system

Abstract

The system according to this embodiment aims to efficiently manage a large volume of incoming emails and to respond quickly to important emails. [Solution] The system according to the embodiment comprises an acquisition unit, a classification unit, a summary generation unit, a reply generation unit, and a transmission unit. The acquisition unit acquires incoming emails. The classification unit classifies the emails acquired by the acquisition unit. The summary generation unit summarizes the content of the emails classified by the classification unit. The reply generation unit generates a reply to the emails summarized by the summary generation unit. The transmission unit transmits 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 is difficult to efficiently manage a large number of received mails and quickly respond without missing important mails.

[0005] The system according to the embodiment aims to efficiently manage a large number of received mails and quickly respond to important mails.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an acquisition unit, a classification unit, a summary generation unit, a reply generation unit, and a transmission unit. The acquisition unit acquires incoming emails. The classification unit classifies the emails acquired by the acquisition unit. The summary generation unit summarizes the content of the emails classified by the classification unit. The reply generation unit generates replies to the emails summarized by the summary generation unit. The transmission unit transmits the replies generated by the reply generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently manage a large volume of incoming emails and respond quickly to important emails. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 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 management system according to an embodiment of the present invention is a system that streamlines email management by utilizing generative AI. This system is an extremely useful tool for companies and individuals that need to deal with a large volume of emails on a daily basis. The email management system has an intelligent classification function that automatically classifies incoming emails and sorts them based on priority. This minimizes the risk of users missing important emails. For example, urgent inquiry emails from customers are automatically sorted into an "important" folder, and routine business communication emails are classified into a "routine" folder. Next, the email management system has a news-style summarization function that displays the content of each email as a headline and a concise summary. This allows users to quickly grasp information, contributing to time savings and efficient information processing. For example, even with long emails, users can grasp the important points by simply reading the summary. Furthermore, the email management system has an AI-assisted reply function that generates appropriate automatic replies to important emails or presents multiple reply options. This improves the quality and speed of replies and enables consistent communication. For example, in response to an inquiry from a customer, the AI ​​can automatically generate a reply, which the user can then review and send. Furthermore, the email management system features continuous learning capabilities that allow it to learn user behavior patterns and improve classification and prioritization over time. This means the system continuously evolves to meet user needs. For example, if a user consistently treats emails from a particular sender as "important," the system learns this pattern and automatically moves emails from that sender to the "important" folder in the future. In this way, the email management system leverages generative AI to streamline email management and improve user productivity. As a result, the email management system makes email management more efficient for users and minimizes the risk of missing important emails.

[0029] The email management system according to this embodiment comprises an acquisition unit, a classification unit, a summary generation unit, a reply generation unit, and a sending unit. The acquisition unit acquires incoming emails. The acquisition unit can, for example, acquire incoming emails from a mail server. The acquisition unit can communicate with a mail server using protocols such as POP3 or IMAP to acquire incoming emails. The acquisition unit can, for example, access a mail server at specific time intervals to acquire new emails. The acquisition unit can also allow users to manually acquire emails. The classification unit classifies the emails acquired by the acquisition unit. The classification unit can, for example, automatically categorize emails based on their content. The classification unit can analyze the content of emails using natural language processing technology and classify them based on pre-learned categories. The classification unit can, for example, automatically move urgent inquiry emails from customers to an "important" folder. The classification unit can also classify routine business communication emails into a "routine business" folder. The summary generation unit summarizes the content of emails classified by the classification unit. The summary generation unit can, for example, convert long emails into concise summaries. The summary generation unit can analyze the content of an email using natural language processing technology, extract key points, and generate a summary. For example, the summary generation unit can display the email's headline and a concise summary. Even with lengthy emails, the summary generation unit allows users to grasp the key points simply by reading the summary. The reply generation unit generates a reply to the email summarized by the summary generation unit. For example, the reply generation unit can analyze the email content and past exchanges to generate an appropriate reply. The reply generation unit can analyze the email content using natural language processing technology to generate an appropriate reply. For example, the reply generation unit can present multiple reply options, allowing the user to select or edit one. The reply generation unit can pass the user's selected reply to the sender. The sender sends the reply generated by the reply generation unit. The sender can send the reply via a mail server, for example. The sender can communicate with the mail server using the SMTP protocol to send the reply. The sender can also accept replies sent manually by the user.As a result, the email management system according to this embodiment can efficiently retrieve, classify, summarize, generate replies to, and send emails.

[0030] The retrieval unit retrieves incoming emails. For example, the retrieval unit can retrieve incoming emails from a mail server. The retrieval unit can communicate with the mail server using protocols such as POP3 and IMAP to retrieve incoming emails. Specifically, when using the POP3 protocol, the retrieval unit connects to the mail server, sends user authentication information, and downloads new emails. When using the IMAP protocol, the retrieval unit accesses the mail folder on the mail server, retrieves the email header information, and then downloads the necessary email body. The retrieval unit can, for example, access the mail server at specific time intervals to retrieve new emails. This allows users to check for new emails in real time. The retrieval unit can also retrieve emails manually. For example, when a user clicks the "Receive" button in their email client, the retrieval unit immediately accesses the mail server and retrieves the new email. The retrieval unit also has a function to log the email retrieval status and notify the user if an error occurs. This ensures that the retrieval unit reliably retrieves incoming emails and allows users to always check for the latest emails.

[0031] The classification unit categorizes emails acquired by the acquisition unit. For example, the classification unit can automatically categorize emails based on their content. The classification unit can analyze email content using natural language processing technology and classify them based on pre-learned categories. Specifically, the classification unit analyzes the email subject, body, sender information, etc., and uses machine learning algorithms to sort emails into the appropriate category. For example, it can automatically sort urgent customer inquiry emails into the "Important" folder. The classification unit can also classify routine business communication emails into the "Routine" folder. Furthermore, the classification unit allows users to manually set categories and move emails to specific folders according to user instructions. The classification unit also has a function to log the email classification results so that users can review them later. This allows the classification unit to efficiently organize emails and enable users to quickly find the emails they need.

