system

Abstract

The system according to this embodiment aims to streamline email processing and generate quick and appropriate replies based on urgency and importance. [Solution] The system according to the embodiment comprises a collection unit, a summarization unit, a notification unit, a priority setting unit, a reply generation unit, and a scheduling unit. The collection unit retrieves emails from an email client. The summarization unit summarizes the content of the emails retrieved by the collection unit. The notification unit notifies the chat tool of the content summarized by the summarization unit. The priority setting unit sets the urgency and importance based on the content notified by the notification unit. The reply generation unit generates a reply based on the urgency and importance set by the priority setting unit. The scheduling unit schedules the sending of the reply generated by the reply generation unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 takes a lot of time to process emails, it is difficult to judge urgency and importance, and it is difficult to create a prompt and appropriate reply.

[0005] The system according to the embodiment aims to improve the efficiency of email processing and generate a prompt and appropriate reply based on urgency and importance.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a summarization unit, a notification unit, a priority setting unit, a reply generation unit, and a scheduling unit. The collection unit retrieves emails from an email client. The summarization unit summarizes the content of the emails retrieved by the collection unit. The notification unit notifies the chat tool of the content summarized by the summarization unit. The priority setting unit sets the urgency and importance based on the content notified by the notification unit. The reply generation unit generates a reply based on the urgency and importance set by the priority setting unit. The scheduling unit schedules the sending of the reply generated by the reply generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline email processing and generate quick and appropriate replies based on urgency and importance. [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 numbered 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 applicable 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 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 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 email agent system according to an embodiment of the present invention is a system that utilizes AI to streamline email processing, determine urgency and importance, and support the creation of quick and appropriate replies. This email agent system retrieves emails from an email client, and the AI ​​summarizes the sender, content, and subject and notifies the user. This allows the user to quickly grasp the content of the email. Next, it integrates with a chat tool and displays the summary in a dedicated channel. The AI ​​sets priorities based on the urgency and importance of the email. This allows the user to process important emails with priority. Furthermore, the generation AI automatically generates contextually appropriate replies. The user can select and adjust the tone of the replies. The generated replies are scheduled to be sent at a specified time. This allows the user to respond in a manner appropriate to business etiquette. This system streamlines email management and significantly reduces email processing time through summarization and prioritization. In addition, contextually appropriate replies and scheduled sending enable flexible communication support. Furthermore, setting reminders for subsequent tasks and automatic email classification can be expected to improve task management and organization. For example, a user retrieves emails from Outlook, and AI summarizes them and displays them in a dedicated channel on the communication platform. The AI ​​determines the urgency and importance of the emails and sets priorities. The user reviews the automatically generated reply, selects and adjusts the tone. The reply is scheduled to be sent at a specified time. This allows users to process emails efficiently and respond in a manner appropriate to business etiquette. In this way, the email agent system can help streamline email processing, determine urgency and importance, and create quick and appropriate replies.

[0029] The email agent system according to this embodiment comprises a collection unit, a summarization unit, a notification unit, a priority setting unit, a reply generation unit, and a scheduling unit. The collection unit retrieves emails from email clients. The collection unit can retrieve emails from, for example, Outlook or Gmail. The summarization unit summarizes the content of the emails retrieved by the collection unit. The summarization unit can summarize, for example, the sender, content, and subject. The notification unit notifies a chat tool of the content summarized by the summarization unit. The notification unit can display the summary in a dedicated channel of a communication tool or communication platform, for example. The priority setting unit sets urgency and importance based on the content notified by the notification unit. The priority setting unit can set priorities based on the urgency and importance of the emails, for example. The reply generation unit generates a reply based on the urgency and importance set by the priority setting unit. The reply generation unit can automatically generate a contextually appropriate reply, for example. The scheduling unit schedules the sending of the reply generated by the reply generation unit. The scheduling unit can schedule the sending of the generated reply at a specified time, for example. As a result, the email agent system according to this embodiment can efficiently retrieve, summarize, notify, prioritize, generate replies, and schedule emails.

[0030] The collection unit retrieves emails from email clients. For example, it can retrieve emails from Outlook or Gmail. Specifically, the collection unit uses email protocols such as IMAP and POP3 to access the user's mailbox and retrieve new and unread emails. This allows the collection unit to retrieve emails from various email services, regardless of the email client the user is using. Furthermore, the collection unit has a function to periodically check the mailbox and immediately retrieve new emails as soon as they arrive. This allows users to view email content in real time. The collection unit also has a database for temporarily storing retrieved emails, enabling subsequent processing departments to efficiently access the email data. When retrieving emails, the collection unit securely manages user authentication information and uses encryption technology to ensure security. This ensures reliable email retrieval while protecting user privacy.

[0031] The summarization unit summarizes the content of emails obtained by the collection unit. For example, the summarization unit can summarize the sender, content, and subject. Specifically, it uses natural language processing techniques to extract key parts of the email body and generate a concise summary. For instance, it extracts keywords and important phrases from the email body and combines them to create a summary. The summarization unit also analyzes the email sender and subject and includes them in the summary, enabling users to quickly grasp the email's main points. Furthermore, the summarization unit can apply different summarization methods depending on the email's content. For example, it might emphasize important instructions and requests in business emails, or focus on emotional and relationship-related information in personal emails. The summarization unit also has the functionality to evaluate the quality of the generated summary and make corrections as needed. This allows the summarization unit to provide users with useful information concisely and help them quickly understand the email's content.

[0032] The notification unit notifies the chat tool of the content summarized by the summarization unit. For example, the notification unit can display the summary in a dedicated channel on a communication tool or communication platform. Specifically, the notification unit sends the summary text received from the summarization unit using the API of the designated chat tool. This allows users to view email summaries on the chat tool without opening their email client. The notification unit can adjust the timing and frequency of notifications according to the user's settings. For example, it can notify immediately when an important email arrives, and notify users of regular emails in batches at regular intervals. The notification unit can also include links in the notification content, allowing users to easily view detailed email content. Furthermore, the notification unit has a function to set notification priorities, and can notify users of high-priority emails using special notification methods. In this way, the notification unit can help users efficiently manage their emails without missing important emails.

[0033] The priority setting unit sets urgency and importance based on the content notified by the notification unit. For example, the priority setting unit can set priorities based on the urgency and importance of an email. Specifically, the priority setting unit analyzes the email sender, subject, content, and past email history to evaluate the importance and urgency of the email. For example, emails from a supervisor or project-related emails are set to high priority, while advertising emails and newsletters are set to low priority. The priority setting unit uses AI to analyze the content of emails and automatically sets contextual priorities. Furthermore, the priority setting unit can learn the user's past email processing patterns and set priorities according to the user's preferences. This allows the priority setting unit to enable users to respond quickly to important emails and improve the efficiency of email management. The priority setting unit also has a function to adjust the display order and notification method of emails based on the set priorities. This allows users to check the most important emails first and respond quickly.

[0034] The reply generation unit generates replies based on the urgency and importance set by the priority setting unit. For example, the reply generation unit can automatically generate context-appropriate replies. Specifically, it uses AI to analyze the email content and generate appropriate replies. For instance, it automatically creates replies that correspond to the email content, such as acceptance of a request or answers to questions. The reply generation unit learns the user's past reply history and can generate replies that match the user's writing style and expressions. Furthermore, the reply generation unit provides an interface that allows the user to review and edit the generated replies, enabling them to confirm the content before final sending. This reduces the user's burden and helps them provide quick and appropriate replies. The reply generation unit also has a function to present multiple reply options, allowing the user to select the most suitable reply. This enables the user to quickly provide the most appropriate reply for the situation.

