system

Abstract

The system according to this embodiment aims to automate email and task management and reduce the workload of users. [Solution] The system according to the embodiment comprises a classification unit, a labeling unit, an extraction unit, a list creation unit, a tracking unit, a reminder unit, an agenda creation unit, a follow-up unit, a proposal unit, and a notification setting unit. The classification unit automatically classifies emails. The labeling unit labels emails based on their importance, based on the classification unit. The extraction unit extracts tasks based on the emails labeled by the labeling unit. The list creation unit creates a list of tasks extracted by the extraction unit. The tracking unit tracks the progress of the task list created by the list creation unit. The reminder unit sets reminders based on the progress tracked by the tracking unit. The agenda creation unit automatically creates a meeting agenda from calendar notifications. The follow-up unit automatically generates and notifies of follow-up tasks after the meeting. The proposal unit proposes the next action. The notification setting unit provides customizable notification settings.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that mail and task management are often performed manually, resulting in a large workload.

[0005] The system according to the embodiment aims to automate mail and task management and reduce the workload of users.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a classification unit, a labeling unit, an extraction unit, a list creation unit, a tracking unit, a reminder unit, an agenda creation unit, a follow-up unit, a proposal unit, and a notification setting unit. The classification unit automatically classifies emails. The labeling unit labels emails based on their importance, based on the classification unit. The extraction unit extracts tasks based on the emails labeled by the labeling unit. The list creation unit creates a list of the tasks extracted by the extraction unit. The tracking unit tracks the progress of the task list created by the list creation unit. The reminder unit sets reminders based on the progress tracked by the tracking unit. The agenda creation unit automatically creates a meeting agenda from calendar notifications. The follow-up unit automatically generates and notifies of follow-up tasks after the meeting. The proposal unit proposes the next action. The notification setting unit configures customizable notification settings. [Effects of the Invention]

[0007] The system according to this embodiment can automate email and task management, thereby reducing the workload on users. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the tagged communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (for example, a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The virtual secretary application according to an embodiment of the present invention is an application that reduces the user's workload and supports them in concentrating on important tasks. This virtual secretary application utilizes AI to automatically manage emails and calendars and efficiently process tasks. For example, the virtual secretary application has an email management function in which the AI ​​automatically categorizes emails and labels their importance. When the user is busy, the AI ​​provides an automatic response function that can be reviewed later. The virtual secretary application also has a task management function in which it automatically extracts tasks from emails and creates a task list. By tracking progress and setting automatic reminders, it ensures that the user does not forget to complete tasks. For example, if an email contains the message "Prepare for the meeting," the AI ​​automatically extracts the task and sets a reminder. Furthermore, the virtual secretary application has a meeting support function in which it automatically creates a meeting agenda from calendar notifications and automatically generates and notifies the user of follow-up tasks after the meeting. For example, if a meeting is scheduled in the calendar, the AI ​​automatically creates an agenda and generates and notifies the user of follow-up tasks after the meeting. Furthermore, the virtual assistant app features proactive support functions, with a virtual AI suggesting the next action and providing customizable notification settings. For example, the AI ​​suggests the next action the user should take and sets notifications and reminders according to the user's preferences and work style. This app helps busy business professionals avoid missing important emails and work efficiently, supporting efficient task management and meeting preparation. It also includes a function that suggests skill development based on personal information. In this way, the virtual assistant app can reduce the user's workload and help them focus on important work.

[0029] The virtual secretary application according to this embodiment includes a classification unit, a labeling unit, an extraction unit, a list creation unit, a tracking unit, a reminder unit, an agenda creation unit, a follow-up unit, a suggestion unit, and a notification setting unit. The classification unit automatically classifies emails. The classification unit can classify emails using, for example, keyword matching or machine learning algorithms. The classification unit can also learn the user's past email history to perform more accurate classifications. The labeling unit labels emails based on their importance based on the classification unit. The labeling unit can evaluate importance and assign labels based on, for example, the content of the email or the sender's job title. The labeling unit can also learn the user's past email processing history to perform more appropriate labelings. The extraction unit extracts tasks based on the emails labeled by the labeling unit. The extraction unit can extract tasks by, for example, analyzing the content of the email or keywords. The extraction unit can also learn the user's past task processing history to perform more appropriate task extractions. The list creation unit creates lists from the tasks extracted by the extraction unit. For example, the list creation unit can classify tasks by priority or project and create lists. The list creation unit can also learn the user's past task list creation history to create more appropriate lists. The tracking unit tracks the progress of the task lists created by the list creation unit. For example, the tracking unit can manage task completion status and deadlines and track progress. The tracking unit can also learn the user's past task progress to track progress more appropriately. The reminder unit sets reminders based on the progress tracked by the tracking unit. For example, the reminder unit can set the timing and frequency of notifications and provide reminders. The reminder unit can also learn the user's past reminder setting history to set more appropriate reminders. The agenda creation unit automatically creates meeting agendas from calendar notifications. For example, the agenda creation unit can create agendas based on the meeting's purpose and the priority of the topics.Furthermore, the agenda creation unit can learn the user's past meeting agenda creation history and create more appropriate agendas. The follow-up unit automatically generates and notifies of follow-up tasks after meetings. The follow-up unit can generate and notify follow-up tasks based, for example, on the content of the meeting and action items. The follow-up unit can also learn the user's past follow-up task generation history and generate more appropriate follow-up tasks. The suggestion unit proposes the next action. The suggestion unit can propose the next action based, for example, on the task priority and the user's past behavior history. The suggestion unit can also consider the user's current situation and propose more appropriate actions. The notification settings unit provides customizable notification settings. The notification settings unit can provide customizable notifications by setting, for example, the type and display method of notifications. The notification settings unit can also learn the user's past notification setting history and configure more appropriate notification settings. As a result, the virtual secretary application according to the embodiment can reduce the user's workload and support them in focusing on important tasks.

[0030] The classification unit automatically categorizes emails. For example, it can classify emails using keyword matching or machine learning algorithms. Specifically, keyword matching detects specific keywords in the email subject and body, and categorizes emails based on these keywords. For instance, emails containing keywords like "meeting" or "important" are classified as meeting-related or important emails. On the other hand, using machine learning algorithms allows the system to learn from past email data, enabling it to comprehensively assess email content and sender information for more accurate classification. For example, natural language processing techniques can be used to analyze email content and automatically categorize emails into business-related, personal, or spam categories. Furthermore, the classification unit can learn from the user's past email history, improving classification accuracy based on the user's email processing patterns and preferences. For instance, if a user tends to consider emails from a particular sender important, emails from that sender will be prioritized and classified as important. This allows the classification unit to achieve flexible email classification tailored to user needs, significantly improving the efficiency of email management.

[0031] The labeling unit labels emails based on their importance, as classified by the classification unit. For example, the labeling unit can evaluate and label emails based on their content and the sender's job title. Specifically, it analyzes the email body and detects important keywords and phrases to determine the email's importance. For instance, emails containing phrases like "urgent" or "important notice" are labeled as highly important. The sender's job title and position within the organization are also factors in the importance assessment. For example, emails from superiors or important clients are labeled as more important than others. Furthermore, the labeling unit learns the user's past email processing history to understand what emails the user considers important, enabling more appropriate labeling. For example, it learns the characteristics of emails the user frequently opened and responded to quickly in the past, and labels new emails with those characteristics as highly important. This allows the labeling unit to quickly identify important emails and prompt appropriate responses, improving the user's work efficiency.

[0032] The extraction unit extracts tasks based on emails labeled by the labeling unit. For example, the extraction unit can analyze the content and keywords of emails to extract tasks. Specifically, it uses natural language processing technology to analyze the email body and identify action items and instructions related to the tasks. For example, it can extract tasks from emails that contain specific instructions such as "prepare for the meeting" or "submit the documents." Furthermore, the extraction unit can learn from the user's past task processing history and understand which tasks the user considers important, enabling more appropriate task extraction. For example, it can learn the characteristics of tasks that the user has frequently handled in the past and prioritize the extraction of new tasks that possess those characteristics. In addition, the extraction unit can consider metadata such as the email sender and reception date and time to set task priorities and deadlines. This allows the extraction unit to support users in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0033] The list creation unit creates lists from the tasks extracted by the extraction unit. For example, the list creation unit can classify tasks by priority or project and create lists. Specifically, it sets priorities for the extracted tasks and places higher-priority tasks at the top. Furthermore, classifying tasks by project makes it easier for users to manage tasks on a project-by-project basis. For example, separate task lists for "Project A" and "Project B" can be created, and the progress of each can be managed. In addition, the list creation unit can learn from the user's past task list creation history and understand how the user classifies tasks, enabling it to create more appropriate lists. For example, if the user has previously used specific categories or tags to classify tasks, those categories or tags will be automatically applied. In this way, the list creation unit can support users in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0034] The tracking unit tracks the progress of task lists created by the list creation unit. For example, the tracking unit can manage task completion status and deadlines, and track progress. Specifically, it periodically checks the completion status of tasks and sends reminders for incomplete tasks. It also notifies the user when a task deadline is approaching, encouraging them to complete the task within the deadline. Furthermore, the tracking unit can learn from the user's past task progress and understand the pace at which the user completes tasks, enabling more accurate progress tracking. For example, it can predict the completion time of future tasks based on the time it took the user to complete a particular task in the past, and send reminders at the appropriate time. In this way, the tracking unit can support the user in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0035] The reminder unit sets reminders based on the progress tracked by the tracking unit. The reminder unit can, for example, set the timing and frequency of notifications and provide reminders. Specifically, it notifies the user when a task deadline is approaching, encouraging them to complete the task. It can also adjust the frequency of notifications according to the importance and priority of the task. For example, it sends frequent reminders for high-importance tasks and reminders at a moderate frequency for low-importance tasks. Furthermore, the reminder unit can learn from the user's past reminder setting history and understand when the user prefers to receive reminders, enabling it to set more appropriate reminders. For example, if a user has previously preferred to receive reminders at a specific time, it will send reminders at that time. In this way, the reminder unit can support users in efficiently managing tasks and ensuring they don't miss important tasks.