[0032] The summary generation unit summarizes the content of emails classified by the classification unit. For example, the summary generation unit can convert a long email into a concise summary. Using natural language processing technology, the summary generation unit analyzes the email content, extracts key points, and generates a summary. Specifically, it extracts keywords and important phrases from the email body and generates a concise summary based on them. The summary generation unit can display, for example, the email headline and a concise summary. This allows users to grasp the key points of even long emails simply by reading the summary. The summary generation unit also includes a function that allows users to adjust the accuracy of the summary, changing the level of detail to their preference. Furthermore, the summary generation unit has a function to log the summary results for later review. This enables the summary generation unit to efficiently summarize email content, allowing users to quickly grasp important information.

[0033] The reply generation unit generates replies to emails summarized by the summary generation unit. For example, the reply generation unit can analyze the email content and past exchanges to generate appropriate replies. It can also analyze email content using natural language processing techniques to generate appropriate replies. Specifically, it analyzes the email body and generates the optimal reply by referencing past reply patterns and standard phrases. For example, it can present multiple reply options, allowing the user to select or edit one. This allows the user to choose the reply that best suits their intentions. The reply generation unit can then pass the user's selected reply to the sender. Furthermore, the reply generation unit has a function to log the reply generation process, allowing the user to review it later. This enables the reply generation unit to efficiently generate appropriate replies and support the user's reply process.

[0034] The sending unit sends the reply generated by the reply generation unit. The sending unit can send replies, for example, through a mail server. The sending unit can communicate with the mail server using the SMTP protocol and send replies. Specifically, the sending unit connects to the mail server using the user's authentication information and adds the reply email to the sending queue. The sending unit monitors the email sending status and verifies whether the sending was successful. The sending unit can also receive replies manually from the user. For example, when the user clicks the "Send" button, the sending unit immediately connects to the mail server and sends the reply email. The sending unit also has a function to log the sending results and notify the user if an error occurs. This ensures that the sending unit can reliably send reply emails and that users can reliably send emails.

[0035] The classification unit can automatically categorize emails based on their content. For example, the classification unit can analyze the content of emails using natural language processing technology and classify them based on pre-learned categories. For example, the classification unit can automatically move urgent customer inquiry emails to an "important" folder. The classification unit can also classify routine business communication emails into a "routine" folder. This streamlines email management by automatically categorizing emails based on their content. Some or all of the above-described processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can classify emails using an AI model that takes email content as input and outputs categories.

[0036] The summary generation unit can convert long emails into concise summaries. For example, the summary generation unit analyzes the email content using natural language processing technology, extracts key points, and generates a summary. The summary generation unit can display, for example, the email's headline and a concise summary. Even with long emails, the summary generation unit allows users to grasp the key points simply by reading the summary. This enables users to quickly understand information by converting long emails into concise summaries. Some or all of the above-described processes in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can generate a summary using an AI model that takes email content as input and outputs a summary.

[0037] The reply generation unit can analyze the content of the email and past exchanges to generate an appropriate reply. For example, the reply generation unit can analyze the content of the email using natural language processing technology to generate an appropriate reply. For example, the reply generation unit can present multiple reply options and allow the user to select or edit one. The reply generation unit can pass the reply selected by the user to the sender. This allows for the generation of an appropriate reply by analyzing the content of the email and past exchanges. 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 generate a reply using an AI model that takes the content of the email and past exchanges as input and outputs a reply.

[0038] The reply generation unit can present multiple reply options, allowing the user to select or edit one. For example, the reply generation unit can analyze the email content using natural language processing technology and generate multiple reply options. The reply generation unit can then pass the user's selected reply to the sender. This allows the user to select or edit the most suitable reply by presenting multiple options. Some or all of the above processing in the reply generation unit may be performed using AI, or without AI. For example, the reply generation unit can generate reply options using an AI model that takes the email content as input and outputs multiple reply options.

[0039] The sending unit can send the generated reply. The sending unit can send the reply, for example, through a mail server. The sending unit can communicate with a mail server using the SMTP protocol and send the reply. The sending unit can also allow the user to send the reply manually. This streamlines email sending by sending the generated reply. Some or all of the above processing in the sending unit may be performed using AI, for example, or not using AI. For example, the sending unit can send the reply using an AI model that takes the generated reply as input and performs the sending.

[0040] The classification unit can learn user behavior patterns and perform more accurate classification and prioritization over time. For example, the classification unit uses machine learning algorithms to learn user behavior patterns. If a user consistently treats emails from a particular sender as "important," the classification unit can learn this pattern and automatically move emails from that sender to the "important" folder in the future. The classification unit can also adjust email priorities based on user behavior patterns. This improves the accuracy of classification and prioritization by learning user behavior patterns. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can perform classification and prioritization using an AI model that takes user behavior data as input and outputs classifications and priorities.

[0041] The retrieval unit can analyze the user's past email retrieval history and select the optimal retrieval method. For example, if the user frequently checked their email during a specific time period in the past, the retrieval unit will concentrate on retrieving emails during that time period. If the user prioritized emails from a specific sender in the past, the retrieval unit can also prioritize retrieving emails from that sender. If the user checked their email on a specific device in the past, the retrieval unit can also retrieve emails in a way optimized for that device. In this way, the optimal retrieval method can be selected by analyzing the user's past email retrieval history. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can select the retrieval method using an AI model that takes the user's past email retrieval history data as input and outputs the optimal retrieval method.

[0042] The retrieval unit can filter emails based on the user's current projects and areas of interest when retrieving them. For example, the retrieval unit can prioritize retrieving only emails related to projects the user is currently working on. The retrieval unit can also prioritize retrieving emails related to specific topics the user has shown interest in. The retrieval unit can also 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 retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can filter emails using an AI model that takes data on the user's projects and areas of interest as input and outputs filtered emails.

[0043] The retrieval unit can prioritize retrieving highly relevant emails by considering the user's geographical location information when retrieving emails. For example, if the user is in a specific region, the retrieval unit will prioritize retrieving emails related to that region. If the user is on a business trip, the retrieval unit can also prioritize retrieving emails related to the business trip destination. If the user is at home, the retrieval unit can also prioritize retrieving emails related to the home. By prioritizing the retrieval of highly relevant emails by considering the user's geographical location information, the user can quickly obtain information that is important to them. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can retrieve emails using an AI model that takes the user's geographical location information as input and outputs highly relevant emails.

[0044] The acquisition unit can analyze a user's social media activity when acquiring emails and retrieve relevant emails. For example, if a user posts about a specific topic on social media, the acquisition unit will prioritize retrieving emails related to that topic. If a user participates in a specific group on social media, the acquisition unit can also prioritize retrieving emails related to that group. If a user participates in a specific event on social media, the acquisition unit can also prioritize retrieving emails related to that event. 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 acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can acquire emails using an AI model that takes user social media activity data as input and outputs relevant emails.

