system

Abstract

We provide the system. [Solution] An analytical means for extracting information from emails and meeting records, A management system that automatically generates and manages tasks based on extracted information, A notification system that sets deadlines for generated tasks and notifies the user of reminders, A monitoring mechanism that monitors the progress of tasks and automatically deletes completed tasks, A system that includes this.

Description

Technical Field

[0004] , ,

[0005] , , ,

[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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 modern society, with the change of the business environment, many people are forced to manage multiple tasks simultaneously. In particular, tasks generated through communication means such as emails and meeting minutes are often not managed in a timely manner, resulting in problems such as deadline overrun and response omission. In such a situation, efficient task management is required, but there is a problem that the burden on users increases because conventional methods require a lot of labor.

Means for Solving the Problems

[0005] This invention aims to reduce the burden on users by incorporating analysis means for extracting information from emails and meeting records, and by providing management means for automatically generating and managing tasks. Furthermore, deadlines are set for the generated tasks, and reminders are sent to users via notification means, preventing tasks from being overlooked. In addition, by utilizing monitoring means to monitor the progress of tasks and automatically deleting completed tasks, smooth list management is achieved. With these configurations, it is possible to efficiently and effectively manage a large number of tasks and prevent deadlines from being missed or tasks from being overlooked.

[0006] "Analysis means" refers to a device or software that has the function of extracting information from emails or meeting records and generating data related to the task.

[0007] A "management means" is a device or system for automatically generating and managing tasks based on information extracted by an analysis means.

[0008] A "notification device" is a device or system that has the function of sending reminders to the user to ensure that deadlines are met for generated tasks.

[0009] A "monitoring device" is a device or software that checks the progress of a task and automatically deletes completed tasks.

[0010] A "machine learning tool" is a system equipped with algorithms that learn from task progress data to improve the accuracy of task generation and management.

[0011] "Improvement measures" refer to devices or processes used to improve the analysis accuracy or user interface of a system based on user feedback. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] The present invention is implemented as a system that automatically manages tasks mainly generated from emails and meeting minutes using a server. Embodiments of the present invention will be described below in detail from the perspectives of the server, terminal, and user.

[0034] The server periodically retrieves email and meeting record data from email servers and cloud storage with the user's permission. This allows it to collect the latest communication information. The server then processes this data using a natural language processing (NLP) engine to extract important keywords and phrases related to tasks from the text data. For example, from content in an email such as "Submit the report by next Tuesday," it recognizes the task "Submit the report" and sets a deadline.

[0035] The extracted task information is automatically registered by the server in the task management database. This database stores detailed information for each task (task name, due date, assignee, etc.). The server synchronizes this information with the user's terminal, and the user can access their task list using a dedicated application.

[0036] As a means of notification, the server sends reminders to the user's device based on task deadline information. Reminders are provided via email or push notifications, for example, providing warnings such as "Tomorrow is the deadline for submitting the report." This allows users to manage important tasks without forgetting them.

[0037] On the other hand, users can update the task progress using their device. When a user marks a task as complete, that information is sent to the server, and the task is recorded as complete in the database. The server then automatically deletes or updates the status of the task.

[0038] Furthermore, the server can receive feedback from users and collect data to improve analysis accuracy and the interface. Based on this feedback, the server's internal machine learning algorithms can be updated, enabling more efficient task management.

[0039] In this way, the present invention provides a system that streamlines task generation from emails and meeting minutes, enabling users to manage their work stress-free.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] Based on user permission, the server connects to the mail server or cloud storage to retrieve new emails and meeting minutes. This allows for the regular collection of the latest communication data.

[0043] Step 2:

[0044] The server extracts text data from acquired emails and meeting records. For emails, it analyzes the subject and body text; for meeting records, it uses OCR technology to recognize characters as needed.

[0045] Step 3:

[0046] The server uses a natural language processing (NLP) engine to analyze text data and extract keywords and phrases that suggest tasks. For example, it uses trigger words such as "submit," "complete," and "request" to identify when a task is occurring.

[0047] Step 4:

[0048] The server generates task details (task name, deadline, assignee, etc.) based on the extracted information and registers them in the management database. This allows tasks to be centrally managed within the system.

[0049] Step 5:

[0050] The device is synchronized with the server, allowing the user to see the latest task list. Users can view task details on the device and edit them as needed.

[0051] Step 6:

[0052] The server generates reminders based on task deadlines. These reminders are sent to the user's device via email or push notification, ensuring the user is notified at the appropriate time.

[0053] Step 7:

[0054] Users can input task progress via their terminal and mark tasks as complete once they are finished. This progress information is sent to the server.

[0055] Step 8:

[0056] The server updates the task status based on progress information received from the user, and deletes or marks completed tasks from the database. This optimizes task list management.

[0057] Step 9:

[0058] (Optional) The server receives feedback from users and updates algorithms to improve analysis accuracy and the interface. The system is continuously improved through irregularly held feedback sessions.

[0059] (Example 1)

[0060] 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."

[0061] With the increasing volume of information in the modern world, efficiently managing individual work activities presents a significant challenge. In particular, extracting and managing important tasks from a wide range of information sources, such as emails and meeting minutes, without overlooking anything, places a considerable burden on users. Furthermore, performing these tasks manually is time-consuming and prone to human error. Therefore, there is a need to develop a system that automatically extracts information from communication data and optimally manages work activities.

[0062] 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.

[0063] In this invention, the server includes an acquisition means for acquiring data from information communication, an analysis means for extracting important terms through natural language processing, and a management means for generating and storing business activities based on the extracted terms. This enables the automatic generation and management of business activities, freeing users from cumbersome manual work and reducing problems such as overlooking important tasks.

[0064] "Information and communication" refers to various forms of digital data, such as emails and meeting minutes, and the media used for acquiring and managing information.

[0065] A "means of acquiring data" refers to a system that has the function of automatically collecting necessary information from information sources with the user's permission.

[0066] "Natural language processing" is a technology that converts text data into a form that computers can understand and extracts meaning from it.

[0067] "Key terms" refer to keywords and phrases necessary for generating business activities, and are elements that help identify tasks based on them.

[0068] A "management system for generating and storing business activities" is a mechanism for forming tasks from extracted key keywords, registering them in a database, and managing them.

[0069] "Notification methods that notify communication terminals" refers to a function that informs users of important information, such as deadlines for generated business activities, via email or push notifications.

[0070] A "monitoring method that monitors the progress of business activities and automatically reflects completion status" refers to a function that tracks the progress of tasks and updates a database with completed tasks.

[0071] A "learning method" is a technique that uses machine learning algorithms to gain insights from data and continuously improve the performance of a system.

[0072] "Methods for collecting user feedback and making improvements" refers to a system that receives feedback from users and uses it to improve the accuracy of system analysis and the interface.

[0073] This invention provides a system for effectively managing users' digital activities through information and communication. The basic configuration consists of a server for acquiring and analyzing information, generating and managing business activities, a communication terminal for notifying users, and a user interface that allows users to manage information and provide feedback.

[0074] The server periodically retrieves data from information communications with the user's permission. This retrieval utilizes existing mail servers and cloud storage. The server analyzes the collected information using a natural language processing (NLP) engine to extract important words and phrases from the text. For example, this NLP engine recognizes the task "Prepare materials" from a message like "Please prepare materials for next week's meeting" and sets a deadline. The generated work activities are then registered in a database by the server. The database manages detailed information about the work activities (task name, deadline, person in charge, etc.), and this information is simultaneously synchronized with the user's communication terminal.

[0075] The communication terminal receives notifications from the server and provides a means to notify users of important information regarding their work activities. Notifications are sent via email or push notifications, and help users manage important work activities by sending messages such as "The deadline for submitting meeting materials is tomorrow."

[0076] Users can manage the progress of their work activities by operating a communication terminal. When a user marks a work activity as complete, that information is sent to the server, and the status is updated in the database. Furthermore, users can provide feedback to the server through a feedback function to improve the accuracy of the analysis and enhance the user interface. The server uses this feedback to update its generated AI models and machine learning algorithms, thereby improving the system's functionality.

[0077] As a concrete example, suppose a server analyzes multiple emails regarding the progress of a project and automatically generates a work activity called "Create Progress Report." This activity is saved in a database, and a notification such as "The deadline for the progress report is this weekend" is sent to the user's terminal, ensuring that the user does not forget to take action.

[0078] An example of a prompt message might be: "A new project-related email has arrived. Please analyze the email to generate and send notifications for important business activities."

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server periodically retrieves data from email servers and cloud storage with the user's permission. This input data consists of text information contained in emails and meeting minutes. The retrieved data is then loaded into memory in preparation for analysis.

[0082] Step 2:

[0083] The server inputs the acquired text data into a natural language processing (NLP) engine. The NLP engine performs analysis to extract important words and phrases from the text data. As output, keywords related to business activities and tasks based on them are generated. For example, from an email that says, "Please prepare the materials before the meeting," the task "Prepare materials" is extracted.

[0084] Step 3:

[0085] The server registers the extracted task information in the task management database. In this step, detailed information such as the task name, due date, and assignee is stored in the database. The output from the database is a task list organized for each user.

[0086] Step 4:

[0087] The server sends notifications to the user's terminal based on task information registered in the database. The input is task deadline information, which is delivered via communication. The output is a reminder in the form of email or push notification. For example, a notification might say, "Tomorrow is the deadline for creating the document."

[0088] Step 5:

[0089] Users check their task list and update their progress using an application on their device. Input is the user's action, and output is the updated task status. When a user marks a task as complete, that information is sent to the server, and the task completion is recorded in the database.

[0090] Step 6:

[0091] The server analyzes user feedback and updates the generated AI model. This feedback process collects data for improving analysis accuracy and the interface. The input is user opinions and usage, and the output is improved system performance. This improves the efficiency of task management and usability.

[0092] (Application Example 1)

[0093] 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."

[0094] Current electronic payment services require the individual management of transaction information and related notifications, necessitating increased operational efficiency. However, performing this manually is time-consuming and labor-intensive; therefore, a system is needed to automatically generate related tasks based on transaction information and manage them appropriately.

[0095] 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.

[0096] In this invention, the server includes an analysis means for extracting information from communication information, a management means for automatically generating and managing tasks based on the extracted information, and a notification means for setting deadlines for the generated tasks and providing warnings to the user. This makes it possible to efficiently generate and manage tasks from transaction information.

[0097] "Communication information" refers to information sent and received in digital format, including emails and meeting minutes.

[0098] "Business" refers to tasks and activities related to transactions that have objectives to be achieved.

[0099] A "warning" refers to a notification or reminder sent to draw the user's attention.

[0100] "Users" refers to individuals or corporations that use this system.

[0101] "Analytical means" refers to techniques or methods for processing information to find significant patterns or relationships.

[0102] "Control measures" refer to techniques or methods for systematically controlling and supervising operations.

[0103] "Notification means" refers to a technology or method for electronically transmitting information or warnings to users.

[0104] "Learning methods" refer to techniques and methods that recognize patterns from data and improve performance based on these patterns.

[0105] This invention is a system for efficiently managing transaction information in electronic payment services. The system consists of several main elements and aims to improve the operational efficiency of users.

[0106] The server first collects communication information and then uses analysis tools to extract meaningful data from that information. This analysis uses natural language processing engines such as Google Cloud Natural Language API. For example, if an email contains descriptions of important dates or tasks related to a transaction, this information is extracted and used later.

[0107] Based on this extracted data, the management system automatically generates and manages tasks. Each generated task has a deadline, and alerts are set to notify users at the appropriate time. The notification system displays information as push notifications on smartphones through an application developed with React Native.

[0108] Users can view their task list and update their progress through this application. When a task is completed, the task is deleted from the database with the corresponding action.

[0109] Furthermore, the server utilizes learning tools to analyze feedback and improve the task generation algorithm. This process uses machine learning algorithms running on AWS® to improve the accuracy of data processing.

[0110] For example, when a user conducts a financial transaction, this system can automatically generate a payment task related to that transaction and notify the user as a reminder on a specified date. This allows users to efficiently carry out their work without forgetting important deadlines.

[0111] Examples of prompt messages include, "Please extract the information needed to automatically generate a payment task from this transaction email."

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server periodically retrieves communication information from email servers and payment databases authorized by the user. Emails and transaction records are transferred to the server as input data. Based on this data, the server prepares to analyze new information.

[0115] Step 2:

[0116] The server analyzes the collected communication information using the Google Cloud Natural Language API. It extracts important phrases and keywords necessary for task generation from the input emails and records. This process yields output data such as the task name (e.g., "invoice") and payment deadline.

[0117] Step 3:

[0118] The server automatically generates tasks based on the analyzed data. Here, based on the extracted task information, detailed information (task name, deadline, related actions, etc.) is saved to the database for each task. The input is the analysis results, and the output is the registration of a new task in the task management database.