[0035] The scheduling unit schedules the sending of replies generated by the reply generation unit. For example, the scheduling unit can schedule the sending of generated replies to a specified time. Specifically, the scheduling unit works in conjunction with the user's calendar or schedule to calculate the optimal sending time. For example, if the user is in a meeting or on vacation, the sending of the reply can be delayed to an appropriate time. The scheduling unit can also manually set the sending date and time of the reply based on the user's instructions. Furthermore, the scheduling unit has a function to display a list of emails scheduled to be sent, allowing the user to check the sending schedule at a glance. This enables the user to efficiently manage emails scheduled to be sent and reply at the appropriate time. The scheduling unit also has a function to set reminders before sending to ensure that emails scheduled to be sent are sent reliably. This enables the user to respond reliably without forgetting to send important emails.

[0036] The collection unit can retrieve emails from Outlook and Gmail. For example, the collection unit retrieves emails from Outlook and Gmail. This allows it to support a wide range of email clients.

[0037] The summary section can summarize the sender, content, and subject. For example, the summary section summarizes the sender, content, and subject. This allows for a quick understanding of the email's content by summarizing the sender, content, and subject.

[0038] The notification unit can display summaries in dedicated channels of communication tools and communication platforms. For example, the notification unit can display summaries in dedicated channels of communication tools and communication platforms. This makes it easier to share the content of emails by displaying summaries in dedicated channels of communication tools and communication platforms.

[0039] The priority setting unit can set priorities based on the urgency and importance of emails. For example, the priority setting unit sets priorities based on the urgency and importance of emails. This allows important emails to be processed preferentially.

[0040] The reply generation unit can automatically generate reply text appropriate to the context. For example, the reply generation unit automatically generates reply text appropriate to the context. This enables quick and appropriate replies by automatically generating context-appropriate replies.

[0041] The scheduling function allows you to schedule the sending of generated replies to a specified time. For example, the scheduling function can schedule the sending of generated replies to a specified time. This allows for responses that are in line with business etiquette by scheduling the sending of generated replies to a specified time.

[0042] The collection unit can analyze the user's past email processing history and select the optimal retrieval method. For example, the collection unit can prioritize retrieving emails from senders that the user has frequently opened in the past. The collection unit can also learn patterns of emails that the user has previously deemed important and prioritize retrieving similar emails. Furthermore, if the collection unit has a tendency to process emails during specific time periods in the past, it can also retrieve emails during those times. This allows the optimal retrieval method to be selected by analyzing the user's past email processing history. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's past email processing history data into a generating AI and have the generating AI select the optimal retrieval method.

[0043] The collection unit can filter emails based on the user's current projects and areas of interest when retrieving them. For example, the collection unit can prioritize retrieving emails related to projects the user is currently working on. The collection unit can also filter and retrieve emails related to topics the user has shown interest in. Furthermore, the collection unit can prioritize retrieving emails that contain specific keywords the user has used. This allows for the priority retrieval of highly relevant emails by filtering based on the user's current projects and areas of interest. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, the collection unit can input data on the user's projects and areas of interest into a generating AI and have the generating AI perform the filtering.

[0044] The collection unit can prioritize the retrieval of highly relevant emails by considering the user's geographical location information when acquiring emails. For example, if the user is in a specific region, the collection unit will prioritize the retrieval of emails related to that region. Furthermore, if the user is on a business trip, the collection unit can prioritize the retrieval of emails related to the destination. Additionally, if the user is at home, the collection unit can prioritize the retrieval of emails related to home. This allows for the prioritization of highly relevant emails by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location data into a generating AI and have the generating AI retrieve highly relevant emails.

[0045] The collection unit can analyze the user's social media activity when acquiring emails and retrieve relevant emails. For example, the collection unit can prioritize retrieving emails related to topics the user has shown interest in on social media. It can also prioritize retrieving emails from people the user follows on social media. Furthermore, the collection unit can prioritize retrieving emails related to groups the user participates in on social media. In this way, relevant emails can be prioritized by analyzing the user's social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or not using AI. For example, the collection unit can input the user's social media activity data into a generating AI and have the generating AI retrieve relevant emails.

[0046] The summarization unit can adjust the level of detail in the summary based on the importance of the email during summary generation. For example, the summarization unit can provide a detailed summary for high-importance emails. It can also provide a concise summary for low-importance emails. Furthermore, it can provide a quick summary for urgent emails. This allows for a detailed understanding of important email content by adjusting the level of detail in the summary based on the importance of the email. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0047] The summarization unit can apply different summarization algorithms depending on the email category when generating summaries. For example, the summarization unit can apply a business-oriented summarization algorithm to business emails. It can also apply a private-oriented summarization algorithm to private emails. Furthermore, it can apply an advertising-oriented summarization algorithm to advertising emails. This allows for the provision of summaries appropriate to each category by applying different summarization algorithms depending on the email category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email category data into a generation AI and have the generation AI execute the application of the summarization algorithm.

[0048] The summarization unit can determine the priority of summaries based on when the emails were received during the summarization process. For example, the summarization unit may prioritize summarizing recently received emails. It can also prioritize summarizing emails received immediately before an important event. Furthermore, the summarization unit may prioritize summarizing emails received by the user during a specific time period. This allows for prioritizing the summarization of the most recent emails by determining the priority of summarization based on when the emails were received. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email reception data into a generation AI and have the generation AI perform the determination of the summary priority.

[0049] The summarization unit can adjust the order of summaries based on the relevance of the emails during summary generation. For example, the summarization unit can prioritize summarizing highly relevant emails. It can also postpone summarizing less relevant emails. Furthermore, the summarization unit can adjust the order of summaries based on user interests. This allows for prioritizing the summarization of highly relevant emails by adjusting the order of summaries based on their relevance. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0050] The notification unit can select the optimal notification method by referring to the user's past notification history when sending a notification. For example, the notification unit can prioritize providing notification methods that the user has preferred to use in the past. It can also avoid notification methods that the user has ignored in the past. Furthermore, the notification unit can select the optimal notification timing from the user's past notification history. In this way, the optimal notification method can be selected by referring to the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's past notification history data into a generating AI and have the generating AI perform the selection of the optimal notification method.

[0051] The notification unit can apply different notification methods depending on the content of the email when it sends a notification. For example, the notification unit can use push notifications for important emails. It can also use voice notifications for urgent emails. Furthermore, it can use badge notifications for general emails. This allows for appropriate notification of important emails by applying different notification methods depending on the content of the email. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input email content data into a generating AI and have the generating AI perform the application of notification methods.

[0052] The notification unit can select the optimal notification method by considering the user's device information when sending a notification. For example, if the user is using a smartphone, the notification unit can provide a push notification. It can also provide a notification optimized for a larger screen if the user is using a tablet. Furthermore, if the user is using a smartwatch, the notification unit can provide a concise and highly visible notification. This allows the system to select the optimal notification method by considering the user's device information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user device information data into a generating AI and have the generating AI select the optimal notification method.

[0053] The notification unit can adjust the timing of notifications, taking into account the user's schedule. For example, if the user is in a meeting, the notification unit will refrain from sending a notification. It can also prioritize displaying notifications if the user is on a break. Furthermore, the notification unit can select the optimal notification timing based on the user's schedule. This allows for the selection of the best notification timing by considering the user's schedule. Some or all of the above processing in the notification unit may be performed using AI, or without AI. For example, the notification unit can input user schedule data into a generating AI and have the generating AI adjust the timing of notifications.

[0054] The priority setting unit can improve the accuracy of priority settings by considering the relationships between emails. For example, the priority setting unit can set the priority of emails related to the same project all at once. The priority setting unit can also set priorities by considering the relationship between the sender and recipient. Furthermore, the priority setting unit can set priorities by analyzing the relationship between the content of an email and past emails. This improves the accuracy of priority settings by considering the relationships between emails. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input email relationship data into a generating AI and have the generating AI perform the priority accuracy improvement.

