system

Abstract

The system according to this embodiment aims to efficiently manage messages from multiple tools and ensure that tasks relevant to the user are not overlooked. [Solution] The system according to the embodiment comprises a reading unit, an extraction unit, a summarizing unit, and an aggregation unit. The reading unit reads the received messages. The extraction unit extracts from the messages read by the reading unit those that are relevant to the user or require action. The summarizing unit summarizes the tasks extracted by the extraction unit into a single line. The aggregation unit aggregates the tasks summarized by the summarizing unit into a single management screen.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , ,

[0003] , , , ,

[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 it is difficult to efficiently manage messages from a plurality of tools and grasp tasks related to oneself without overlooking them.

[0005] The system according to the embodiment aims to efficiently manage messages from a plurality of tools and grasp tasks related to oneself without overlooking them.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reading unit, an extraction unit, a summarizing unit, and an aggregation unit. The reading unit reads the received messages. The extraction unit extracts from the messages read by the reading unit those that are relevant to the user or require action. The summarizing unit summarizes the tasks extracted by the extraction unit into a single line. The aggregation unit aggregates the tasks summarized by the summarizing unit into a single management screen. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently manage messages from multiple tools and ensure that tasks relevant to the user are not overlooked. [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 signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 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 �0, 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the 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 task management system according to an embodiment of the present invention is a system that extracts tasks relevant to the user from multiple communication tools and manages them centrally. This task management system uses a generating AI to read messages from received emails and communication tools (e.g., email and group chat tools) that the user has mentioned. Next, the generating AI extracts the messages that are relevant to the user or require action and summarizes them in one line. As a result, tasks generated on multiple tools are automatically consolidated into a single management screen, eliminating the possibility of overlooking anything. Furthermore, because tasks are summarized in one line, it becomes possible to instantly determine which tasks should be prioritized. First, the generating AI reads received emails and messages that the user has mentioned. At this time, the generating AI also refers to past interactions to reduce the risk of making inaccurate summaries. For example, data is automatically imported from email and group chat tools and analyzed by the generating AI. Next, the generating AI extracts the messages that are relevant to the user or require action from the messages it has read and summarizes them in one line. For example, tasks such as "Please check the invoice" or "Please prepare for the next meeting" are summarized in one line. Furthermore, the summarized tasks are automatically consolidated into a single management screen. This allows for centralized management of tasks generated across multiple tools, eliminating the risk of overlooking tasks. For example, tasks extracted from email, group chat tools, etc., are displayed on a single management screen. This system summarizes tasks in a single line, making it possible to instantly determine which tasks should be prioritized. Users can avoid the hassle of checking multiple tools and see all their tasks on a single management screen. For example, the management screen displays the task content along with a label indicating which tool it was extracted from, allowing for immediate action. Furthermore, once a task is completed, it automatically disappears from the list as soon as it is acknowledged in the email or group chat tool. This ensures that users always have access to the latest task status. For example, by automatically removing completed tasks from the list, only incomplete tasks are displayed. In this way, by utilizing generation AI to extract tasks from multiple communication tools and managing them centrally, work efficiency is improved and oversights are eliminated.Furthermore, since tasks are summarized in a single line, it becomes possible to instantly determine what should be prioritized. This allows the task management system to extract relevant tasks from multiple communication tools and manage them centrally.

[0029] The task management system according to this embodiment comprises a reading unit, an extraction unit, a summarization unit, and an aggregation unit. The reading unit reads received messages. The reading unit can automatically retrieve data from, for example, email or group chat tools. For example, the reading unit periodically scans the email inbox to detect new messages. The reading unit can also retrieve messages in real time using the API of a group chat tool. Furthermore, the reading unit can also retrieve messages based on specific trigger events (for example, the receipt of a new message). The extraction unit extracts messages that are relevant to the user or require action from the messages read by the reading unit. For example, the extraction unit can extract tasks based on specific keywords or phrases. For example, the extraction unit extracts messages containing keywords such as "confirm," "respond," and "prepare." The extraction unit can also extract tasks based on the sender or recipient of the message. For example, it can prioritize extracting messages from a supervisor or messages addressed to the user. Furthermore, the extraction unit can analyze the content of the messages and extract tasks based on their importance and urgency. The summarization section summarizes the tasks extracted by the extraction section into a single line. The summarization section can, for example, concisely summarize the content of the extracted tasks. For example, the summarization section can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. The summarization section can also extract important information about the tasks and reflect it in the summary. For example, it can include the task's deadline and priority in the summary. Furthermore, the summarization section can use natural language processing techniques to express the task content concisely. The aggregation section aggregates the tasks summarized by the summarization section into a single management screen. For example, the aggregation section can display the summarized tasks in a list. For example, the aggregation section can display the tool from which the task was extracted along with the task content using a label. The aggregation section can also adjust the display order based on the task priority. For example, it can display high-priority tasks at the top. Furthermore, the aggregation section has a function that automatically removes tasks from the list when they are completed.This allows users to always be aware of the latest task status. As a result, the task management system according to this embodiment can extract tasks relevant to the user from multiple communication tools and manage them centrally.

[0030] The reading unit reads received messages. For example, it can automatically retrieve data from email and group chat tools. Specifically, it has the functionality to periodically scan email inboxes and detect new messages, eliminating the need for users to manually check their emails. The reading unit can also retrieve messages in real time using group chat tool APIs. Furthermore, it can retrieve messages based on specific trigger events (e.g., the arrival of a new message), ensuring that important messages are not missed and are immediately incorporated into the system. By combining these functions, the reading unit efficiently collects data from multiple communication tools used by users, providing a foundation for task management. Additionally, the reading unit performs appropriate data transformations based on the message format and content, making it easy for subsequent processing departments to analyze. For example, it can convert HTML emails to text format or extract metadata from chat messages. In this way, the reading unit plays a role in improving the overall data processing efficiency of the system.

[0031] The extraction unit extracts messages that are relevant to the user or require action from the messages read by the reading unit. For example, the extraction unit can extract tasks based on specific keywords or phrases. Specifically, it can extract messages containing keywords such as "confirm," "respond," and "prepare." The extraction unit can also extract tasks based on the sender or recipient of the message. For example, it can prioritize extracting messages from a supervisor or messages addressed to the user. Furthermore, the extraction unit can analyze the content of messages and extract tasks based on importance and urgency. This involves a process that uses natural language processing (NLP) techniques to understand the context of the message and evaluate the importance of the task. For example, using NLP techniques, if a message contains words such as "urgent" or "important," that task will be extracted as a high-priority task. In addition, the extraction unit can learn from past task history and user behavior patterns to perform more accurate task extraction. As a result, the extraction unit can efficiently extract the tasks that the user truly needs, improving the accuracy of task management.

[0032] The summarization unit summarizes the tasks extracted by the extraction unit into a single line. For example, the summarization unit can concisely summarize the content of the extracted tasks. Specifically, it can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. The summarization unit can also extract important information about the tasks and incorporate it into the summary. For example, it can include the task's deadline and priority in the summary. Furthermore, the summarization unit can use natural language processing techniques to express the task content concisely. This allows the summarization unit to extract necessary information from long messages and convert it into a format that users can understand at a glance. The summarization unit automates the process of understanding the context of a message and extracting important information using AI. For example, the AI ​​identifies important keywords and phrases in the message and generates a summary based on them. The summarization unit can also learn from the user's past summarization history to provide summaries that better suit the user's needs. This allows the summarization unit to help users manage tasks efficiently and improve the accuracy and efficiency of task management.