[0045] The classification unit can improve the accuracy of classification by considering the interrelationships between emails during the classification process. For example, the classification unit can group and classify emails from the same sender. It can also group and classify emails related to the same project. It can also group and classify emails related to the same topic. This improves the accuracy of classification by considering the interrelationships between emails. Some or all of the above processing in the classification unit may be performed using AI, for example, or not. For example, the classification unit can improve the accuracy of classification by using an AI model that takes interrelationship data of emails as input and outputs classification results.

[0046] The classification unit can classify emails while considering the sender's attribute information. For example, if the sender is a customer, the classification unit will classify it into the customer folder. If the sender is a supervisor, the classification unit can also classify it into the supervisor folder. If the sender is a colleague, the classification unit can also classify it into the colleague folder. In this way, by considering the sender's attribute information, emails can be classified into the appropriate folder. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can perform classification using an AI model that takes sender attribute information as input and outputs classification results.

[0047] The classification unit can classify emails while considering their geographical distribution. For example, if the sender is in a specific region, the classification unit can classify the email into a folder related to that region. If the sender is on a business trip, the classification unit can also classify the email into a folder related to the destination. If the sender is at home, the classification unit can also classify the email into a folder related to their home. In this way, by considering the geographical distribution of emails, they can be classified into relevant folders. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can perform classification using an AI model that takes sender geographical distribution data as input and outputs classification results.

[0048] The classification unit can improve the accuracy of its classification by referring to relevant literature for emails during the classification process. For example, the classification unit can refer to literature related to the content of an email and classify it into the appropriate category. The classification unit can also refer to past emails related to the content of an email and classify them into the appropriate category. The classification unit can also refer to websites related to the content of an email and classify them into the appropriate category. This improves the accuracy of the classification by referring to relevant literature for emails. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can improve the accuracy of its classification by using an AI model that takes relevant literature data as input and outputs classification results.

[0049] The summary generation unit can adjust the level of detail in the summary based on the importance of the email during summary generation. For example, the summary generation unit can provide a detailed summary for high-importance emails, and a concise summary for low-importance emails. The summary generation unit can also adjust the length of the summary according to its importance. This allows for an appropriate summary of important information 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 summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can adjust the level of detail using an AI model that takes email importance data as input and outputs the level of detail in the summary.

[0050] The summary generation unit can apply different summarization algorithms depending on the email category when generating summaries. For example, the summary generation unit can apply a business-oriented summarization algorithm to business emails. It can also apply a private-oriented summarization algorithm to private emails. It can also apply a newsletter-oriented summarization algorithm to newsletters. By applying different summarization algorithms depending on the email category, it is possible to generate summaries that are optimal for each category. Some or all of the above processing in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can generate summaries using an AI model that takes email category data as input and outputs a summarization algorithm.

[0051] The summary generation unit can determine the priority of summaries based on the email sending date during summary generation. For example, the summary generation unit prioritizes summarizing recently sent emails. The summary generation unit can also summarize older emails more concisely. The summary generation unit can also adjust the level of detail in the summary according to the sending date. This allows for prioritizing the summaries based on the email sending date, thereby ensuring that the most up-to-date information is summarized first. Some or all of the above processing in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can determine the priority using an AI model that takes email sending date data as input and outputs the priority of summaries.

[0052] The summary generation unit can adjust the order of summaries based on the relevance of the emails during the summaries generation process. For example, the summary generation unit prioritizes summarizing highly relevant emails. The summary generation unit can also summarize less relevant emails concisely. The summary generation unit can also adjust the order of summaries according to their relevance. This allows for prioritizing the summarization of highly relevant information by adjusting the order of summaries based on the relevance of the emails. Some or all of the above processing in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can adjust the order using an AI model that takes email relevance data as input and outputs the order of summaries.

[0053] 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 provide a detailed reply to a high-importance email. The reply generation unit can also provide a concise reply to a low-importance email. The reply generation unit can also adjust the length of the reply according to its importance. This allows for the provision of appropriate replies to important emails by adjusting the level of detail based on the importance of the email. 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 adjust the level of detail using an AI model that takes email importance data as input and outputs the level of detail of the reply.

[0054] 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. It can also apply a newsletter-oriented reply algorithm to newsletters. By applying different reply algorithms depending on the email category, it is possible to generate the most appropriate reply 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 generate replies using an AI model that takes email category data as input and outputs a reply algorithm.

[0055] The reply generation unit can determine the priority of replies based on when the email was sent. For example, the reply generation unit will quickly reply to recently sent emails. The reply generation unit can also reply concisely to older emails. The reply generation unit can also adjust the level of detail in the reply according to when it was sent. This enables quick replies by determining the priority of replies based on when the email was sent. 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 determine the priority using an AI model that takes email sending time data as input and outputs the priority of replies.

[0056] 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 will prioritize replying to highly relevant emails. The reply generation unit can also reply concisely to less relevant emails. The reply generation unit can also adjust the order of replies according to relevance. This allows for prioritizing replies to highly relevant emails by adjusting the order of replies based on the relevance of the 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 adjust the order using an AI model that takes email relevance data as input and outputs the order of replies.

[0057] The sending unit can determine the sending priority based on the importance of the emails at the time of sending. For example, the sending unit may prioritize sending emails with high importance. The sending unit may also postpone sending emails with low importance. The sending unit may also adjust the sending order according to importance. In this way, by determining the sending priority based on the importance of the emails, important emails can be sent preferentially. Some or all of the above processing in the sending unit may be performed using AI, for example, or not using AI. For example, the sending unit can determine the priority using an AI model that takes email importance data as input and outputs the sending priority.

[0058] The sending unit can consider the sender's attribute information when sending emails. For example, if the sender is a customer, the sending unit can prioritize sending emails classified in the customer folder. If the sender is a supervisor, the sending unit can also prioritize sending emails classified in the supervisor folder. If the sender is a colleague, the sending unit can also prioritize sending emails classified in the colleague folder. This allows for appropriate sending by considering the sender's attribute information. Some or all of the above processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit can perform sending using an AI model that takes sender attribute information as input and outputs the sending result.