[0036] The agenda creation function automatically generates meeting agendas from calendar notifications. For example, it can create agendas based on the meeting's purpose and the priority of its topics. Specifically, it analyzes meeting information registered in the calendar and extracts the meeting's purpose and topics. For instance, it identifies the meeting's purpose from the meeting title and description, such as "Project Progress Report Meeting" or "New Product Development Meeting." It also supports efficient meeting management by setting priorities for topics and placing important ones at the top. Furthermore, the agenda creation function learns from the user's past meeting agenda creation history, understanding the format and content of agendas the user has created, enabling it to create more appropriate agendas. For example, if the user has previously used a specific format or items when creating agendas, it automatically applies those formats and items. This allows the agenda creation function to support users in efficiently preparing for meetings and ensuring that important topics are not overlooked.

[0037] The follow-up department automatically generates and notifies users of follow-up tasks after meetings. For example, the follow-up department can generate and notify users of follow-up tasks based on the content of the meeting and action items. Specifically, it analyzes meeting minutes and notes to identify action items and assigned personnel decided during the meeting. For example, it extracts specific tasks such as "submitting materials" or "preparing for the next meeting" and notifies the respective responsible parties. Furthermore, the follow-up department learns the user's past follow-up task generation history and understands which tasks the user considers important, enabling it to generate more appropriate follow-up tasks. For example, it learns the characteristics of tasks the user has frequently handled in the past and prioritizes the generation of new tasks with those characteristics. In this way, the follow-up department can support users in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0038] The suggestion function proposes the next action. For example, it can propose the next action based on the task priority and the user's past behavior history. Specifically, it considers the progress and deadline of the current task and proposes the next task to be tackled. For example, it prioritizes suggesting tasks with approaching deadlines or high importance. Furthermore, by learning the user's past behavior history and understanding the order in which the user processes tasks, it can make more appropriate action suggestions. For example, if the user has processed tasks in a specific order in the past, it will propose the next action based on that order. In addition, the suggestion function can consider the user's current situation and propose actions at the optimal time. For example, it will suggest low-priority tasks during busy times and high-priority tasks during less busy times. In this way, the suggestion function can support the user in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0039] The notification settings section allows for customizable notification settings. For example, it can provide customizable notifications by setting the type and display method of notifications. Specifically, users can select the type of notifications they want to receive and set how and when they are displayed. For example, they can choose from multiple notification methods, such as email notifications, push notifications, and voice notifications. Furthermore, the notification display method can be customized to the user's preference, such as pop-up displays, banner displays, and voice alerts. In addition, the notification settings section learns the user's past notification setting history and understands what kind of notification methods and timings the user prefers, enabling it to provide more appropriate notification settings. For example, if a user has previously preferred to receive notifications at a specific time, the notification settings section will send notifications at that time. In this way, the notification settings section can support users in efficiently managing tasks and ensuring they do not miss important notifications.

[0040] The classification unit can classify emails by project based on their content. For example, the classification unit can analyze keywords contained in the subject line and body of an email and classify them by project. The classification unit can also classify emails by related projects based on the sender and recipient information. Furthermore, the classification unit can analyze the content of email attachments and classify them by project. This streamlines email management by classifying emails by project based on their content. Some or all of the above processing in the classification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the classification unit can input email content data into a generative AI and have the generative AI perform the classification by project.

[0041] The classification unit can classify emails based on the sender's attribute information. For example, if the sender is a supervisor, the classification unit will classify the email as important. Furthermore, if the sender is a customer, the classification unit can classify the email as a customer service project. Additionally, if the sender is a colleague, the classification unit can classify the email as an internal communication project. This allows for priority processing of important emails by classifying them based on the sender's attribute information. Some or all of the above processing in the classification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the classification unit can input the email sender information into a generative AI and have the generative AI perform classification based on attribute information.

[0042] The labeling unit can label emails based on their urgency. For example, the labeling unit can analyze keywords in the email subject and body and label them accordingly. It can also label emails based on the sender and recipient information. Furthermore, the labeling unit can analyze the content of email attachments and label them accordingly. This allows important emails to be processed preferentially by labeling them based on their content. Some or all of the above processing in the labeling unit may be performed using, for example, a generation AI, or without a generation AI. For example, the labeling unit can input email content data into a generation AI and have the generation AI perform the urgency labeling.

[0043] The labeling unit can label emails based on their importance, taking into account the job title of the email sender. For example, if the email sender is a superior, the labeling unit will label the email as "high" in importance. If the email sender is a customer, the labeling unit may label it as "medium" in importance. Furthermore, if the email sender is a colleague, the labeling unit may label it as "low" in importance. By labeling emails based on the job title of the email sender, important emails can be processed preferentially. Some or all of the above processing in the labeling unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the labeling unit can input the email sender information into a generating AI and have the generating AI perform labeling based on job title information.

[0044] The extraction unit can extract task priorities based on the content of emails. For example, the extraction unit can analyze keywords contained in the subject and body of an email to extract task priorities. The extraction unit can also extract task priorities based on the sender and recipient information of the email. Furthermore, the extraction unit can analyze the content of email attachments to extract task priorities. This allows important tasks to be processed preferentially by extracting task priorities based on the content of emails. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the extraction unit can input email content data into a generative AI and have the generative AI perform the task priority extraction.

[0045] The extraction unit can extract tasks while considering the job title information of the email sender. For example, if the email sender is a superior, the extraction unit will extract it as an important task. The extraction unit can also extract tasks related to customer service if the email sender is a customer. Furthermore, if the email sender is a colleague, the extraction unit can extract tasks related to internal communication. This allows important tasks to be processed preferentially by extracting tasks while considering the job title information of the email sender. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the extraction unit can input the email sender information into a generating AI and have the generating AI perform task extraction based on job title information.

[0046] The list creation unit can create lists for each project based on the content of tasks. For example, the list creation unit can analyze keywords contained in the subject and content of tasks and create lists for each project. The list creation unit can also create lists for related projects based on information about the sender and recipient of tasks. Furthermore, the list creation unit can analyze the content of attachments to tasks and create lists for each project. This streamlines task management by creating lists for each project based on the content of tasks. Some or all of the above processing in the list creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the list creation unit can input task content data into a generation AI and have the generation AI perform the creation of project-specific lists.

[0047] The list creation unit can adjust the order of the list based on the priority of the tasks. For example, the list creation unit can place tasks higher in the list based on their importance. It can also place tasks higher in the list based on their urgency. Furthermore, the list creation unit can adjust the order of the list based on the task deadline. This allows important tasks to be processed preferentially by adjusting the order of the list based on task priority. Some or all of the above processing in the list creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the list creation unit can input task priority data into a generation AI and have the generation AI perform the list order adjustment.

[0048] The tracking unit can track each project based on the progress of tasks. For example, the tracking unit can summarize the progress of tasks for each project, making it possible to check the progress at a glance. The tracking unit can also track the progress of tasks for each project and prioritize displaying projects that are behind schedule. Furthermore, the tracking unit can track the progress of tasks for each project and display a list of projects that are progressing on time. This streamlines progress management by tracking each project based on the progress of tasks. Some or all of the above processing in the tracking unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the tracking unit can input task progress data into a generative AI and have the generative AI perform project-based tracking.

[0049] The tracking unit can adjust the frequency of tracking based on the task priority. For example, the tracking unit can frequently track the progress of important tasks and notify if progress is behind schedule. It can also frequently track the progress of urgent tasks and notify if progress is behind schedule. Furthermore, it can frequently track the progress of tasks with approaching deadlines and notify if progress is behind schedule. This allows important tasks to be managed preferentially by adjusting the frequency of tracking based on the task priority. Some or all of the above processing in the tracking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the tracking unit can input task priority data into a generative AI and have the generative AI perform the adjustment of the tracking frequency.

[0050] The reminder unit can adjust the frequency of reminders based on the progress of tasks. For example, the reminder unit can set frequent reminders for tasks that are behind schedule and postpone tasks that are progressing well. It can also set frequent reminders for urgent tasks and allow other tasks to be checked later. Furthermore, it can set frequent reminders for tasks with approaching deadlines and allow other tasks to be checked later. This allows important tasks to be managed preferentially by adjusting the frequency of reminders based on the progress of tasks. Some or all of the above processing in the reminder unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the reminder unit can input task progress data into a generating AI and have the generating AI adjust the reminder frequency.

[0051] The reminder function can customize the content of reminders based on task priority. For example, the reminder function can include detailed explanations in reminders for important tasks. It can also include messages urging prompt action in reminders for urgent tasks. Furthermore, it can include messages emphasizing deadlines in reminders for tasks with approaching deadlines. This allows important tasks to be processed preferentially by customizing the content of reminders based on task priority. Some or all of the above processing in the reminder function may be performed using, for example, a generative AI, or without a generative AI. For example, the reminder function can input task priority data into a generative AI and have the generative AI perform the customization of the reminder content.