[0119] Step 4:

[0120] The terminal sets reminders related to registered tasks based on instructions from the server. It then executes a notification function using React Native on the user's smartphone, displaying warnings such as "Payment deadline is approaching." This serves as an important notification for the user.

[0121] Step 5:

[0122] Users use a terminal to check their task list and update their progress. Information on tasks marked as complete is sent to the server, and the server deletes the processed tasks from the database. Input is the user's updated information, and output is an update of the task status.

[0123] Step 6:

[0124] The server updates its machine learning algorithms using data collected throughout all processes. It analyzes feedback and usage history to improve the accuracy of future task generation. The input is historical task data and feedback, and the output is an optimized algorithm.

[0125] 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.

[0126] This invention aims to achieve more personalized task management by combining an emotion engine with a task management system. Specific embodiments are shown below.

[0127] The server periodically retrieves information from users' emails and meeting records and automatically extracts task-related information using analytical tools. This extracted task information is registered by the server in a management database. Detailed task information (task name, due date, priority, etc.) is stored in this database.

[0128] This system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine uses user input information, voice, and facial expression data to analyze the user's emotional state in real time. Based on the analysis results of the emotion engine, the server can dynamically adjust task priorities. For example, if the user is feeling stressed, the server will change the priority of tasks to reduce the burden on the user.

[0129] The device has the function of displaying a task list sent from the server to the user. Tasks are prioritized based on emotional information, allowing users to manage tasks optimally according to their own emotional state. The device also receives reminders from the emotional engine and sends notifications at a time and with content that takes the user's emotions into consideration.

[0130] When a user updates the progress of a task, that information is transmitted to the server. The server monitors the task status based on this progress information and completes or deletes the task as needed. By utilizing the sentiment engine, it is possible to provide advice and feedback that reflects the user's emotions even for completed tasks.

[0131] Furthermore, the server collects emotion-related feedback from users to improve the accuracy of the analysis results and the user interface. The data obtained through the emotion engine is continuously optimized by machine learning algorithms to improve the accuracy of subsequent analyses.

[0132] Embodiments of the present invention are systems that go beyond simple task management, taking into account the user's emotions and providing individually customized task management. The aim is to reduce the user's psychological burden and support efficient and effective task execution.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] With user permission, the server periodically retrieves new emails and meeting minutes from the mail server and cloud storage, accumulating the latest data.

[0136] Step 2:

[0137] The server analyzes the content of the retrieved emails and meeting minutes using natural language processing technology to extract phrases and keywords related to the task. This then creates an outline of the task.

[0138] Step 3:

[0139] The server registers tasks in the management database based on the extracted task information. Each task is assigned attributes such as name, due date, priority, and assignee.

[0140] Step 4:

[0141] The emotion engine acquires voice and facial expression data transmitted from the user's device and analyzes the user's emotional state in real time. This process is performed with the user's consent.

[0142] Step 5:

[0143] The server receives the results of the emotion engine's analysis and dynamically adjusts the priority of each task based on that. For example, if the user is determined to be in a high-stress state, the server will change the priority of important but non-urgent tasks to be lowered.

[0144] Step 6:

[0145] The device presents the user with an updated task list. Each task is displayed in order of priority based on the user's emotional state, making it intuitively clear which tasks should be addressed.

[0146] Step 7:

[0147] The server generates reminders based on task deadlines and sends notifications to the device at a time and with message content that takes the user's emotional state into consideration. This allows users to manage their tasks more effectively.

[0148] Step 8:

[0149] Users update task progress via their devices. This information is immediately sent to the server, and the task status is updated to "In Progress," "Completed," etc.

[0150] Step 9:

[0151] When a task is deemed complete, the server removes it from the database and provides the user with sentiment feedback, along with the relevant information.

[0152] Step 10:

[0153] The server collects emotional feedback from users and uses it to improve analysis results and the user interface. This feedback is fed into machine learning algorithms and used to improve the system's accuracy.

[0154] (Example 2)

[0155] 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".

[0156] Traditional task management systems struggle to flexibly respond to users' emotional states and the urgency of their activities. Furthermore, they lack mechanisms to efficiently utilize user feedback and improve management accuracy, creating a need for more personalized activity management.

[0157] 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.

[0158] In this invention, the server includes analysis means for extracting information from electronic communications and schedule records, control means for automatically generating and managing activities based on the extracted information, and evaluation means for analyzing the user's state and dynamically adjusting the priority of activities. This enables optimal task management according to the user's emotional state and the urgency of the activities.

[0159] "Electronic communications" refers to means of transmitting information through networks, including email and digital messages.

[0160] "Schedule records" refer to documents or data that contain the user's activity plans, such as meeting schedules and timetables.

[0161] "Analysis methods" is a general term for technologies and methods used to extract necessary information from electronic communications and schedule records and to analyze their content.

[0162] "Control measures" refer to technologies and methods for automatically generating activities based on extracted information and efficiently managing them.

[0163] "Notification means" refers to technologies and methods for informing users of deadlines for activities or important events.

[0164] "Evaluation methods" refer to technologies and methods for analyzing the user's emotional state and other factors, and dynamically adjusting the priority of activities based on those analyses.

[0165] "Monitoring measures" refer to technologies and methods for checking the progress of activities and automatically deleting completed activities.

[0166] "Learning methods" refer to techniques and methods for progressively improving processing accuracy based on the progress of an activity.

[0167] "Improvement methods" refer to technologies and methods for receiving feedback from users and improving the analysis results and user interface.

[0168] To implement this invention in practice, it is necessary to effectively utilize servers and terminals. The server first uses external services such as APIs to collect electronic communications and schedule records. This includes digital communication software and calendar services using cloud services. The server acquires this data and extracts information using analytical means. At this time, natural language processing tools are used to analyze the text data and identify the details, deadlines, and priorities of activities.

[0169] Next, the server records the extracted activity information in a management database using control mechanisms. This database is built using an open-source database management system, enabling continuous management of activities.

[0170] Furthermore, the server analyzes the user's emotional state through evaluation tools. This involves using emotion recognition software to analyze voice data and facial expression data, thereby understanding the user's psychological state in real time.

[0171] The device displays an activity list sent from the server to the user. It features an intuitive and easy-to-understand UI that responds to the user's psychological state and can highlight items according to priority. Furthermore, the device uses notification methods to provide reminders that take into account the deadlines and emotions set by the user.

[0172] When a user updates the progress of an activity, that information is fed back to the server, which then uses monitoring mechanisms to complete or invalidate the activity. Furthermore, user feedback is used to improve system performance through refinement mechanisms.

[0173] As a concrete example, consider a situation where a user feels they "need to prepare for next week's meeting, but are too busy to find the time." In this case, the server assesses the user's stress level and, based on the assessment, sets meeting-related activities as a high priority, adjusting other activities to a lower priority.

[0174] An example of a prompt message could be input into the generating AI model, such as, "If the user is feeling fatigued, reduce reminder notifications and display only important tasks." In this way, the system can provide optimal activity management based on the user's emotional state, improving efficiency and user satisfaction.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server collects information from electronic communications and schedule records. In this step, data is retrieved via APIs from email services and schedule management systems. Inputs include user emails and schedule information, which are used to collect raw data about activities. From this raw data, activity plans and message content are output.

[0178] Step 2:

[0179] The server analyzes the collected information using analytical tools. Specifically, it extracts activity-related information from the raw data using natural language processing tools. For example, it selects items such as the activity title, deadline, and priority. As a result of this process, structured activity information is output after analyzing the text data.

[0180] Step 3:

[0181] The server automatically generates activities using the analyzed data and registers them in the management database. The structured activity information obtained in step 2 is used as input, and the activity details are stored in the database. This database entry will be used for future task management.

[0182] Step 4:

[0183] The server utilizes emotion recognition methods to evaluate the user's psychological state. Using emotion recognition software, it acquires voice and facial expression data as input and analyzes the emotional state. The analysis outputs emotional information such as the user's stress level and happiness level.

[0184] Step 5:

[0185] The server dynamically adjusts activity priorities based on emotional information. An evaluation method is used to rearrange activities according to the user's emotions. Inputs include emotional information and existing activity information, and a rearranged activity list is output.

[0186] Step 6:

[0187] The device presents the user with a reorganized list of activities sent from the server. In this step, the reorganized list becomes the input and is visually presented to the user. Specifically, the activity priority is highlighted on the device's UI.

[0188] Step 7:

[0189] The device notifies the user of reminders. It receives deadlines and alert information sent from the server as input and notifies the user. The output is an alert message with appropriate timing and content to be emotionally sensitive.

[0190] Step 8:

[0191] Users provide feedback on their activity progress to the server via their terminal. This data is monitored, and decisions are made to determine whether the activity is complete or invalid. The input is user progress information, and the existing management database is updated accordingly.

[0192] Step 9:

[0193] The server collects user feedback and uses it to improve analysis results and the user interface. The collected feedback is used as input for improvement measures to enhance the user interface. The output is optimized system performance.

[0194] (Application Example 2)

[0195] 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".

[0196] While many simple task management systems exist today, they have the drawback of failing to alleviate users' psychological burden because they manage task priorities uniformly without considering the emotional state of individual users. In particular, they may fail to assign tasks appropriately when users are stressed, potentially reducing productivity.

[0197] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0198] In this invention, the server includes analysis means for extracting information from emails and meeting records, management means for automatically generating and managing tasks based on the extracted information, and emotion analysis means for measuring the user's emotional state and dynamically changing the priority of tasks based on that state. This enables efficient task management while flexibly adjusting task priorities according to the user's emotions and reducing psychological burden.

[0199] "Analysis means" refers to the software or hardware functions used to extract necessary information from emails or meeting records.

[0200] A "management tool" is a system element that automatically generates tasks based on extracted information and manages them efficiently.

[0201] A "notification method" is a function that informs the user of the deadline set for a generated task.

[0202] A "monitoring tool" is a function that tracks the progress of tasks and deletes completed tasks as needed.

[0203] An "emotion analysis tool" is a function that measures the user's emotional state and dynamically changes the priority of tasks based on that emotion.

[0204] In this invention, the entire system consists of three elements: a server, a terminal, and a user. The server includes analysis means, management means, notification means, monitoring means, and sentiment analysis means. The analysis means is an algorithm for extracting necessary information from information sources such as emails and meeting minutes, and is implemented using data mining technology. The management means has the function of automatically generating tasks based on the extracted information and saving them in a database. Task management software is used, and each task is assigned a deadline and priority.

[0205] The notification system sends notifications to the user's device about generated tasks and displays reminders at the appropriate time. For example, it provides early notifications for tasks that the user needs to prepare before an important meeting. The monitoring system tracks task progress in real time, automatically deletes completed tasks, and keeps the database clean.

[0206] The emotion analysis system analyzes voice and facial expression data acquired from the user to evaluate the user's emotional state. The algorithm uses machine learning techniques to detect the user's emotions in real time and flexibly adjusts task priorities accordingly. For example, when a user is feeling stressed, it can recommend more intuitive and simpler tasks as a priority.

[0207] The hardware used includes a camera and microphone for analyzing user emotions, and the software is implemented in a programming language such as Python. An external library called emotion_recognition_sdk is used for emotion analysis. Task management is handled using a class called TaskManager.

[0208] As a concrete example, if a user is feeling stressed during their morning commute, they might receive a notification on their smartphone saying, "Your schedule is flexible today, so I've postponed one task." This notification would be automatically sent if voice analysis determines that the user's stress level is high.

[0209] An example of a prompt to input into a generative AI model is: "Create a script that uses emotion recognition to determine if the user is experiencing stress and suggests advice tailored to their task management needs."

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The server periodically collects users' emails and meeting records. The collected data is analyzed using initial analytical tools to extract task-related information. The input here is email and meeting record data, and the output is identified task information. This information is structured and stored in a management database.

[0213] Step 2:

[0214] The server uses emotion analysis tools to collect user voice and facial expression data and analyzes their emotional state in real time. Input is voice and image data, and output is an evaluation of the user's emotional state. The emotion_recognition_sdk is used to extract emotional features from the data and determine the type and intensity of the emotion.

[0215] Step 3:

[0216] The server dynamically adjusts task priorities based on extracted task information and sentiment analysis results. Inputs are task information and sentiment state evaluation results stored in the database, and output is a task list with adjusted priorities. Task reprioritization takes into account the user's psychological burden.

[0217] Step 4:

[0218] The device retrieves the adjusted task list sent from the server and notifies the user. The input is the task list sent from the server, and the output is reminder information displayed to the user. The device sends notifications at the optimal time, taking into account the user's emotional state.

[0219] Step 5:

[0220] When a user updates the progress of a task, that information is transmitted from the terminal to the server. The input is the progress status as performed by the user, and the output is the updated task information. The server checks the status of the task based on this information and completes or deletes it as necessary.