[0055] The priority setting unit can set priorities by considering the attribute information of the email sender. For example, the priority setting unit can set a higher priority for emails from important business partners. It can also set a higher priority for emails from superiors. Furthermore, it can also set a higher priority for emails from new customers. This allows for priority processing of emails from important senders by considering the attribute information of the email sender. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input sender attribute information data into a generating AI and have the generating AI perform the priority setting.

[0056] The priority setting unit can set priorities while considering the geographical distribution of emails. For example, the priority setting unit can set a higher priority for emails related to the user's current location. It can also set a higher priority for emails related to the user's business trip destination if the user is on a business trip. Furthermore, it can set a higher priority for emails related to the user's home if the user is at home. This allows for the processing of highly relevant emails with priority, by considering the geographical distribution of emails. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input geographical distribution data of emails into a generating AI and have the generating AI perform the priority setting.

[0057] The priority setting unit can improve the accuracy of priority settings by referring to relevant literature in emails. For example, the priority setting unit sets priority by referring to literature related to the content of the email. The priority setting unit can also set priority by referring to literature cited by the email sender. Furthermore, the priority setting unit can set priority by referring to the latest research related to the content of the email. This improves the accuracy of priority settings by referring to relevant literature in emails. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input relevant literature data into a generating AI and have the generating AI perform the priority accuracy improvement.

[0058] The reply generation unit can adjust the level of detail in the reply based on the importance of the email when generating a reply. For example, the reply generation unit can generate a detailed reply for high-importance emails. It can also generate a concise reply for low-importance emails. Furthermore, it can quickly generate a reply for urgent emails. By adjusting the level of detail in the reply based on the importance of the email, it is possible to provide an appropriate reply to important emails. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the reply.

[0059] The reply generation unit can apply different reply algorithms depending on the email category when generating replies. For example, the reply generation unit can apply a business-oriented reply algorithm to business emails. It can also apply a private-oriented reply algorithm to private emails. Furthermore, it can apply an advertising-oriented reply algorithm to advertising emails. By applying different reply algorithms depending on the email category, it is possible to generate replies appropriate for each category. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email category data into a generation AI and have the generation AI execute the application of the reply algorithm.

[0060] The reply generation unit can determine the priority of replies based on when the email was received. For example, the reply generation unit can prioritize generating replies to recently received emails. It can also prioritize generating replies to emails received immediately before an important event. Furthermore, it can prioritize generating replies to emails received by the user during a specific time period. This allows for quick responses to the latest emails by prioritizing replies based on when the email was received. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email reception data into a generation AI and have the generation AI determine the priority of replies.

[0061] The reply generation unit can adjust the order of replies based on the relevance of the emails when generating replies. For example, the reply generation unit can prioritize generating replies for highly relevant emails. It can also postpone generating replies for less relevant emails. Furthermore, the reply generation unit can adjust the order of replies based on user interests. This allows for priority replies to highly relevant emails by adjusting the order of replies based on email relevance. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email relevance data into a generation AI and have the generation AI perform the adjustment of the order of replies.

[0062] The scheduling unit can select the optimal sending timing by referring to the user's past scheduling history when setting a schedule. For example, the scheduling unit can prioritize sending timings that the user has preferred to use in the past. The scheduling unit can also avoid sending timings that the user has ignored in the past. Furthermore, the scheduling unit can select the optimal sending timing from the user's past scheduling history. In this way, the optimal sending timing can be selected by referring to the user's past scheduling history. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without using AI. For example, the scheduling unit can input the user's past scheduling history data into a generating AI and have the generating AI perform the selection of the optimal sending timing.

[0063] The scheduling unit can apply different sending schedules depending on the content of the email when setting the schedule. For example, the scheduling unit can set an immediate sending schedule for important emails. It can also set a rapid sending schedule for highly urgent emails. Furthermore, the scheduling unit can set a normal sending schedule for general emails. This allows important emails to be sent at the appropriate time by applying different sending schedules depending on the content of the email. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can input email content data into a generating AI and have the generating AI execute the application of the sending schedule.

[0064] The scheduling unit can select the optimal transmission timing by considering the user's device information when setting the schedule. For example, if the user is using a smartphone, the scheduling unit can set the transmission timing using push notifications. The scheduling unit can also set a transmission timing optimized for a larger screen if the user is using a tablet. Furthermore, if the user is using a smartwatch, the scheduling unit can set a concise and highly visible transmission timing. This allows for the selection of the optimal transmission timing by considering the user's device information. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can input user device information data into a generating AI and have the generating AI select the optimal transmission timing.

[0065] The scheduling unit can adjust the sending timing when setting a schedule, taking the user's schedule into consideration. For example, the scheduling unit may refrain from sending if the user is in a meeting. It can also prioritize sending if the user is on a break. Furthermore, the scheduling unit can select the optimal sending timing according to the user's schedule. This allows for the selection of the optimal sending timing by considering the user's schedule. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can input the user's schedule data into a generating AI and have the generating AI perform the adjustment of the sending timing.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The data collection unit can analyze a user's past email processing history and select the optimal retrieval method. For example, it can prioritize retrieving emails from senders that the user has frequently opened in the past. It can also learn patterns of emails that the user has previously deemed important and prioritize retrieving similar emails. Furthermore, if a user tends to process emails at specific times in the past, it can retrieve emails during those times. In this way, by analyzing a user's past email processing history, the optimal retrieval method can be selected.

[0068] The collection unit can filter emails based on the user's current projects and areas of interest. For example, it can prioritize retrieving emails related to projects the user is currently working on. It can also filter and retrieve emails related to topics the user has shown interest in. Furthermore, it can prioritize retrieving emails containing specific keywords the user has used. This allows for the priority retrieval of highly relevant emails by filtering based on the user's current projects and areas of interest.

[0069] The collection unit can prioritize retrieving highly relevant emails by considering the user's geographical location when acquiring emails. For example, if the user is in a specific region, it will prioritize retrieving emails related to that region. Similarly, if the user is on a business trip, it can prioritize retrieving emails related to their destination. Furthermore, if the user is at home, it can prioritize retrieving emails related to their home. This allows for the prioritization of highly relevant emails by considering the user's geographical location.

[0070] The collection unit can analyze the user's social media activity when acquiring emails and retrieve relevant emails. For example, it can prioritize retrieving emails related to topics the user has shown interest in on social media. It can also prioritize retrieving emails from people the user follows on social media. Furthermore, it can prioritize retrieving emails related to groups the user participates in on social media. In this way, by analyzing the user's social media activity, it is possible to prioritize the retrieval of relevant emails.

[0071] The summarization function can adjust the level of detail in a summary based on the importance of the email during the summary generation process. For example, it can provide a detailed summary for high-priority emails and a concise summary for low-priority emails. Furthermore, it can provide a quick summary for urgent emails. This allows users to gain a detailed understanding of important email content by adjusting the level of detail in the summary based on the email's importance.

[0072] The summarization section can apply different summarization algorithms depending on the email category during summary generation. For example, a business-oriented summarization algorithm can be applied to business emails. Similarly, a private-oriented summarization algorithm can be applied to private emails. Furthermore, an advertising-oriented summarization algorithm can be applied to advertising emails. This allows for the provision of summaries tailored to each category by applying different summarization algorithms depending on the email category.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The collection unit retrieves emails from the email client. For example, it can retrieve emails from Outlook or Gmail. Step 2: The summarization unit summarizes the content of the emails obtained by the collection unit. For example, it can summarize the sender, content, and subject. Step 3: The notification unit notifies the chat tool of the content summarized by the summarization unit. For example, the summary can be displayed in a dedicated channel on a communication tool or communication platform. Step 4: The priority setting unit sets the urgency and importance based on the information notified by the notification unit. For example, the priority can be set based on the urgency and importance of the email. Step 5: The reply generation unit generates a reply based on the urgency and importance set by the priority setting unit. For example, it can automatically generate a reply that is appropriate to the context. Step 6: The scheduling unit schedules the sending of the reply text generated by the reply generation unit. For example, the sending of the generated reply text can be scheduled for a specified time.