[0052] The agenda creation unit can adjust the level of detail of the agenda based on the meeting content. For example, for important meetings, the agenda creation unit can create a detailed agenda and set time allocations for each topic. For short meetings, the agenda creation unit can also create a concise agenda and include only the main topics. Furthermore, for regular meetings, the agenda creation unit can refer to past agendas and add necessary topics. This streamlines the preparation of important meetings by adjusting the level of detail of the agenda based on the meeting content. Some or all of the above processes in the agenda creation unit may be performed using, for example, a generative AI, or not. For example, the agenda creation unit can input meeting content data into a generative AI and have the generative AI perform the adjustment of the level of detail of the agenda.

[0053] The agenda creation unit can create an agenda taking into account the job titles of the meeting participants. For example, if a participant is a superior, the agenda creation unit can prioritize including important topics in the agenda. Similarly, if a participant is a client, the agenda creation unit can prioritize including client-related topics. Furthermore, if a participant is a colleague, the agenda creation unit can include internal communication topics. This ensures that important topics are prioritized by creating an agenda that takes into account the job titles of the meeting participants. Some or all of the above processing in the agenda creation unit may be performed using, for example, a generative AI, or without one. For example, the agenda creation unit can input meeting participant information into a generative AI and have the generative AI create an agenda based on job title information.

[0054] The follow-up unit can adjust the level of detail of follow-up tasks based on the content of the meeting. For example, for important meetings, the follow-up unit can generate detailed follow-up tasks that include specific action plans. For short meetings, the follow-up unit can also generate concise follow-up tasks that include only key actions. Furthermore, for regular meetings, the follow-up unit can refer to past follow-up tasks and add necessary actions. This streamlines the follow-up of important meetings by adjusting the level of detail of follow-up tasks based on the content of the meeting. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI perform the adjustment of the level of detail of the follow-up tasks.

[0055] The follow-up unit can generate follow-up tasks considering the job titles of meeting participants. For example, if a participant is a supervisor, the follow-up unit can prioritize including important actions in the follow-up tasks. Similarly, if a participant is a customer, the follow-up unit can prioritize including customer service actions in the follow-up tasks. Furthermore, if a participant is a colleague, the follow-up unit can include internal communication actions in the follow-up tasks. This allows for priority processing of important actions by generating follow-up tasks considering the job titles of meeting participants. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or without one. For example, the follow-up unit can input meeting participant information into a generative AI and have the generative AI generate follow-up tasks based on job title information.

[0056] The suggestion unit can propose the next action based on the user's past behavior history. For example, the suggestion unit can propose the next action based on actions the user has frequently performed in the past. Furthermore, the suggestion unit can propose the optimal action based on the user's past behavior history. In addition, the suggestion unit can analyze the user's past behavior history and propose efficient actions. This enables efficient action proposals by suggesting the next action based on the user's past behavior history. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the user's past behavior history data into a generative AI and have the generative AI execute the next action proposal.

[0057] The suggestion unit can customize the next action based on the user's current situation. For example, the suggestion unit can suggest the next action considering the user's current work situation. It can also suggest the next action considering the user's current schedule. Furthermore, it can suggest the next action considering the user's current project status. This allows for more appropriate action suggestions by customizing the next action based on the user's current situation. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the user's current situation data into a generative AI and have the generative AI perform the next action customization.

[0058] The notification settings unit can customize notification settings based on the user's past notification history. For example, the notification settings unit can customize notification settings based on notifications the user has frequently received in the past. The notification settings unit can also prioritize the display of important notifications based on the user's past notification history. Furthermore, the notification settings unit can analyze the user's past notification history and hide unnecessary notifications. This allows for the priority display of important notifications by customizing notification settings based on the user's past notification history. Some or all of the above processing in the notification settings unit may be performed using, for example, a generative AI, or without a generative AI. For example, the notification settings unit can input the user's past notification history data into a generative AI and have the generative AI perform the customization of notification settings.

[0059] The notification settings unit can adjust the frequency of notifications based on the user's current situation. For example, if the user is busy, the notification settings unit can display only important notifications and postpone other notifications. If the user is relaxed, the notification settings unit can display all notifications and allow the user to choose which ones to receive. Furthermore, if the user is in a hurry, the notification settings unit can display only high-priority notifications and allow other notifications to be reviewed later. This allows important notifications to be prioritized by adjusting the frequency of notifications based on the user's current situation. Some or all of the above processing in the notification settings unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the notification settings unit can input the user's current situation data into a generative AI and have the generative AI perform the notification frequency adjustment.

[0060] The notification settings unit can determine the priority of notifications based on the user's schedule. For example, the notification settings unit can prioritize the display of important notifications based on the user's schedule. It can also prioritize the display of urgent notifications based on the user's schedule. Furthermore, it can prioritize the display of notifications with approaching deadlines based on the user's schedule. In this way, by determining the priority of notifications based on the user's schedule, important notifications can be displayed preferentially. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's schedule data into a generation AI and have the generation AI perform the notification priority determination.

[0061] The notification settings unit can improve the accuracy of notification settings by referring to the user's relevant literature. For example, the notification settings unit can refer to literature related to the user's work content and set appropriate notifications. It can also refer to literature related to the user's projects and set appropriate notifications. Furthermore, the notification settings unit can refer to literature related to the user's skill development and set appropriate notifications. In this way, by improving the accuracy of notification settings by referring to the user's relevant literature, appropriate notifications can be set. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's relevant literature data into a generation AI and have the generation AI perform the improvement of notification setting accuracy.

[0062] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0063] A virtual assistant application can suggest the next action based on the user's past behavior history. For example, it can suggest the next action based on actions the user has frequently performed in the past. It can also suggest the optimal action based on the user's past behavior history. Furthermore, it can analyze the user's past behavior history and suggest efficient actions. This enables efficient action suggestions by suggesting the next action based on the user's past behavior history. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the user's past behavior history data into a generative AI and have the generative AI execute the next action suggestion.

[0064] The virtual assistant application can customize the next action based on the user's current situation. For example, it can suggest the next action considering the user's current work status. It can also suggest the next action considering the user's current schedule. Furthermore, it can suggest the next action considering the user's current project status. By customizing the next action based on the user's current situation, it becomes possible to suggest more appropriate actions. Some or all of the above processing in the suggestion section may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion section can input the user's current situation data into a generative AI and have the generative AI perform the next action customization.

[0065] The virtual assistant app can customize notification settings based on the user's past notification history. For example, it can customize notification settings based on notifications the user has frequently received in the past. It can also prioritize the display of important notifications based on the user's past notification history. Furthermore, it can analyze the user's past notification history and hide unnecessary notifications. This allows for the priority display of important notifications by customizing notification settings based on the user's past notification history. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's past notification history data into a generation AI and have the generation AI perform the customization of notification settings.

[0066] The virtual assistant app can prioritize notifications based on the user's schedule. For example, it can prioritize important notifications based on the user's schedule. It can also prioritize urgent notifications based on the user's schedule. Furthermore, it can prioritize notifications with approaching deadlines based on the user's schedule. In this way, by prioritizing notifications based on the user's schedule, important notifications can be displayed preferentially. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's schedule data into a generation AI and have the generation AI perform the notification priority determination.

[0067] The virtual secretary app can improve the accuracy of notification settings by referring to the user's relevant literature. For example, it can refer to literature related to the user's work and set appropriate notifications. It can also refer to literature related to the user's projects and set appropriate notifications. Furthermore, it can refer to literature related to the user's skill development and set appropriate notifications. In this way, by improving the accuracy of notification settings by referring to the user's relevant literature, appropriate notifications can be set. Some or all of the above processing in the notification setting unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification setting unit can input the user's relevant literature data into a generation AI and have the generation AI perform the improvement of notification setting accuracy.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The classification unit automatically classifies emails. The classification unit can classify emails using, for example, keyword matching or machine learning algorithms. It can also learn from the user's past email history to perform more accurate classifications. Step 2: The labeling unit labels emails based on their importance, as classified by the classification unit. The labeling unit can evaluate importance and assign labels based, for example, on the content of the email or the sender's job title. The labeling unit can also learn from the user's past email processing history to perform more appropriate labeling. Step 3: The extraction unit extracts tasks based on the emails labeled by the labeling unit. The extraction unit can, for example, analyze the content and keywords of the emails to extract tasks. The extraction unit can also learn from the user's past task processing history to perform more appropriate task extraction. Step 4: The list creation unit creates a list of tasks extracted by the extraction unit. The list creation unit can, for example, classify tasks by priority or project and create a list. The list creation unit can also learn from the user's past task list creation history to create more appropriate lists. Step 5: The tracking unit tracks the progress of the task list created by the list creation unit. The tracking unit can, for example, manage the completion status and deadlines of tasks and track their progress. The tracking unit can also learn from the user's past task progress to perform more appropriate progress tracking. Step 6: The reminder unit sets reminders based on the progress tracked by the tracking unit. The reminder unit can, for example, set the timing and frequency of notifications and provide reminders. The reminder unit can also learn from the user's past reminder setting history and set more appropriate reminders. Step 7: The agenda creation function automatically generates a meeting agenda from calendar notifications. The agenda creation function can create an agenda based, for example, on the purpose of the meeting or the priority of the topics. The agenda creation function can also learn from the user's past meeting agenda creation history to create a more appropriate agenda. Step 8: The follow-up unit automatically generates and notifies users of follow-up tasks after the meeting. The follow-up unit can generate and notify users of follow-up tasks based, for example, on the content of the meeting and action items. The follow-up unit can also learn from the user's past follow-up task generation history to generate more appropriate follow-up tasks. Step 9: The suggestion team proposes the next action. The suggestion team can propose the next action based, for example, on the task priority or the user's past behavior history. The suggestion team can also consider the user's current situation to make more appropriate action suggestions. Step 10: The notification settings unit configures customizable notification settings. For example, the notification settings unit can configure the type and display method of notifications, providing customizable notifications. The notification settings unit can also learn the user's past notification setting history and configure more appropriate notification settings.