[0033] The aggregation section consolidates tasks summarized by the summarization section into a single management screen. For example, the aggregation section can display summarized tasks in a list. Specifically, it displays the task content along with a label indicating the tool from which it was extracted. The aggregation section can also adjust the display order based on task priority, for example, displaying high-priority tasks at the top. Furthermore, the aggregation section has a function that automatically removes tasks from the list when they are completed, allowing users to always stay informed of the latest task status. The aggregation section is designed to allow users to easily check task progress through its user interface. For example, it categorizes task statuses into categories such as "incomplete," "in progress," and "completed," displaying them visually for clarity. The aggregation section also includes a function to set reminders based on task deadlines and priorities, notifying users. This allows users to efficiently manage important tasks without forgetting them. Additionally, the aggregation section supports collaborative task management by multiple users, facilitating task assignment and progress sharing. This enables the aggregation section to support task management not only for individuals but for entire teams, leading to increased work efficiency.

[0034] The reading unit can automatically retrieve data from email and group chat tools. For example, the reading unit can periodically scan the email inbox to detect new messages. It can also use the API of a group chat tool to retrieve messages in real time. Furthermore, the reading unit can retrieve messages based on specific trigger events (e.g., the arrival of a new message). This allows for efficient message reading by automatically retrieving data from email and group chat tools. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or not. For example, the reading unit can input the email inbox into a generative AI and have the generative AI perform the detection of new messages.

[0035] The extraction unit can extract tasks based on specific keywords or phrases. For example, it can extract messages containing keywords such as "confirm," "respond," or "prepare." The extraction unit can also extract tasks based on the sender or recipient of a message. For example, it can prioritize extracting messages from a supervisor or messages addressed to the user. Furthermore, the extraction unit can analyze the message content and extract tasks based on importance and urgency. This allows for the efficient identification of important tasks by extracting tasks based on specific keywords or phrases. Some or all of the above-described processes 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 the message content into a generative AI and have the generative AI perform task extraction based on importance and urgency.

[0036] The summarization unit can summarize the extracted tasks into a single line. For example, the summarization unit can concisely summarize the content of the extracted tasks. For instance, it can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. The summarization unit can also extract important information about the tasks and incorporate it into the summary. For example, it can include the task's deadline and priority in the summary. Furthermore, the summarization unit can use natural language processing techniques to express the task content concisely. This allows for quick determination of which tasks should be prioritized by summarizing the extracted tasks into a single line. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input the content of the extracted tasks into a generative AI and have the generative AI perform the process of summarizing them into a single line.

[0037] The aggregation unit can display summarized tasks on a single management screen. For example, the aggregation unit can display summarized tasks in a list. For example, the aggregation unit can display the task content along with a label indicating which tool extracted it from. The aggregation unit can also adjust the display order based on task priority. For example, it can display high-priority tasks at the top. Furthermore, the aggregation unit has a function that automatically removes tasks from the list when they are completed. This allows users to always know the latest task status. By displaying summarized tasks on a single management screen, it is possible to prevent tasks from being overlooked. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the aggregation unit can input summarized tasks into a generation AI and have the generation AI execute the process of displaying them on the management screen.

[0038] The aggregation unit can display the task content along with a label indicating the tool from which it was extracted. For example, the aggregation unit can display labels such as email and group chat tools along with the task content. The aggregation unit can also customize the type and display position of the labels. For example, it can change the color and font of the labels. This allows for quick identification of the origin of tasks by displaying the tool from which they were extracted along with the task content. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the aggregation unit can input the task content and label information into a generation AI and have the generation AI display the labels.

[0039] The aggregation unit can automatically remove tasks from the list when they are completed. For example, the aggregation unit can detect task completion and automatically remove it from the list. The aggregation unit can also monitor task completion status in real time and immediately remove completed tasks from the list. This ensures that the latest task status is always known by automatically removing tasks from the list when they are completed. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the aggregation unit can input the task completion status to a generation AI and have the generation AI perform the removal from the list.

[0040] The reading unit can select the optimal reading method by referring to the user's past message history when reading a message. For example, the reading unit may prioritize reading messages from people the user has frequently communicated with in the past. It can also prioritize reading messages containing keywords that the user has previously deemed important. Furthermore, the reading unit can learn patterns of messages the user has ignored in the past and postpone similar messages. This allows the reading unit to select the optimal reading method by referring to the user's past message history. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reading unit can input the user's past message history into a generative AI and have the generative AI select the optimal reading method.

[0041] The reading unit can filter messages based on the user's current projects and areas of interest when reading them. For example, the reading unit can prioritize reading messages related to projects the user is currently working on. It can also prioritize reading messages related to topics the user is interested in. Furthermore, the reading unit can filter and read highly relevant messages based on keywords set by the user. This allows the reading unit to prioritize reading highly relevant messages by filtering based on the user's current projects and areas of interest. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reading unit can input the user's project information and areas of interest into a generative AI and have the generative AI perform the filtering.

[0042] The reading unit can prioritize reading messages that are highly relevant by considering the user's geographical location when reading messages. For example, if the user is in a specific location, the reading unit will prioritize reading messages related to that location. Furthermore, if the user is on a business trip, the reading unit can prioritize reading messages related to the destination. Additionally, if the user is at home, the reading unit can prioritize reading messages related to home. This allows the reading unit to prioritize reading highly relevant messages by considering the user's geographical location. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reading unit can input the user's geographical location information into a generative AI and cause the generative AI to prioritize reading highly relevant messages.

[0043] The reading unit can analyze the user's social media activity and read relevant messages when reading messages. For example, the reading unit can prioritize reading messages related to topics the user has mentioned on social media. It can also prioritize reading messages from people or groups the user follows. Furthermore, it can prioritize reading messages related to events the user has participated in on social media. In this way, by analyzing the user's social media activity, it is possible to prioritize reading relevant messages. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reading unit can input the user's social media activity data into a generative AI and have the generative AI perform the reading of relevant messages.

[0044] The extraction unit can improve the accuracy of task extraction by considering the interrelationships between messages. For example, the extraction unit can analyze the reply relationships between messages and extract related tasks in a batch. It can also analyze the quoted portion of messages and extract tasks in relation to the original message. Furthermore, the extraction unit can analyze the thread structure of messages and extract tasks for the entire thread. This allows for efficient extraction of related tasks by considering the interrelationships between messages. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input message interrelationship data into a generation AI and have the generation AI perform task extraction.

[0045] The extraction unit can extract tasks while considering the attribute information of the message sender. For example, if the message sender is a superior, the extraction unit will extract tasks of high importance. The extraction unit can also extract related tasks if the message sender is a colleague. Furthermore, if the message sender is an external business partner, the extraction unit can extract tasks of high urgency. In this way, important tasks can be efficiently extracted by considering the attribute information of the message sender. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input the attribute information of the message sender into the generation AI and have the generation AI perform task extraction.