[0059] The sending unit can send emails while considering their geographical distribution. For example, if the recipient is in a specific region, the sending unit can prioritize sending emails related to that region. If the recipient is on a business trip, the sending unit can also prioritize sending emails related to the destination. If the recipient is at home, the sending unit can also prioritize sending emails related to home. By considering the geographical distribution of emails, the sending unit can send appropriate emails to relevant regions. Some or all of the above processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit can perform sending using an AI model that takes geographical distribution data of recipients as input and outputs the sending results.

[0060] The sending unit can improve the accuracy of email transmission by referring to relevant literature during transmission. For example, the sending unit can refer to literature related to the content of the email and select an appropriate transmission method. The sending unit can also refer to past emails related to the content of the email and select an appropriate transmission method. The sending unit can also refer to websites related to the content of the email and select an appropriate transmission method. This improves the accuracy of transmission by referring to relevant literature. Some or all of the above processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit can improve the accuracy of transmission by using an AI model that takes relevant literature data as input and outputs a transmission method.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] An email management system can analyze a user's past email viewing history and select the optimal display method. For example, if a user frequently checked their email during a specific time period in the past, emails from that time period can be concentrated and displayed. If a user previously prioritized emails from a particular sender, emails from that sender can be displayed preferentially. Furthermore, if a user previously checked their email on a specific device, emails can be displayed in a way optimized for that device. In this way, by analyzing a user's past email viewing history, the system can select the most optimal display method.

[0063] The email management system can customize how emails are displayed based on the user's current projects and areas of interest. For example, it can prioritize displaying only emails related to the user's current projects. It can also prioritize emails related to specific topics the user is interested in. Furthermore, it can prioritize emails containing specific keywords the user is using. This allows for the prioritization of highly relevant emails by tailoring the display method to the user's current projects and areas of interest.

[0064] An email management system can adjust how emails are displayed based on the user's geographical location. For example, if a user is in a specific region, emails related to that region can be prioritized. If a user is on a business trip, emails related to their destination can be prioritized. Similarly, if a user is at home, emails related to their home can be prioritized. By adjusting how emails are displayed based on the user's geographical location, important information can be displayed quickly to the user.

[0065] An email management system can analyze a user's social media activity and prioritize the display of relevant emails. For example, if a user posts about a specific topic on social media, emails related to that topic can be prioritized. If a user belongs to a specific group on social media, emails related to that group can be prioritized. Furthermore, if a user participates in a specific event on social media, emails related to that event can be prioritized. In this way, by analyzing a user's social media activity, relevant emails can be prioritized.

[0066] An email management system can analyze a user's past email sending history and select the optimal sending method. For example, if a user frequently sent emails during a specific time period in the past, the system can concentrate email sending during that time. If a user previously prioritized sending emails to a specific sender, the system can prioritize sending emails to that sender. Furthermore, if a user previously sent emails using a specific device, the system can send emails using a method optimized for that device. In this way, by analyzing a user's past email sending history, the system can select the most suitable sending method.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The retrieval unit retrieves incoming emails. The retrieval unit can retrieve incoming emails from, for example, a mail server. The retrieval unit can communicate with the mail server using protocols such as POP3 or IMAP to retrieve incoming emails. The retrieval unit can access the mail server at specific time intervals to retrieve new emails. The retrieval unit can also retrieve emails manually by the user. Step 2: The classification unit classifies the emails acquired by the acquisition unit. The classification unit can, for example, automatically categorize emails based on their content. The classification unit can analyze the content of emails using natural language processing technology and classify them based on pre-learned categories. For example, the classification unit can automatically move urgent customer inquiry emails to the "Important" folder. The classification unit can also classify routine business communication emails into the "Daily Business" folder. Step 3: The summary generation unit summarizes the content of the emails classified by the classification unit. The summary generation unit can, for example, convert long emails into concise summaries. The summary generation unit can analyze the content of emails using natural language processing technology, extract important points, and generate summaries. The summary generation unit can, for example, display the email headlines and concise summaries. Even with long emails, the summary generation unit allows users to grasp the important points simply by reading the summary. Step 4: The reply generation unit generates a reply to the email summarized by the summary generation unit. The reply generation unit can, for example, analyze the content of the email and past exchanges to generate an appropriate reply. The reply generation unit can analyze the content of the email using natural language processing techniques to generate an appropriate reply. The reply generation unit can, for example, present multiple reply options and allow the user to select or edit one. The reply generation unit can pass the reply selected by the user to the sender. Step 5: The sender sends the reply generated by the reply generation unit. The sender can send the reply, for example, through a mail server. The sender can communicate with the mail server using the SMTP protocol and send the reply. The sender can also send the reply manually by the user.

[0069] (Example of form 2) The email management system according to an embodiment of the present invention is a system that streamlines email management by utilizing generative AI. This system is an extremely useful tool for companies and individuals that need to deal with a large volume of emails on a daily basis. The email management system has an intelligent classification function that automatically classifies incoming emails and sorts them based on priority. This minimizes the risk of users missing important emails. For example, urgent inquiry emails from customers are automatically sorted into an "important" folder, and routine business communication emails are classified into a "routine" folder. Next, the email management system has a news-style summarization function that displays the content of each email as a headline and a concise summary. This allows users to quickly grasp information, contributing to time savings and efficient information processing. For example, even with long emails, users can grasp the important points by simply reading the summary. Furthermore, the email management system has an AI-assisted reply function that generates appropriate automatic replies to important emails or presents multiple reply options. This improves the quality and speed of replies and enables consistent communication. For example, in response to an inquiry from a customer, the AI ​​can automatically generate a reply, which the user can then review and send. Furthermore, the email management system features continuous learning capabilities that allow it to learn user behavior patterns and improve classification and prioritization over time. This means the system continuously evolves to meet user needs. For example, if a user consistently treats emails from a particular sender as "important," the system learns this pattern and automatically moves emails from that sender to the "important" folder in the future. In this way, the email management system leverages generative AI to streamline email management and improve user productivity. As a result, the email management system makes email management more efficient for users and minimizes the risk of missing important emails.