[0070] (Example of form 2) The virtual secretary application according to an embodiment of the present invention is an application that reduces the user's workload and supports them in concentrating on important tasks. This virtual secretary application utilizes AI to automatically manage emails and calendars and efficiently process tasks. For example, the virtual secretary application has an email management function in which the AI ​​automatically categorizes emails and labels their importance. When the user is busy, the AI ​​provides an automatic response function that can be reviewed later. The virtual secretary application also has a task management function in which it automatically extracts tasks from emails and creates a task list. By tracking progress and setting automatic reminders, it ensures that the user does not forget to complete tasks. For example, if an email contains the message "Prepare for the meeting," the AI ​​automatically extracts the task and sets a reminder. Furthermore, the virtual secretary application has a meeting support function in which it automatically creates a meeting agenda from calendar notifications and automatically generates and notifies the user of follow-up tasks after the meeting. For example, if a meeting is scheduled in the calendar, the AI ​​automatically creates an agenda and generates and notifies the user of follow-up tasks after the meeting. Furthermore, the virtual assistant app features proactive support functions, with a virtual AI suggesting the next action and providing customizable notification settings. For example, the AI ​​suggests the next action the user should take and sets notifications and reminders according to the user's preferences and work style. This app helps busy business professionals avoid missing important emails and work efficiently, supporting efficient task management and meeting preparation. It also includes a function that suggests skill development based on personal information. In this way, the virtual assistant app can reduce the user's workload and help them focus on important work.

[0071] The virtual secretary application according to this embodiment includes a classification unit, a labeling unit, an extraction unit, a list creation unit, a tracking unit, a reminder unit, an agenda creation unit, a follow-up unit, a suggestion unit, and a notification setting unit. The classification unit automatically classifies emails. The classification unit can classify emails using, for example, keyword matching or machine learning algorithms. The classification unit can also learn the user's past email history to perform more accurate classifications. The labeling unit labels emails based on their importance based on the classification unit. The labeling unit can evaluate importance and assign labels based on, for example, the content of the email or the sender's job title. The labeling unit can also learn the user's past email processing history to perform more appropriate labelings. The extraction unit extracts tasks based on the emails labeled by the labeling unit. The extraction unit can extract tasks by, for example, analyzing the content of the email or keywords. The extraction unit can also learn the user's past task processing history to perform more appropriate task extractions. The list creation unit creates lists from the tasks extracted by the extraction unit. For example, the list creation unit can classify tasks by priority or project and create lists. The list creation unit can also learn the user's past task list creation history to create more appropriate lists. The tracking unit tracks the progress of the task lists created by the list creation unit. For example, the tracking unit can manage task completion status and deadlines and track progress. The tracking unit can also learn the user's past task progress to track progress more appropriately. The reminder unit sets reminders based on the progress tracked by the tracking unit. For example, the reminder unit can set the timing and frequency of notifications and provide reminders. The reminder unit can also learn the user's past reminder setting history to set more appropriate reminders. The agenda creation unit automatically creates meeting agendas from calendar notifications. For example, the agenda creation unit can create agendas based on the meeting's purpose and the priority of the topics.Furthermore, the agenda creation unit can learn the user's past meeting agenda creation history and create more appropriate agendas. The follow-up unit automatically generates and notifies of follow-up tasks after meetings. The follow-up unit can generate and notify follow-up tasks based, for example, on the content of the meeting and action items. The follow-up unit can also learn the user's past follow-up task generation history and generate more appropriate follow-up tasks. The suggestion unit proposes the next action. The suggestion unit can propose the next action based, for example, on the task priority and the user's past behavior history. The suggestion unit can also consider the user's current situation and propose more appropriate actions. The notification settings unit provides customizable notification settings. The notification settings unit can provide customizable notifications by setting, for example, the type and display method of notifications. The notification settings unit can also learn the user's past notification setting history and configure more appropriate notification settings. As a result, the virtual secretary application according to the embodiment can reduce the user's workload and support them in focusing on important tasks.

[0072] The classification unit automatically categorizes emails. For example, it can classify emails using keyword matching or machine learning algorithms. Specifically, keyword matching detects specific keywords in the email subject and body, and categorizes emails based on these keywords. For instance, emails containing keywords like "meeting" or "important" are classified as meeting-related or important emails. On the other hand, using machine learning algorithms allows the system to learn from past email data, enabling it to comprehensively assess email content and sender information for more accurate classification. For example, natural language processing techniques can be used to analyze email content and automatically categorize emails into business-related, personal, or spam categories. Furthermore, the classification unit can learn from the user's past email history, improving classification accuracy based on the user's email processing patterns and preferences. For instance, if a user tends to consider emails from a particular sender important, emails from that sender will be prioritized and classified as important. This allows the classification unit to achieve flexible email classification tailored to user needs, significantly improving the efficiency of email management.

[0073] The labeling unit labels emails based on their importance, as classified by the classification unit. For example, the labeling unit can evaluate and label emails based on their content and the sender's job title. Specifically, it analyzes the email body and detects important keywords and phrases to determine the email's importance. For instance, emails containing phrases like "urgent" or "important notice" are labeled as highly important. The sender's job title and position within the organization are also factors in the importance assessment. For example, emails from superiors or important clients are labeled as more important than others. Furthermore, the labeling unit learns the user's past email processing history to understand what emails the user considers important, enabling more appropriate labeling. For example, it learns the characteristics of emails the user frequently opened and responded to quickly in the past, and labels new emails with those characteristics as highly important. This allows the labeling unit to quickly identify important emails and prompt appropriate responses, improving the user's work efficiency.

[0074] The extraction unit extracts tasks based on emails labeled by the labeling unit. For example, the extraction unit can analyze the content and keywords of emails to extract tasks. Specifically, it uses natural language processing technology to analyze the email body and identify action items and instructions related to the tasks. For example, it can extract tasks from emails that contain specific instructions such as "prepare for the meeting" or "submit the documents." Furthermore, the extraction unit can learn from the user's past task processing history and understand which tasks the user considers important, enabling more appropriate task extraction. For example, it can learn the characteristics of tasks that the user has frequently handled in the past and prioritize the extraction of new tasks that possess those characteristics. In addition, the extraction unit can consider metadata such as the email sender and reception date and time to set task priorities and deadlines. This allows the extraction unit to support users in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0075] The list creation unit creates lists from the tasks extracted by the extraction unit. For example, the list creation unit can classify tasks by priority or project and create lists. Specifically, it sets priorities for the extracted tasks and places higher-priority tasks at the top. Furthermore, classifying tasks by project makes it easier for users to manage tasks on a project-by-project basis. For example, separate task lists for "Project A" and "Project B" can be created, and the progress of each can be managed. In addition, the list creation unit can learn from the user's past task list creation history and understand how the user classifies tasks, enabling it to create more appropriate lists. For example, if the user has previously used specific categories or tags to classify tasks, those categories or tags will be automatically applied. In this way, the list creation unit can support users in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0076] The tracking unit tracks the progress of task lists created by the list creation unit. For example, the tracking unit can manage task completion status and deadlines, and track progress. Specifically, it periodically checks the completion status of tasks and sends reminders for incomplete tasks. It also notifies the user when a task deadline is approaching, encouraging them to complete the task within the deadline. Furthermore, the tracking unit can learn from the user's past task progress and understand the pace at which the user completes tasks, enabling more accurate progress tracking. For example, it can predict the completion time of future tasks based on the time it took the user to complete a particular task in the past, and send reminders at the appropriate time. In this way, the tracking unit can support the user in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0077] The reminder unit sets reminders based on the progress tracked by the tracking unit. The reminder unit can, for example, set the timing and frequency of notifications and provide reminders. Specifically, it notifies the user when a task deadline is approaching, encouraging them to complete the task. It can also adjust the frequency of notifications according to the importance and priority of the task. For example, it sends frequent reminders for high-importance tasks and reminders at a moderate frequency for low-importance tasks. Furthermore, the reminder unit can learn from the user's past reminder setting history and understand when the user prefers to receive reminders, enabling it to set more appropriate reminders. For example, if a user has previously preferred to receive reminders at a specific time, it will send reminders at that time. In this way, the reminder unit can support users in efficiently managing tasks and ensuring they don't miss important tasks.

[0078] The agenda creation function automatically generates meeting agendas from calendar notifications. For example, it can create agendas based on the meeting's purpose and the priority of its topics. Specifically, it analyzes meeting information registered in the calendar and extracts the meeting's purpose and topics. For instance, it identifies the meeting's purpose from the meeting title and description, such as "Project Progress Report Meeting" or "New Product Development Meeting." It also supports efficient meeting management by setting priorities for topics and placing important ones at the top. Furthermore, the agenda creation function learns from the user's past meeting agenda creation history, understanding the format and content of agendas the user has created, enabling it to create more appropriate agendas. For example, if the user has previously used a specific format or items when creating agendas, it automatically applies those formats and items. This allows the agenda creation function to support users in efficiently preparing for meetings and ensuring that important topics are not overlooked.