[0221] Step 6:

[0222] The server provides the user with feedback reflecting the sentiment analysis results after the task is completed. The input is information about the completed task and the user's current sentiment state, and the output is a feedback message. The feedback is provided to help the user improve their work and provide psychological support.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] The present invention is implemented as a system that automatically manages tasks mainly generated from emails and meeting minutes using a server. Embodiments of the present invention will be described below in detail from the perspectives of the server, terminal, and user.

[0240] The server periodically retrieves email and meeting record data from email servers and cloud storage with the user's permission. This allows it to collect the latest communication information. The server then processes this data using a natural language processing (NLP) engine to extract important keywords and phrases related to tasks from the text data. For example, from content in an email such as "Submit the report by next Tuesday," it recognizes the task "Submit the report" and sets a deadline.

[0241] The extracted task information is automatically registered by the server in the task management database. This database stores detailed information for each task (task name, due date, assignee, etc.). The server synchronizes this information with the user's terminal, and the user can access their task list using a dedicated application.

[0242] As a means of notification, the server sends reminders to the user's device based on task deadline information. Reminders are provided via email or push notifications, for example, providing warnings such as "Tomorrow is the deadline for submitting the report." This allows users to manage important tasks without forgetting them.

[0243] On the other hand, users can update the task progress using their device. When a user marks a task as complete, that information is sent to the server, and the task is recorded as complete in the database. The server then automatically deletes or updates the status of the task.

[0244] Furthermore, the server can receive feedback from users and collect data to improve analysis accuracy and the interface. Based on this feedback, the server's internal machine learning algorithms can be updated, enabling more efficient task management.

[0245] In this way, the present invention provides a system that streamlines task generation from emails and meeting minutes, enabling users to manage their work stress-free.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] Based on user permission, the server connects to the mail server or cloud storage to retrieve new emails and meeting minutes. This allows for the regular collection of the latest communication data.

[0249] Step 2:

[0250] The server extracts text data from acquired emails and meeting records. For emails, it analyzes the subject and body text; for meeting records, it uses OCR technology to recognize characters as needed.

[0251] Step 3:

[0252] The server uses a natural language processing (NLP) engine to analyze text data and extract keywords and phrases that suggest tasks. For example, it uses trigger words such as "submit," "complete," and "request" to identify when a task is occurring.

[0253] Step 4:

[0254] The server generates task details (task name, deadline, assignee, etc.) based on the extracted information and registers them in the management database. This allows tasks to be centrally managed within the system.

[0255] Step 5:

[0256] The device is synchronized with the server, allowing the user to see the latest task list. Users can view task details on the device and edit them as needed.

[0257] Step 6:

[0258] The server generates reminders based on task deadlines. These reminders are sent to the user's device via email or push notification, ensuring the user is notified at the appropriate time.

[0259] Step 7:

[0260] Users can input task progress via their terminal and mark tasks as complete once they are finished. This progress information is sent to the server.

[0261] Step 8:

[0262] The server updates the task status based on progress information received from the user, and deletes or marks completed tasks from the database. This optimizes task list management.

[0263] Step 9:

[0264] (Optional) The server receives feedback from users and updates algorithms to improve analysis accuracy and the interface. The system is continuously improved through irregularly held feedback sessions.

[0265] (Example 1)

[0266] 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."

[0267] With the increasing volume of information in the modern world, efficiently managing individual work activities presents a significant challenge. In particular, extracting and managing important tasks from a wide range of information sources, such as emails and meeting minutes, without overlooking anything, places a considerable burden on users. Furthermore, performing these tasks manually is time-consuming and prone to human error. Therefore, there is a need to develop a system that automatically extracts information from communication data and optimally manages work activities.

[0268] 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.

[0269] In this invention, the server includes an acquisition means for acquiring data from information communication, an analysis means for extracting important terms through natural language processing, and a management means for generating and storing business activities based on the extracted terms. This enables the automatic generation and management of business activities, freeing users from cumbersome manual work and reducing problems such as overlooking important tasks.

[0270] "Information and communication" refers to various forms of digital data, such as emails and meeting minutes, and the media used for acquiring and managing information.

[0271] A "means of acquiring data" refers to a system that has the function of automatically collecting necessary information from information sources with the user's permission.

[0272] "Natural language processing" is a technology that converts text data into a form that computers can understand and extracts meaning from it.

[0273] "Key terms" refer to keywords and phrases necessary for generating business activities, and are elements that help identify tasks based on them.

[0274] A "management system for generating and storing business activities" is a mechanism for forming tasks from extracted key keywords, registering them in a database, and managing them.

[0275] "Notification methods that notify communication terminals" refers to a function that informs users of important information, such as deadlines for generated business activities, via email or push notifications.

[0276] A "monitoring method that monitors the progress of business activities and automatically reflects completion status" refers to a function that tracks the progress of tasks and updates a database with completed tasks.

[0277] A "learning method" is a technique that uses machine learning algorithms to gain insights from data and continuously improve the performance of a system.

[0278] "Methods for collecting user feedback and making improvements" refers to a system that receives feedback from users and uses it to improve the accuracy of system analysis and the interface.

[0279] This invention provides a system for effectively managing users' digital activities through information and communication. The basic configuration consists of a server for acquiring and analyzing information, generating and managing business activities, a communication terminal for notifying users, and a user interface that allows users to manage information and provide feedback.

[0280] The server periodically retrieves data from information communications with the user's permission. This retrieval utilizes existing mail servers and cloud storage. The server analyzes the collected information using a natural language processing (NLP) engine to extract important words and phrases from the text. For example, this NLP engine recognizes the task "Prepare materials" from a message like "Please prepare materials for next week's meeting" and sets a deadline. The generated work activities are then registered in a database by the server. The database manages detailed information about the work activities (task name, deadline, person in charge, etc.), and this information is simultaneously synchronized with the user's communication terminal.

[0281] The communication terminal receives notifications from the server and provides a means to notify the user of important information regarding business activities. The notifications are sent in the form of emails or push notifications, and support the management of important business activities by sending messages to the user, such as "The deadline for submitting meeting materials is tomorrow."

[0282] The user can operate the communication terminal to manage the progress of their own business activities. When the user marks a business activity as completed, the information is sent to the server and the status is updated in the database. Furthermore, the user can convey opinions to the server for improving the accuracy of analysis and the user interface through the function of providing feedback. The server updates the generated AI model and machine learning algorithm based on this to improve the system's functionality.

[0283] As a specific example, assume that the server analyzes multiple emails regarding the progress of a certain project and automatically generates a business activity called "Create progress report." This activity is saved in the database, and a notification such as "The deadline for the progress report is this weekend" is sent to the terminal, enabling the user to respond without forgetting.

[0284] As an example of a prompt sentence, something like "New project-related emails have arrived. Analyze and generate important business activities from the emails and send notifications." can be considered.

[0285] The flow of the specific process in Example 1 will be described using Figure 11.

[0286] Step 1:

[0287] The server periodically obtains data from the mail server and cloud storage with the user's permission. This input data is text information contained in emails and meeting records. An operation is performed to read the obtained data into the memory in preparation for analysis.

[0288] Step 2:

[0289] The server inputs the acquired text data into a natural language processing (NLP) engine. The NLP engine performs analysis to extract important words and phrases from the text data. As output, keywords related to business activities and tasks based on them are generated. For example, from an email that says, "Please prepare the materials before the meeting," the task "Prepare materials" is extracted.

[0290] Step 3:

[0291] The server registers the extracted task information in the task management database. In this step, detailed information such as the task name, due date, and assignee is stored in the database. The output from the database is a task list organized for each user.

[0292] Step 4:

[0293] The server sends notifications to the user's terminal based on task information registered in the database. The input is task deadline information, which is delivered via communication. The output is a reminder in the form of email or push notification. For example, a notification might say, "Tomorrow is the deadline for creating the document."

[0294] Step 5:

[0295] Users check their task list and update their progress using an application on their device. Input is the user's action, and output is the updated task status. When a user marks a task as complete, that information is sent to the server, and the task completion is recorded in the database.

[0296] Step 6:

[0297] The server analyzes user feedback and updates the generated AI model. This feedback process collects data for improving analysis accuracy and the interface. The input is user opinions and usage, and the output is improved system performance. This improves the efficiency of task management and usability.

[0298] (Application Example 1)

[0299] 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."

[0300] Current electronic payment services require the individual management of transaction information and related notifications, necessitating increased operational efficiency. However, performing this manually is time-consuming and labor-intensive; therefore, a system is needed to automatically generate related tasks based on transaction information and manage them appropriately.

[0301] 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.

[0302] In this invention, the server includes an analysis means for extracting information from communication information, a management means for automatically generating and managing tasks based on the extracted information, and a notification means for setting deadlines for the generated tasks and providing warnings to the user. This makes it possible to efficiently generate and manage tasks from transaction information.

[0303] "Communication information" refers to information sent and received in digital format, including emails and meeting minutes.

[0304] "Business" refers to tasks and activities related to transactions that have objectives to be achieved.

[0305] A "warning" refers to a notification or reminder sent to draw the user's attention.

[0306] "User" refers to an individual or a legal entity that uses this system.

[0307] "Analysis means" refers to a technology or method that processes information to find significant patterns and relationships.

[0308] "Management means" refers to a technology or method for systematically controlling and supervising operations.

[0309] "Notification means" refers to a technology or method for electronically transmitting information or warnings to users.

[0310] "Learning means" refers to technologies or methods that recognize patterns from data and improve performance based on them.

[0311] This invention is a system for efficiently managing transaction information in electronic payment services. The system consists of multiple major elements and aims to improve the business efficiency of users.

[0312] The server first collects communication information and extracts significant data from that information using analysis means. For this analysis, a natural language processing engine such as the Google Cloud Natural Language API is used. For example, if an email contains descriptions of important dates or tasks related to a transaction, this is extracted and used later.

[0313] Based on this extracted data, management means automatically generates and manages operations. Deadlines are set for the generated operations, and alerts are set to notify users of warnings at appropriate times. The notification means displays information as push notifications on smartphones through an application developed with React Native.

[0314] Users can view their business lists and update progress through this application. When a task is completed, the corresponding operation is deleted from the database with the corresponding action.

[0315] Furthermore, the server utilizes learning tools to analyze feedback and improve the task generation algorithm. This process uses machine learning algorithms running on AWS to improve the accuracy of data processing.

[0316] For example, when a user conducts a financial transaction, this system can automatically generate a payment task related to that transaction and notify the user as a reminder on a specified date. This allows users to efficiently carry out their work without forgetting important deadlines.

[0317] Examples of prompt messages include, "Please extract the information needed to automatically generate a payment task from this transaction email."

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The server periodically retrieves communication information from email servers and payment databases authorized by the user. Emails and transaction records are transferred to the server as input data. Based on this data, the server prepares to analyze new information.

[0321] Step 2:

[0322] The server analyzes the collected communication information using the Google Cloud Natural Language API. It extracts important phrases and keywords necessary for task generation from the input emails and records. This process yields output data such as the task name (e.g., "invoice") and payment deadline.

[0323] Step 3:

[0324] The server automatically generates tasks based on the analyzed data. Here, based on the extracted task information, detailed information (task name, deadline, related actions, etc.) is saved to the database for each task. The input is the analysis results, and the output is the registration of a new task in the task management database.

[0325] Step 4:

[0326] The terminal sets reminders related to registered tasks based on instructions from the server. It then executes a notification function using React Native on the user's smartphone, displaying warnings such as "Payment deadline is approaching." This serves as an important notification for the user.

[0327] Step 5:

[0328] Users use a terminal to check their task list and update their progress. Information on tasks marked as complete is sent to the server, and the server deletes the processed tasks from the database. Input is the user's updated information, and output is an update of the task status.

[0329] Step 6:

[0330] The server updates its machine learning algorithms using data collected throughout all processes. It analyzes feedback and usage history to improve the accuracy of future task generation. The input is historical task data and feedback, and the output is an optimized algorithm.

[0331] 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.

[0332] This invention aims to achieve more personalized task management by combining an emotion engine with a task management system. Specific embodiments are shown below.

[0333] The server periodically retrieves information from users' emails and meeting records and automatically extracts task-related information using analytical tools. This extracted task information is registered by the server in a management database. Detailed task information (task name, due date, priority, etc.) is stored in this database.

[0334] This system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine uses user input information, voice, and facial expression data to analyze the user's emotional state in real time. Based on the analysis results of the emotion engine, the server can dynamically adjust task priorities. For example, if the user is feeling stressed, the server will change the priority of tasks to reduce the burden on the user.

[0335] The device has the function of displaying a task list sent from the server to the user. Tasks are prioritized based on emotional information, allowing users to manage tasks optimally according to their own emotional state. The device also receives reminders from the emotional engine and sends notifications at a time and with content that takes the user's emotions into consideration.