[0046] The extraction unit can extract tasks while considering the geographical distribution of messages. For example, if the message sender is nearby, the extraction unit may extract tasks as high urgency. Similarly, if the message sender is far away, the extraction unit may extract tasks as high importance. Furthermore, if the message sender is in a specific region, the extraction unit may extract tasks related to that region. This allows for the efficient extraction of highly relevant tasks by considering the geographical distribution of messages. 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 geographical distribution data of messages into a generative AI and have the generative AI perform task extraction.

[0047] The extraction unit can improve the accuracy of task extraction by referring to relevant literature in the message. For example, the extraction unit can analyze the literature cited in the message and extract relevant tasks. The extraction unit can also refer to literature related to the content of the message and evaluate the importance of the tasks. Furthermore, the extraction unit can determine the urgency of the tasks based on the literature referenced by the message sender. In this way, the accuracy of task extraction can be improved by referring to relevant literature in the message. 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 the relevant literature data of the message into a generative AI and have the generative AI perform task extraction.

[0048] The summarization unit can adjust the level of detail in a summary based on the importance of the task during summary generation. For example, the summarization unit can generate a detailed summary for high-importance tasks. It can also generate a concise summary for low-importance tasks. Furthermore, it can generate a short, to-the-point summary for urgent tasks. This allows for a detailed understanding of important tasks by adjusting the level of detail in the summary based on the importance of the task. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0049] The summarization unit can apply different summarization algorithms depending on the task category when generating summaries. For example, for project management tasks, the summarization unit can generate summaries that reflect the project's progress. It can also generate summaries that reflect message exchanges for communication tasks. Furthermore, for document review tasks, it can generate summaries that reflect the review's progress. This allows for the generation of optimal summaries for each category by applying different summarization algorithms depending on the task category. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task category data into a generation AI and have the generation AI apply the summarization algorithm.

[0050] The summarization unit can determine the priority of summaries based on the task submission dates when generating summaries. For example, the summarization unit will prioritize generating summaries for tasks with approaching deadlines. It can also postpone generating summaries for tasks with distant submission dates. Furthermore, for tasks with unknown submission dates, the summarization unit can generate summaries after other tasks have been completed. This allows for prioritizing urgent tasks by determining the priority of summaries based on their submission dates. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task submission date data into a generation AI and have the generation AI determine the priority of summaries.

[0051] The summarization unit can adjust the order of summaries based on the relevance of tasks during the summarization process. For example, the summarization unit can prioritize the generation of summaries for highly relevant tasks. It can also postpone the generation of summaries for less relevant tasks. Furthermore, for tasks whose relevance is unknown, the summarization unit can generate summaries for them after the summaries for other tasks have been completed. This allows for the prioritization of highly relevant tasks by adjusting the order of summaries based on the relevance of tasks. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0052] The aggregation unit can optimize the current aggregation method by referring to past aggregation data during aggregation. For example, the aggregation unit can analyze past aggregation data and apply the most efficient aggregation method. The aggregation unit can also learn and apply the display format preferred by the user from past aggregation data. Furthermore, the aggregation unit can provide an aggregation method tailored to the user's work pattern based on past aggregation data. This allows the current aggregation method to be optimized by referring to past aggregation data. Some or all of the above processing in the aggregation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the aggregation unit can input past aggregation data into a generative AI and have the generative AI perform the optimization of the current aggregation method.

[0053] The aggregation unit can apply different aggregation methods to each task category during aggregation. For example, for project management tasks, the aggregation unit aggregates them by project. For communication tasks, it can aggregate them by message exchange. Furthermore, for document review tasks, it can aggregate them by review progress. This allows for optimal aggregation for each category by applying different aggregation methods to each task category. Some or all of the above processing in the aggregation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the aggregation unit can input task category data into a generative AI and have the generative AI apply the aggregation method.

[0054] The aggregation unit can adjust the aggregation order based on the task submission dates during aggregation. For example, the aggregation unit will prioritize aggregation of tasks with approaching deadlines. It can also postpone the aggregation of tasks with later submission dates. Furthermore, it can aggregate tasks with unknown submission dates after the aggregation of other tasks is complete. This allows for the prioritization of urgent tasks by adjusting the aggregation order based on task submission dates. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the aggregation unit can input task submission date data into a generation AI and have the generation AI perform the adjustment of the aggregation order.

[0055] The aggregation unit can perform aggregation by referring to relevant market data for tasks. For example, the aggregation unit can prioritize the aggregation of highly relevant tasks based on market data. The aggregation unit can also extract and aggregate tasks related to the user's work from market data. Furthermore, the aggregation unit can analyze market data and aggregate tasks that are optimal for the user's work. This allows for the efficient aggregation of highly relevant tasks by referring to relevant market data for tasks. Some or all of the above processing in the aggregation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the aggregation unit can input relevant market data into a generative AI and have the generative AI perform the task aggregation.

[0056] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0057] The task management system can also include a calendar function. This calendar function can automatically retrieve the user's schedule and suggest an optimal schedule based on task deadlines and importance. For example, it can detect the user's free time and assign tasks to those times. Furthermore, if the user's schedule is full, the calendar function can adjust task priorities, scheduling important tasks first. Additionally, if there are changes to the user's schedule, the calendar function can automatically readjust task schedules. This enables optimal task management based on the user's schedule.

[0058] A task management system can also include an analysis unit. This unit can analyze the user's task completion status and propose efficient task management methods. For example, it can analyze which tasks the user is spending the most time on and suggest efficient task allocation methods. It can also analyze the user's task completion rate and suggest areas for improvement. Furthermore, it can analyze the user's task management patterns and propose the optimal task management method. This enables efficient task management based on the user's task completion status.

[0059] A task management system can also include a shared section. This section allows users to share tasks with other users and manage them collaboratively. For example, a shared section can be used to share tasks within a project team and track each member's progress in real time. It can also assign tasks to specific members, clearly defining their roles. Furthermore, the shared section can automatically send notifications based on task progress, streamlining task management for the entire team. This enables efficient task management by allowing users to share tasks with others.

[0060] The task management system can also include a customization section. This customization section allows users to customize the task management system's settings according to their preferences. For example, the customization section allows users to set their preferred display format and notification methods. It also allows users to set their preferred task classification methods. Furthermore, the customization section allows users to add or remove functions from the task management system according to their work content. This enables efficient task management by customizing the task management system to suit user preferences.

[0061] The task management system can also include a prediction unit. This unit analyzes the user's past task completion data and predicts future task completion. For example, it can predict future task completion times based on the user's past task completion times. It can also predict future task completion rates based on the user's past task completion rates. Furthermore, it can suggest future task management methods based on the user's past task management patterns. This enables efficient task management by predicting future task completion based on the user's past task completion data.

[0062] The following briefly describes the processing flow for example form 1.