[0079] The follow-up department automatically generates and notifies users of follow-up tasks after meetings. For example, the follow-up department can generate and notify users of follow-up tasks based on the content of the meeting and action items. Specifically, it analyzes meeting minutes and notes to identify action items and assigned personnel decided during the meeting. For example, it extracts specific tasks such as "submitting materials" or "preparing for the next meeting" and notifies the respective responsible parties. Furthermore, the follow-up department learns the user's past follow-up task generation history and understands which tasks the user considers important, enabling it to generate more appropriate follow-up tasks. For example, it learns the characteristics of tasks the user has frequently handled in the past and prioritizes the generation of new tasks with those characteristics. In this way, the follow-up department can support users in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0080] The suggestion function proposes the next action. For example, it can propose the next action based on the task priority and the user's past behavior history. Specifically, it considers the progress and deadline of the current task and proposes the next task to be tackled. For example, it prioritizes suggesting tasks with approaching deadlines or high importance. Furthermore, by learning the user's past behavior history and understanding the order in which the user processes tasks, it can make more appropriate action suggestions. For example, if the user has processed tasks in a specific order in the past, it will propose the next action based on that order. In addition, the suggestion function can consider the user's current situation and propose actions at the optimal time. For example, it will suggest low-priority tasks during busy times and high-priority tasks during less busy times. In this way, the suggestion function can support the user in efficiently managing tasks and ensuring that important tasks are not overlooked.

[0081] The notification settings section allows for customizable notification settings. For example, it can provide customizable notifications by setting the type and display method of notifications. Specifically, users can select the type of notifications they want to receive and set how and when they are displayed. For example, they can choose from multiple notification methods, such as email notifications, push notifications, and voice notifications. Furthermore, the notification display method can be customized to the user's preference, such as pop-up displays, banner displays, and voice alerts. In addition, the notification settings section learns the user's past notification setting history and understands what kind of notification methods and timings the user prefers, enabling it to provide more appropriate notification settings. For example, if a user has previously preferred to receive notifications at a specific time, the notification settings section will send notifications at that time. In this way, the notification settings section can support users in efficiently managing tasks and ensuring they do not miss important notifications.

[0082] The classification unit can estimate the user's emotions and adjust the email classification criteria based on the estimated emotions. For example, if the user is stressed, the classification unit can prioritize displaying important emails and hide unnecessary ones. If the user is relaxed, the classification unit can display all emails and allow the user to choose freely. Furthermore, if the user is in a hurry, the classification unit can display only high-priority emails and allow other emails to be reviewed later. This allows for more appropriate email classification by adjusting the email classification criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the classification unit may be performed using AI or not. For example, the classification unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0083] The classification unit can classify emails by project based on their content. For example, the classification unit can analyze keywords contained in the subject line and body of an email and classify them by project. The classification unit can also classify emails by related projects based on the sender and recipient information. Furthermore, the classification unit can analyze the content of email attachments and classify them by project. This streamlines email management by classifying emails by project based on their content. Some or all of the above processing in the classification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the classification unit can input email content data into a generative AI and have the generative AI perform the classification by project.

[0084] The classification unit can classify emails based on the sender's attribute information. For example, if the sender is a supervisor, the classification unit will classify the email as important. Furthermore, if the sender is a customer, the classification unit can classify the email as a customer service project. Additionally, if the sender is a colleague, the classification unit can classify the email as an internal communication project. This allows for priority processing of important emails by classifying them based on the sender's attribute information. Some or all of the above processing in the classification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the classification unit can input the email sender information into a generative AI and have the generative AI perform classification based on attribute information.

[0085] The labeling unit can estimate the user's emotions and adjust the importance labeling criteria based on the estimated emotions. For example, if the user is stressed, the labeling unit can label important emails as "high priority." Alternatively, if the user is relaxed, the labeling unit can leave all emails unlabeled, allowing the user to choose freely. Furthermore, if the user is in a hurry, the labeling unit can label urgent emails as "high priority." This allows for more appropriate email importance labeling by adjusting the importance labeling criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the labeling unit may be performed using AI or not. For example, the labeling unit can input user facial expression data into the generative AI and have the generative AI perform the user emotion estimation.

[0086] The labeling unit can label emails based on their urgency. For example, the labeling unit can analyze keywords in the email subject and body and label them accordingly. It can also label emails based on the sender and recipient information. Furthermore, the labeling unit can analyze the content of email attachments and label them accordingly. This allows important emails to be processed preferentially by labeling them based on their content. Some or all of the above processing in the labeling unit may be performed using, for example, a generation AI, or without a generation AI. For example, the labeling unit can input email content data into a generation AI and have the generation AI perform the urgency labeling.

[0087] The labeling unit can label emails based on their importance, taking into account the job title of the email sender. For example, if the email sender is a superior, the labeling unit will label the email as "high" in importance. If the email sender is a customer, the labeling unit may label it as "medium" in importance. Furthermore, if the email sender is a colleague, the labeling unit may label it as "low" in importance. By labeling emails based on the job title of the email sender, important emails can be processed preferentially. Some or all of the above processing in the labeling unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the labeling unit can input the email sender information into a generating AI and have the generating AI perform labeling based on job title information.

[0088] The extraction unit can estimate the user's emotions and adjust the task extraction criteria based on the estimated emotions. For example, if the user is stressed, the extraction unit can prioritize extracting important tasks and postpone other tasks. If the user is relaxed, the extraction unit can extract all tasks and allow the user to choose freely. Furthermore, if the user is in a hurry, the extraction unit can extract only high-priority tasks and allow other tasks to be reviewed later. This allows for more appropriate task extraction by adjusting the task extraction criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI or not. For example, the extraction unit can input user facial expression data into the generative AI and have the generative AI perform the user's emotion estimation.

[0089] The extraction unit can extract task priorities based on the content of emails. For example, the extraction unit can analyze keywords contained in the subject and body of an email to extract task priorities. The extraction unit can also extract task priorities based on the sender and recipient information of the email. Furthermore, the extraction unit can analyze the content of email attachments to extract task priorities. This allows important tasks to be processed preferentially by extracting task priorities based on the content of emails. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the extraction unit can input email content data into a generative AI and have the generative AI perform the task priority extraction.

[0090] The extraction unit can extract tasks while considering the job title information of the email sender. For example, if the email sender is a superior, the extraction unit will extract it as an important task. The extraction unit can also extract tasks related to customer service if the email sender is a customer. Furthermore, if the email sender is a colleague, the extraction unit can extract tasks related to internal communication. This allows important tasks to be processed preferentially by extracting tasks while considering the job title information of the email sender. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the extraction unit can input the email sender information into a generating AI and have the generating AI perform task extraction based on job title information.

[0091] The list creation unit can estimate the user's emotions and adjust the task list creation criteria based on the estimated emotions. For example, if the user is stressed, the list creation unit can prioritize listing important tasks and postpone other tasks. If the user is relaxed, the list creation unit can list all tasks and allow the user to choose freely. Furthermore, if the user is in a hurry, the list creation unit can list only high-priority tasks and allow other tasks to be reviewed later. This allows for the creation of more appropriate task lists by adjusting the task list creation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the list creation unit may be performed using AI or not. For example, the list creation unit can input user facial expression data into the generative AI and have the generative AI perform the user's emotion estimation.

[0092] The list creation unit can create lists for each project based on the content of tasks. For example, the list creation unit can analyze keywords contained in the subject and content of tasks and create lists for each project. The list creation unit can also create lists for related projects based on information about the sender and recipient of tasks. Furthermore, the list creation unit can analyze the content of attachments to tasks and create lists for each project. This streamlines task management by creating lists for each project based on the content of tasks. Some or all of the above processing in the list creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the list creation unit can input task content data into a generation AI and have the generation AI perform the creation of project-specific lists.

[0093] The list creation unit can adjust the order of the list based on the priority of the tasks. For example, the list creation unit can place tasks higher in the list based on their importance. It can also place tasks higher in the list based on their urgency. Furthermore, the list creation unit can adjust the order of the list based on the task deadline. This allows important tasks to be processed preferentially by adjusting the order of the list based on task priority. Some or all of the above processing in the list creation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the list creation unit can input task priority data into a generation AI and have the generation AI perform the list order adjustment.

[0094] The tracking unit can estimate the user's emotions and adjust the progress tracking criteria based on the estimated emotions. For example, if the user is stressed, the tracking unit can prioritize tracking the progress of important tasks and postpone other tasks. If the user is relaxed, the tracking unit can track the progress of all tasks and allow the user to choose freely. Furthermore, if the user is in a hurry, the tracking unit can track only the progress of high-priority tasks and allow other tasks to be reviewed later. This allows for more appropriate progress tracking by adjusting the progress tracking criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the tracking unit may be performed using AI or not. For example, the tracking unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0095] The tracking unit can track each project based on the progress of tasks. For example, the tracking unit can summarize the progress of tasks for each project, making it possible to check the progress at a glance. The tracking unit can also track the progress of tasks for each project and prioritize displaying projects that are behind schedule. Furthermore, the tracking unit can track the progress of tasks for each project and display a list of projects that are progressing on time. This streamlines progress management by tracking each project based on the progress of tasks. Some or all of the above processing in the tracking unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the tracking unit can input task progress data into a generative AI and have the generative AI perform project-based tracking.

[0096] The tracking unit can adjust the frequency of tracking based on the task priority. For example, the tracking unit can frequently track the progress of important tasks and notify if progress is behind schedule. It can also frequently track the progress of urgent tasks and notify if progress is behind schedule. Furthermore, it can frequently track the progress of tasks with approaching deadlines and notify if progress is behind schedule. This allows important tasks to be managed preferentially by adjusting the frequency of tracking based on the task priority. Some or all of the above processing in the tracking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the tracking unit can input task priority data into a generative AI and have the generative AI perform the adjustment of the tracking frequency.