[0336] When a user updates the progress of a task, that information is transmitted to the server. The server monitors the task status based on this progress information and completes or deletes the task as needed. By utilizing the sentiment engine, it is possible to provide advice and feedback that reflects the user's emotions even for completed tasks.

[0337] Furthermore, the server collects emotion-related feedback from users to improve the accuracy of the analysis results and the user interface. The data obtained through the emotion engine is continuously optimized by machine learning algorithms to improve the accuracy of subsequent analyses.

[0338] Embodiments of the present invention are systems that go beyond simple task management, taking into account the user's emotions and providing individually customized task management. The aim is to reduce the user's psychological burden and support efficient and effective task execution.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] With user permission, the server periodically retrieves new emails and meeting minutes from the mail server and cloud storage, accumulating the latest data.

[0342] Step 2:

[0343] The server analyzes the content of the retrieved emails and meeting minutes using natural language processing technology to extract phrases and keywords related to the task. This then creates an outline of the task.

[0344] Step 3:

[0345] The server registers tasks in the management database based on the extracted task information. Each task is assigned attributes such as name, due date, priority, and assignee.

[0346] Step 4:

[0347] The emotion engine acquires voice and facial expression data transmitted from the user's device and analyzes the user's emotional state in real time. This process is performed with the user's consent.

[0348] Step 5:

[0349] The server receives the results of the emotion engine's analysis and dynamically adjusts the priority of each task based on that. For example, if the user is determined to be in a high-stress state, the server will change the priority of important but non-urgent tasks to be lowered.

[0350] Step 6:

[0351] The device presents the user with an updated task list. Each task is displayed in order of priority based on the user's emotional state, making it intuitively clear which tasks should be addressed.

[0352] Step 7:

[0353] The server generates reminders based on task deadlines and sends notifications to the device at a time and with message content that takes the user's emotional state into consideration. This allows users to manage their tasks more effectively.

[0354] Step 8:

[0355] Users update task progress via their devices. This information is immediately sent to the server, and the task status is updated to "In Progress," "Completed," etc.

[0356] Step 9:

[0357] When a task is deemed complete, the server removes it from the database and provides the user with sentiment feedback, along with the relevant information.

[0358] Step 10:

[0359] The server collects emotional feedback from users and uses it to improve analysis results and the user interface. This feedback is fed into machine learning algorithms and used to improve the system's accuracy.

[0360] (Example 2)

[0361] 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".

[0362] Traditional task management systems struggle to flexibly respond to users' emotional states and the urgency of their activities. Furthermore, they lack mechanisms to efficiently utilize user feedback and improve management accuracy, creating a need for more personalized activity management.

[0363] 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.

[0364] In this invention, the server includes analysis means for extracting information from electronic communications and schedule records, control means for automatically generating and managing activities based on the extracted information, and evaluation means for analyzing the user's state and dynamically adjusting the priority of activities. This enables optimal task management according to the user's emotional state and the urgency of the activities.

[0365] "Electronic communications" refers to means of transmitting information through networks, including email and digital messages.

[0366] "Schedule records" refer to documents or data that contain the user's activity plans, such as meeting schedules and timetables.

[0367] "Analysis methods" is a general term for technologies and methods used to extract necessary information from electronic communications and schedule records and to analyze their content.

[0368] "Control measures" refer to technologies and methods for automatically generating activities based on extracted information and efficiently managing them.

[0369] "Notification means" refers to technologies and methods for informing users of deadlines for activities or important events.

[0370] "Evaluation methods" refer to technologies and methods for analyzing the user's emotional state and other factors, and dynamically adjusting the priority of activities based on those analyses.

[0371] "Monitoring measures" refer to technologies and methods for checking the progress of activities and automatically deleting completed activities.

[0372] "Learning methods" refer to techniques and methods for progressively improving processing accuracy based on the progress of an activity.

[0373] "Improvement methods" refer to technologies and methods for receiving feedback from users and improving the analysis results and user interface.

[0374] To implement this invention in practice, it is necessary to effectively utilize servers and terminals. The server first uses external services such as APIs to collect electronic communications and schedule records. This includes digital communication software and calendar services using cloud services. The server acquires this data and extracts information using analytical means. At this time, natural language processing tools are used to analyze the text data and identify the details, deadlines, and priorities of activities.

[0375] Next, the server records the extracted activity information in a management database using control mechanisms. This database is built using an open-source database management system, enabling continuous management of activities.

[0376] Furthermore, the server analyzes the user's emotional state through evaluation tools. This involves using emotion recognition software to analyze voice data and facial expression data, thereby understanding the user's psychological state in real time.

[0377] The device displays an activity list sent from the server to the user. It features an intuitive and easy-to-understand UI that responds to the user's psychological state and can highlight items according to priority. Furthermore, the device uses notification methods to provide reminders that take into account the deadlines and emotions set by the user.

[0378] When a user updates the progress of an activity, that information is fed back to the server, which then uses monitoring mechanisms to complete or invalidate the activity. Furthermore, user feedback is used to improve system performance through refinement mechanisms.

[0379] As a concrete example, consider a situation where a user feels they "need to prepare for next week's meeting, but are too busy to find the time." In this case, the server assesses the user's stress level and, based on the assessment, sets meeting-related activities as a high priority, adjusting other activities to a lower priority.

[0380] An example of a prompt message could be input into the generating AI model, such as, "If the user is feeling fatigued, reduce reminder notifications and display only important tasks." In this way, the system can provide optimal activity management based on the user's emotional state, improving efficiency and user satisfaction.

[0381] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0382] Step 1:

[0383] The server collects information from electronic communications and schedule records. In this step, data is retrieved via APIs from email services and schedule management systems. Inputs include user emails and schedule information, which are used to collect raw data about activities. From this raw data, activity plans and message content are output.

[0384] Step 2:

[0385] The server analyzes the collected information using analytical tools. Specifically, it extracts activity-related information from the raw data using natural language processing tools. For example, it selects items such as the activity title, deadline, and priority. As a result of this process, structured activity information is output after analyzing the text data.

[0386] Step 3:

[0387] The server automatically generates activities using the analyzed data and registers them in the management database. The structured activity information obtained in step 2 is used as input, and the activity details are stored in the database. This database entry will be used for future task management.

[0388] Step 4:

[0389] The server utilizes emotion recognition methods to evaluate the user's psychological state. Using emotion recognition software, it acquires voice and facial expression data as input and analyzes the emotional state. The analysis outputs emotional information such as the user's stress level and happiness level.

[0390] Step 5:

[0391] The server dynamically adjusts activity priorities based on emotional information. An evaluation method is used to rearrange activities according to the user's emotions. Inputs include emotional information and existing activity information, and a rearranged activity list is output.

[0392] Step 6:

[0393] The device presents the user with a reorganized list of activities sent from the server. In this step, the reorganized list becomes the input and is visually presented to the user. Specifically, the activity priority is highlighted on the device's UI.

[0394] Step 7:

[0395] The device notifies the user of reminders. It receives deadlines and alert information sent from the server as input and notifies the user. The output is an alert message with appropriate timing and content to be emotionally sensitive.

[0396] Step 8:

[0397] Users provide feedback on their activity progress to the server via their terminal. This data is monitored, and decisions are made to determine whether the activity is complete or invalid. The input is user progress information, and the existing management database is updated accordingly.

[0398] Step 9:

[0399] The server collects user feedback and uses it to improve analysis results and the user interface. The collected feedback is used as input for improvement measures to enhance the user interface. The output is optimized system performance.

[0400] (Application Example 2)

[0401] 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."

[0402] While many simple task management systems exist today, they have the drawback of failing to alleviate users' psychological burden because they manage task priorities uniformly without considering the emotional state of individual users. In particular, they may fail to assign tasks appropriately when users are stressed, potentially reducing productivity.

[0403] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0404] In this invention, the server includes analysis means for extracting information from emails and meeting records, management means for automatically generating and managing tasks based on the extracted information, and emotion analysis means for measuring the user's emotional state and dynamically changing the priority of tasks based on that state. This enables efficient task management while flexibly adjusting task priorities according to the user's emotions and reducing psychological burden.

[0405] "Analysis means" refers to the software or hardware functions used to extract necessary information from emails or meeting records.

[0406] A "management tool" is a system element that automatically generates tasks based on extracted information and manages them efficiently.

[0407] A "notification method" is a function that informs the user of the deadline set for a generated task.

[0408] A "monitoring tool" is a function that tracks the progress of tasks and deletes completed tasks as needed.

[0409] An "emotion analysis tool" is a function that measures the user's emotional state and dynamically changes the priority of tasks based on that emotion.

[0410] In this invention, the entire system consists of three elements: a server, a terminal, and a user. The server includes analysis means, management means, notification means, monitoring means, and sentiment analysis means. The analysis means is an algorithm for extracting necessary information from information sources such as emails and meeting minutes, and is implemented using data mining technology. The management means has the function of automatically generating tasks based on the extracted information and saving them in a database. Task management software is used, and each task is assigned a deadline and priority.

[0411] The notification system sends notifications to the user's device about generated tasks and displays reminders at the appropriate time. For example, it provides early notifications for tasks that the user needs to prepare before an important meeting. The monitoring system tracks task progress in real time, automatically deletes completed tasks, and keeps the database clean.

[0412] The emotion analysis system analyzes voice and facial expression data acquired from the user to evaluate the user's emotional state. The algorithm uses machine learning techniques to detect the user's emotions in real time and flexibly adjusts task priorities accordingly. For example, when a user is feeling stressed, it can recommend more intuitive and simpler tasks as a priority.

[0413] The hardware used includes a camera and microphone for analyzing user emotions, and the software is implemented in a programming language such as Python. An external library called emotion_recognition_sdk is used for emotion analysis. Task management is handled using a class called TaskManager.

[0414] As a concrete example, if a user is feeling stressed during their morning commute, they might receive a notification on their smartphone saying, "Your schedule is flexible today, so I've postponed one task." This notification would be automatically sent if voice analysis determines that the user's stress level is high.

[0415] An example of a prompt to input into a generative AI model is: "Create a script that uses emotion recognition to determine if the user is experiencing stress and suggests advice tailored to their task management needs."

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] The server periodically collects users' emails and meeting records. The collected data is analyzed using initial analytical tools to extract task-related information. The input here is email and meeting record data, and the output is identified task information. This information is structured and stored in a management database.

[0419] Step 2:

[0420] The server uses emotion analysis tools to collect user voice and facial expression data and analyzes their emotional state in real time. Input is voice and image data, and output is an evaluation of the user's emotional state. The emotion_recognition_sdk is used to extract emotional features from the data and determine the type and intensity of the emotion.

[0421] Step 3:

[0422] The server dynamically adjusts task priorities based on extracted task information and sentiment analysis results. Inputs are task information and sentiment state evaluation results stored in the database, and output is a task list with adjusted priorities. Task reprioritization takes into account the user's psychological burden.

[0423] Step 4:

[0424] The device retrieves the adjusted task list sent from the server and notifies the user. The input is the task list sent from the server, and the output is reminder information displayed to the user. The device sends notifications at the optimal time, taking into account the user's emotional state.

[0425] Step 5:

[0426] When a user updates the progress of a task, that information is transmitted from the terminal to the server. The input is the progress status as performed by the user, and the output is the updated task information. The server checks the status of the task based on this information and completes or deletes it as necessary.

[0427] Step 6:

[0428] The server provides the user with feedback reflecting the sentiment analysis results after the task is completed. The input is information about the completed task and the user's current sentiment state, and the output is a feedback message. The feedback is provided to help the user improve their work and provide psychological support.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Third Embodiment]

[0433] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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".

[0445] The present invention is implemented as a system that automatically manages tasks mainly generated from emails and meeting minutes using a server. Embodiments of the present invention will be described below in detail from the perspectives of the server, terminal, and user.

[0446] The server periodically retrieves email and meeting record data from email servers and cloud storage with the user's permission. This allows it to collect the latest communication information. The server then processes this data using a natural language processing (NLP) engine to extract important keywords and phrases related to tasks from the text data. For example, from content in an email such as "Submit the report by next Tuesday," it recognizes the task "Submit the report" and sets a deadline.

[0447] The extracted task information is automatically registered by the server in the task management database. This database stores detailed information for each task (task name, due date, assignee, etc.). The server synchronizes this information with the user's terminal, and the user can access their task list using a dedicated application.

[0448] As a means of notification, the server sends reminders to the user's device based on task deadline information. Reminders are provided via email or push notifications, for example, providing warnings such as "Tomorrow is the deadline for submitting the report." This allows users to manage important tasks without forgetting them.

[0449] On the other hand, users can update the task progress using their device. When a user marks a task as complete, that information is sent to the server, and the task is recorded as complete in the database. The server then automatically deletes or updates the status of the task.