[0070] The email management system according to this embodiment comprises an acquisition unit, a classification unit, a summary generation unit, a reply generation unit, and a sending unit. The acquisition unit acquires incoming emails. The acquisition unit can, for example, acquire incoming emails from a mail server. The acquisition unit can communicate with a mail server using protocols such as POP3 or IMAP to acquire incoming emails. The acquisition unit can, for example, access a mail server at specific time intervals to acquire new emails. The acquisition unit can also allow users to manually acquire emails. The classification unit classifies the emails acquired by the acquisition unit. The classification unit can, for example, automatically categorize emails based on their content. The classification unit can analyze the content of emails using natural language processing technology and classify them based on pre-learned categories. The classification unit can, for example, automatically move urgent inquiry emails from customers to an "important" folder. The classification unit can also classify routine business communication emails into a "routine business" folder. The summary generation unit summarizes the content of emails classified by the classification unit. The summary generation unit can, for example, convert long emails into concise summaries. The summary generation unit can analyze the content of an email using natural language processing technology, extract key points, and generate a summary. For example, the summary generation unit can display the email's headline and a concise summary. Even with lengthy emails, the summary generation unit allows users to grasp the key points simply by reading the summary. The reply generation unit generates a reply to the email summarized by the summary generation unit. For example, the reply generation unit can analyze the email content and past exchanges to generate an appropriate reply. The reply generation unit can analyze the email content using natural language processing technology to generate an appropriate reply. For example, the reply generation unit can present multiple reply options, allowing the user to select or edit one. The reply generation unit can pass the user's selected reply to the sender. The sender sends the reply generated by the reply generation unit. The sender can send the reply via a mail server, for example. The sender can communicate with the mail server using the SMTP protocol to send the reply. The sender can also accept replies sent manually by the user.As a result, the email management system according to this embodiment can efficiently retrieve, classify, summarize, generate replies to, and send emails.

[0071] The retrieval unit retrieves incoming emails. For example, the retrieval unit can retrieve incoming emails from a mail server. The retrieval unit can communicate with the mail server using protocols such as POP3 and IMAP to retrieve incoming emails. Specifically, when using the POP3 protocol, the retrieval unit connects to the mail server, sends user authentication information, and downloads new emails. When using the IMAP protocol, the retrieval unit accesses the mail folder on the mail server, retrieves the email header information, and then downloads the necessary email body. The retrieval unit can, for example, access the mail server at specific time intervals to retrieve new emails. This allows users to check for new emails in real time. The retrieval unit can also retrieve emails manually. For example, when a user clicks the "Receive" button in their email client, the retrieval unit immediately accesses the mail server and retrieves the new email. The retrieval unit also has a function to log the email retrieval status and notify the user if an error occurs. This ensures that the retrieval unit reliably retrieves incoming emails and allows users to always check for the latest emails.

[0072] The classification unit categorizes emails acquired by the acquisition unit. For example, the classification unit can automatically categorize emails based on their content. The classification unit can analyze email content using natural language processing technology and classify them based on pre-learned categories. Specifically, the classification unit analyzes the email subject, body, sender information, etc., and uses machine learning algorithms to sort emails into the appropriate category. For example, it can automatically sort urgent customer inquiry emails into the "Important" folder. The classification unit can also classify routine business communication emails into the "Routine" folder. Furthermore, the classification unit allows users to manually set categories and move emails to specific folders according to user instructions. The classification unit also has a function to log the email classification results so that users can review them later. This allows the classification unit to efficiently organize emails and enable users to quickly find the emails they need.

[0073] The summary generation unit summarizes the content of emails classified by the classification unit. For example, the summary generation unit can convert a long email into a concise summary. Using natural language processing technology, the summary generation unit analyzes the email content, extracts key points, and generates a summary. Specifically, it extracts keywords and important phrases from the email body and generates a concise summary based on them. The summary generation unit can display, for example, the email headline and a concise summary. This allows users to grasp the key points of even long emails simply by reading the summary. The summary generation unit also includes a function that allows users to adjust the accuracy of the summary, changing the level of detail to their preference. Furthermore, the summary generation unit has a function to log the summary results for later review. This enables the summary generation unit to efficiently summarize email content, allowing users to quickly grasp important information.

[0074] The reply generation unit generates replies to emails summarized by the summary generation unit. For example, the reply generation unit can analyze the email content and past exchanges to generate appropriate replies. It can also analyze email content using natural language processing techniques to generate appropriate replies. Specifically, it analyzes the email body and generates the optimal reply by referencing past reply patterns and standard phrases. For example, it can present multiple reply options, allowing the user to select or edit one. This allows the user to choose the reply that best suits their intentions. The reply generation unit can then pass the user's selected reply to the sender. Furthermore, the reply generation unit has a function to log the reply generation process, allowing the user to review it later. This enables the reply generation unit to efficiently generate appropriate replies and support the user's reply process.

[0075] The sending unit sends the reply generated by the reply generation unit. The sending unit can send replies, for example, through a mail server. The sending unit can communicate with the mail server using the SMTP protocol and send replies. Specifically, the sending unit connects to the mail server using the user's authentication information and adds the reply email to the sending queue. The sending unit monitors the email sending status and verifies whether the sending was successful. The sending unit can also receive replies manually from the user. For example, when the user clicks the "Send" button, the sending unit immediately connects to the mail server and sends the reply email. The sending unit also has a function to log the sending results and notify the user if an error occurs. This ensures that the sending unit can reliably send reply emails and that users can reliably send emails.

[0076] The classification unit can automatically categorize emails based on their content. For example, the classification unit can analyze the content of emails using natural language processing technology and classify them based on pre-learned categories. For example, the classification unit can automatically move urgent customer inquiry emails to an "important" folder. The classification unit can also classify routine business communication emails into a "routine" folder. This streamlines email management by automatically categorizing emails based on their content. Some or all of the above-described processes in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can classify emails using an AI model that takes email content as input and outputs categories.

[0077] The summary generation unit can convert long emails into concise summaries. For example, the summary generation unit analyzes the email content using natural language processing technology, extracts key points, and generates a summary. The summary generation unit can display, for example, the email's headline and a concise summary. Even with long emails, the summary generation unit allows users to grasp the key points simply by reading the summary. This enables users to quickly understand information by converting long emails into concise summaries. Some or all of the above-described processes in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can generate a summary using an AI model that takes email content as input and outputs a summary.

[0078] The reply generation unit can analyze the content of the email and past exchanges to generate an appropriate reply. For example, the reply generation unit can analyze the content of the email using natural language processing technology to generate an appropriate reply. For example, the reply generation unit can present multiple reply options and allow the user to select or edit one. The reply generation unit can pass the reply selected by the user to the sender. This allows for the generation of an appropriate reply by analyzing the content of the email and past exchanges. 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 generate a reply using an AI model that takes the content of the email and past exchanges as input and outputs a reply.