[0097] The reminder function can estimate the user's emotions and adjust the reminder setting criteria based on the estimated emotions. For example, if the user is stressed, the reminder function can set frequent reminders for important tasks and postpone other tasks. If the user is relaxed, the reminder function can set reminders for all tasks and allow the user to choose freely. Furthermore, if the user is in a hurry, the reminder function can set reminders only for high-priority tasks and allow other tasks to be reviewed later. This allows for more appropriate reminder settings by adjusting the reminder setting criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reminder function may be performed using AI or not using AI. For example, the reminder unit can input the user's facial expression data into a generating AI, which can then perform an estimation of the user's emotions.

[0098] The reminder unit can adjust the frequency of reminders based on the progress of tasks. For example, the reminder unit can set frequent reminders for tasks that are behind schedule and postpone tasks that are progressing well. It can also set frequent reminders for urgent tasks and allow other tasks to be checked later. Furthermore, it can set frequent reminders for tasks with approaching deadlines and allow other tasks to be checked later. This allows important tasks to be managed preferentially by adjusting the frequency of reminders based on the progress of tasks. Some or all of the above processing in the reminder unit may be performed using, for example, a generating AI, or not using a generating AI. For example, the reminder unit can input task progress data into a generating AI and have the generating AI adjust the reminder frequency.

[0099] The reminder function can customize the content of reminders based on task priority. For example, the reminder function can include detailed explanations in reminders for important tasks. It can also include messages urging prompt action in reminders for urgent tasks. Furthermore, it can include messages emphasizing deadlines in reminders for tasks with approaching deadlines. This allows important tasks to be processed preferentially by customizing the content of reminders based on task priority. Some or all of the above processing in the reminder function may be performed using, for example, a generative AI, or without a generative AI. For example, the reminder function can input task priority data into a generative AI and have the generative AI perform the customization of the reminder content.

[0100] The agenda creation unit can estimate the user's emotions and adjust the agenda creation criteria based on the estimated emotions. For example, if the user is stressed, the agenda creation unit can prioritize important topics in the agenda and postpone others. If the user is relaxed, the agenda creation unit can include all topics in the agenda and allow the user to choose freely. Furthermore, if the user is in a hurry, the agenda creation unit can include only high-priority topics in the agenda and allow others to be reviewed later. This allows for the creation of more appropriate agendas by adjusting the agenda creation criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the agenda creation unit may be performed using AI or not using AI. For example, the agenda creation unit can input user facial expression data into a generating AI and have the AI ​​perform an estimation of the user's emotions.

[0101] The agenda creation unit can adjust the level of detail of the agenda based on the meeting content. For example, for important meetings, the agenda creation unit can create a detailed agenda and set time allocations for each topic. For short meetings, the agenda creation unit can also create a concise agenda and include only the main topics. Furthermore, for regular meetings, the agenda creation unit can refer to past agendas and add necessary topics. This streamlines the preparation of important meetings by adjusting the level of detail of the agenda based on the meeting content. Some or all of the above processes in the agenda creation unit may be performed using, for example, a generative AI, or not. For example, the agenda creation unit can input meeting content data into a generative AI and have the generative AI perform the adjustment of the level of detail of the agenda.

[0102] The agenda creation unit can create an agenda taking into account the job titles of the meeting participants. For example, if a participant is a superior, the agenda creation unit can prioritize including important topics in the agenda. Similarly, if a participant is a client, the agenda creation unit can prioritize including client-related topics. Furthermore, if a participant is a colleague, the agenda creation unit can include internal communication topics. This ensures that important topics are prioritized by creating an agenda that takes into account the job titles of the meeting participants. Some or all of the above processing in the agenda creation unit may be performed using, for example, a generative AI, or without one. For example, the agenda creation unit can input meeting participant information into a generative AI and have the generative AI create an agenda based on job title information.

[0103] The follow-up unit can estimate the user's emotions and adjust the criteria for generating follow-up tasks based on the estimated emotions. For example, if the user is stressed, the follow-up unit can prioritize generating important follow-up tasks and postpone other tasks. If the user is relaxed, the follow-up unit can generate all follow-up tasks and allow the user to choose freely. Furthermore, if the user is in a hurry, the follow-up unit can generate only high-priority follow-up tasks and allow other tasks to be reviewed later. This allows for the generation of more appropriate follow-up tasks by adjusting the criteria for generating follow-up tasks according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the follow-up unit may be performed using AI or not. For example, the follow-up unit can input user facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0104] The follow-up unit can adjust the level of detail of follow-up tasks based on the content of the meeting. For example, for important meetings, the follow-up unit can generate detailed follow-up tasks that include specific action plans. For short meetings, the follow-up unit can also generate concise follow-up tasks that include only key actions. Furthermore, for regular meetings, the follow-up unit can refer to past follow-up tasks and add necessary actions. This streamlines the follow-up of important meetings by adjusting the level of detail of follow-up tasks based on the content of the meeting. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the follow-up unit can input meeting content data into a generative AI and have the generative AI perform the adjustment of the level of detail of the follow-up tasks.

[0105] The follow-up unit can generate follow-up tasks considering the job titles of meeting participants. For example, if a participant is a supervisor, the follow-up unit can prioritize including important actions in the follow-up tasks. Similarly, if a participant is a customer, the follow-up unit can prioritize including customer service actions in the follow-up tasks. Furthermore, if a participant is a colleague, the follow-up unit can include internal communication actions in the follow-up tasks. This allows for priority processing of important actions by generating follow-up tasks considering the job titles of meeting participants. Some or all of the above processing in the follow-up unit may be performed using, for example, a generative AI, or without one. For example, the follow-up unit can input meeting participant information into a generative AI and have the generative AI generate follow-up tasks based on job title information.

[0106] The suggestion unit can estimate the user's emotions and adjust the criteria for suggesting the next action based on the estimated emotions. For example, if the user is stressed, the suggestion unit can prioritize suggesting important actions and postpone other actions. If the user is relaxed, the suggestion unit can suggest all actions and allow the user to choose freely. Furthermore, if the user is in a hurry, the suggestion unit can suggest only high-priority actions and allow other actions to be reviewed later. This allows for more appropriate action suggestions by adjusting the criteria for suggesting the next action according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user facial expression data into a generative AI and have the generative AI perform the user's emotion estimation.

[0107] The suggestion unit can propose the next action based on the user's past behavior history. For example, the suggestion unit can propose the next action based on actions the user has frequently performed in the past. Furthermore, the suggestion unit can propose the optimal action based on the user's past behavior history. In addition, the suggestion unit can analyze the user's past behavior history and propose efficient actions. This enables efficient action proposals by suggesting the next action based on the user's past behavior history. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the user's past behavior history data into a generative AI and have the generative AI execute the next action proposal.

[0108] The suggestion unit can customize the next action based on the user's current situation. For example, the suggestion unit can suggest the next action considering the user's current work situation. It can also suggest the next action considering the user's current schedule. Furthermore, it can suggest the next action considering the user's current project status. This allows for more appropriate action suggestions by customizing the next action based on the user's current situation. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the user's current situation data into a generative AI and have the generative AI perform the next action customization.

[0109] The notification settings unit can estimate the user's emotions and adjust the notification settings criteria based on the estimated emotions. For example, if the user is stressed, the notification settings unit can display only important notifications and hide others. If the user is relaxed, the notification settings unit can display all notifications and allow the user to choose which ones to view. Furthermore, if the user is in a hurry, the notification settings unit can display only high-priority notifications and allow other notifications to be reviewed later. This allows for more appropriate notification settings by adjusting the notification settings criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification settings unit may be performed using AI or not. For example, the notification settings unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0110] The notification settings unit can customize notification settings based on the user's past notification history. For example, the notification settings unit can customize notification settings based on notifications the user has frequently received in the past. The notification settings unit can also prioritize the display of important notifications based on the user's past notification history. Furthermore, the notification settings unit can analyze the user's past notification history and hide unnecessary notifications. This allows for the priority display of important notifications by customizing notification settings based on the user's past notification history. Some or all of the above processing in the notification settings unit may be performed using, for example, a generative AI, or without a generative AI. For example, the notification settings unit can input the user's past notification history data into a generative AI and have the generative AI perform the customization of notification settings.

[0111] The notification settings unit can adjust the frequency of notifications based on the user's current situation. For example, if the user is busy, the notification settings unit can display only important notifications and postpone other notifications. If the user is relaxed, the notification settings unit can display all notifications and allow the user to choose which ones to receive. Furthermore, if the user is in a hurry, the notification settings unit can display only high-priority notifications and allow other notifications to be reviewed later. This allows important notifications to be prioritized by adjusting the frequency of notifications based on the user's current situation. Some or all of the above processing in the notification settings unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the notification settings unit can input the user's current situation data into a generative AI and have the generative AI perform the notification frequency adjustment.

[0112] The notification settings unit can estimate the user's emotions and adjust how notifications are displayed based on the estimated emotions. For example, if the user is stressed, the notification settings unit can highlight important notifications and hide others. If the user is relaxed, the notification settings unit can display all notifications in a list and allow the user to select which ones to view. Furthermore, if the user is in a hurry, the notification settings unit can display only high-priority notifications and allow other notifications to be reviewed later. This allows important notifications to be highlighted by adjusting how notifications are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification settings unit may be performed using AI or not. For example, the notification settings unit can input user facial expression data into a generative AI and have the generative AI perform the estimation of the user's emotions.