[0450] Furthermore, the server can receive feedback from users and collect data to improve analysis accuracy and the interface. Based on this feedback, the server's internal machine learning algorithms can be updated, enabling more efficient task management.

[0451] In this way, the present invention provides a system that streamlines task generation from emails and meeting minutes, enabling users to manage their work stress-free.

[0452] The following describes the processing flow.

[0453] Step 1:

[0454] Based on user permission, the server connects to the mail server or cloud storage to retrieve new emails and meeting minutes. This allows for the regular collection of the latest communication data.

[0455] Step 2:

[0456] The server extracts text data from acquired emails and meeting records. For emails, it analyzes the subject and body text; for meeting records, it uses OCR technology to recognize characters as needed.

[0457] Step 3:

[0458] The server uses a natural language processing (NLP) engine to analyze text data and extract keywords and phrases that suggest tasks. For example, it uses trigger words such as "submit," "complete," and "request" to identify when a task is occurring.

[0459] Step 4:

[0460] The server generates task details (task name, deadline, assignee, etc.) based on the extracted information and registers them in the management database. This allows tasks to be centrally managed within the system.

[0461] Step 5:

[0462] The device is synchronized with the server, allowing the user to see the latest task list. Users can view task details on the device and edit them as needed.

[0463] Step 6:

[0464] The server generates reminders based on task deadlines. These reminders are sent to the user's device via email or push notification, ensuring the user is notified at the appropriate time.

[0465] Step 7:

[0466] Users can input task progress via their terminal and mark tasks as complete once they are finished. This progress information is sent to the server.

[0467] Step 8:

[0468] The server updates the task status based on progress information received from the user, and deletes or marks completed tasks from the database. This optimizes task list management.

[0469] Step 9:

[0470] (Optional) The server receives feedback from users and updates algorithms to improve analysis accuracy and the interface. The system is continuously improved through irregularly held feedback sessions.

[0471] (Example 1)

[0472] 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."

[0473] With the increasing volume of information in the modern world, efficiently managing individual work activities presents a significant challenge. In particular, extracting and managing important tasks from a wide range of information sources, such as emails and meeting minutes, without overlooking anything, places a considerable burden on users. Furthermore, performing these tasks manually is time-consuming and prone to human error. Therefore, there is a need to develop a system that automatically extracts information from communication data and optimally manages work activities.

[0474] 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.

[0475] In this invention, the server includes an acquisition means for acquiring data from information communication, an analysis means for extracting important terms through natural language processing, and a management means for generating and storing business activities based on the extracted terms. This enables the automatic generation and management of business activities, freeing users from cumbersome manual work and reducing problems such as overlooking important tasks.

[0476] "Information and communication" refers to various forms of digital data, such as emails and meeting minutes, and the media used for acquiring and managing information.

[0477] A "means of acquiring data" refers to a system that has the function of automatically collecting necessary information from information sources with the user's permission.

[0478] "Natural language processing" is a technology that converts text data into a form that computers can understand and extracts meaning from it.

[0479] "Key terms" refer to keywords and phrases necessary for generating business activities, and are elements that help identify tasks based on them.

[0480] A "management system for generating and storing business activities" is a mechanism for forming tasks from extracted key keywords, registering them in a database, and managing them.

[0481] "Notification methods that notify communication terminals" refers to a function that informs users of important information, such as deadlines for generated business activities, via email or push notifications.

[0482] A "monitoring method that monitors the progress of business activities and automatically reflects completion status" refers to a function that tracks the progress of tasks and updates a database with completed tasks.

[0483] A "learning method" is a technique that uses machine learning algorithms to gain insights from data and continuously improve the performance of a system.

[0484] "Methods for collecting user feedback and making improvements" refers to a system that receives feedback from users and uses it to improve the accuracy of system analysis and the interface.

[0485] This invention provides a system for effectively managing users' digital activities through information and communication. The basic configuration consists of a server for acquiring and analyzing information, generating and managing business activities, a communication terminal for notifying users, and a user interface that allows users to manage information and provide feedback.

[0486] The server periodically retrieves data from information communications with the user's permission. This retrieval utilizes existing mail servers and cloud storage. The server analyzes the collected information using a natural language processing (NLP) engine to extract important words and phrases from the text. For example, this NLP engine recognizes the task "Prepare materials" from a message like "Please prepare materials for next week's meeting" and sets a deadline. The generated work activities are then registered in a database by the server. The database manages detailed information about the work activities (task name, deadline, person in charge, etc.), and this information is simultaneously synchronized with the user's communication terminal.

[0487] The communication terminal receives notifications from the server and provides a means to notify users of important information regarding their work activities. Notifications are sent via email or push notifications, and help users manage important work activities by sending messages such as "The deadline for submitting meeting materials is tomorrow."

[0488] Users can manage the progress of their work activities by operating a communication terminal. When a user marks a work activity as complete, that information is sent to the server, and the status is updated in the database. Furthermore, users can provide feedback to the server through a feedback function to improve the accuracy of the analysis and enhance the user interface. The server uses this feedback to update its generated AI models and machine learning algorithms, thereby improving the system's functionality.

[0489] As a concrete example, suppose a server analyzes multiple emails regarding the progress of a project and automatically generates a work activity called "Create Progress Report." This activity is saved in a database, and a notification such as "The deadline for the progress report is this weekend" is sent to the user's terminal, ensuring that the user does not forget to take action.

[0490] An example of a prompt message might be: "A new project-related email has arrived. Please analyze the email to generate and send notifications for important business activities."

[0491] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0492] Step 1:

[0493] The server periodically retrieves data from email servers and cloud storage with the user's permission. This input data consists of text information contained in emails and meeting minutes. The retrieved data is then loaded into memory in preparation for analysis.

[0494] Step 2:

[0495] The server inputs the acquired text data into a natural language processing (NLP) engine. The NLP engine performs analysis to extract important words and phrases from the text data. As output, keywords related to business activities and tasks based on them are generated. For example, from an email that says, "Please prepare the materials before the meeting," the task "Prepare materials" is extracted.

[0496] Step 3:

[0497] The server registers the extracted task information in the task management database. In this step, detailed information such as the task name, due date, and assignee is stored in the database. The output from the database is a task list organized for each user.

[0498] Step 4:

[0499] The server sends notifications to the user's terminal based on task information registered in the database. The input is task deadline information, which is delivered via communication. The output is a reminder in the form of email or push notification. For example, a notification might say, "Tomorrow is the deadline for creating the document."

[0500] Step 5:

[0501] Users check their task list and update their progress using an application on their device. Input is the user's action, and output is the updated task status. When a user marks a task as complete, that information is sent to the server, and the task completion is recorded in the database.

[0502] Step 6:

[0503] The server analyzes user feedback and updates the generated AI model. This feedback process collects data for improving analysis accuracy and the interface. The input is user opinions and usage, and the output is improved system performance. This improves the efficiency of task management and usability.

[0504] (Application Example 1)

[0505] 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."

[0506] Current electronic payment services require the individual management of transaction information and related notifications, necessitating increased operational efficiency. However, performing this manually is time-consuming and labor-intensive; therefore, a system is needed to automatically generate related tasks based on transaction information and manage them appropriately.

[0507] 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.

[0508] In this invention, the server includes an analysis means for extracting information from communication information, a management means for automatically generating and managing tasks based on the extracted information, and a notification means for setting deadlines for the generated tasks and providing warnings to the user. This makes it possible to efficiently generate and manage tasks from transaction information.

[0509] "Communication information" refers to information sent and received in digital format, including emails and meeting minutes.

[0510] "Business" refers to tasks and activities related to transactions that have objectives to be achieved.

[0511] A "warning" refers to a notification or reminder sent to draw the user's attention.

[0512] "Users" refers to individuals or corporations that use this system.

[0513] "Analytical means" refers to techniques or methods for processing information to find significant patterns or relationships.

[0514] "Control measures" refer to techniques or methods for systematically controlling and supervising operations.

[0515] "Notification means" refers to a technology or method for electronically transmitting information or warnings to users.

[0516] "Learning methods" refer to techniques and methods that recognize patterns from data and improve performance based on these patterns.

[0517] This invention is a system for efficiently managing transaction information in electronic payment services. The system consists of several main elements and aims to improve the operational efficiency of users.

[0518] The server first collects communication information and then uses analysis tools to extract meaningful data from that information. This analysis uses natural language processing engines such as the Google Cloud Natural Language API. For example, if an email contains descriptions of important dates or tasks related to a transaction, this information is extracted and used later.

[0519] Based on this extracted data, the management system automatically generates and manages tasks. Each generated task has a deadline, and alerts are set to notify users at the appropriate time. The notification system displays information as push notifications on smartphones through an application developed with React Native.

[0520] Users can view their task list and update their progress through this application. When a task is completed, the task is deleted from the database with the corresponding action.

[0521] Furthermore, the server utilizes learning tools to analyze feedback and improve the task generation algorithm. This process uses machine learning algorithms running on AWS to improve the accuracy of data processing.

[0522] For example, when a user conducts a financial transaction, this system can automatically generate a payment task related to that transaction and notify the user as a reminder on a specified date. This allows users to efficiently carry out their work without forgetting important deadlines.

[0523] Examples of prompt messages include, "Please extract the information needed to automatically generate a payment task from this transaction email."

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Step 1:

[0526] The server periodically retrieves communication information from email servers and payment databases authorized by the user. Emails and transaction records are transferred to the server as input data. Based on this data, the server prepares to analyze new information.

[0527] Step 2:

[0528] The server analyzes the collected communication information using the Google Cloud Natural Language API. It extracts important phrases and keywords necessary for task generation from the input emails and records. This process yields output data such as the task name (e.g., "invoice") and payment deadline.

[0529] Step 3:

[0530] The server automatically generates tasks based on the analyzed data. Here, based on the extracted task information, detailed information (task name, deadline, related actions, etc.) is saved to the database for each task. The input is the analysis results, and the output is the registration of a new task in the task management database.

[0531] Step 4:

[0532] The terminal sets reminders related to registered tasks based on instructions from the server. It then executes a notification function using React Native on the user's smartphone, displaying warnings such as "Payment deadline is approaching." This serves as an important notification for the user.

[0533] Step 5:

[0534] Users use a terminal to check their task list and update their progress. Information on tasks marked as complete is sent to the server, and the server deletes the processed tasks from the database. Input is the user's updated information, and output is an update of the task status.

[0535] Step 6:

[0536] The server updates its machine learning algorithms using data collected throughout all processes. It analyzes feedback and usage history to improve the accuracy of future task generation. The input is historical task data and feedback, and the output is an optimized algorithm.

[0537] 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.

[0538] This invention aims to achieve more personalized task management by combining an emotion engine with a task management system. Specific embodiments are shown below.

[0539] The server periodically retrieves information from users' emails and meeting records and automatically extracts task-related information using analytical tools. This extracted task information is registered by the server in a management database. Detailed task information (task name, due date, priority, etc.) is stored in this database.

[0540] This system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine uses user input information, voice, and facial expression data to analyze the user's emotional state in real time. Based on the analysis results of the emotion engine, the server can dynamically adjust task priorities. For example, if the user is feeling stressed, the server will change the priority of tasks to reduce the burden on the user.

[0541] The device has the function of displaying a task list sent from the server to the user. Tasks are prioritized based on emotional information, allowing users to manage tasks optimally according to their own emotional state. The device also receives reminders from the emotional engine and sends notifications at a time and with content that takes the user's emotions into consideration.

[0542] When a user updates the progress of a task, that information is transmitted to the server. The server monitors the task status based on this progress information and completes or deletes the task as needed. By utilizing the sentiment engine, it is possible to provide advice and feedback that reflects the user's emotions even for completed tasks.

[0543] Furthermore, the server collects emotion-related feedback from users to improve the accuracy of the analysis results and the user interface. The data obtained through the emotion engine is continuously optimized by machine learning algorithms to improve the accuracy of subsequent analyses.

[0544] Embodiments of the present invention are systems that go beyond simple task management, taking into account the user's emotions and providing individually customized task management. The aim is to reduce the user's psychological burden and support efficient and effective task execution.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] With user permission, the server periodically retrieves new emails and meeting minutes from the mail server and cloud storage, accumulating the latest data.

[0548] Step 2:

[0549] The server analyzes the content of the retrieved emails and meeting minutes using natural language processing technology to extract phrases and keywords related to the task. This then creates an outline of the task.

[0550] Step 3:

[0551] The server registers tasks in the management database based on the extracted task information. Each task is assigned attributes such as name, due date, priority, and assignee.

[0552] Step 4:

[0553] The emotion engine acquires voice and facial expression data transmitted from the user's device and analyzes the user's emotional state in real time. This process is performed with the user's consent.