[0075] (Example of form 2) The email agent system according to an embodiment of the present invention is a system that utilizes AI to streamline email processing, determine urgency and importance, and support the creation of quick and appropriate replies. This email agent system retrieves emails from an email client, and the AI ​​summarizes the sender, content, and subject and notifies the user. This allows the user to quickly grasp the content of the email. Next, it integrates with a chat tool and displays the summary in a dedicated channel. The AI ​​sets priorities based on the urgency and importance of the email. This allows the user to process important emails with priority. Furthermore, the generation AI automatically generates contextually appropriate replies. The user can select and adjust the tone of the replies. The generated replies are scheduled to be sent at a specified time. This allows the user to respond in a manner appropriate to business etiquette. This system streamlines email management and significantly reduces email processing time through summarization and prioritization. In addition, contextually appropriate replies and scheduled sending enable flexible communication support. Furthermore, setting reminders for subsequent tasks and automatic email classification can be expected to improve task management and organization. For example, a user retrieves emails from Outlook, and AI summarizes them and displays them in a dedicated channel on the communication platform. The AI ​​determines the urgency and importance of the emails and sets priorities. The user reviews the automatically generated reply, selects and adjusts the tone. The reply is scheduled to be sent at a specified time. This allows users to process emails efficiently and respond in a manner appropriate to business etiquette. In this way, the email agent system can help streamline email processing, determine urgency and importance, and create quick and appropriate replies.

[0076] The email agent system according to this embodiment comprises a collection unit, a summarization unit, a notification unit, a priority setting unit, a reply generation unit, and a scheduling unit. The collection unit retrieves emails from email clients. The collection unit can retrieve emails from, for example, Outlook or Gmail. The summarization unit summarizes the content of the emails retrieved by the collection unit. The summarization unit can summarize, for example, the sender, content, and subject. The notification unit notifies a chat tool of the content summarized by the summarization unit. The notification unit can display the summary in a dedicated channel of a communication tool or communication platform, for example. The priority setting unit sets urgency and importance based on the content notified by the notification unit. The priority setting unit can set priorities based on the urgency and importance of the emails, for example. The reply generation unit generates a reply based on the urgency and importance set by the priority setting unit. The reply generation unit can automatically generate a contextually appropriate reply, for example. The scheduling unit schedules the sending of the reply generated by the reply generation unit. The scheduling unit can schedule the sending of the generated reply at a specified time, for example. As a result, the email agent system according to this embodiment can efficiently retrieve, summarize, notify, prioritize, generate replies, and schedule emails.

[0077] The collection unit retrieves emails from email clients. For example, it can retrieve emails from Outlook or Gmail. Specifically, the collection unit uses email protocols such as IMAP and POP3 to access the user's mailbox and retrieve new and unread emails. This allows the collection unit to retrieve emails from various email services, regardless of the email client the user is using. Furthermore, the collection unit has a function to periodically check the mailbox and immediately retrieve new emails as soon as they arrive. This allows users to view email content in real time. The collection unit also has a database for temporarily storing retrieved emails, enabling subsequent processing departments to efficiently access the email data. When retrieving emails, the collection unit securely manages user authentication information and uses encryption technology to ensure security. This ensures reliable email retrieval while protecting user privacy.

[0078] The summarization unit summarizes the content of emails obtained by the collection unit. For example, the summarization unit can summarize the sender, content, and subject. Specifically, it uses natural language processing techniques to extract key parts of the email body and generate a concise summary. For instance, it extracts keywords and important phrases from the email body and combines them to create a summary. The summarization unit also analyzes the email sender and subject and includes them in the summary, enabling users to quickly grasp the email's main points. Furthermore, the summarization unit can apply different summarization methods depending on the email's content. For example, it might emphasize important instructions and requests in business emails, or focus on emotional and relationship-related information in personal emails. The summarization unit also has the functionality to evaluate the quality of the generated summary and make corrections as needed. This allows the summarization unit to provide users with useful information concisely and help them quickly understand the email's content.

[0079] The notification unit notifies the chat tool of the content summarized by the summarization unit. For example, the notification unit can display the summary in a dedicated channel on a communication tool or communication platform. Specifically, the notification unit sends the summary text received from the summarization unit using the API of the designated chat tool. This allows users to view email summaries on the chat tool without opening their email client. The notification unit can adjust the timing and frequency of notifications according to the user's settings. For example, it can notify immediately when an important email arrives, and notify users of regular emails in batches at regular intervals. The notification unit can also include links in the notification content, allowing users to easily view detailed email content. Furthermore, the notification unit has a function to set notification priorities, and can notify users of high-priority emails using special notification methods. In this way, the notification unit can help users efficiently manage their emails without missing important emails.

[0080] The priority setting unit sets urgency and importance based on the content notified by the notification unit. For example, the priority setting unit can set priorities based on the urgency and importance of an email. Specifically, the priority setting unit analyzes the email sender, subject, content, and past email history to evaluate the importance and urgency of the email. For example, emails from a supervisor or project-related emails are set to high priority, while advertising emails and newsletters are set to low priority. The priority setting unit uses AI to analyze the content of emails and automatically sets contextual priorities. Furthermore, the priority setting unit can learn the user's past email processing patterns and set priorities according to the user's preferences. This allows the priority setting unit to enable users to respond quickly to important emails and improve the efficiency of email management. The priority setting unit also has a function to adjust the display order and notification method of emails based on the set priorities. This allows users to check the most important emails first and respond quickly.

[0081] The reply generation unit generates replies based on the urgency and importance set by the priority setting unit. For example, the reply generation unit can automatically generate context-appropriate replies. Specifically, it uses AI to analyze the email content and generate appropriate replies. For instance, it automatically creates replies that correspond to the email content, such as acceptance of a request or answers to questions. The reply generation unit learns the user's past reply history and can generate replies that match the user's writing style and expressions. Furthermore, the reply generation unit provides an interface that allows the user to review and edit the generated replies, enabling them to confirm the content before final sending. This reduces the user's burden and helps them provide quick and appropriate replies. The reply generation unit also has a function to present multiple reply options, allowing the user to select the most suitable reply. This enables the user to quickly provide the most appropriate reply for the situation.

[0082] The scheduling unit schedules the sending of replies generated by the reply generation unit. For example, the scheduling unit can schedule the sending of generated replies to a specified time. Specifically, the scheduling unit works in conjunction with the user's calendar or schedule to calculate the optimal sending time. For example, if the user is in a meeting or on vacation, the sending of the reply can be delayed to an appropriate time. The scheduling unit can also manually set the sending date and time of the reply based on the user's instructions. Furthermore, the scheduling unit has a function to display a list of emails scheduled to be sent, allowing the user to check the sending schedule at a glance. This enables the user to efficiently manage emails scheduled to be sent and reply at the appropriate time. The scheduling unit also has a function to set reminders before sending to ensure that emails scheduled to be sent are sent reliably. This enables the user to respond reliably without forgetting to send important emails.

[0083] The collection unit can retrieve emails from Outlook and Gmail. For example, the collection unit retrieves emails from Outlook and Gmail. This allows it to support a wide range of email clients.

[0084] The summary section can summarize the sender, content, and subject. For example, the summary section summarizes the sender, content, and subject. This allows for a quick understanding of the email's content by summarizing the sender, content, and subject.

[0085] The notification unit can display summaries in dedicated channels of communication tools and communication platforms. For example, the notification unit can display summaries in dedicated channels of communication tools and communication platforms. This makes it easier to share the content of emails by displaying summaries in dedicated channels of communication tools and communication platforms.