[0113] The notification settings unit can determine the priority of notifications based on the user's schedule. For example, the notification settings unit can prioritize the display of important notifications based on the user's schedule. It can also prioritize the display of urgent notifications based on the user's schedule. Furthermore, it can prioritize the display of notifications with approaching deadlines based on the user's schedule. In this way, by determining the priority of notifications based on the user's schedule, important notifications can be displayed preferentially. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's schedule data into a generation AI and have the generation AI perform the notification priority determination.

[0114] The notification settings unit can improve the accuracy of notification settings by referring to the user's relevant literature. For example, the notification settings unit can refer to literature related to the user's work content and set appropriate notifications. It can also refer to literature related to the user's projects and set appropriate notifications. Furthermore, the notification settings unit can refer to literature related to the user's skill development and set appropriate notifications. In this way, by improving the accuracy of notification settings by referring to the user's relevant literature, appropriate notifications can be set. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's relevant literature data into a generation AI and have the generation AI perform the improvement of notification setting accuracy.

[0115] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0116] A virtual assistant app can estimate the user's emotions and adjust task priorities based on those emotions. For example, if the user is stressed, important tasks can be displayed first, while other tasks are postponed. If the user is relaxed, all tasks can be displayed, allowing the user to choose freely. Furthermore, if the user is in a hurry, only high-priority tasks can be displayed, with other tasks to be reviewed later. This allows for more appropriate task management by adjusting task priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in task management may be performed using AI, or not. For example, the task management unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0117] A virtual assistant application can suggest the next action based on the user's past behavior history. For example, it can suggest the next action based on actions the user has frequently performed in the past. It can also suggest the optimal action based on the user's past behavior history. Furthermore, it can analyze the user's past behavior history and suggest efficient actions. This enables efficient action suggestions by suggesting the next action based on the user's past behavior history. Some or all of the above processing in the suggestion unit may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion unit can input the user's past behavior history data into a generative AI and have the generative AI execute the next action suggestion.

[0118] A virtual assistant app can estimate the user's emotions and adjust reminder settings based on those emotions. For example, if the user is stressed, it can set frequent reminders for important tasks and postpone other tasks. If the user is relaxed, it can set reminders for all tasks and allow the user to choose freely. Furthermore, if the user is in a hurry, it can set reminders only for high-priority tasks and allow other tasks to be reviewed later. This allows for more appropriate reminder settings by adjusting reminder settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in reminder setting may be performed using AI or not. For example, the reminder unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0119] The virtual assistant application can customize the next action based on the user's current situation. For example, it can suggest the next action considering the user's current work status. It can also suggest the next action considering the user's current schedule. Furthermore, it can suggest the next action considering the user's current project status. By customizing the next action based on the user's current situation, it becomes possible to suggest more appropriate actions. Some or all of the above processing in the suggestion section may be performed using, for example, a generative AI, or without a generative AI. For example, the suggestion section can input the user's current situation data into a generative AI and have the generative AI perform the next action customization.

[0120] A virtual assistant app can estimate the user's emotions and adjust the agenda creation criteria based on those emotions. For example, if the user is stressed, important topics can be prioritized in the agenda, while others are postponed. If the user is relaxed, all topics can be included in the agenda, allowing the user to choose freely. Furthermore, if the user is in a hurry, only high-priority topics can be included in the agenda, with others to be reviewed later. This allows for the creation of a more appropriate agenda by adjusting the criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in agenda creation may be performed using AI or not. For example, the agenda creation unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0121] The virtual assistant app can customize notification settings based on the user's past notification history. For example, it can customize notification settings based on notifications the user has frequently received in the past. It can also prioritize the display of important notifications based on the user's past notification history. Furthermore, it can analyze the user's past notification history and hide unnecessary notifications. This allows for the priority display of important notifications by customizing notification settings based on the user's past notification history. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's past notification history data into a generation AI and have the generation AI perform the customization of notification settings.

[0122] A virtual assistant app can estimate the user's emotions and adjust notification settings based on those emotions. For example, if the user is stressed, only important notifications can be displayed, and others can be hidden. If the user is relaxed, all notifications can be displayed, allowing the user to choose which ones to view. Furthermore, if the user is in a hurry, only high-priority notifications can be displayed, and others can be reviewed later. This allows for more appropriate notification settings by adjusting notification settings according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in notification settings may be performed using AI, or not. For example, the notification settings unit can input the user's facial expression data into the generative AI and have the generative AI perform the estimation of the user's emotions.

[0123] The virtual assistant app can prioritize notifications based on the user's schedule. For example, it can prioritize important notifications based on the user's schedule. It can also prioritize urgent notifications based on the user's schedule. Furthermore, it can prioritize notifications with approaching deadlines based on the user's schedule. In this way, by prioritizing notifications based on the user's schedule, important notifications can be displayed preferentially. Some or all of the above processing in the notification settings unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification settings unit can input the user's schedule data into a generation AI and have the generation AI perform the notification priority determination.

[0124] A virtual assistant app can estimate the user's emotions and adjust the criteria for generating follow-up tasks based on those emotions. For example, if the user is stressed, important follow-up tasks can be prioritized, while other tasks are postponed. If the user is relaxed, all follow-up tasks can be generated, allowing the user to choose freely. Furthermore, if the user is in a hurry, only high-priority follow-up tasks can be generated, allowing other tasks to be reviewed later. This allows for more appropriate follow-up task generation by adjusting the criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in follow-up task generation may be performed using AI or not. For example, the follow-up unit can input the user's facial expression data into the generative AI and have the generative AI perform the user's emotion estimation.

[0125] The virtual secretary app can improve the accuracy of notification settings by referring to the user's relevant literature. For example, it can refer to literature related to the user's work and set appropriate notifications. It can also refer to literature related to the user's projects and set appropriate notifications. Furthermore, it can refer to literature related to the user's skill development and set appropriate notifications. In this way, by improving the accuracy of notification settings by referring to the user's relevant literature, appropriate notifications can be set. Some or all of the above processing in the notification setting unit may be performed using, for example, a generation AI, or without a generation AI. For example, the notification setting unit can input the user's relevant literature data into a generation AI and have the generation AI perform the improvement of notification setting accuracy.

[0126] The following briefly describes the processing flow for example form 2.

[0127] Step 1: The classification unit automatically classifies emails. The classification unit can classify emails using, for example, keyword matching or machine learning algorithms. It can also learn from the user's past email history to perform more accurate classifications. Step 2: The labeling unit labels emails based on their importance, as classified by the classification unit. The labeling unit can evaluate importance and assign labels based, for example, on the content of the email or the sender's job title. The labeling unit can also learn from the user's past email processing history to perform more appropriate labeling. Step 3: The extraction unit extracts tasks based on the emails labeled by the labeling unit. The extraction unit can, for example, analyze the content and keywords of the emails to extract tasks. The extraction unit can also learn from the user's past task processing history to perform more appropriate task extraction. Step 4: The list creation unit creates a list of tasks extracted by the extraction unit. The list creation unit can, for example, classify tasks by priority or project and create a list. The list creation unit can also learn from the user's past task list creation history to create more appropriate lists. Step 5: The tracking unit tracks the progress of the task list created by the list creation unit. The tracking unit can, for example, manage the completion status and deadlines of tasks and track their progress. The tracking unit can also learn from the user's past task progress to perform more appropriate progress tracking. Step 6: The reminder unit sets reminders based on the progress tracked by the tracking unit. The reminder unit can, for example, set the timing and frequency of notifications and provide reminders. The reminder unit can also learn from the user's past reminder setting history and set more appropriate reminders. Step 7: The agenda creation function automatically generates a meeting agenda from calendar notifications. The agenda creation function can create an agenda based, for example, on the purpose of the meeting or the priority of the topics. The agenda creation function can also learn from the user's past meeting agenda creation history to create a more appropriate agenda. Step 8: The follow-up unit automatically generates and notifies users of follow-up tasks after the meeting. The follow-up unit can generate and notify users of follow-up tasks based, for example, on the content of the meeting and action items. The follow-up unit can also learn from the user's past follow-up task generation history to generate more appropriate follow-up tasks. Step 9: The suggestion team proposes the next action. The suggestion team can propose the next action based, for example, on the task priority or the user's past behavior history. The suggestion team can also consider the user's current situation to make more appropriate action suggestions. Step 10: The notification settings unit configures customizable notification settings. For example, the notification settings unit can configure the type and display method of notifications, providing customizable notifications. The notification settings unit can also learn the user's past notification setting history and configure more appropriate notification settings.

[0128] 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.

[0129] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0130] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0131] Each of the multiple elements described above, including the classification unit, labeling unit, extraction unit, list creation unit, tracking unit, reminder unit, agenda creation unit, follow-up unit, proposal unit, and notification setting unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the classification unit is implemented by the control unit 46A of the smart device 14 and automatically classifies emails. The labeling unit is implemented by the identification processing unit 290 of the data processing unit 12 and labels the importance of the classified emails. The extraction unit is implemented by the control unit 46A of the smart device 14 and extracts tasks based on the labeled emails. The list creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and creates a list of the extracted tasks. The tracking unit is implemented by the control unit 46A of the smart device 14 and tracks the progress of the task list. The reminder unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets reminders based on the progress. The agenda creation unit is implemented by the control unit 46A of the smart device 14 and automatically creates a meeting agenda from calendar notifications. The follow-up unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically generates and notifies of follow-up tasks after the meeting. The suggestion unit is implemented by the control unit 46A of the smart device 14 and suggests the next action. The notification setting unit is implemented by the specific processing unit 290 of the data processing device 12 and performs customizable notification settings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0132] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0133] 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.