[0554] Step 5:

[0555] The server receives the results of the emotion engine's analysis and dynamically adjusts the priority of each task based on that. For example, if the user is determined to be in a high-stress state, the server will change the priority of important but non-urgent tasks to be lowered.

[0556] Step 6:

[0557] The device presents the user with an updated task list. Each task is displayed in order of priority based on the user's emotional state, making it intuitively clear which tasks should be addressed.

[0558] Step 7:

[0559] The server generates reminders based on task deadlines and sends notifications to the device at a time and with message content that takes the user's emotional state into consideration. This allows users to manage their tasks more effectively.

[0560] Step 8:

[0561] Users update task progress via their devices. This information is immediately sent to the server, and the task status is updated to "In Progress," "Completed," etc.

[0562] Step 9:

[0563] When a task is deemed complete, the server removes it from the database and provides the user with sentiment feedback, along with the relevant information.

[0564] Step 10:

[0565] The server collects emotional feedback from users and uses it to improve analysis results and the user interface. This feedback is fed into machine learning algorithms and used to improve the system's accuracy.

[0566] (Example 2)

[0567] 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."

[0568] Traditional task management systems struggle to flexibly respond to users' emotional states and the urgency of their activities. Furthermore, they lack mechanisms to efficiently utilize user feedback and improve management accuracy, creating a need for more personalized activity management.

[0569] 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.

[0570] In this invention, the server includes analysis means for extracting information from electronic communications and schedule records, control means for automatically generating and managing activities based on the extracted information, and evaluation means for analyzing the user's state and dynamically adjusting the priority of activities. This enables optimal task management according to the user's emotional state and the urgency of the activities.

[0571] "Electronic communications" refers to means of transmitting information through networks, including email and digital messages.

[0572] "Schedule records" refer to documents or data that contain the user's activity plans, such as meeting schedules and timetables.

[0573] "Analysis methods" is a general term for technologies and methods used to extract necessary information from electronic communications and schedule records and to analyze their content.

[0574] "Control measures" refer to technologies and methods for automatically generating activities based on extracted information and efficiently managing them.

[0575] "Notification means" refers to technologies and methods for informing users of deadlines for activities or important events.

[0576] "Evaluation methods" refer to technologies and methods for analyzing the user's emotional state and other factors, and dynamically adjusting the priority of activities based on those analyses.

[0577] "Monitoring measures" refer to technologies and methods for checking the progress of activities and automatically deleting completed activities.

[0578] "Learning methods" refer to techniques and methods for progressively improving processing accuracy based on the progress of an activity.

[0579] "Improvement methods" refer to technologies and methods for receiving feedback from users and improving the analysis results and user interface.

[0580] To implement this invention in practice, it is necessary to effectively utilize servers and terminals. The server first uses external services such as APIs to collect electronic communications and schedule records. This includes digital communication software and calendar services using cloud services. The server acquires this data and extracts information using analytical means. At this time, natural language processing tools are used to analyze the text data and identify the details, deadlines, and priorities of activities.

[0581] Next, the server records the extracted activity information in a management database using control mechanisms. This database is built using an open-source database management system, enabling continuous management of activities.

[0582] Furthermore, the server analyzes the user's emotional state through evaluation tools. This involves using emotion recognition software to analyze voice data and facial expression data, thereby understanding the user's psychological state in real time.

[0583] The device displays an activity list sent from the server to the user. It features an intuitive and easy-to-understand UI that responds to the user's psychological state and can highlight items according to priority. Furthermore, the device uses notification methods to provide reminders that take into account the deadlines and emotions set by the user.

[0584] When a user updates the progress of an activity, that information is fed back to the server, which then uses monitoring mechanisms to complete or invalidate the activity. Furthermore, user feedback is used to improve system performance through refinement mechanisms.

[0585] As a concrete example, consider a situation where a user feels they "need to prepare for next week's meeting, but are too busy to find the time." In this case, the server assesses the user's stress level and, based on the assessment, sets meeting-related activities as a high priority, adjusting other activities to a lower priority.

[0586] An example of a prompt message could be input into the generating AI model, such as, "If the user is feeling fatigued, reduce reminder notifications and display only important tasks." In this way, the system can provide optimal activity management based on the user's emotional state, improving efficiency and user satisfaction.

[0587] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0588] Step 1:

[0589] The server collects information from electronic communications and schedule records. In this step, data is retrieved via APIs from email services and schedule management systems. Inputs include user emails and schedule information, which are used to collect raw data about activities. From this raw data, activity plans and message content are output.

[0590] Step 2:

[0591] The server analyzes the collected information using analytical tools. Specifically, it extracts activity-related information from the raw data using natural language processing tools. For example, it selects items such as the activity title, deadline, and priority. As a result of this process, structured activity information is output after analyzing the text data.

[0592] Step 3:

[0593] The server automatically generates activities using the analyzed data and registers them in the management database. The structured activity information obtained in step 2 is used as input, and the activity details are stored in the database. This database entry will be used for future task management.

[0594] Step 4:

[0595] The server utilizes emotion recognition methods to evaluate the user's psychological state. Using emotion recognition software, it acquires voice and facial expression data as input and analyzes the emotional state. The analysis outputs emotional information such as the user's stress level and happiness level.

[0596] Step 5:

[0597] The server dynamically adjusts activity priorities based on emotional information. An evaluation method is used to rearrange activities according to the user's emotions. Inputs include emotional information and existing activity information, and a rearranged activity list is output.

[0598] Step 6:

[0599] The device presents the user with a reorganized list of activities sent from the server. In this step, the reorganized list becomes the input and is visually presented to the user. Specifically, the activity priority is highlighted on the device's UI.

[0600] Step 7:

[0601] The device notifies the user of reminders. It receives deadlines and alert information sent from the server as input and notifies the user. The output is an alert message with appropriate timing and content to be emotionally sensitive.

[0602] Step 8:

[0603] Users provide feedback on their activity progress to the server via their terminal. This data is monitored, and decisions are made to determine whether the activity is complete or invalid. The input is user progress information, and the existing management database is updated accordingly.

[0604] Step 9:

[0605] The server collects user feedback and uses it to improve analysis results and the user interface. The collected feedback is used as input for improvement measures to enhance the user interface. The output is optimized system performance.

[0606] (Application Example 2)

[0607] 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."

[0608] While many simple task management systems exist today, they have the drawback of failing to alleviate users' psychological burden because they manage task priorities uniformly without considering the emotional state of individual users. In particular, they may fail to assign tasks appropriately when users are stressed, potentially reducing productivity.

[0609] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0610] In this invention, the server includes analysis means for extracting information from emails and meeting records, management means for automatically generating and managing tasks based on the extracted information, and emotion analysis means for measuring the user's emotional state and dynamically changing the priority of tasks based on that state. This enables efficient task management while flexibly adjusting task priorities according to the user's emotions and reducing psychological burden.

[0611] "Analysis means" refers to the software or hardware functions used to extract necessary information from emails or meeting records.

[0612] A "management tool" is a system element that automatically generates tasks based on extracted information and manages them efficiently.

[0613] A "notification method" is a function that informs the user of the deadline set for a generated task.

[0614] A "monitoring tool" is a function that tracks the progress of tasks and deletes completed tasks as needed.

[0615] An "emotion analysis tool" is a function that measures the user's emotional state and dynamically changes the priority of tasks based on that emotion.

[0616] In this invention, the entire system consists of three elements: a server, a terminal, and a user. The server includes analysis means, management means, notification means, monitoring means, and sentiment analysis means. The analysis means is an algorithm for extracting necessary information from information sources such as emails and meeting minutes, and is implemented using data mining technology. The management means has the function of automatically generating tasks based on the extracted information and saving them in a database. Task management software is used, and each task is assigned a deadline and priority.

[0617] The notification system sends notifications to the user's device about generated tasks and displays reminders at the appropriate time. For example, it provides early notifications for tasks that the user needs to prepare before an important meeting. The monitoring system tracks task progress in real time, automatically deletes completed tasks, and keeps the database clean.

[0618] The emotion analysis system analyzes voice and facial expression data acquired from the user to evaluate the user's emotional state. The algorithm uses machine learning techniques to detect the user's emotions in real time and flexibly adjusts task priorities accordingly. For example, when a user is feeling stressed, it can recommend more intuitive and simpler tasks as a priority.

[0619] The hardware used includes a camera and microphone for analyzing user emotions, and the software is implemented in a programming language such as Python. An external library called emotion_recognition_sdk is used for emotion analysis. Task management is handled using a class called TaskManager.

[0620] As a concrete example, if a user is feeling stressed during their morning commute, they might receive a notification on their smartphone saying, "Your schedule is flexible today, so I've postponed one task." This notification would be automatically sent if voice analysis determines that the user's stress level is high.

[0621] An example of a prompt to input into a generative AI model is: "Create a script that uses emotion recognition to determine if the user is experiencing stress and suggests advice tailored to their task management needs."

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The server periodically collects users' emails and meeting records. The collected data is analyzed using initial analytical tools to extract task-related information. The input here is email and meeting record data, and the output is identified task information. This information is structured and stored in a management database.

[0625] Step 2:

[0626] The server uses emotion analysis tools to collect user voice and facial expression data and analyzes their emotional state in real time. Input is voice and image data, and output is an evaluation of the user's emotional state. The emotion_recognition_sdk is used to extract emotional features from the data and determine the type and intensity of the emotion.

[0627] Step 3:

[0628] The server dynamically adjusts task priorities based on extracted task information and sentiment analysis results. Inputs are task information and sentiment state evaluation results stored in the database, and output is a task list with adjusted priorities. Task reprioritization takes into account the user's psychological burden.

[0629] Step 4:

[0630] The device retrieves the adjusted task list sent from the server and notifies the user. The input is the task list sent from the server, and the output is reminder information displayed to the user. The device sends notifications at the optimal time, taking into account the user's emotional state.

[0631] Step 5:

[0632] When a user updates the progress of a task, that information is transmitted from the terminal to the server. The input is the progress status as performed by the user, and the output is the updated task information. The server checks the status of the task based on this information and completes or deletes it as necessary.

[0633] Step 6:

[0634] The server provides the user with feedback reflecting the sentiment analysis results after the task is completed. The input is information about the completed task and the user's current sentiment state, and the output is a feedback message. The feedback is provided to help the user improve their work and provide psychological support.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] [Fourth Embodiment]

[0639] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0640] 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.

[0641] 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).

[0642] 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.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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".

[0652] The present invention is implemented as a system that automatically manages tasks mainly generated from emails and meeting minutes using a server. Embodiments of the present invention will be described below in detail from the perspectives of the server, terminal, and user.

[0653] The server periodically retrieves email and meeting record data from email servers and cloud storage with the user's permission. This allows it to collect the latest communication information. The server then processes this data using a natural language processing (NLP) engine to extract important keywords and phrases related to tasks from the text data. For example, from content in an email such as "Submit the report by next Tuesday," it recognizes the task "Submit the report" and sets a deadline.

[0654] The extracted task information is automatically registered by the server in the task management database. This database stores detailed information for each task (task name, due date, assignee, etc.). The server synchronizes this information with the user's terminal, and the user can access their task list using a dedicated application.

[0655] As a means of notification, the server sends reminders to the user's device based on task deadline information. Reminders are provided via email or push notifications, for example, providing warnings such as "Tomorrow is the deadline for submitting the report." This allows users to manage important tasks without forgetting them.

[0656] On the other hand, users can update the task progress using their device. When a user marks a task as complete, that information is sent to the server, and the task is recorded as complete in the database. The server then automatically deletes or updates the status of the task.

[0657] Furthermore, the server can receive feedback from users and collect data to improve analysis accuracy and the interface. Based on this feedback, the server's internal machine learning algorithms can be updated, enabling more efficient task management.

[0658] In this way, the present invention provides a system that streamlines task generation from emails and meeting minutes, enabling users to manage their work stress-free.

[0659] The following describes the processing flow.

[0660] Step 1:

[0661] Based on user permission, the server connects to the mail server or cloud storage to retrieve new emails and meeting minutes. This allows for the regular collection of the latest communication data.

[0662] Step 2:

[0663] The server extracts text data from acquired emails and meeting records. For emails, it analyzes the subject and body text; for meeting records, it uses OCR technology to recognize characters as needed.

[0664] Step 3:

[0665] The server uses a natural language processing (NLP) engine to analyze text data and extract keywords and phrases that suggest tasks. For example, it uses trigger words such as "submit," "complete," and "request" to identify when a task is occurring.

[0666] Step 4:

[0667] The server generates task details (task name, deadline, assignee, etc.) based on the extracted information and registers them in the management database. This allows tasks to be centrally managed within the system.

[0668] Step 5:

[0669] The device is synchronized with the server, allowing the user to see the latest task list. Users can view task details on the device and edit them as needed.