[0063] Step 1: The reading unit reads the received messages. For example, it can automatically import data from email or group chat tools. The reading unit periodically scans the email inbox to detect new messages. It can also use the API of a group chat tool to retrieve messages in real time. Furthermore, it can import messages based on specific trigger events (for example, the arrival of a new message). Step 2: The extraction unit extracts messages that are relevant to the user or require action from the messages read by the reading unit. For example, tasks can be extracted based on specific keywords or phrases. The extraction unit extracts messages containing keywords such as "confirm," "respond," and "prepare." Tasks can also be extracted based on the sender or recipient of the message. For example, messages from a supervisor or messages addressed to the user can be prioritized. Furthermore, the content of the messages can be analyzed, and tasks can be extracted based on importance and urgency. Step 3: The summarization section summarizes the tasks extracted by the extraction section into a single line. For example, it can concisely summarize the content of the extracted tasks. The summarization section can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. It can also extract important information about the tasks and reflect it in the summary. For example, it can include the task's deadline or priority in the summary. Furthermore, natural language processing techniques can be used to express the content of the tasks concisely. Step 4: The aggregation section consolidates the tasks summarized by the summarization section into a single management screen. For example, summarized tasks can be displayed in a list. The aggregation section displays the task content along with a label indicating which tool extracted the task. It can also adjust the display order based on task priority. For example, tasks with higher importance can be displayed at the top. Furthermore, it has a function that automatically removes tasks from the list when they are completed. This allows you to always keep track of the latest task status.

[0064] (Example of form 2) The task management system according to an embodiment of the present invention is a system that extracts tasks relevant to the user from multiple communication tools and manages them centrally. This task management system uses a generating AI to read messages from received emails and communication tools (e.g., email and group chat tools) that the user has mentioned. Next, the generating AI extracts the messages that are relevant to the user or require action and summarizes them in one line. As a result, tasks generated on multiple tools are automatically consolidated into a single management screen, eliminating the possibility of overlooking anything. Furthermore, because tasks are summarized in one line, it becomes possible to instantly determine which tasks should be prioritized. First, the generating AI reads received emails and messages that the user has mentioned. At this time, the generating AI also refers to past interactions to reduce the risk of making inaccurate summaries. For example, data is automatically imported from email and group chat tools and analyzed by the generating AI. Next, the generating AI extracts the messages that are relevant to the user or require action from the messages it has read and summarizes them in one line. For example, tasks such as "Please check the invoice" or "Please prepare for the next meeting" are summarized in one line. Furthermore, the summarized tasks are automatically consolidated into a single management screen. This allows for centralized management of tasks generated across multiple tools, eliminating the risk of overlooking tasks. For example, tasks extracted from email, group chat tools, etc., are displayed on a single management screen. This system summarizes tasks in a single line, making it possible to instantly determine which tasks should be prioritized. Users can avoid the hassle of checking multiple tools and see all their tasks on a single management screen. For example, the management screen displays the task content along with a label indicating which tool it was extracted from, allowing for immediate action. Furthermore, once a task is completed, it automatically disappears from the list as soon as it is acknowledged in the email or group chat tool. This ensures that users always have access to the latest task status. For example, by automatically removing completed tasks from the list, only incomplete tasks are displayed. In this way, by utilizing generation AI to extract tasks from multiple communication tools and managing them centrally, work efficiency is improved and oversights are eliminated.Furthermore, since tasks are summarized in a single line, it becomes possible to instantly determine what should be prioritized. This allows the task management system to extract relevant tasks from multiple communication tools and manage them centrally.

[0065] The task management system according to this embodiment comprises a reading unit, an extraction unit, a summarization unit, and an aggregation unit. The reading unit reads received messages. The reading unit can automatically retrieve data from, for example, email or group chat tools. For example, the reading unit periodically scans the email inbox to detect new messages. The reading unit can also retrieve messages in real time using the API of a group chat tool. Furthermore, the reading unit can also retrieve messages based on specific trigger events (for example, the receipt of a new message). The extraction unit extracts messages that are relevant to the user or require action from the messages read by the reading unit. For example, the extraction unit can extract tasks based on specific keywords or phrases. For example, the extraction unit extracts messages containing keywords such as "confirm," "respond," and "prepare." The extraction unit can also extract tasks based on the sender or recipient of the message. For example, it can prioritize extracting messages from a supervisor or messages addressed to the user. Furthermore, the extraction unit can analyze the content of the messages and extract tasks based on their importance and urgency. The summarization section summarizes the tasks extracted by the extraction section into a single line. The summarization section can, for example, concisely summarize the content of the extracted tasks. For example, the summarization section can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. The summarization section can also extract important information about the tasks and reflect it in the summary. For example, it can include the task's deadline and priority in the summary. Furthermore, the summarization section can use natural language processing techniques to express the task content concisely. The aggregation section aggregates the tasks summarized by the summarization section into a single management screen. For example, the aggregation section can display the summarized tasks in a list. For example, the aggregation section can display the tool from which the task was extracted along with the task content using a label. The aggregation section can also adjust the display order based on the task priority. For example, it can display high-priority tasks at the top. Furthermore, the aggregation section has a function that automatically removes tasks from the list when they are completed.This allows users to always be aware of the latest task status. As a result, the task management system according to this embodiment can extract tasks relevant to the user from multiple communication tools and manage them centrally.

[0066] The reading unit reads received messages. For example, it can automatically retrieve data from email and group chat tools. Specifically, it has the functionality to periodically scan email inboxes and detect new messages, eliminating the need for users to manually check their emails. The reading unit can also retrieve messages in real time using group chat tool APIs. Furthermore, it can retrieve messages based on specific trigger events (e.g., the arrival of a new message), ensuring that important messages are not missed and are immediately incorporated into the system. By combining these functions, the reading unit efficiently collects data from multiple communication tools used by users, providing a foundation for task management. Additionally, the reading unit performs appropriate data transformations based on the message format and content, making it easy for subsequent processing departments to analyze. For example, it can convert HTML emails to text format or extract metadata from chat messages. In this way, the reading unit plays a role in improving the overall data processing efficiency of the system.

[0067] The extraction unit extracts messages that are relevant to the user or require action from the messages read by the reading unit. For example, the extraction unit can extract tasks based on specific keywords or phrases. Specifically, it can extract messages containing keywords such as "confirm," "respond," and "prepare." The extraction unit can also extract tasks based on the sender or recipient of the message. For example, it can prioritize extracting messages from a supervisor or messages addressed to the user. Furthermore, the extraction unit can analyze the content of messages and extract tasks based on importance and urgency. This involves a process that uses natural language processing (NLP) techniques to understand the context of the message and evaluate the importance of the task. For example, using NLP techniques, if a message contains words such as "urgent" or "important," that task will be extracted as a high-priority task. In addition, the extraction unit can learn from past task history and user behavior patterns to perform more accurate task extraction. As a result, the extraction unit can efficiently extract the tasks that the user truly needs, improving the accuracy of task management.

[0068] The summarization unit summarizes the tasks extracted by the extraction unit into a single line. For example, the summarization unit can concisely summarize the content of the extracted tasks. Specifically, it can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. The summarization unit can also extract important information about the tasks and incorporate it into the summary. For example, it can include the task's deadline and priority in the summary. Furthermore, the summarization unit can use natural language processing techniques to express the task content concisely. This allows the summarization unit to extract necessary information from long messages and convert it into a format that users can understand at a glance. The summarization unit automates the process of understanding the context of a message and extracting important information using AI. For example, the AI ​​identifies important keywords and phrases in the message and generates a summary based on them. The summarization unit can also learn from the user's past summarization history to provide summaries that better suit the user's needs. This allows the summarization unit to help users manage tasks efficiently and improve the accuracy and efficiency of task management.