[0086] The priority setting unit can set priorities based on the urgency and importance of emails. For example, the priority setting unit sets priorities based on the urgency and importance of emails. This allows important emails to be processed preferentially.

[0087] The reply generation unit can automatically generate reply text appropriate to the context. For example, the reply generation unit automatically generates reply text appropriate to the context. This enables quick and appropriate replies by automatically generating context-appropriate replies.

[0088] The scheduling function allows you to schedule the sending of generated replies to a specified time. For example, the scheduling function can schedule the sending of generated replies to a specified time. This allows for responses that are in line with business etiquette by scheduling the sending of generated replies to a specified time.

[0089] The data collection unit can estimate the user's emotions and adjust the timing of email retrieval based on the estimated emotions. For example, if the user is stressed, the data collection unit can reduce the frequency of email retrieval and refrain from sending notifications. Conversely, if the user is relaxed, the data collection unit can retrieve emails in real time and send immediate notifications. Furthermore, if the user is busy, the data collection unit can prioritize retrieving only important emails and postpone other emails. This reduces the user's burden by adjusting the timing of email retrieval according to their emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI or not. For example, the data collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0090] The collection unit can analyze the user's past email processing history and select the optimal retrieval method. For example, the collection unit can prioritize retrieving emails from senders that the user has frequently opened in the past. The collection unit can also learn patterns of emails that the user has previously deemed important and prioritize retrieving similar emails. Furthermore, if the collection unit has a tendency to process emails during specific time periods in the past, it can also retrieve emails during those times. This allows the optimal retrieval method to be selected by analyzing the user's past email processing history. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's past email processing history data into a generating AI and have the generating AI select the optimal retrieval method.

[0091] The collection unit can filter emails based on the user's current projects and areas of interest when retrieving them. For example, the collection unit can prioritize retrieving emails related to projects the user is currently working on. The collection unit can also filter and retrieve emails related to topics the user has shown interest in. Furthermore, the collection unit can prioritize retrieving emails that contain specific keywords the user has used. This allows for the priority retrieval of highly relevant emails by filtering based on the user's current projects and areas of interest. Some or all of the above processing in the collection unit may be performed using AI, for example, or not. For example, the collection unit can input data on the user's projects and areas of interest into a generating AI and have the generating AI perform the filtering.

[0092] The collection unit can estimate the user's emotions and determine the priority of emails to retrieve based on the estimated emotions. For example, if the user is stressed, the collection unit may postpone retrieving less important emails. Conversely, if the user is relaxed, the collection unit may retrieve all emails equally. Furthermore, if the user is busy, the collection unit may prioritize retrieving urgent emails. This allows for the priority of important emails to be retrieved by determining the priority of emails according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collection unit may be performed using AI or not. For example, the collection unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0093] The collection unit can prioritize the retrieval of highly relevant emails by considering the user's geographical location information when acquiring emails. For example, if the user is in a specific region, the collection unit will prioritize the retrieval of emails related to that region. Furthermore, if the user is on a business trip, the collection unit can prioritize the retrieval of emails related to the destination. Additionally, if the user is at home, the collection unit can prioritize the retrieval of emails related to home. This allows for the prioritization of highly relevant emails by considering the user's geographical location information. Some or all of the above processing in the collection unit may be performed using AI, for example, or without AI. For example, the collection unit can input the user's geographical location data into a generating AI and have the generating AI retrieve highly relevant emails.

[0094] The collection unit can analyze the user's social media activity when acquiring emails and retrieve relevant emails. For example, the collection unit can prioritize retrieving emails related to topics the user has shown interest in on social media. It can also prioritize retrieving emails from people the user follows on social media. Furthermore, the collection unit can prioritize retrieving emails related to groups the user participates in on social media. In this way, relevant emails can be prioritized by analyzing the user's social media activity. Some or all of the above processing in the collection unit may be performed using AI, for example, or not using AI. For example, the collection unit can input the user's social media activity data into a generating AI and have the generating AI retrieve relevant emails.

[0095] 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 can provide a concise and to-the-point summary. If the user is relaxed, the summarization unit can also provide a detailed summary. Furthermore, if the user is in a hurry, the summarization unit can provide a summary containing only the most important information. In this way, by adjusting the way the summary is presented according to the user's emotions, a summary that is easy for the user to understand can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI, for example, or not using AI. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the way the summary is presented.

[0096] The summarization unit can adjust the level of detail in the summary based on the importance of the email during summary generation. For example, the summarization unit can provide a detailed summary for high-importance emails. It can also provide a concise summary for low-importance emails. Furthermore, it can provide a quick summary for urgent emails. This allows for a detailed understanding of important email content by adjusting the level of detail in the summary based on the importance of the email. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the summary.

[0097] The summarization unit can apply different summarization algorithms depending on the email category when generating summaries. For example, the summarization unit can apply a business-oriented summarization algorithm to business emails. It can also apply a private-oriented summarization algorithm to private emails. Furthermore, it can apply an advertising-oriented summarization algorithm to advertising emails. This allows for the provision of summaries appropriate to each category by applying different summarization algorithms depending on the email category. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email category data into a generation AI and have the generation AI execute the application of the summarization algorithm.

[0098] 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 provide a short, concise summary. If the user is relaxed, the summarization unit can provide a detailed summary. Furthermore, if the user is in a hurry, the summarization unit can provide a short summary containing only the most important information. This allows the system to provide the user with the most suitable summary by adjusting the length of the summary according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the summarization unit may be performed using AI or not. For example, the summarization unit can input user emotion data into the generative AI and have the generative AI adjust the length of the summary.

[0099] The summarization unit can determine the priority of summaries based on when the emails were received during the summarization process. For example, the summarization unit may prioritize summarizing recently received emails. It can also prioritize summarizing emails received immediately before an important event. Furthermore, the summarization unit may prioritize summarizing emails received by the user during a specific time period. This allows for prioritizing the summarization of the most recent emails by determining the priority of summarization based on when the emails were received. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email reception data into a generation AI and have the generation AI perform the determination of the summary priority.

[0100] The summarization unit can adjust the order of summaries based on the relevance of the emails during summary generation. For example, the summarization unit can prioritize summarizing highly relevant emails. It can also postpone summarizing less relevant emails. Furthermore, the summarization unit can adjust the order of summaries based on user interests. This allows for prioritizing the summarization of highly relevant emails by adjusting the order of summaries based on their relevance. Some or all of the above processing in the summarization unit may be performed using AI, for example, or without AI. For example, the summarization unit can input email relevance data into a generation AI and have the generation AI perform the adjustment of the summary order.

[0101] The notification unit can estimate the user's emotions and adjust how notifications are displayed based on the estimated emotions. For example, if the user is stressed, the notification unit can provide a simple and highly visible notification. If the user is relaxed, the notification unit can also provide a detailed notification. Furthermore, if the user is in a hurry, the notification unit can provide a notification containing only the most important information. This allows the system to provide the most suitable notifications to the user by adjusting how notifications are displayed according to their emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not. For example, the notification unit can input user emotion data into a generative AI and have the generative AI adjust how notifications are displayed.

[0102] The notification unit can select the optimal notification method by referring to the user's past notification history when sending a notification. For example, the notification unit can prioritize providing notification methods that the user has preferred to use in the past. It can also avoid notification methods that the user has ignored in the past. Furthermore, the notification unit can select the optimal notification timing from the user's past notification history. In this way, the optimal notification method can be selected by referring to the user's past notification history. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input the user's past notification history data into a generating AI and have the generating AI perform the selection of the optimal notification method.