[0670] Step 6:

[0671] The server generates reminders based on task deadlines. These reminders are sent to the user's device via email or push notification, ensuring the user is notified at the appropriate time.

[0672] Step 7:

[0673] Users can input task progress via their terminal and mark tasks as complete once they are finished. This progress information is sent to the server.

[0674] Step 8:

[0675] The server updates the task status based on progress information received from the user, and deletes or marks completed tasks from the database. This optimizes task list management.

[0676] Step 9:

[0677] (Optional) The server receives feedback from users and updates algorithms to improve analysis accuracy and the interface. The system is continuously improved through irregularly held feedback sessions.

[0678] (Example 1)

[0679] 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".

[0680] With the increasing volume of information in the modern world, efficiently managing individual work activities presents a significant challenge. In particular, extracting and managing important tasks from a wide range of information sources, such as emails and meeting minutes, without overlooking anything, places a considerable burden on users. Furthermore, performing these tasks manually is time-consuming and prone to human error. Therefore, there is a need to develop a system that automatically extracts information from communication data and optimally manages work activities.

[0681] 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.

[0682] In this invention, the server includes an acquisition means for acquiring data from information communication, an analysis means for extracting important terms through natural language processing, and a management means for generating and storing business activities based on the extracted terms. This enables the automatic generation and management of business activities, freeing users from cumbersome manual work and reducing problems such as overlooking important tasks.

[0683] "Information and communication" refers to various forms of digital data, such as emails and meeting minutes, and the media used for acquiring and managing information.

[0684] A "means of acquiring data" refers to a system that has the function of automatically collecting necessary information from information sources with the user's permission.

[0685] "Natural language processing" is a technology that converts text data into a form that computers can understand and extracts meaning from it.

[0686] "Key terms" refer to keywords and phrases necessary for generating business activities, and are elements that help identify tasks based on them.

[0687] A "management system for generating and storing business activities" is a mechanism for forming tasks from extracted key keywords, registering them in a database, and managing them.

[0688] "Notification methods that notify communication terminals" refers to a function that informs users of important information, such as deadlines for generated business activities, via email or push notifications.

[0689] A "monitoring method that monitors the progress of business activities and automatically reflects completion status" refers to a function that tracks the progress of tasks and updates a database with completed tasks.

[0690] A "learning method" is a technique that uses machine learning algorithms to gain insights from data and continuously improve the performance of a system.

[0691] "Methods for collecting user feedback and making improvements" refers to a system that receives feedback from users and uses it to improve the accuracy of system analysis and the interface.

[0692] This invention provides a system for effectively managing users' digital activities through information and communication. The basic configuration consists of a server for acquiring and analyzing information, generating and managing business activities, a communication terminal for notifying users, and a user interface that allows users to manage information and provide feedback.

[0693] The server periodically retrieves data from information communications with the user's permission. This retrieval utilizes existing mail servers and cloud storage. The server analyzes the collected information using a natural language processing (NLP) engine to extract important words and phrases from the text. For example, this NLP engine recognizes the task "Prepare materials" from a message like "Please prepare materials for next week's meeting" and sets a deadline. The generated work activities are then registered in a database by the server. The database manages detailed information about the work activities (task name, deadline, person in charge, etc.), and this information is simultaneously synchronized with the user's communication terminal.

[0694] The communication terminal receives notifications from the server and provides a means to notify users of important information regarding their work activities. Notifications are sent via email or push notifications, and help users manage important work activities by sending messages such as "The deadline for submitting meeting materials is tomorrow."

[0695] Users can manage the progress of their work activities by operating a communication terminal. When a user marks a work activity as complete, that information is sent to the server, and the status is updated in the database. Furthermore, users can provide feedback to the server through a feedback function to improve the accuracy of the analysis and enhance the user interface. The server uses this feedback to update its generated AI models and machine learning algorithms, thereby improving the system's functionality.

[0696] As a concrete example, suppose a server analyzes multiple emails regarding the progress of a project and automatically generates a work activity called "Create Progress Report." This activity is saved in a database, and a notification such as "The deadline for the progress report is this weekend" is sent to the user's terminal, ensuring that the user does not forget to take action.

[0697] An example of a prompt message might be: "A new project-related email has arrived. Please analyze the email to generate and send notifications for important business activities."

[0698] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0699] Step 1:

[0700] The server periodically retrieves data from email servers and cloud storage with the user's permission. This input data consists of text information contained in emails and meeting minutes. The retrieved data is then loaded into memory in preparation for analysis.

[0701] Step 2:

[0702] The server inputs the acquired text data into a natural language processing (NLP) engine. The NLP engine performs analysis to extract important words and phrases from the text data. As output, keywords related to business activities and tasks based on them are generated. For example, from an email that says, "Please prepare the materials before the meeting," the task "Prepare materials" is extracted.

[0703] Step 3:

[0704] The server registers the extracted task information in the task management database. In this step, detailed information such as the task name, due date, and assignee is stored in the database. The output from the database is a task list organized for each user.

[0705] Step 4:

[0706] The server sends notifications to the user's terminal based on task information registered in the database. The input is task deadline information, which is delivered via communication. The output is a reminder in the form of email or push notification. For example, a notification might say, "Tomorrow is the deadline for creating the document."

[0707] Step 5:

[0708] Users check their task list and update their progress using an application on their device. Input is the user's action, and output is the updated task status. When a user marks a task as complete, that information is sent to the server, and the task completion is recorded in the database.

[0709] Step 6:

[0710] The server analyzes user feedback and updates the generated AI model. This feedback process collects data for improving analysis accuracy and the interface. The input is user opinions and usage, and the output is improved system performance. This improves the efficiency of task management and usability.

[0711] (Application Example 1)

[0712] 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".

[0713] Current electronic payment services require the individual management of transaction information and related notifications, necessitating increased operational efficiency. However, performing this manually is time-consuming and labor-intensive; therefore, a system is needed to automatically generate related tasks based on transaction information and manage them appropriately.

[0714] 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.

[0715] In this invention, the server includes an analysis means for extracting information from communication information, a management means for automatically generating and managing tasks based on the extracted information, and a notification means for setting deadlines for the generated tasks and providing warnings to the user. This makes it possible to efficiently generate and manage tasks from transaction information.

[0716] "Communication information" refers to information sent and received in digital format, including emails and meeting minutes.

[0717] "Business" refers to tasks and activities related to transactions that have objectives to be achieved.

[0718] A "warning" refers to a notification or reminder sent to draw the user's attention.

[0719] "Users" refers to individuals or corporations that use this system.

[0720] "Analytical means" refers to techniques or methods for processing information to find significant patterns or relationships.

[0721] "Control measures" refer to techniques or methods for systematically controlling and supervising operations.

[0722] "Notification means" refers to a technology or method for electronically transmitting information or warnings to users.

[0723] "Learning methods" refer to techniques and methods that recognize patterns from data and improve performance based on these patterns.

[0724] This invention is a system for efficiently managing transaction information in electronic payment services. The system consists of several main elements and aims to improve the operational efficiency of users.

[0725] The server first collects communication information and then uses analysis tools to extract meaningful data from that information. This analysis uses natural language processing engines such as the Google Cloud Natural Language API. For example, if an email contains descriptions of important dates or tasks related to a transaction, this information is extracted and used later.

[0726] Based on this extracted data, the management system automatically generates and manages tasks. Each generated task has a deadline, and alerts are set to notify users at the appropriate time. The notification system displays information as push notifications on smartphones through an application developed with React Native.

[0727] Users can view their task list and update their progress through this application. When a task is completed, the task is deleted from the database with the corresponding action.

[0728] Furthermore, the server utilizes learning tools to analyze feedback and improve the task generation algorithm. This process uses machine learning algorithms running on AWS to improve the accuracy of data processing.

[0729] For example, when a user conducts a financial transaction, this system can automatically generate a payment task related to that transaction and notify the user as a reminder on a specified date. This allows users to efficiently carry out their work without forgetting important deadlines.

[0730] Examples of prompt messages include, "Please extract the information needed to automatically generate a payment task from this transaction email."

[0731] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0732] Step 1:

[0733] The server periodically retrieves communication information from email servers and payment databases authorized by the user. Emails and transaction records are transferred to the server as input data. Based on this data, the server prepares to analyze new information.

[0734] Step 2:

[0735] The server analyzes the collected communication information using the Google Cloud Natural Language API. It extracts important phrases and keywords necessary for task generation from the input emails and records. This process yields output data such as the task name (e.g., "invoice") and payment deadline.

[0736] Step 3:

[0737] The server automatically generates tasks based on the analyzed data. Here, based on the extracted task information, detailed information (task name, deadline, related actions, etc.) is saved to the database for each task. The input is the analysis results, and the output is the registration of a new task in the task management database.

[0738] Step 4:

[0739] The terminal sets reminders related to registered tasks based on instructions from the server. It then executes a notification function using React Native on the user's smartphone, displaying warnings such as "Payment deadline is approaching." This serves as an important notification for the user.

[0740] Step 5:

[0741] Users use a terminal to check their task list and update their progress. Information on tasks marked as complete is sent to the server, and the server deletes the processed tasks from the database. Input is the user's updated information, and output is an update of the task status.

[0742] Step 6:

[0743] The server updates its machine learning algorithms using data collected throughout all processes. It analyzes feedback and usage history to improve the accuracy of future task generation. The input is historical task data and feedback, and the output is an optimized algorithm.

[0744] 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.

[0745] This invention aims to achieve more personalized task management by combining an emotion engine with a task management system. Specific embodiments are shown below.

[0746] The server periodically retrieves information from users' emails and meeting records and automatically extracts task-related information using analytical tools. This extracted task information is registered by the server in a management database. Detailed task information (task name, due date, priority, etc.) is stored in this database.

[0747] This system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine uses user input information, voice, and facial expression data to analyze the user's emotional state in real time. Based on the analysis results of the emotion engine, the server can dynamically adjust task priorities. For example, if the user is feeling stressed, the server will change the priority of tasks to reduce the burden on the user.

[0748] The device has the function of displaying a task list sent from the server to the user. Tasks are prioritized based on emotional information, allowing users to manage tasks optimally according to their own emotional state. The device also receives reminders from the emotional engine and sends notifications at a time and with content that takes the user's emotions into consideration.

[0749] When a user updates the progress of a task, that information is transmitted to the server. The server monitors the task status based on this progress information and completes or deletes the task as needed. By utilizing the sentiment engine, it is possible to provide advice and feedback that reflects the user's emotions even for completed tasks.

[0750] Furthermore, the server collects emotion-related feedback from users to improve the accuracy of the analysis results and the user interface. The data obtained through the emotion engine is continuously optimized by machine learning algorithms to improve the accuracy of subsequent analyses.

[0751] Embodiments of the present invention are systems that go beyond simple task management, taking into account the user's emotions and providing individually customized task management. The aim is to reduce the user's psychological burden and support efficient and effective task execution.

[0752] The following describes the processing flow.

[0753] Step 1:

[0754] With user permission, the server periodically retrieves new emails and meeting minutes from the mail server and cloud storage, accumulating the latest data.

[0755] Step 2:

[0756] The server analyzes the content of the retrieved emails and meeting minutes using natural language processing technology to extract phrases and keywords related to the task. This then creates an outline of the task.

[0757] Step 3:

[0758] The server registers tasks in the management database based on the extracted task information. Each task is assigned attributes such as name, due date, priority, and assignee.

[0759] Step 4:

[0760] The emotion engine acquires voice and facial expression data transmitted from the user's device and analyzes the user's emotional state in real time. This process is performed with the user's consent.

[0761] Step 5:

[0762] The server receives the results of the emotion engine's analysis and dynamically adjusts the priority of each task based on that. For example, if the user is determined to be in a high-stress state, the server will change the priority of important but non-urgent tasks to be lowered.

[0763] Step 6:

[0764] The device presents the user with an updated task list. Each task is displayed in order of priority based on the user's emotional state, making it intuitively clear which tasks should be addressed.

[0765] Step 7:

[0766] The server generates reminders based on task deadlines and sends notifications to the device at a time and with message content that takes the user's emotional state into consideration. This allows users to manage their tasks more effectively.

[0767] Step 8:

[0768] Users update task progress via their devices. This information is immediately sent to the server, and the task status is updated to "In Progress," "Completed," etc.

[0769] Step 9:

[0770] When a task is deemed complete, the server removes it from the database and provides the user with sentiment feedback, along with the relevant information.

[0771] Step 10:

[0772] The server collects emotional feedback from users and uses it to improve analysis results and the user interface. This feedback is fed into machine learning algorithms and used to improve the system's accuracy.

[0773] (Example 2)

[0774] 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".

[0775] Traditional task management systems struggle to flexibly respond to users' emotional states and the urgency of their activities. Furthermore, they lack mechanisms to efficiently utilize user feedback and improve management accuracy, creating a need for more personalized activity management.