[0069] The aggregation section consolidates tasks summarized by the summarization section into a single management screen. For example, the aggregation section can display summarized tasks in a list. Specifically, it displays the task content along with a label indicating the tool from which it was extracted. The aggregation section can also adjust the display order based on task priority, for example, displaying high-priority tasks at the top. Furthermore, the aggregation section has a function that automatically removes tasks from the list when they are completed, allowing users to always stay informed of the latest task status. The aggregation section is designed to allow users to easily check task progress through its user interface. For example, it categorizes task statuses into categories such as "incomplete," "in progress," and "completed," displaying them visually for clarity. The aggregation section also includes a function to set reminders based on task deadlines and priorities, notifying users. This allows users to efficiently manage important tasks without forgetting them. Additionally, the aggregation section supports collaborative task management by multiple users, facilitating task assignment and progress sharing. This enables the aggregation section to support task management not only for individuals but for entire teams, leading to increased work efficiency.

[0070] The reading unit can automatically retrieve data from email and group chat tools. For example, the reading unit can periodically scan the email inbox to detect new messages. It can also use the API of a group chat tool to retrieve messages in real time. Furthermore, the reading unit can retrieve messages based on specific trigger events (e.g., the arrival of a new message). This allows for efficient message reading by automatically retrieving data from email and group chat tools. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or not. For example, the reading unit can input the email inbox into a generative AI and have the generative AI perform the detection of new messages.

[0071] The extraction unit can extract tasks based on specific keywords or phrases. For example, it can extract messages containing keywords such as "confirm," "respond," or "prepare." The extraction unit can also extract tasks based on the sender or recipient of a message. For example, it can prioritize extracting messages from a supervisor or messages addressed to the user. Furthermore, the extraction unit can analyze the message content and extract tasks based on importance and urgency. This allows for the efficient identification of important tasks by extracting tasks based on specific keywords or phrases. Some or all of the above-described processes 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 the message content into a generative AI and have the generative AI perform task extraction based on importance and urgency.

[0072] The summarization unit can summarize the extracted tasks into a single line. For example, the summarization unit can concisely summarize the content of the extracted tasks. For instance, it can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. The summarization unit can also extract important information about the tasks and incorporate it into the summary. For example, it can include the task's deadline and priority in the summary. Furthermore, the summarization unit can use natural language processing techniques to express the task content concisely. This allows for quick determination of which tasks should be prioritized by summarizing the extracted tasks into a single line. Some or all of the above processing in the summarization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the summarization unit can input the content of the extracted tasks into a generative AI and have the generative AI perform the process of summarizing them into a single line.

[0073] The aggregation unit can display summarized tasks on a single management screen. For example, the aggregation unit can display summarized tasks in a list. For example, the aggregation unit can display the task content along with a label indicating which tool extracted it from. The aggregation unit can also adjust the display order based on task priority. For example, it can display high-priority tasks at the top. Furthermore, the aggregation unit has a function that automatically removes tasks from the list when they are completed. This allows users to always know the latest task status. By displaying summarized tasks on a single management screen, it is possible to prevent tasks from being overlooked. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the aggregation unit can input summarized tasks into a generation AI and have the generation AI execute the process of displaying them on the management screen.

[0074] The aggregation unit can display the task content along with a label indicating the tool from which it was extracted. For example, the aggregation unit can display labels such as email and group chat tools along with the task content. The aggregation unit can also customize the type and display position of the labels. For example, it can change the color and font of the labels. This allows for quick identification of the origin of tasks by displaying the tool from which they were extracted along with the task content. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the aggregation unit can input the task content and label information into a generation AI and have the generation AI display the labels.

[0075] The aggregation unit can automatically remove tasks from the list when they are completed. For example, the aggregation unit can detect task completion and automatically remove it from the list. The aggregation unit can also monitor task completion status in real time and immediately remove completed tasks from the list. This ensures that the latest task status is always known by automatically removing tasks from the list when they are completed. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or not using a generation AI. For example, the aggregation unit can input the task completion status to a generation AI and have the generation AI perform the removal from the list.

[0076] The reading unit can estimate the user's emotions and adjust the timing of message reading based on the estimated emotions. For example, if the user is stressed, the reading unit's generating AI can delay message reading until the user is relaxed. Alternatively, if the user is focused, the reading unit can have the generating AI read the message immediately and quickly extract important tasks. Furthermore, if the user is tired, the reading unit can have the generating AI temporarily stop message reading and resume after the user has rested. This reduces user stress by adjusting the timing of message reading based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating 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 reading unit may be performed using or without a generating AI. For example, the reading unit can input user emotion data into a generating AI and have the generating AI adjust the reading timing based on emotions.

[0077] The reading unit can select the optimal reading method by referring to the user's past message history when reading a message. For example, the reading unit may prioritize reading messages from people the user has frequently communicated with in the past. It can also prioritize reading messages containing keywords that the user has previously deemed important. Furthermore, the reading unit can learn patterns of messages the user has ignored in the past and postpone similar messages. This allows the reading unit to select the optimal reading method by referring to the user's past message history. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reading unit can input the user's past message history into a generative AI and have the generative AI select the optimal reading method.

[0078] The reading unit can filter messages based on the user's current projects and areas of interest when reading them. For example, the reading unit can prioritize reading messages related to projects the user is currently working on. It can also prioritize reading messages related to topics the user is interested in. Furthermore, the reading unit can filter and read highly relevant messages based on keywords set by the user. This allows the reading unit to prioritize reading highly relevant messages by filtering based on the user's current projects and areas of interest. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reading unit can input the user's project information and areas of interest into a generative AI and have the generative AI perform the filtering.

[0079] The reading unit can estimate the user's emotions and determine the priority of messages to read based on the estimated emotions. For example, if the user is stressed, the reading unit's generating AI can postpone less important messages. Conversely, if the user is relaxed, the reading unit can have the generating AI read all messages equally. Furthermore, if the user is in a hurry, the reading unit can have the generating AI prioritize reading urgent messages. This allows for the priority of important messages by determining the priority of messages based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating 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 reading unit may be performed using or without a generating AI. For example, the reading unit can input user emotion data into a generating AI and have the generating AI determine the priority of messages based on emotions.

[0080] The reading unit can prioritize reading messages that are highly relevant by considering the user's geographical location when reading messages. For example, if the user is in a specific location, the reading unit will prioritize reading messages related to that location. Furthermore, if the user is on a business trip, the reading unit can prioritize reading messages related to the destination. Additionally, if the user is at home, the reading unit can prioritize reading messages related to home. This allows the reading unit to prioritize reading highly relevant messages by considering the user's geographical location. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reading unit can input the user's geographical location information into a generative AI and cause the generative AI to prioritize reading highly relevant messages.

[0081] The reading unit can analyze the user's social media activity and read relevant messages when reading messages. For example, the reading unit can prioritize reading messages related to topics the user has mentioned on social media. It can also prioritize reading messages from people or groups the user follows. Furthermore, it can prioritize reading messages related to events the user has participated in on social media. In this way, by analyzing the user's social media activity, it is possible to prioritize reading relevant messages. Some or all of the above processing in the reading unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reading unit can input the user's social media activity data into a generative AI and have the generative AI perform the reading of relevant messages.