[0134] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0135] 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.

[0136] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0137] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0138] 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.

[0139] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0140] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0141] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0142] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0143] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0144] 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.

[0145] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0146] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0147] Each of the multiple elements described above, including the classification unit, labeling unit, extraction unit, list creation unit, tracking unit, reminder unit, agenda creation unit, follow-up unit, proposal unit, and notification setting unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the classification unit is implemented by the control unit 46A of the smart glasses 214 and automatically classifies emails. The labeling unit is implemented by the identification processing unit 290 of the data processing unit 12 and labels the importance of the classified emails. The extraction unit is implemented by the control unit 46A of the smart glasses 214 and extracts tasks based on the labeled emails. The list creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and lists the extracted tasks. The tracking unit is implemented by the control unit 46A of the smart glasses 214 and tracks the progress of the task list. The reminder unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets reminders based on the progress. The agenda creation unit is implemented by the control unit 46A of the smart glasses 214 and automatically creates a meeting agenda from calendar notifications. The follow-up unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically generates and notifies of follow-up tasks after the meeting. The suggestion unit is implemented by the control unit 46A of the smart glasses 214 and suggests the next action. The notification setting unit is implemented by the specific processing unit 290 of the data processing device 12 and performs customizable notification settings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0148] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0149] 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.

[0150] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0151] 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.

[0152] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0153] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0154] 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.

[0155] 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.

[0156] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] 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.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] Each of the multiple elements described above, including the classification unit, labeling unit, extraction unit, list creation unit, tracking unit, reminder unit, agenda creation unit, follow-up unit, proposal unit, and notification setting unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the classification unit is implemented by the control unit 46A of the headset terminal 314 and automatically classifies emails. The labeling unit is implemented by the identification processing unit 290 of the data processing unit 12 and labels the importance of the classified emails. The extraction unit is implemented by the control unit 46A of the headset terminal 314 and extracts tasks based on the labeled emails. The list creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and lists the extracted tasks. The tracking unit is implemented by the control unit 46A of the headset terminal 314 and tracks the progress of the task list. The reminder unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets reminders based on the progress. The agenda creation unit is implemented by the control unit 46A of the headset terminal 314 and automatically creates a meeting agenda from calendar notifications. The follow-up unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically generates and notifies of follow-up tasks after the meeting. The suggestion unit is implemented by the control unit 46A of the headset terminal 314 and suggests the next action. The notification setting unit is implemented by the specific processing unit 290 of the data processing device 12 and performs customizable notification settings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0164] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0165] 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.

[0166] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0167] 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.

[0168] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0169] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0170] 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.

[0171] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0172] 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.

[0173] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0174] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0175] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0176] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0177] 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.

[0178] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0179] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0180] Each of the multiple elements described above, including the classification unit, labeling unit, extraction unit, list creation unit, tracking unit, reminder unit, agenda creation unit, follow-up unit, proposal unit, and notification setting unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the classification unit is implemented by the control unit 46A of the robot 414 and automatically classifies emails. The labeling unit is implemented by the identification processing unit 290 of the data processing unit 12 and labels the importance of the classified emails. The extraction unit is implemented by the control unit 46A of the robot 414 and extracts tasks based on the labeled emails. The list creation unit is implemented by the identification processing unit 290 of the data processing unit 12 and lists the extracted tasks. The tracking unit is implemented by the control unit 46A of the robot 414 and tracks the progress of the task list. The reminder unit is implemented by the identification processing unit 290 of the data processing unit 12 and sets reminders based on the progress. The agenda creation unit is implemented by the control unit 46A of the robot 414 and automatically creates a meeting agenda from calendar notifications. The follow-up unit is implemented by the specific processing unit 290 of the data processing device 12 and automatically generates and notifies of follow-up tasks after the meeting. The proposal unit is implemented by the control unit 46A of the robot 414 and proposes the next action. The notification setting unit is implemented by the specific processing unit 290 of the data processing device 12 and performs customizable notification settings. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0181] 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.

[0182] Figure 9 shows the 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.

[0183] 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.

[0184] 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.

[0185] 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, and motorcycles, 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 based, for example, 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.

[0186] 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."

[0187] 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.

[0188] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0197] 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 other things 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.

[0198] 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.

[0199] (Note 1) A classification unit that automatically sorts emails, A labeling unit that labels the importance of emails based on the classification of emails by the aforementioned classification unit, An extraction unit extracts tasks based on emails labeled by the labeling unit, A list creation unit that lists the tasks extracted by the extraction unit, A tracking unit that tracks the progress of the task list created by the list creation unit, A reminder unit sets a reminder based on the progress tracked by the aforementioned tracking unit, The agenda creation section automatically generates meeting agendas from calendar notifications, The follow-up unit automatically generates and notifies of follow-up tasks after meetings, The proposal team will propose the next action, It includes a notification settings section for customizable notification settings. A system characterized by the following features. (Note 2) The aforementioned classification unit is It estimates the user's sentiment and adjusts email classification criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned classification unit is Based on the content of the emails, categorize them by project. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned classification unit is Classification is performed based on the attribute information of the email sender. The system described in Appendix 1, characterized by the features described herein. (Note 5) The labeling section is, We estimate the user's emotions and adjust the importance labeling criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The labeling section is, Label the urgency based on the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 7) The labeling section is, The importance of the email is labeled based on the sender's job title. The system described in Appendix 1, characterized by the features described herein. (Note 8) The extraction unit is We estimate the user's emotions and adjust the task selection criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The extraction unit is Extract task priorities based on the email content. The system described in Appendix 1, characterized by the features described herein. (Note 10) The extraction unit is Extract tasks considering the job title information of the email sender. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned list creation unit, The system estimates the user's emotions and adjusts the task list creation criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned list creation unit, Create a list for each project based on the task content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned list creation unit, Adjust the order of the list based on task priority. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned tracking unit is We estimate user sentiment and adjust progress tracking criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned tracking unit is Track each project based on the progress of its tasks. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned tracking unit is Adjust tracking frequency based on task priority. The system described in Appendix 1, characterized by the features described herein. (Note 17) The reminder unit is, It estimates the user's emotions and adjusts the reminder setting criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The reminder unit is, Adjust the frequency of reminders based on the task's progress. The system described in Appendix 1, characterized by the features described herein. (Note 19) The reminder unit is, Customize reminder content based on task priority. The system described in Appendix 1, characterized by the features described herein. (Note 20) The agenda creation unit, We estimate user sentiment and adjust agenda creation criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The agenda creation unit, Adjust the level of detail in the agenda based on the content of the meeting. The system described in Appendix 1, characterized by the features described herein. (Note 22) The agenda creation unit, Create an agenda that takes into account the job titles of the meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned follow-up unit is, It estimates the user's emotions and adjusts the criteria for generating follow-up tasks based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned follow-up unit is, Adjust the level of detail in follow-up tasks based on the meeting content. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned follow-up unit is, Generate follow-up tasks considering the job titles of meeting participants. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned proposal section is, It estimates the user's emotions and adjusts the criteria for suggesting the next action based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned proposal section is, Based on the user's past behavior history, we suggest the next action. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned proposal section is, Customize the next action based on the user's current status. The system described in Appendix 1, characterized by the features described herein. (Note 29) The notification setting unit is, It estimates the user's emotions and adjusts the notification settings criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The notification setting unit is, Customize notification settings based on the user's past notification history. The system described in Appendix 1, characterized by the features described herein. (Note 31) The notification setting unit is, Adjust the frequency of notifications based on the user's current status. The system described in Appendix 1, characterized by the features described herein. (Note 32) The notification setting unit is, It estimates the user's emotions and adjusts how notifications are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The notification setting unit is, Prioritize notifications based on the user's schedule. The system described in Appendix 1, characterized by the features described herein. (Note 34) The notification setting unit is, Improve the accuracy of notification settings by referring to the user's relevant literature. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0200] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A classification unit that automatically sorts emails, A labeling unit that labels the importance of emails based on the classification of emails by the aforementioned classification unit, An extraction unit extracts tasks based on emails labeled by the labeling unit, A list creation unit that lists the tasks extracted by the extraction unit, A tracking unit that tracks the progress of the task list created by the list creation unit, A reminder unit sets a reminder based on the progress tracked by the aforementioned tracking unit, The agenda creation section automatically generates meeting agendas from calendar notifications, The follow-up department automatically generates and notifies about follow-up tasks after meetings, The proposal team will propose the next action, It includes a notification settings section for customizable notification settings. A system characterized by the following features.

2. The aforementioned classification unit is It estimates the user's sentiment and adjusts email classification criteria based on the estimated user sentiment. The system according to feature 1.

3. The aforementioned classification unit is Based on the content of the emails, categorize them by project. The system according to feature 1.

4. The aforementioned classification unit is Classification is performed based on the attribute information of the email sender. The system according to feature 1.

5. The labeling section is, We estimate the user's emotions and adjust the importance labeling criteria based on the estimated user emotions. The system according to feature 1.

6. The labeling section is, Label the urgency based on the content of the email. The system according to feature 1.

7. The labeling section is, The importance of the email is labeled based on the sender's job title. The system according to feature 1.

8. The extraction unit is We estimate the user's emotions and adjust the task selection criteria based on the estimated user emotions. The system according to feature 1.

9. The extraction unit is Extract task priorities based on the email content. The system according to feature 1.

10. The extraction unit is Extract tasks considering the job title information of the email sender. The system according to feature 1.

Images