[0103] The notification unit can apply different notification methods depending on the content of the email when it sends a notification. For example, the notification unit can use push notifications for important emails. It can also use voice notifications for urgent emails. Furthermore, it can use badge notifications for general emails. This allows for appropriate notification of important emails by applying different notification methods depending on the content of the email. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input email content data into a generating AI and have the generating AI perform the application of notification methods.

[0104] The notification unit can estimate the user's emotions and determine the priority of notifications based on the estimated emotions. For example, if the user is stressed, the notification unit may postpone less important notifications. If the user is relaxed, the notification unit may display all notifications equally. Furthermore, if the user is busy, the notification unit may prioritize displaying urgent notifications. In this way, important notifications can be displayed preferentially by determining the priority of notifications according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using AI or not using AI. For example, the notification unit can input user emotion data into a generative AI and have the generative AI determine the priority of notifications.

[0105] The notification unit can select the optimal notification method by considering the user's device information when sending a notification. For example, if the user is using a smartphone, the notification unit can provide a push notification. It can also provide a notification optimized for a larger screen if the user is using a tablet. Furthermore, if the user is using a smartwatch, the notification unit can provide a concise and highly visible notification. This allows the system to select the optimal notification method by considering the user's device information. Some or all of the above processing in the notification unit may be performed using AI, for example, or without AI. For example, the notification unit can input user device information data into a generating AI and have the generating AI select the optimal notification method.

[0106] The notification unit can adjust the timing of notifications, taking into account the user's schedule. For example, if the user is in a meeting, the notification unit will refrain from sending a notification. It can also prioritize displaying notifications if the user is on a break. Furthermore, the notification unit can select the optimal notification timing based on the user's schedule. This allows for the selection of the best notification timing by considering the user's schedule. Some or all of the above processing in the notification unit may be performed using AI, or without AI. For example, the notification unit can input user schedule data into a generating AI and have the generating AI adjust the timing of notifications.

[0107] The priority setting unit can estimate the user's emotions and adjust the priority setting criteria based on the estimated emotions. For example, if the user is stressed, the priority setting unit can lower the priority of low-priority emails. Conversely, if the user is relaxed, the priority setting unit can also set the priority of all emails equally. Furthermore, if the user is busy, the priority setting unit can raise the priority of urgent emails. In this way, important emails can be processed preferentially by adjusting the priority setting criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the priority setting unit may be performed using AI, or not using AI. For example, the priority setting unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the priority setting criteria.

[0108] The priority setting unit can improve the accuracy of priority settings by considering the relationships between emails. For example, the priority setting unit can set the priority of emails related to the same project all at once. The priority setting unit can also set priorities by considering the relationship between the sender and recipient. Furthermore, the priority setting unit can set priorities by analyzing the relationship between the content of an email and past emails. This improves the accuracy of priority settings by considering the relationships between emails. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input email relationship data into a generating AI and have the generating AI perform the priority accuracy improvement.

[0109] The priority setting unit can set priorities by considering the attribute information of the email sender. For example, the priority setting unit can set a higher priority for emails from important business partners. It can also set a higher priority for emails from superiors. Furthermore, it can also set a higher priority for emails from new customers. This allows for priority processing of emails from important senders by considering the attribute information of the email sender. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input sender attribute information data into a generating AI and have the generating AI perform the priority setting.

[0110] The priority setting unit can estimate the user's emotions and adjust the display method of priorities based on the estimated emotions. For example, if the user is stressed, the priority setting unit may reduce the display of low-priority emails. Conversely, if the user is relaxed, the priority setting unit may display all emails equally. Furthermore, if the user is busy, the priority setting unit may make urgent emails stand out. In this way, important emails can be highlighted by adjusting the display method of priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the priority setting unit may be performed using AI, or not using AI. For example, the priority setting unit can input user emotion data into the generative AI and have the generative AI adjust the display method of priorities.

[0111] The priority setting unit can set priorities while considering the geographical distribution of emails. For example, the priority setting unit can set a higher priority for emails related to the user's current location. It can also set a higher priority for emails related to the user's business trip destination if the user is on a business trip. Furthermore, it can set a higher priority for emails related to the user's home if the user is at home. This allows for the processing of highly relevant emails with priority, by considering the geographical distribution of emails. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input geographical distribution data of emails into a generating AI and have the generating AI perform the priority setting.

[0112] The priority setting unit can improve the accuracy of priority settings by referring to relevant literature in emails. For example, the priority setting unit sets priority by referring to literature related to the content of the email. The priority setting unit can also set priority by referring to literature cited by the email sender. Furthermore, the priority setting unit can set priority by referring to the latest research related to the content of the email. This improves the accuracy of priority settings by referring to relevant literature in emails. Some or all of the above processing in the priority setting unit may be performed using AI, for example, or without AI. For example, the priority setting unit can input relevant literature data into a generating AI and have the generating AI perform the priority accuracy improvement.

[0113] The reply generation unit can estimate the user's emotions and adjust the wording of the reply based on the estimated emotions. For example, if the user is stressed, the reply generation unit can generate a concise and to-the-point reply. If the user is relaxed, the reply generation unit can also generate a detailed reply. Furthermore, if the user is in a hurry, the reply generation unit can generate a reply containing only the most important information. In this way, by adjusting the wording of the reply according to the user's emotions, an appropriate reply can be generated. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or not using AI. For example, the reply generation unit can input user emotion data into the generative AI and have the generative AI adjust the wording of the reply.

[0114] The reply generation unit can adjust the level of detail in the reply based on the importance of the email when generating a reply. For example, the reply generation unit can generate a detailed reply for high-importance emails. It can also generate a concise reply for low-importance emails. Furthermore, it can quickly generate a reply for urgent emails. By adjusting the level of detail in the reply based on the importance of the email, it is possible to provide an appropriate reply to important emails. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email importance data into a generation AI and have the generation AI perform the adjustment of the level of detail in the reply.

[0115] The reply generation unit can apply different reply algorithms depending on the email category when generating replies. For example, the reply generation unit can apply a business-oriented reply algorithm to business emails. It can also apply a private-oriented reply algorithm to private emails. Furthermore, it can apply an advertising-oriented reply algorithm to advertising emails. By applying different reply algorithms depending on the email category, it is possible to generate replies appropriate for each category. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email category data into a generation AI and have the generation AI execute the application of the reply algorithm.

[0116] The reply generation unit can estimate the user's emotions and adjust the length of the reply based on the estimated emotions. For example, if the user is stressed, the reply generation unit can generate a short, concise reply. If the user is relaxed, the reply generation unit can also generate a detailed reply. Furthermore, if the user is in a hurry, the reply generation unit can generate a short reply containing only the most important information. This allows for the generation of a reply of appropriate length by adjusting the length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative 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 reply generation unit may be performed using AI or not. For example, the reply generation unit can input user emotion data into the generative AI and have the generative AI adjust the length of the reply.

[0117] The reply generation unit can determine the priority of replies based on when the email was received. For example, the reply generation unit can prioritize generating replies to recently received emails. It can also prioritize generating replies to emails received immediately before an important event. Furthermore, it can prioritize generating replies to emails received by the user during a specific time period. This allows for quick responses to the latest emails by prioritizing replies based on when the email was received. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email reception data into a generation AI and have the generation AI determine the priority of replies.

[0118] The reply generation unit can adjust the order of replies based on the relevance of the emails when generating replies. For example, the reply generation unit can prioritize generating replies for highly relevant emails. It can also postpone generating replies for less relevant emails. Furthermore, the reply generation unit can adjust the order of replies based on user interests. This allows for priority replies to highly relevant emails by adjusting the order of replies based on email relevance. Some or all of the above processing in the reply generation unit may be performed using AI, for example, or without AI. For example, the reply generation unit can input email relevance data into a generation AI and have the generation AI perform the adjustment of the order of replies.