[0082] 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 generation AI can extract only high-priority tasks. If the user is relaxed, the generation AI can also extract all tasks equally. Furthermore, if the user is in a hurry, the generation AI can prioritize the extraction of urgent tasks. This allows for the efficient extraction of important tasks by adjusting the task extraction criteria based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation 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 or without a generation AI. For example, the extraction unit can input user emotion data into a generation AI and have the generation AI adjust the task extraction criteria based on emotions.

[0083] The extraction unit can improve the accuracy of task extraction by considering the interrelationships between messages. For example, the extraction unit can analyze the reply relationships between messages and extract related tasks in a batch. It can also analyze the quoted portion of messages and extract tasks in relation to the original message. Furthermore, the extraction unit can analyze the thread structure of messages and extract tasks for the entire thread. This allows for efficient extraction of related tasks by considering the interrelationships between messages. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input message interrelationship data into a generation AI and have the generation AI perform task extraction.

[0084] The extraction unit can extract tasks while considering the attribute information of the message sender. For example, if the message sender is a superior, the extraction unit will extract tasks of high importance. The extraction unit can also extract related tasks if the message sender is a colleague. Furthermore, if the message sender is an external business partner, the extraction unit can extract tasks of high urgency. In this way, important tasks can be efficiently extracted by considering the attribute information of the message sender. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input the attribute information of the message sender into the generation AI and have the generation AI perform task extraction.

[0085] The extraction unit can estimate the user's emotions and determine the priority of tasks to extract based on the estimated emotions. For example, if the user is stressed, the generation AI can postpone less important tasks. If the user is relaxed, the generation AI can extract all tasks evenly. Furthermore, if the user is in a hurry, the generation AI can prioritize the extraction of urgent tasks. This allows important tasks to be processed preferentially by determining task priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation 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 or without a generation AI. For example, the extraction unit can input user emotion data into a generation AI and have the generation AI perform the task prioritization based on emotions.

[0086] The extraction unit can extract tasks while considering the geographical distribution of messages. For example, if the message sender is nearby, the extraction unit may extract tasks as high urgency. Similarly, if the message sender is far away, the extraction unit may extract tasks as high importance. Furthermore, if the message sender is in a specific region, the extraction unit may extract tasks related to that region. This allows for the efficient extraction of highly relevant tasks by considering the geographical distribution of messages. 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 geographical distribution data of messages into a generative AI and have the generative AI perform task extraction.

[0087] The extraction unit can improve the accuracy of task extraction by referring to relevant literature in the message. For example, the extraction unit can analyze the literature cited in the message and extract relevant tasks. The extraction unit can also refer to literature related to the content of the message and evaluate the importance of the tasks. Furthermore, the extraction unit can determine the urgency of the tasks based on the literature referenced by the message sender. In this way, the accuracy of task extraction can be improved by referring to relevant literature in the message. 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 the relevant literature data of the message into a generative AI and have the generative AI perform task extraction.

[0088] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated emotions. For example, if the user is stressed, the summarization unit's generating AI can provide a concise and clear summary. If the user is relaxed, the summarization unit's generating AI can provide a summary containing more detailed information. Furthermore, if the user is in a hurry, the summarization unit's generating AI can provide a short, to-the-point summary. This allows the system to provide the optimal summary for the user by adjusting the way the summary is presented based on their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the summarization unit may be performed using a generating AI, or not. For example, the summarization unit can input user emotion data into a generating AI and have the generating AI adjust the way the summary is presented based on the emotion.

[0089] The summarization unit can adjust the level of detail in a summary based on the importance of the task during summary generation. For example, the summarization unit can generate a detailed summary for high-importance tasks. It can also generate a concise summary for low-importance tasks. Furthermore, it can generate a short, to-the-point summary for urgent tasks. This allows for a detailed understanding of important tasks by adjusting the level of detail in the summary based on the importance of the task. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0090] The summarization unit can apply different summarization algorithms depending on the task category when generating summaries. For example, for project management tasks, the summarization unit can generate summaries that reflect the project's progress. It can also generate summaries that reflect message exchanges for communication tasks. Furthermore, for document review tasks, it can generate summaries that reflect the review's progress. This allows for the generation of optimal summaries for each category by applying different summarization algorithms depending on the task category. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task category data into a generation AI and have the generation AI apply the summarization algorithm.

[0091] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated emotions. For example, if the user is stressed, the summarization unit can use a generating AI to provide a short, concise summary. If the user is relaxed, the summarization unit can use a generating AI to provide a longer summary containing more detailed information. Furthermore, if the user is in a hurry, the summarization unit can use a generating AI to provide a concise and quickly understandable summary. By adjusting the length of the summary based on the user's emotions, the summarization unit can provide a summary of the optimal length for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using a generating AI, or not. For example, the summarization unit can input user emotion data into a generating AI and have the generating AI adjust the length of the summary based on the emotions.

[0092] The summarization unit can determine the priority of summaries based on the task submission dates when generating summaries. For example, the summarization unit will prioritize generating summaries for tasks with approaching deadlines. It can also postpone generating summaries for tasks with distant submission dates. Furthermore, for tasks with unknown submission dates, the summarization unit can generate summaries after other tasks have been completed. This allows for prioritizing urgent tasks by determining the priority of summaries based on their submission dates. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task submission date data into a generation AI and have the generation AI determine the priority of summaries.

[0093] The summarization unit can adjust the order of summaries based on the relevance of tasks during the summarization process. For example, the summarization unit can prioritize the generation of summaries for highly relevant tasks. It can also postpone the generation of summaries for less relevant tasks. Furthermore, for tasks whose relevance is unknown, the summarization unit can generate summaries for them after the summaries for other tasks have been completed. This allows for the prioritization of highly relevant tasks by adjusting the order of summaries based on the relevance of tasks. Some or all of the above processing in the summarization unit may be performed using, for example, a generation AI, or without a generation AI. For example, the summarization unit can input task relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0094] The aggregation unit can estimate the user's emotions and adjust the display method of the aggregation based on the estimated user emotions. For example, if the user is stressed, the aggregation unit can use a generating AI to provide a simple and highly visible display method. The aggregation unit can also provide a display method that includes detailed information if the user is relaxed. Furthermore, if the user is in a hurry, the aggregation unit can use a generating AI to provide a concise display method. This allows the aggregation unit to provide the optimal display method for the user by adjusting the display method of the aggregation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the aggregation unit may be performed using a generating AI, or not. For example, the aggregation unit can input user emotion data into a generating AI and have the generating AI perform emotion-based display method adjustments.

[0095] The aggregation unit can optimize the current aggregation method by referring to past aggregation data during aggregation. For example, the aggregation unit can analyze past aggregation data and apply the most efficient aggregation method. The aggregation unit can also learn and apply the display format preferred by the user from past aggregation data. Furthermore, the aggregation unit can provide an aggregation method tailored to the user's work pattern based on past aggregation data. This allows the current aggregation method to be optimized by referring to past aggregation data. Some or all of the above processing in the aggregation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the aggregation unit can input past aggregation data into a generative AI and have the generative AI perform the optimization of the current aggregation method.