[0079] The reply generation unit can present multiple reply options, allowing the user to select or edit one. For example, the reply generation unit can analyze the email content using natural language processing technology and generate multiple reply options. The reply generation unit can then pass the user's selected reply to the sender. This allows the user to select or edit the most suitable reply by presenting multiple options. Some or all of the above processing in the reply generation unit may be performed using AI, or without AI. For example, the reply generation unit can generate reply options using an AI model that takes the email content as input and outputs multiple reply options.

[0080] The sending unit can send the generated reply. The sending unit can send the reply, for example, through a mail server. The sending unit can communicate with a mail server using the SMTP protocol and send the reply. The sending unit can also allow the user to send the reply manually. This streamlines email sending by sending the generated reply. Some or all of the above processing in the sending unit may be performed using AI, for example, or not using AI. For example, the sending unit can send the reply using an AI model that takes the generated reply as input and performs the sending.

[0081] The classification unit can learn user behavior patterns and perform more accurate classification and prioritization over time. For example, the classification unit uses machine learning algorithms to learn user behavior patterns. If a user consistently treats emails from a particular sender as "important," the classification unit can learn this pattern and automatically move emails from that sender to the "important" folder in the future. The classification unit can also adjust email priorities based on user behavior patterns. This improves the accuracy of classification and prioritization by learning user behavior patterns. Some or all of the above processes in the classification unit may be performed using AI, for example, or not. For example, the classification unit can perform classification and prioritization using an AI model that takes user behavior data as input and outputs classifications and priorities.

[0082] The retrieval 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 retrieval unit can reduce the frequency of email retrieval and reduce notifications. If the user is relaxed, the retrieval unit can also retrieve emails in real time and notify immediately. If the user is in a hurry, the retrieval unit can prioritize retrieving only important emails and notify immediately. This reduces user stress by adjusting the timing of email retrieval based on 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 retrieval unit may be performed using AI, for example, or not using AI. For example, the retrieval unit can adjust the retrieval timing using an AI model that takes user emotion data as input and outputs the timing of email retrieval.

[0083] The retrieval unit can analyze the user's past email retrieval history and select the optimal retrieval method. For example, if the user frequently checked their email during a specific time period in the past, the retrieval unit will concentrate on retrieving emails during that time period. If the user prioritized emails from a specific sender in the past, the retrieval unit can also prioritize retrieving emails from that sender. If the user checked their email on a specific device in the past, the retrieval unit can also retrieve emails in a way optimized for that device. In this way, the optimal retrieval method can be selected by analyzing the user's past email retrieval history. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can select the retrieval method using an AI model that takes the user's past email retrieval history data as input and outputs the optimal retrieval method.

[0084] The retrieval unit can filter emails based on the user's current projects and areas of interest when retrieving them. For example, the retrieval unit can prioritize retrieving only emails related to projects the user is currently working on. The retrieval unit can also prioritize retrieving emails related to specific topics the user has shown interest in. The retrieval unit can also 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 retrieval unit may be performed using AI, for example, or not. For example, the retrieval unit can filter emails using an AI model that takes data on the user's projects and areas of interest as input and outputs filtered emails.

[0085] The retrieval 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 retrieval unit may postpone retrieving less important emails. If the user is relaxed, the retrieval unit may retrieve all emails equally. If the user is in a hurry, the retrieval unit may prioritize retrieving only important emails. This allows for the priority of retrieving important emails by determining the priority of emails based on 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 retrieval unit may be performed using AI or not. For example, the retrieval unit can determine priorities using an AI model that takes user emotion data as input and outputs email priorities.

[0086] The retrieval unit can prioritize retrieving highly relevant emails by considering the user's geographical location information when retrieving emails. For example, if the user is in a specific region, the retrieval unit will prioritize retrieving emails related to that region. If the user is on a business trip, the retrieval unit can also prioritize retrieving emails related to the business trip destination. If the user is at home, the retrieval unit can also prioritize retrieving emails related to the home. By prioritizing the retrieval of highly relevant emails by considering the user's geographical location information, the user can quickly obtain information that is important to them. Some or all of the above processing in the retrieval unit may be performed using AI, for example, or without AI. For example, the retrieval unit can retrieve emails using an AI model that takes the user's geographical location information as input and outputs highly relevant emails.

[0087] The acquisition unit can analyze a user's social media activity when acquiring emails and retrieve relevant emails. For example, if a user posts about a specific topic on social media, the acquisition unit will prioritize retrieving emails related to that topic. If a user participates in a specific group on social media, the acquisition unit can also prioritize retrieving emails related to that group. If a user participates in a specific event on social media, the acquisition unit can also prioritize retrieving emails related to that event. 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 acquisition unit may be performed using AI, for example, or without AI. For example, the acquisition unit can acquire emails using an AI model that takes user social media activity data as input and outputs relevant emails.

[0088] The classification unit can estimate the user's emotions and adjust the classification criteria based on the estimated emotions. For example, if the user is stressed, the classification unit may prioritize classifying high-priority emails. If the user is relaxed, the classification unit may classify all emails equally. If the user is in a hurry, the classification unit may prioritize classifying only important emails. This allows for the priority of important emails by adjusting the classification criteria based on 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 classification unit may be performed using AI, or not. For example, the classification unit may adjust the classification criteria using an AI model that takes user emotion data as input and outputs classification criteria.

[0089] The classification unit can improve the accuracy of classification by considering the interrelationships between emails during the classification process. For example, the classification unit can group and classify emails from the same sender. It can also group and classify emails related to the same project. It can also group and classify emails related to the same topic. This improves the accuracy of classification by considering the interrelationships between emails. Some or all of the above processing in the classification unit may be performed using AI, for example, or not. For example, the classification unit can improve the accuracy of classification by using an AI model that takes interrelationship data of emails as input and outputs classification results.

[0090] The classification unit can classify emails while considering the sender's attribute information. For example, if the sender is a customer, the classification unit will classify it into the customer folder. If the sender is a supervisor, the classification unit can also classify it into the supervisor folder. If the sender is a colleague, the classification unit can also classify it into the colleague folder. In this way, by considering the sender's attribute information, emails can be classified into the appropriate folder. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can perform classification using an AI model that takes sender attribute information as input and outputs classification results.