[0119] The scheduling unit can estimate the user's emotions and adjust the sending schedule based on the estimated emotions. For example, if the user is stressed, the scheduling unit may delay the sending schedule. Conversely, if the user is relaxed, the scheduling unit may speed up the sending schedule. Furthermore, if the user is in a hurry, the scheduling unit may send immediately. This allows emails to be sent at the appropriate time by adjusting the sending schedule according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scheduling unit may be performed using AI or not. For example, the scheduling unit can input user emotion data into a generative AI and have the generative AI adjust the sending schedule.

[0120] The scheduling unit can select the optimal sending timing by referring to the user's past scheduling history when setting a schedule. For example, the scheduling unit can prioritize sending timings that the user has preferred to use in the past. The scheduling unit can also avoid sending timings that the user has ignored in the past. Furthermore, the scheduling unit can select the optimal sending timing from the user's past scheduling history. In this way, the optimal sending timing can be selected by referring to the user's past scheduling history. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without using AI. For example, the scheduling unit can input the user's past scheduling history data into a generating AI and have the generating AI perform the selection of the optimal sending timing.

[0121] The scheduling unit can apply different sending schedules depending on the content of the email when setting the schedule. For example, the scheduling unit can set an immediate sending schedule for important emails. It can also set a rapid sending schedule for highly urgent emails. Furthermore, the scheduling unit can set a normal sending schedule for general emails. This allows important emails to be sent at the appropriate time by applying different sending schedules depending on the content of the email. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can input email content data into a generating AI and have the generating AI execute the application of the sending schedule.

[0122] The scheduling unit can estimate the user's emotions and determine the priority of the email sending schedule based on the estimated emotions. For example, if the user is stressed, the scheduling unit may postpone sending less important emails. If the user is relaxed, the scheduling unit may also set all emails to be sent equally. Furthermore, if the user is busy, the scheduling unit may prioritize sending urgent emails. This allows important emails to be sent preferentially by determining the priority of the sending schedule according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scheduling unit may be performed using AI or not. For example, the scheduling unit can input user emotion data into a generative AI and have the generative AI determine the priority of the email sending schedule.

[0123] The scheduling unit can select the optimal transmission timing by considering the user's device information when setting the schedule. For example, if the user is using a smartphone, the scheduling unit can set the transmission timing using push notifications. The scheduling unit can also set a transmission timing optimized for a larger screen if the user is using a tablet. Furthermore, if the user is using a smartwatch, the scheduling unit can set a concise and highly visible transmission timing. This allows for the selection of the optimal transmission timing by considering the user's device information. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can input user device information data into a generating AI and have the generating AI select the optimal transmission timing.

[0124] The scheduling unit can adjust the sending timing when setting a schedule, taking the user's schedule into consideration. For example, the scheduling unit may refrain from sending if the user is in a meeting. It can also prioritize sending if the user is on a break. Furthermore, the scheduling unit can select the optimal sending timing according to the user's schedule. This allows for the selection of the optimal sending timing by considering the user's schedule. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can input the user's schedule data into a generating AI and have the generating AI perform the adjustment of the sending timing.

[0125] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0126] The collection unit can estimate the user's emotions and adjust the timing of email retrieval based on those emotions. For example, if the user is stressed, the frequency of email retrieval will be reduced and notifications will be kept to a minimum. Conversely, if the user is relaxed, emails can be retrieved in real time and notifications can be sent immediately. Furthermore, if the user is busy, only important emails can be prioritized, and other emails can be delayed. In this way, the user's burden can be reduced by adjusting the timing of email retrieval according to their emotions.

[0127] The data collection unit can analyze a user's past email processing history and select the optimal retrieval method. For example, it can prioritize retrieving emails from senders that the user has frequently opened in the past. It can also learn patterns of emails that the user has previously deemed important and prioritize retrieving similar emails. Furthermore, if a user tends to process emails at specific times in the past, it can retrieve emails during those times. In this way, by analyzing a user's past email processing history, the optimal retrieval method can be selected.

[0128] The collection unit can filter emails based on the user's current projects and areas of interest. For example, it can prioritize retrieving emails related to projects the user is currently working on. It can also filter and retrieve emails related to topics the user has shown interest in. Furthermore, it can prioritize retrieving emails containing specific keywords the user has used. This allows for the priority retrieval of highly relevant emails by filtering based on the user's current projects and areas of interest.

[0129] The collection unit can estimate the user's emotions and determine the priority of emails to retrieve based on those emotions. For example, if the user is stressed, less important emails will be prioritized. If the user is relaxed, all emails can be retrieved equally. Furthermore, if the user is busy, urgent emails can be prioritized. In this way, by prioritizing emails according to the user's emotions, important emails can be retrieved preferentially.

[0130] The collection unit can prioritize retrieving highly relevant emails by considering the user's geographical location when acquiring emails. For example, if the user is in a specific region, it will prioritize retrieving emails related to that region. Similarly, if the user is on a business trip, it can prioritize retrieving emails related to their destination. Furthermore, if the user is at home, it can prioritize retrieving emails related to their home. This allows for the prioritization of highly relevant emails by considering the user's geographical location.

[0131] The collection unit can analyze the user's social media activity when acquiring emails and retrieve relevant emails. For example, it can prioritize retrieving emails related to topics the user has shown interest in on social media. It can also prioritize retrieving emails from people the user follows on social media. Furthermore, it can prioritize retrieving emails related to groups the user participates in on social media. In this way, by analyzing the user's social media activity, it is possible to prioritize the retrieval of relevant emails.

[0132] The summarization function can estimate the user's emotions and adjust the way the summary is presented based on those emotions. For example, if the user is stressed, it can provide a concise and to-the-point summary. If the user is relaxed, it can provide a more detailed summary. Furthermore, if the user is in a hurry, it can provide a summary containing only the most important information. By adjusting the way the summary is presented according to the user's emotions, it can provide a summary that is easy for the user to understand.

[0133] The summarization function can adjust the level of detail in a summary based on the importance of the email during the summary generation process. For example, it can provide a detailed summary for high-priority emails and a concise summary for low-priority emails. Furthermore, it can provide a quick summary for urgent emails. This allows users to gain a detailed understanding of important email content by adjusting the level of detail in the summary based on the email's importance.

[0134] The summarization section can apply different summarization algorithms depending on the email category during summary generation. For example, a business-oriented summarization algorithm can be applied to business emails. Similarly, a private-oriented summarization algorithm can be applied to private emails. Furthermore, an advertising-oriented summarization algorithm can be applied to advertising emails. This allows for the provision of summaries tailored to each category by applying different summarization algorithms depending on the email category.

[0135] The summarization function can estimate the user's emotions and adjust the length of the summary based on that estimation. For example, if the user is stressed, it can provide a short, to-the-point summary. If the user is relaxed, it can provide a more detailed summary. Furthermore, if the user is in a hurry, it can provide a short summary containing only the most important information. By adjusting the length of the summary according to the user's emotions, it can provide the user with the most optimal summary.

[0136] The following briefly describes the processing flow for example form 2.

[0137] Step 1: The collection unit retrieves emails from the email client. For example, it can retrieve emails from Outlook or Gmail. Step 2: The summarization unit summarizes the content of the emails obtained by the collection unit. For example, it can summarize the sender, content, and subject. Step 3: The notification unit notifies the chat tool of the content summarized by the summarization unit. For example, the summary can be displayed in a dedicated channel on a communication tool or communication platform. Step 4: The priority setting unit sets the urgency and importance based on the information notified by the notification unit. For example, the priority can be set based on the urgency and importance of the email. Step 5: The reply generation unit generates a reply based on the urgency and importance set by the priority setting unit. For example, it can automatically generate a reply that is appropriate to the context. Step 6: The scheduling unit schedules the sending of the reply text generated by the reply generation unit. For example, the sending of the generated reply text can be scheduled for a specified time.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] Each of the multiple elements described above, including the collection unit, summarization unit, notification unit, priority setting unit, reply generation unit, and scheduling unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the smart device 14 and retrieves emails from the email client. The summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and summarizes the content of the retrieved emails. The notification unit is implemented by the control unit 46A of the smart device 14 and notifies the chat tool of the summarized content. The priority setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets the urgency and importance based on the notified content. The reply generation unit is implemented by the control unit 46A of the smart device 14 and generates a reply based on the set urgency and importance. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12 and schedules the sending of the generated reply. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0142] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.).