[0096] The aggregation unit can apply different aggregation methods to each task category during aggregation. For example, for project management tasks, the aggregation unit aggregates them by project. For communication tasks, it can aggregate them by message exchange. Furthermore, for document review tasks, it can aggregate them by review progress. This allows for optimal aggregation for each category by applying different aggregation methods to each task category. Some or all of the above processing in the aggregation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the aggregation unit can input task category data into a generative AI and have the generative AI apply the aggregation method.

[0097] The aggregation unit can estimate the user's emotions and determine aggregation priorities based on the estimated emotions. For example, if the user is stressed, the aggregation unit's generative AI can postpone less important tasks. If the user is relaxed, the aggregation unit can also have the generative AI aggregate all tasks evenly. Furthermore, if the user is in a hurry, the aggregation unit can have the generative AI prioritize the aggregation of high-priority tasks. This allows for the prioritization of important tasks by determining aggregation priorities based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The 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 the aggregation unit may be performed using or without the generative AI. For example, the aggregation unit can input user emotion data into the generative AI and have the generative AI perform emotion-based aggregation prioritization.

[0098] The aggregation unit can adjust the aggregation order based on the task submission dates during aggregation. For example, the aggregation unit will prioritize aggregation of tasks with approaching deadlines. It can also postpone the aggregation of tasks with later submission dates. Furthermore, it can aggregate tasks with unknown submission dates after the aggregation of other tasks is complete. This allows for the prioritization of urgent tasks by adjusting the aggregation order based on task submission dates. Some or all of the above processing in the aggregation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the aggregation unit can input task submission date data into a generation AI and have the generation AI perform the adjustment of the aggregation order.

[0099] The aggregation unit can perform aggregation by referring to relevant market data for tasks. For example, the aggregation unit can prioritize the aggregation of highly relevant tasks based on market data. The aggregation unit can also extract and aggregate tasks related to the user's work from market data. Furthermore, the aggregation unit can analyze market data and aggregate tasks that are optimal for the user's work. This allows for the efficient aggregation of highly relevant tasks by referring to relevant market data for tasks. Some or all of the above processing in the aggregation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the aggregation unit can input relevant market data into a generative AI and have the generative AI perform the task aggregation.

[0100] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0101] A task management system can also include a notification function. This notification function can estimate the user's emotions and adjust the timing and method of notifications based on those emotions. For example, if the user is stressed, the notification function will be less frequent and only notify about important tasks. Conversely, if the user is relaxed, the notification function can notify about all tasks. Furthermore, if the user is in a hurry, the notification function can prioritize notifications for high-priority tasks. By adjusting the timing and method of notifications based on the user's emotions, the system can reduce the user's burden and achieve efficient task management.

[0102] A task management system can also include a feedback function. This feedback function can estimate the user's emotions and adjust the content and method of feedback based on those emotions. For example, if the user is stressed, the feedback function will prioritize providing positive feedback. If the user is relaxed, the feedback function can provide detailed feedback. Furthermore, if the user is in a hurry, the feedback function can provide concise and to-the-point feedback. By adjusting the content and method of feedback based on the user's emotions, this system can maintain user motivation and achieve efficient task management.

[0103] The task management system can also include a learning component. This component can estimate the user's emotions and adjust the learning progress based on those emotions. For example, if the user is stressed, the learning component will slow down the learning process and resume it when the user is relaxed. Conversely, if the user is relaxed, the learning component can accelerate the learning process. Furthermore, if the user is in a hurry, the learning component can prioritize learning the most important points. This allows for efficient learning by adjusting the learning progress based on the user's emotions.

[0104] The task management system can also include a reminder function. This reminder function can estimate the user's emotions and adjust the frequency and content of reminders based on those emotions. For example, if the user is stressed, the reminder function will reduce the frequency of reminders and only remind users of important tasks. Conversely, if the user is relaxed, the reminder function can remind users of all tasks. Furthermore, if the user is in a hurry, the reminder function can prioritize reminders of urgent tasks. By adjusting the frequency and content of reminders based on the user's emotions, this reduces the user's burden and enables efficient task management.

[0105] The task management system can also include an assistant unit. This assistant unit can estimate the user's emotions and adjust its response based on those emotions. For example, if the user is stressed, the assistant unit will use gentle language and encourage the user. If the user is relaxed, the assistant unit can provide detailed information. Furthermore, if the user is in a hurry, the assistant unit can provide concise and quick responses. By adjusting the assistant unit's response based on the user's emotions, the system can reduce the user's burden and achieve efficient task management.

[0106] The task management system can also include a calendar function. This calendar function can automatically retrieve the user's schedule and suggest an optimal schedule based on task deadlines and importance. For example, it can detect the user's free time and assign tasks to those times. Furthermore, if the user's schedule is full, the calendar function can adjust task priorities, scheduling important tasks first. Additionally, if there are changes to the user's schedule, the calendar function can automatically readjust task schedules. This enables optimal task management based on the user's schedule.

[0107] A task management system can also include an analysis unit. This unit can analyze the user's task completion status and propose efficient task management methods. For example, it can analyze which tasks the user is spending the most time on and suggest efficient task allocation methods. It can also analyze the user's task completion rate and suggest areas for improvement. Furthermore, it can analyze the user's task management patterns and propose the optimal task management method. This enables efficient task management based on the user's task completion status.

[0108] A task management system can also include a shared section. This section allows users to share tasks with other users and manage them collaboratively. For example, a shared section can be used to share tasks within a project team and track each member's progress in real time. It can also assign tasks to specific members, clearly defining their roles. Furthermore, the shared section can automatically send notifications based on task progress, streamlining task management for the entire team. This enables efficient task management by allowing users to share tasks with others.

[0109] The task management system can also include a customization section. This customization section allows users to customize the task management system's settings according to their preferences. For example, the customization section allows users to set their preferred display format and notification methods. It also allows users to set their preferred task classification methods. Furthermore, the customization section allows users to add or remove functions from the task management system according to their work content. This enables efficient task management by customizing the task management system to suit user preferences.

[0110] The task management system can also include a prediction unit. This unit analyzes the user's past task completion data and predicts future task completion. For example, it can predict future task completion times based on the user's past task completion times. It can also predict future task completion rates based on the user's past task completion rates. Furthermore, it can suggest future task management methods based on the user's past task management patterns. This enables efficient task management by predicting future task completion based on the user's past task completion data.

[0111] The following briefly describes the processing flow for example form 2.

