "setting up a meeting" to the automation system and "sending notification emails" to users.

[2188] Input: A trained machine learning model and the task to be analyzed.

[2189] Output: Distributed tasks.

[2190] Step 7:

[2191] Task execution and progress display

[2192] Server: Issues instructions to the automation system to execute tasks. Specifically, it uses the Google Calendar API to schedule meetings.

[2193] Terminal: Provides a dashboard to display task progress to the user in real time.

[2194] Input: Assigned tasks.

[2195] Output: Tasks performed and their progress.

[2196] Step 8:

[2197] User verification and intervention

[2198] Terminal: Displays the results of completed tasks on the dashboard and notifies the user.

[2199] User: Review the task results and make corrections or provide feedback as needed.

[2200] Terminal: Sends corrections and feedback to the server.

[2201] Server: Updates the machine learning model based on feedback.

[2202] Input: User feedback.

[2203] Output: Updated machine learning model.

[2204] These processing steps enable the system to efficiently automate users' routine tasks and achieve task distribution that takes emotions into account.

[2205] (Application Example 2)

[2206] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2207] Modern factories and logistics centers have numerous routine tasks that must be handled efficiently. In particular, since employee performance fluctuates depending on their emotional state, task allocation that takes emotions into account is crucial. However, current systems often fail to consider user emotions when assigning tasks, limiting efficiency. Furthermore, assigning tasks without considering employee emotions can cause stress, leading to decreased satisfaction and productivity. Therefore, a system is needed that not only streamlines routine tasks but also dynamically reflects user emotions in task allocation.

[2208] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for the user to input routine tasks in text format, means for analyzing the input task content and dividing it into specific tasks, means for training a machine learning model based on the analyzed tasks, means for distributing tasks to the user and the automation system using the trained learning model, means for analyzing emotional data and distributing and adjusting tasks according to the emotional state, means for executing the distributed tasks and displaying their progress to the user, and means for obtaining user feedback and updating the learning model. This enables dynamic task distribution that takes the user's emotions into consideration, making it possible to simultaneously achieve increased work efficiency and reduced stress.

[2209] "Routine tasks" refer to standardized tasks that are performed repeatedly on a daily basis.

[2210] "Text format" refers to a format that uses strings of characters to represent information.

[2211] "Analysis" refers to the process of breaking down input information and understanding its contents in detail.

[2212] A "task" refers to an individual work or activity performed to achieve a specific objective.

[2213] A "machine learning model" refers to the structure of an algorithm that learns from data and performs predictions and classifications.

[2214] "Training" refers to the process of using data to allow a machine learning model to learn.

[2215] An "automation system" refers to a system that performs specific tasks or processes without human intervention.

[2216] "Distribution" refers to the process of allocating specific resources or tasks to multiple targets.

[2217] "Emotional data" refers to data that represents the emotional state of a user.

[2218] "Analysis" refers to the process of examining data in detail and understanding its patterns and meanings.

[2219] "Adjustment" refers to changing the arrangement or content based on specific conditions.

[2220] "Execution" refers to actually carrying out the planned tasks.

[2221] "Progress status" refers to information that indicates the degree of completion during the task's execution process.

[2222] "Display" refers to the visual presentation of information.

[2223] "Feedback" refers to providing information or opinions about a particular action or outcome.

[2224] "Updating" refers to improving or changing existing data or systems based on new information.

[2225] This invention is a system that enables users to efficiently automate their routine tasks, thereby improving work efficiency and work-life balance, while also recognizing and reflecting the user's emotions in the work process. Specific embodiments are described in detail below.

[2226] System Configuration

[2227] This system automates tasks through the collaboration of terminals, servers, and users. The main hardware used includes smart glasses and factory robots, while the software includes EmotionEngine (emotion recognition engine), TaskParser (task analysis engine), RobotController (robot control API), and SmartGlasses (smart glasses API).

[2228] Specific actions

[2229] 1. Collect information about the work from the user.

[2230] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, where users can enter specific details about their tasks.

[2231] Users input task details such as, "Schedule a meeting every Monday at 9:00 AM and send a notification email to participants."

[2232] 2. Analyze the work content and generate tasks.

[2233] The terminal sends the entered work information to the server.

[2234] The server analyzes the received work content using TaskParser and divides it into specific tasks. For example, it might divide it into two tasks: "Schedule a meeting" and "Send a notification email."

[2235] 3. Utilizing the Emotional Engine

[2236] When a user inputs work details, the terminal collects data for EmotionEngine to recognize the user's emotions. This includes text analysis and facial recognition via the camera.

[2237] The server uses EmotionEngine to analyze the user's emotions and prioritizes tasks based on the results. For example, if the user is feeling stressed, the emotion engine will adjust the tasks, such as assigning easier tasks first.

[2238] 4. Creating and optimizing the learning model

[2239] The server trains a machine learning model based on the analyzed task and sentiment data. The trained model learns both the user's work patterns and sentiment patterns.

[2240] 5. Division and execution of tasks

[2241] The server uses a trained learning model to distribute tasks between "users" and "automation systems." For example, it might assign "setting up a meeting" to the automation system and "sending notification emails" to the user.

[2242] The server issues instructions to the automated system to perform specific tasks. For example, it might use the Calendar API to schedule a meeting.