[0154] 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.

[0155] 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.

[0156] 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.

[0157] Each of the multiple elements described above, including the collection unit, summarization unit, notification unit, priority setting unit, reply generation unit, and scheduling unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the smart glasses 214 and retrieves emails from the email client. The summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and summarizes the content of the retrieved emails. The notification unit is implemented by the control unit 46A of the smart glasses 214 and notifies the chat tool of the summarized content. The priority setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets the urgency and importance based on the notified content. The reply generation unit is implemented by the control unit 46A of the smart glasses 214 and generates a reply based on the set urgency and importance. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12 and schedules the sending of the generated reply. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0158] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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).

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.).

[0170] 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.

[0171] 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.

[0172] 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.

[0173] Each of the multiple elements described above, including the collection unit, summarization unit, notification unit, priority setting unit, reply generation unit, and scheduling unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the headset terminal 314 and retrieves emails from the email client. The summarization unit is implemented by the specific processing unit 290 of the data processing unit 12 and summarizes the content of the retrieved emails. The notification unit is implemented by the control unit 46A of the headset terminal 314 and notifies the chat tool of the summarized content. The priority setting unit is implemented by the specific processing unit 290 of the data processing unit 12 and sets the urgency and importance based on the notified content. The reply generation unit is implemented by the control unit 46A of the headset terminal 314 and generates a reply based on the set urgency and importance. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12 and schedules the sending of the generated reply. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0174] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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).

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] Each of the multiple elements described above, including the collection unit, summarization unit, notification unit, priority setting unit, reply generation unit, and scheduling unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the robot 414 and retrieves emails from the mail client. The summarization unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and summarizes the content of the retrieved emails. The notification unit is implemented by, for example, the control unit 46A of the robot 414 and notifies the chat tool of the summarized content. The priority setting unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and sets the urgency and importance based on the notified content. The reply generation unit is implemented by, for example, the control unit 46A of the robot 414 and generates a reply based on the set urgency and importance. The scheduling unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and schedules the transmission of the generated reply. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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."

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] (Note 1) A collection unit that retrieves emails from email clients, A summarization unit that summarizes the contents of emails obtained by the collection unit, A notification unit that notifies the chat tool of the content summarized by the summarization unit, A priority setting unit sets the urgency and importance based on the content notified by the notification unit, A reply generation unit generates a reply message based on the urgency and importance set by the priority setting unit, The system includes a scheduling unit that schedules the transmission of the reply message generated by the reply generation unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Retrieve emails from Outlook or Gmail The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary section above is, Summarize the sender, content, and subject. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned notification unit, Display the summary in a dedicated channel on a communication tool or communication platform. The system described in Appendix 1, characterized by the features described herein. (Note 5) The priority setting unit is, Prioritize emails based on their urgency and importance. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reply generation unit, Automatically generate context-appropriate replies. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned scheduling unit is Schedule the sending of the generated reply message at a specified time. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of email retrieval based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is Analyze the user's past email processing history and select the optimal method for retrieving it. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is When retrieving emails, 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 aforementioned collection unit is It estimates the user's emotions and determines the priority of emails to retrieve based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When retrieving emails, the system prioritizes retrieving highly relevant emails by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When retrieving emails, the system analyzes the user's social media activity and retrieves relevant emails. The system described in Appendix 1, characterized by the features described herein. (Note 14) 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 15) The summary section above is, When generating a summary, adjust the level of detail in the summary based on the importance of the email. The system described in Appendix 1, characterized by the features described herein. (Note 16) The summary section above is, When generating summaries, different summarization algorithms are applied depending on the email category. The system described in Appendix 1, characterized by the features described herein. (Note 17) 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 18) The summary section above is, When generating summaries, the priority of summaries is determined based on when the emails were received. The system described in Appendix 1, characterized by the features described herein. (Note 19) The summary section above is, When generating summaries, the order of the summaries is adjusted based on the relevance of the emails. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned notification unit, It estimates the user's emotions and adjusts how notifications are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned notification unit, When sending a notification, the system will refer to the user's past notification history to select the most suitable notification method. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned notification unit, When sending notifications, different notification methods will be applied depending on the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned notification unit, It estimates the user's emotions and prioritizes notifications based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned notification unit, When sending notifications, the system selects the most suitable notification method, taking into account the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned notification unit, When sending notifications, the timing of the notifications will be adjusted to take the user's schedule into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 26) The priority setting unit is, It estimates the user's emotions and adjusts the priority setting criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The priority setting unit is, When setting priorities, the accuracy of prioritization is improved by considering the interrelationships between emails. The system described in Appendix 1, characterized by the features described herein. (Note 28) The priority setting unit is, When setting priorities, the sender's attribute information is taken into consideration when setting priorities. The system described in Appendix 1, characterized by the features described herein. (Note 29) The priority setting unit is, It estimates the user's emotions and adjusts how priorities are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The priority setting unit is, When setting priorities, consider the geographical distribution of emails. The system described in Appendix 1, characterized by the features described herein. (Note 31) The priority setting unit is, When setting priorities, we refer to relevant literature in emails to improve the accuracy of prioritization. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned reply generation unit, The system estimates the user's emotions and adjusts the wording of the reply based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned reply generation unit, When generating a reply, adjust the level of detail in the reply text based on the importance of the email. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned reply generation unit, When generating replies, apply different reply algorithms depending on the email category. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned reply generation unit, It estimates the user's emotions and adjusts the length of the reply based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned reply generation unit, When generating a reply, the priority of the reply message is determined based on when the email was received. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned reply generation unit, When generating a reply, the order of the reply text is adjusted based on the relevance of the emails. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned scheduling unit is It estimates the user's emotions and adjusts the sending schedule based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned scheduling unit is When setting a schedule, the system refers to the user's past schedule history to select the optimal sending timing. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned scheduling unit is When setting the schedule, apply different sending schedules depending on the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned scheduling unit is It estimates the user's emotions and determines the priority of the sending schedule based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned scheduling unit is When scheduling, the system selects the optimal transmission timing by considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned scheduling unit is When setting the schedule, the sending timing is adjusted to take the user's schedule into consideration. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0210] 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 collection unit that retrieves emails from email clients, A summarization unit that summarizes the contents of emails obtained by the collection unit, A notification unit that notifies the chat tool of the content summarized by the summarization unit, A priority setting unit sets the urgency and importance based on the content notified by the notification unit, A reply generation unit generates a reply message based on the urgency and importance set by the priority setting unit, The system includes a scheduling unit that schedules the transmission of the reply message generated by the reply generation unit. A system characterized by the following features.

2. The summary section above is, Summarize the sender, content, and subject. The system according to feature 1.

3. The aforementioned notification unit, Display the summary in a dedicated channel on a communication tool or communication platform. The system according to feature 1.

4. The priority setting unit is, Prioritize emails based on their urgency and importance. The system according to feature 1.

5. The aforementioned reply generation unit, Automatically generate context-appropriate replies. The system according to feature 1.

6. The aforementioned scheduling unit is Schedule the sending of the generated reply message at a specified time. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and adjusts the timing of email retrieval based on the estimated emotions. The system according to feature 1.

Images