[0112] Step 1: The reading unit reads the received messages. For example, it can automatically import data from email or group chat tools. The reading unit periodically scans the email inbox to detect new messages. It can also use the API of a group chat tool to retrieve messages in real time. Furthermore, it can import messages based on specific trigger events (for example, the arrival of a new message). Step 2: The extraction unit extracts messages that are relevant to the user or require action from the messages read by the reading unit. For example, tasks can be extracted based on specific keywords or phrases. The extraction unit extracts messages containing keywords such as "confirm," "respond," and "prepare." Tasks can also be extracted based on the sender or recipient of the message. For example, messages from a supervisor or messages addressed to the user can be prioritized. Furthermore, the content of the messages can be analyzed, and tasks can be extracted based on importance and urgency. Step 3: The summarization section summarizes the tasks extracted by the extraction section into a single line. For example, it can concisely summarize the content of the extracted tasks. The summarization section can summarize tasks such as "Please review the invoice" or "Please prepare for the next meeting" into a single line. It can also extract important information about the tasks and reflect it in the summary. For example, it can include the task's deadline or priority in the summary. Furthermore, natural language processing techniques can be used to express the content of the tasks concisely. Step 4: The aggregation section consolidates the tasks summarized by the summarization section into a single management screen. For example, summarized tasks can be displayed in a list. The aggregation section displays the task content along with a label indicating which tool extracted the task. It can also adjust the display order based on task priority. For example, tasks with higher importance can be displayed at the top. Furthermore, it has a function that automatically removes tasks from the list when they are completed. This allows you to always keep track of the latest task status.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] Each of the multiple elements described above, including the reading unit, extraction unit, summarization unit, and aggregation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the reading unit is implemented by the computer 36 of the smart device 14 and automatically retrieves data from email or group chat tools. The extraction unit is implemented by the specific processing unit 290 of the data processing device 12 and extracts tasks from the read messages. The summarization unit is implemented by the control unit 46A of the smart device 14 and summarizes the extracted tasks into a single line. The aggregation unit is implemented by the specific processing unit 290 of the data processing device 12 and aggregates the summarized tasks into a single management screen. 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.

[0117] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] Each of the multiple elements described above, including the reading unit, extraction unit, summarization unit, and aggregation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the reading unit is implemented by the computer 36 of the smart glasses 214 and automatically retrieves data from email and group chat tools. The extraction unit is implemented by the identification processing unit 290 of the data processing device 12 and extracts tasks from the read messages. The summarization unit is implemented by the control unit 46A of the smart glasses 214 and summarizes the extracted tasks into a single line. The aggregation unit is implemented by the identification processing unit 290 of the data processing device 12 and aggregates the summarized tasks into a single management screen. 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.

[0133] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements described above, including the reading unit, extraction unit, summarization unit, and aggregation unit, is implemented in at least one of the headset terminal 314 and the data processing device 12. For example, the reading unit is implemented by the computer 36 of the headset terminal 314 and automatically retrieves data from email and group chat tools. The extraction unit is implemented by the specific processing unit 290 of the data processing device 12 and extracts tasks from the read messages. The summarization unit is implemented by the control unit 46A of the headset terminal 314 and summarizes the extracted tasks into a single line. The aggregation unit is implemented by the specific processing unit 290 of the data processing device 12 and aggregates the summarized tasks into a single management screen. 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.

[0149] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] Each of the multiple elements described above, including the reading unit, extraction unit, summarization unit, and aggregation unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the reading unit is implemented by the computer 36 of the robot 414 and automatically retrieves data from email or group chat tools. The extraction unit is implemented by the specific processing unit 290 of the data processing unit 12 and extracts tasks from the read messages. The summarization unit is implemented by the control unit 46A of the robot 414 and summarizes the extracted tasks into a single line. The aggregation unit is implemented by the specific processing unit 290 of the data processing unit 12 and aggregates the summarized tasks into a single management screen. 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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."

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] (Note 1) A reading unit that reads the received message, An extraction unit extracts messages from the reading unit that are relevant to the user or require action, A summarization unit that summarizes the tasks extracted by the extraction unit into one line, The system includes an aggregation unit that aggregates the tasks summarized by the summarization unit into a single management screen. A system characterized by the following features. (Note 2) The reading unit is Automatically import data from email and group chat tools. The system described in Appendix 1, characterized by the features described herein. (Note 3) The extraction unit is Extract tasks based on specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 4) The summary section above is, Summarize the extracted tasks in one line. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned aggregation unit is Display summarized tasks in a single management screen. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned aggregation unit is The task content is displayed along with a label indicating which tool was used to extract the data. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned aggregation unit is Tasks are automatically removed from the list when completed. The system described in Appendix 1, characterized by the features described herein. (Note 8) The reading unit is It estimates the user's emotions and adjusts the timing of message delivery based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The reading unit is When reading a message, the system refers to the user's past message history to select the optimal reading method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The reading unit is When reading messages, filtering is performed based on the user's current projects and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The reading unit is It estimates the user's emotions and determines the priority of messages to read based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The reading unit is When reading messages, the system prioritizes reading the most relevant messages by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The reading unit is When reading messages, the system analyzes the user's social media activity and identifies relevant messages. The system described in Appendix 1, characterized by the features described herein. (Note 14) 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 15) The extraction unit is When extracting tasks, consider the interrelationships between messages to improve the accuracy of the extraction. The system described in Appendix 1, characterized by the features described herein. (Note 16) The extraction unit is When extracting tasks, the attribute information of the message sender is taken into consideration during the extraction process. The system described in Appendix 1, characterized by the features described herein. (Note 17) The extraction unit is Estimate the user's emotions and determine the priority of tasks to extract based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The extraction unit is When extracting tasks, the geographical distribution of messages should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The extraction unit is When extracting tasks, refer to related literature for messages to improve the accuracy of the extraction. The system described in Appendix 1, characterized by the features described herein. (Note 20) The summary section above is, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the task. The system described in Appendix 1, characterized by the features described herein. (Note 22) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the task category. The system described in Appendix 1, characterized by the features described herein. (Note 23) The summary section above is, It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The summary section above is, When generating summaries, prioritize summaries based on the task submission date. The system described in Appendix 1, characterized by the features described herein. (Note 25) The summary section above is, When generating summaries, adjust the order of summaries based on the relevance of the tasks. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned aggregation unit is It estimates the user's emotions and adjusts how aggregated information is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned aggregation unit is During aggregation, the current aggregation method is optimized by referring to past aggregation data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned aggregation unit is During aggregation, different aggregation methods are applied to each task category. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned aggregation unit is The system estimates user sentiment and determines aggregation priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned aggregation unit is During aggregation, the aggregation order will be adjusted based on the submission date of the tasks. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned aggregation unit is During aggregation, relevant market data for each task is referenced. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0185] 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 reading unit that reads the received message, An extraction unit extracts messages from the reading unit that are relevant to the user or require action, A summarization unit that summarizes the tasks extracted by the extraction unit into one line, The system includes an aggregation unit that aggregates the tasks summarized by the summarization unit into a single management screen. A system characterized by the following features.

2. The reading unit is Automatically import data from email and group chat tools. The system according to feature 1.

3. The extraction unit is Extract tasks based on specific keywords or phrases. The system according to feature 1.

4. The summary section above is, Summarize the extracted tasks in one line. The system according to feature 1.

5. The aforementioned aggregation unit is Display summarized tasks in a single management screen. The system according to feature 1.

6. The aforementioned aggregation unit is The task content is displayed along with a label indicating which tool was used to extract the data. The system according to feature 1.

7. The aforementioned aggregation unit is Tasks are automatically removed from the list when completed. The system according to feature 1.

8. The reading unit is It estimates the user's emotions and adjusts the timing of message delivery based on the estimated emotions. The system according to feature 1.

Images