[0091] The classification unit can estimate the user's emotions and adjust the order in which the classification results are displayed based on the estimated emotions. For example, if the user is stressed, the classification unit can display high-priority emails first. If the user is relaxed, the classification unit can also display all emails equally. If the user is in a hurry, the classification unit can also display only important emails first. This allows for the prioritization of important emails by adjusting the order in which the classification results are displayed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can adjust the display order using an AI model that takes user emotion data as input and outputs the display order.

[0092] The classification unit can classify emails while considering their geographical distribution. For example, if the sender is in a specific region, the classification unit can classify the email into a folder related to that region. If the sender is on a business trip, the classification unit can also classify the email into a folder related to the destination. If the sender is at home, the classification unit can also classify the email into a folder related to their home. In this way, by considering the geographical distribution of emails, they can be classified into relevant folders. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can perform classification using an AI model that takes sender geographical distribution data as input and outputs classification results.

[0093] The classification unit can improve the accuracy of its classification by referring to relevant literature for emails during the classification process. For example, the classification unit can refer to literature related to the content of an email and classify it into the appropriate category. The classification unit can also refer to past emails related to the content of an email and classify them into the appropriate category. The classification unit can also refer to websites related to the content of an email and classify them into the appropriate category. This improves the accuracy of the classification by referring to relevant literature for emails. Some or all of the above processing in the classification unit may be performed using AI, for example, or without AI. For example, the classification unit can improve the accuracy of its classification by using an AI model that takes relevant literature data as input and outputs classification results.

[0094] The summary generation 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 summary generation unit can provide a concise and to-the-point summary. If the user is relaxed, the summary generation unit can also provide a summary that includes detailed information. If the user is in a hurry, the summary generation unit can also summarize only the most important points. In this way, by adjusting the way the summary is presented based on 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 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 summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can adjust the way the summary is presented using an AI model that takes user emotion data as input and outputs a way to present the summary.

[0095] The summary generation unit can adjust the level of detail in the summary based on the importance of the email during summary generation. For example, the summary generation unit can provide a detailed summary for high-importance emails, and a concise summary for low-importance emails. The summary generation unit can also adjust the length of the summary according to its importance. This allows for an appropriate summary of important information 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 summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can adjust the level of detail using an AI model that takes email importance data as input and outputs the level of detail in the summary.

[0096] The summary generation unit can apply different summarization algorithms depending on the email category when generating summaries. For example, the summary generation unit can apply a business-oriented summarization algorithm to business emails. It can also apply a private-oriented summarization algorithm to private emails. It can also apply a newsletter-oriented summarization algorithm to newsletters. By applying different summarization algorithms depending on the email category, it is possible to generate summaries that are optimal for each category. Some or all of the above processing in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can generate summaries using an AI model that takes email category data as input and outputs a summarization algorithm.

[0097] The summary generation 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 summary generation unit can provide a short, concise summary. If the user is relaxed, the summary generation unit can also provide a longer summary containing more detailed information. If the user is in a hurry, the summary generation unit can summarize only the most important points. By adjusting the length of the summary based on the user's emotions, the system can provide a summary of the optimal length for the user. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a 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 summary generation unit may be performed using AI, or not. For example, the summary generation unit can adjust the length using an AI model that takes user emotion data as input and outputs the length of the summary.

[0098] The summary generation unit can determine the priority of summaries based on the email sending date during summary generation. For example, the summary generation unit prioritizes summarizing recently sent emails. The summary generation unit can also summarize older emails more concisely. The summary generation unit can also adjust the level of detail in the summary according to the sending date. This allows for prioritizing the summaries based on the email sending date, thereby ensuring that the most up-to-date information is summarized first. Some or all of the above processing in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can determine the priority using an AI model that takes email sending date data as input and outputs the priority of summaries.

[0099] The summary generation unit can adjust the order of summaries based on the relevance of the emails during the summaries generation process. For example, the summary generation unit prioritizes summarizing highly relevant emails. The summary generation unit can also summarize less relevant emails concisely. The summary generation unit can also adjust the order of summaries according to their relevance. This allows for prioritizing the summarization of highly relevant information by adjusting the order of summaries based on the relevance of the emails. Some or all of the above processing in the summary generation unit may be performed using AI, for example, or without AI. For example, the summary generation unit can adjust the order using an AI model that takes email relevance data as input and outputs the order of summaries.

[0100] The reply generation unit can estimate the user's emotions and adjust the way the reply is expressed based on the estimated emotions. For example, if the user is stressed, the reply generation unit can provide a concise and to-the-point reply. If the user is relaxed, the reply generation unit can also provide a reply that includes detailed information. If the user is in a hurry, the reply generation unit can also reply with only the most important points. In this way, by adjusting the way the reply is expressed based on the user's emotions, it is possible to provide a reply that is appropriate for the user. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 without AI. For example, the reply generation unit can adjust the way the reply is expressed using an AI model that takes user emotion data as input and outputs a way of expressing the reply.

[0101] 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 provide a detailed reply to a high-importance email. The reply generation unit can also provide a concise reply to a low-importance email. The reply generation unit can also adjust the length of the reply according to its importance. This allows for the provision of appropriate replies to important emails by adjusting the level of detail based on the importance of the email. 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 adjust the level of detail using an AI model that takes email importance data as input and outputs the level of detail of the reply.

[0102] 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. It can also apply a newsletter-oriented reply algorithm to newsletters. By applying different reply algorithms depending on the email category, it is possible to generate the most appropriate reply 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 generate replies using an AI model that takes email category data as input and outputs a reply algorithm.

[0103] 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 provide a short, to-the-point reply. If the user is relaxed, the reply generation unit can also provide a longer reply that includes more detailed information. If the user is in a hurry, the reply generation unit can also reply with only the most important points. This allows the system to provide a reply of the optimal length for the user by adjusting the length of the reply based on 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 reply generation unit may be performed using AI, for example, or not using AI. For example, the reply generation unit can adjust the length using an AI model that takes user emotion data as input and outputs the length of the reply.

[0104] The reply generation unit can determine the priority of replies based on when the email was sent. For example, the reply generation unit will quickly reply to recently sent emails. The reply generation unit can also reply concisely to older emails. The reply generation unit can also adjust the level of detail in the reply according to when it was sent. This enables quick replies by determining the priority of replies based on when the email was sent. 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 determine the priority using an AI model that takes email sending time data as input and outputs the priority of replies.