[0776] 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.

[0777] In this invention, the server includes analysis means for extracting information from electronic communications and schedule records, control means for automatically generating and managing activities based on the extracted information, and evaluation means for analyzing the user's state and dynamically adjusting the priority of activities. This enables optimal task management according to the user's emotional state and the urgency of the activities.

[0778] "Electronic communications" refers to means of transmitting information through networks, including email and digital messages.

[0779] "Schedule records" refer to documents or data that contain the user's activity plans, such as meeting schedules and timetables.

[0780] "Analysis methods" is a general term for technologies and methods used to extract necessary information from electronic communications and schedule records and to analyze their content.

[0781] "Control measures" refer to technologies and methods for automatically generating activities based on extracted information and efficiently managing them.

[0782] "Notification means" refers to technologies and methods for informing users of deadlines for activities or important events.

[0783] "Evaluation methods" refer to technologies and methods for analyzing the user's emotional state and other factors, and dynamically adjusting the priority of activities based on those analyses.

[0784] "Monitoring measures" refer to technologies and methods for checking the progress of activities and automatically deleting completed activities.

[0785] "Learning methods" refer to techniques and methods for progressively improving processing accuracy based on the progress of an activity.

[0786] "Improvement methods" refer to technologies and methods for receiving feedback from users and improving the analysis results and user interface.

[0787] To implement this invention in practice, it is necessary to effectively utilize servers and terminals. The server first uses external services such as APIs to collect electronic communications and schedule records. This includes digital communication software and calendar services using cloud services. The server acquires this data and extracts information using analytical means. At this time, natural language processing tools are used to analyze the text data and identify the details, deadlines, and priorities of activities.

[0788] Next, the server records the extracted activity information in a management database using control mechanisms. This database is built using an open-source database management system, enabling continuous management of activities.

[0789] Furthermore, the server analyzes the user's emotional state through evaluation tools. This involves using emotion recognition software to analyze voice data and facial expression data, thereby understanding the user's psychological state in real time.

[0790] The device displays an activity list sent from the server to the user. It features an intuitive and easy-to-understand UI that responds to the user's psychological state and can highlight items according to priority. Furthermore, the device uses notification methods to provide reminders that take into account the deadlines and emotions set by the user.

[0791] When a user updates the progress of an activity, that information is fed back to the server, which then uses monitoring mechanisms to complete or invalidate the activity. Furthermore, user feedback is used to improve system performance through refinement mechanisms.

[0792] As a concrete example, consider a situation where a user feels they "need to prepare for next week's meeting, but are too busy to find the time." In this case, the server assesses the user's stress level and, based on the assessment, sets meeting-related activities as a high priority, adjusting other activities to a lower priority.

[0793] An example of a prompt message could be input into the generating AI model, such as, "If the user is feeling fatigued, reduce reminder notifications and display only important tasks." In this way, the system can provide optimal activity management based on the user's emotional state, improving efficiency and user satisfaction.

[0794] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0795] Step 1:

[0796] The server collects information from electronic communications and schedule records. In this step, data is retrieved via APIs from email services and schedule management systems. Inputs include user emails and schedule information, which are used to collect raw data about activities. From this raw data, activity plans and message content are output.

[0797] Step 2:

[0798] The server analyzes the collected information using analytical tools. Specifically, it extracts activity-related information from the raw data using natural language processing tools. For example, it selects items such as the activity title, deadline, and priority. As a result of this process, structured activity information is output after analyzing the text data.

[0799] Step 3:

[0800] The server automatically generates activities using the analyzed data and registers them in the management database. The structured activity information obtained in step 2 is used as input, and the activity details are stored in the database. This database entry will be used for future task management.

[0801] Step 4:

[0802] The server utilizes emotion recognition methods to evaluate the user's psychological state. Using emotion recognition software, it acquires voice and facial expression data as input and analyzes the emotional state. The analysis outputs emotional information such as the user's stress level and happiness level.

[0803] Step 5:

[0804] The server dynamically adjusts activity priorities based on emotional information. An evaluation method is used to rearrange activities according to the user's emotions. Inputs include emotional information and existing activity information, and a rearranged activity list is output.

[0805] Step 6:

[0806] The device presents the user with a reorganized list of activities sent from the server. In this step, the reorganized list becomes the input and is visually presented to the user. Specifically, the activity priority is highlighted on the device's UI.

[0807] Step 7:

[0808] The device notifies the user of reminders. It receives deadlines and alert information sent from the server as input and notifies the user. The output is an alert message with appropriate timing and content to be emotionally sensitive.

[0809] Step 8:

[0810] Users provide feedback on their activity progress to the server via their terminal. This data is monitored, and decisions are made to determine whether the activity is complete or invalid. The input is user progress information, and the existing management database is updated accordingly.

[0811] Step 9:

[0812] The server collects user feedback and uses it to improve analysis results and the user interface. The collected feedback is used as input for improvement measures to enhance the user interface. The output is optimized system performance.

[0813] (Application Example 2)

[0814] 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".

[0815] While many simple task management systems exist today, they have the drawback of failing to alleviate users' psychological burden because they manage task priorities uniformly without considering the emotional state of individual users. In particular, they may fail to assign tasks appropriately when users are stressed, potentially reducing productivity.

[0816] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0817] In this invention, the server includes analysis means for extracting information from emails and meeting records, management means for automatically generating and managing tasks based on the extracted information, and emotion analysis means for measuring the user's emotional state and dynamically changing the priority of tasks based on that state. This enables efficient task management while flexibly adjusting task priorities according to the user's emotions and reducing psychological burden.

[0818] "Analysis means" refers to the software or hardware functions used to extract necessary information from emails or meeting records.

[0819] A "management tool" is a system element that automatically generates tasks based on extracted information and manages them efficiently.

[0820] A "notification method" is a function that informs the user of the deadline set for a generated task.

[0821] A "monitoring tool" is a function that tracks the progress of tasks and deletes completed tasks as needed.

[0822] An "emotion analysis tool" is a function that measures the user's emotional state and dynamically changes the priority of tasks based on that emotion.

[0823] In this invention, the entire system consists of three elements: a server, a terminal, and a user. The server includes analysis means, management means, notification means, monitoring means, and sentiment analysis means. The analysis means is an algorithm for extracting necessary information from information sources such as emails and meeting minutes, and is implemented using data mining technology. The management means has the function of automatically generating tasks based on the extracted information and saving them in a database. Task management software is used, and each task is assigned a deadline and priority.

[0824] The notification system sends notifications to the user's device about generated tasks and displays reminders at the appropriate time. For example, it provides early notifications for tasks that the user needs to prepare before an important meeting. The monitoring system tracks task progress in real time, automatically deletes completed tasks, and keeps the database clean.

[0825] The emotion analysis system analyzes voice and facial expression data acquired from the user to evaluate the user's emotional state. The algorithm uses machine learning techniques to detect the user's emotions in real time and flexibly adjusts task priorities accordingly. For example, when a user is feeling stressed, it can recommend more intuitive and simpler tasks as a priority.

[0826] The hardware used includes a camera and microphone for analyzing user emotions, and the software is implemented in a programming language such as Python. An external library called emotion_recognition_sdk is used for emotion analysis. Task management is handled using a class called TaskManager.

[0827] As a concrete example, if a user is feeling stressed during their morning commute, they might receive a notification on their smartphone saying, "Your schedule is flexible today, so I've postponed one task." This notification would be automatically sent if voice analysis determines that the user's stress level is high.

[0828] An example of a prompt to input into a generative AI model is: "Create a script that uses emotion recognition to determine if the user is experiencing stress and suggests advice tailored to their task management needs."

[0829] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0830] Step 1:

[0831] The server periodically collects users' emails and meeting records. The collected data is analyzed using initial analytical tools to extract task-related information. The input here is email and meeting record data, and the output is identified task information. This information is structured and stored in a management database.

[0832] Step 2:

[0833] The server uses emotion analysis tools to collect user voice and facial expression data and analyzes their emotional state in real time. Input is voice and image data, and output is an evaluation of the user's emotional state. The emotion_recognition_sdk is used to extract emotional features from the data and determine the type and intensity of the emotion.

[0834] Step 3:

[0835] The server dynamically adjusts task priorities based on extracted task information and sentiment analysis results. Inputs are task information and sentiment state evaluation results stored in the database, and output is a task list with adjusted priorities. Task reprioritization takes into account the user's psychological burden.

[0836] Step 4:

[0837] The device retrieves the adjusted task list sent from the server and notifies the user. The input is the task list sent from the server, and the output is reminder information displayed to the user. The device sends notifications at the optimal time, taking into account the user's emotional state.

[0838] Step 5:

[0839] When a user updates the progress of a task, that information is transmitted from the terminal to the server. The input is the progress status as performed by the user, and the output is the updated task information. The server checks the status of the task based on this information and completes or deletes it as necessary.

[0840] Step 6:

[0841] The server provides the user with feedback reflecting the sentiment analysis results after the task is completed. The input is information about the completed task and the user's current sentiment state, and the output is a feedback message. The feedback is provided to help the user improve their work and provide psychological support.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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."

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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 to be incorporated by reference.

[0863] The following is further disclosed regarding the embodiments described above.

[0864] (Claim 1)

[0865] An analytical means for extracting information from emails and meeting records,

[0866] A management system that automatically generates and manages tasks based on extracted information,

[0867] A notification system that sets deadlines for generated tasks and notifies the user of reminders,

[0868] A monitoring mechanism that monitors the progress of tasks and automatically deletes completed tasks,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, comprising a machine learning means for learning the progress of a task and successively improving processing accuracy.

[0872] (Claim 3)

[0873] The system according to claim 1, further comprising means for receiving user feedback and improving the analysis results and user interface.

[0874] "Example 1"

[0875] (Claim 1)

[0876] A means of acquiring data from information and communication,

[0877] An analysis method for extracting important words and phrases using natural language processing,

[0878] A management system that generates and stores business activities based on extracted terms,

[0879] A notification means that sets a deadline corresponding to the generated business activity and notifies the communication terminal,

[0880] A monitoring system that monitors the progress of business activities and automatically reflects their completion status,

[0881] A system that includes this.

[0882] (Claim 2)

[0883] The system according to claim 1, comprising a learning means for evaluating the progress of business activities using a learning method and improving performance.

[0884] (Claim 3)

[0885] The system according to claim 1, further comprising means for collecting user feedback and improving analysis accuracy and display screen.

[0886] "Application Example 1"

[0887] (Claim 1)

[0888] An analysis method for extracting information from communication information,

[0889] A management system that automatically generates and manages tasks based on extracted information,

[0890] A notification mechanism that sets deadlines for generated tasks and provides warnings to users,

[0891] A monitoring system that monitors the progress of tasks and automatically deletes completed tasks,

[0892] A learning method that sequentially improves data processing accuracy,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, which generates business operations and provides warnings based on the analysis of transaction information.

[0896] (Claim 3)

[0897] The system according to claim 1, further comprising means for receiving feedback from users and improving the analysis results and user interface.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] An analytical method for extracting information from electronic communications and schedule records,

[0901] A control system that automatically generates and manages activities based on extracted information,

[0902] A notification system that sets a deadline for generated activities and alerts the user,

[0903] An evaluation method that analyzes the user's state and dynamically adjusts the priority of activities,

[0904] A monitoring system that monitors the progress of activities and automatically deletes completed activities,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, comprising a learning means for learning the progress of activities and sequentially improving processing accuracy.

[0908] (Claim 3)

[0909] The system according to claim 1, further comprising means for receiving feedback from users and making improvements to the analysis results and user screen.

[0910] "Application example 2 when combining with an emotional engine"

[0911] (Claim 1)

[0912] An analytical means for extracting information from emails and meeting records,

[0913] A management system that automatically generates and manages tasks based on extracted information,

[0914] A notification system that sets deadlines for generated tasks and notifies users of reminders,

[0915] A monitoring mechanism that monitors the progress of tasks and automatically deletes completed tasks,

[0916] An emotion analysis means that measures the user's emotional state and dynamically changes the task priority based on that state,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, comprising a machine learning means for learning the progress of a task and successively improving processing accuracy.

[0920] (Claim 3)

[0921] The system according to claim 1, further comprising means for receiving feedback from users and improving the analysis results and user interface. [Explanation of Symbols]

[0922] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An analytical means for extracting information from emails and meeting records, A management system that automatically generates and manages tasks based on extracted information, A notification system that sets deadlines for generated tasks and notifies the user of reminders, A monitoring mechanism that monitors the progress of tasks and automatically deletes completed tasks, A system that includes this.

2. The system according to claim 1, comprising a machine learning means for learning the progress of a task and successively improving processing accuracy.

3. The system according to claim 1, further comprising an improvement means for receiving user feedback and improving the analysis results and user interface.

Images