[2243] 6. User Verification and Intervention

[2244] The device notifies the user of the results of completed tasks. The dashboard displays the task completion status along with feedback and support messages tailored to the user's emotional state.

[2245] Users review the task results and make corrections or provide feedback as needed.

[2246] Specific example

[2247] For example, in the automation of production operations in a factory:

[2248] 1. The user enters "replenish materials on the packaging line" as their job description, and sentiment data is also collected.

[2249] 2. The terminal sends the input content to the server.

[2250] 3. The server analyzes the work content and divides it into two tasks: "preparing materials" and "replenishing materials." The emotion engine assesses the user's stress level and adjusts the order of the tasks.

[2251] 4. The server trains a learning model based on the analysis results.

[2252] 5. The server distributes the task of "preparing materials" to the automated system and the task of "replenishing materials" to the user.

[2253] 6. The server instructs the robot to "prepare materials," and it executes this automatically.

[2254] 7. The terminal displays the task progress in real time and shows appropriate support messages.

[2255] 8. The user confirms that the task is complete and provides feedback as needed.

[2256] Example of a prompt

[2257] "It seems that worker A is unhappy. Please have them handle the easier tasks first."

[2258] "The next task is 'replenishing materials on the packaging line.' Due to its high stress level, please assign this task to a robot."

[2259] This allows for efficient automation of each process while simultaneously enabling flexible task management that reflects user emotions, resulting in improved overall productivity and satisfaction.

[2260] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2261] Step 1:

[2262] The terminal displays an interface for users to input routine tasks. The interface includes voice input and text boxes, allowing users to input specific details about their tasks. The input data here consists of text or voice information describing the user's work. For example, specific tasks such as "replenishing materials on the packaging line" might be entered.

[2263] Step 2:

[2264] The terminal transmits the entered work information to the server. At this time, the entered text or voice data is transferred to the server and prepared for analysis. The role of the terminal is to transmit the collected data to the server quickly and accurately.

[2265] Step 3:

[2266] The server uses TaskParser to analyze the received business information and divides it into specific tasks. For example, it might divide it into tasks such as "prepare materials" and "replenish materials." This process utilizes natural language processing technology to analyze the text data and identify each business task.

[2267] Step 4:

[2268] The terminal uses EmotionEngine to collect emotional data when users input work-related information. The collected data includes emotion determination through text analysis and facial recognition via the camera. The input data represents information about the user's emotional state, such as stress levels and satisfaction levels.

[2269] Step 5:

[2270] The server analyzes emotional data using EmotionEngine and determines task priorities based on the results. For example, if a user's stress level is high, it will assign them easier tasks first. This process involves performing data calculations that prioritize tasks using emotional analysis data.

[2271] Step 6:

[2272] The server trains a machine learning model based on the analyzed task and sentiment data. In this process, it uses a large amount of historical task and sentiment state data to generate a model that will help with future task allocation and sentiment regulation. The input data is the analyzed task and sentiment data, and the output is the updated machine learning model.

[2273] Step 7:

[2274] The server uses a trained machine learning model to distribute tasks between "users" and "automation systems." For example, it might assign "preparing materials" to the automation system and "replenishing materials" to the user. This process involves data calculations that use the machine learning model to determine the optimal task distribution.

[2275] Step 8:

[2276] The server issues instructions to the automated system to perform specific tasks. For example, it might use RobotController to instruct a factory robot to prepare materials. In this process, specific operation commands are generated as output data that are sent to the robot.

[2277] Step 9:

[2278] The device displays the task progress to the user in real time. Here, the SmartGlasses API is used to visually display the task progress on smart glasses. The displayed data includes the task's progress and completion status.

[2279] Step 10:

[2280] Users review the results of completed tasks and make corrections or provide feedback as needed. This feedback can include comments such as "Task complete" or "Needs correction." This allows the system to reflect the user's intentions.

[2281] Step 11:

[2282] The terminal sends user feedback to the server. This feedback data is used to further optimize task distribution and execution in the future.

[2283] Step 12:

[2284] The server updates the machine learning model based on the feedback received. This allows the model to reflect the latest data, enabling more accurate task allocation and sentiment adjustment. The output data is the updated machine learning model.

[2285] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2286] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2287] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2288] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2289] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2290] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2291] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2292] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[2293] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[2294] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[2295] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[2296] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[2297] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[2298] 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.

[2299] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[2300] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[2301] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[2302] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[2303] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[2304] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[2305] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[2306] The following is further disclosed regarding the embodiments described above.

[2307] (Claim 1)

[2308] A means for users to input r...

Claims

1. A means for users to input routine tasks in text format, A means of analyzing the entered work content and dividing it into specific tasks, A method for training a machine learning model based on the analyzed task, A means of distributing tasks between users and automated systems using a trained learning model, A means of executing assigned tasks and displaying their progress to the user, A means of obtaining user feedback and updating the learning model. A system that includes this.

2. The system according to claim 1, wherein routine tasks are entered, tasks are divided, machine learning models are trained, and tasks are distributed in real time.

3. The system according to claim 1, which includes a dashboard for displaying the progress of a task, wherein the dashboard has a function for the user to modify the task.

Images