[0105] 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 will prioritize replying to highly relevant emails. The reply generation unit can also reply concisely to less relevant emails. The reply generation unit can also adjust the order of replies according to relevance. This allows for prioritizing replies to highly relevant emails by adjusting the order of replies based on the relevance of the 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 adjust the order using an AI model that takes email relevance data as input and outputs the order of replies.

[0106] The sending unit can estimate the user's emotions and adjust the sending timing based on the estimated emotions. For example, if the user is stressed, the sending unit can delay sending to increase the time for confirmation. If the user is relaxed, the sending unit can send immediately. If the user is in a hurry, the sending unit can prioritize sending only important emails. This allows emails to be sent at the appropriate time by adjusting the sending timing based on 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 sending unit may be performed using AI or not. For example, the sending unit can adjust the timing using an AI model that takes user emotion data as input and outputs the timing of sending.

[0107] The sending unit can determine the sending priority based on the importance of the emails at the time of sending. For example, the sending unit may prioritize sending emails with high importance. The sending unit may also postpone sending emails with low importance. The sending unit may also adjust the sending order according to importance. In this way, by determining the sending priority based on the importance of the emails, important emails can be sent preferentially. Some or all of the above processing in the sending unit may be performed using AI, for example, or not using AI. For example, the sending unit can determine the priority using an AI model that takes email importance data as input and outputs the sending priority.

[0108] The sending unit can consider the sender's attribute information when sending emails. For example, if the sender is a customer, the sending unit can prioritize sending emails classified in the customer folder. If the sender is a supervisor, the sending unit can also prioritize sending emails classified in the supervisor folder. If the sender is a colleague, the sending unit can also prioritize sending emails classified in the colleague folder. This allows for appropriate sending by considering the sender's attribute information. Some or all of the above processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit can perform sending using an AI model that takes sender attribute information as input and outputs the sending result.

[0109] The sending unit can estimate the user's emotions and adjust the sending method based on the estimated emotions. For example, if the user is stressed, the sending unit may prompt confirmation before sending. If the user is relaxed, the sending unit may send immediately. If the user is in a hurry, the sending unit may prioritize sending only important emails. This allows emails to be sent in an appropriate manner by adjusting the sending method based on 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 sending unit may be performed using AI or not using AI. For example, the sending unit can adjust the method using an AI model that takes user emotion data as input and outputs a sending method.

[0110] The sending unit can send emails while considering their geographical distribution. For example, if the recipient is in a specific region, the sending unit can prioritize sending emails related to that region. If the recipient is on a business trip, the sending unit can also prioritize sending emails related to the destination. If the recipient is at home, the sending unit can also prioritize sending emails related to home. By considering the geographical distribution of emails, the sending unit can send appropriate emails to relevant regions. Some or all of the above processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit can perform sending using an AI model that takes geographical distribution data of recipients as input and outputs the sending results.

[0111] The sending unit can improve the accuracy of email transmission by referring to relevant literature during transmission. For example, the sending unit can refer to literature related to the content of the email and select an appropriate transmission method. The sending unit can also refer to past emails related to the content of the email and select an appropriate transmission method. The sending unit can also refer to websites related to the content of the email and select an appropriate transmission method. This improves the accuracy of transmission by referring to relevant literature. Some or all of the above processing in the sending unit may be performed using AI, for example, or without AI. For example, the sending unit can improve the accuracy of transmission by using an AI model that takes relevant literature data as input and outputs a transmission method.

[0112] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0113] An email management system can estimate a user's emotions and adjust how emails are displayed based on those emotions. For example, if a user is stressed, important emails can be highlighted while others are displayed less prominently. If a user is relaxed, all emails can be displayed equally. If a user is in a hurry, important emails can be displayed first, while others are displayed later. By adjusting how emails are displayed based on the user's emotions, this system can reduce user stress and enable efficient email management. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] An email management system can analyze a user's past email viewing history and select the optimal display method. For example, if a user frequently checked their email during a specific time period in the past, emails from that time period can be concentrated and displayed. If a user previously prioritized emails from a particular sender, emails from that sender can be displayed preferentially. Furthermore, if a user previously checked their email on a specific device, emails can be displayed in a way optimized for that device. In this way, by analyzing a user's past email viewing history, the system can select the most optimal display method.

[0115] An email management system can estimate a user's emotions and adjust how emails are summarized based on that estimation. For example, if a user is stressed, a concise and to-the-point summary can be provided. If the user is relaxed, a summary with more detailed information can be provided. If the user is in a hurry, only the most important points can be summarized. This allows for summaries that are easier for the user to understand by adjusting the summarization method based on their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0116] The email management system can customize how emails are displayed based on the user's current projects and areas of interest. For example, it can prioritize displaying only emails related to the user's current projects. It can also prioritize emails related to specific topics the user is interested in. Furthermore, it can prioritize emails containing specific keywords the user is using. This allows for the prioritization of highly relevant emails by tailoring the display method to the user's current projects and areas of interest.

[0117] An email management system can estimate a user's emotions and adjust its email response based on those emotions. For example, if a user is stressed, it can provide a concise and to-the-point response. If the user is relaxed, it can provide a response that includes detailed information. If the user is in a hurry, it can respond with only the most important points. This allows the system to provide appropriate responses to users by adjusting the response method based on their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0118] An email management system can adjust how emails are displayed based on the user's geographical location. For example, if a user is in a specific region, emails related to that region can be prioritized. If a user is on a business trip, emails related to their destination can be prioritized. Similarly, if a user is at home, emails related to their home can be prioritized. By adjusting how emails are displayed based on the user's geographical location, important information can be displayed quickly to the user.

[0119] An email management system can estimate a user's emotions and adjust how emails are retrieved based on those emotions. For example, if a user is stressed, the frequency of email retrieval can be reduced and notifications less frequent. If a user is relaxed, emails can be retrieved in real time and notifications can be sent immediately. If a user is in a hurry, only important emails can be prioritized and notifications sent immediately. This reduces user stress by adjusting email retrieval based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] An email management system can analyze a user's social media activity and prioritize the display of relevant emails. For example, if a user posts about a specific topic on social media, emails related to that topic can be prioritized. If a user belongs to a specific group on social media, emails related to that group can be prioritized. Furthermore, if a user participates in a specific event on social media, emails related to that event can be prioritized. In this way, by analyzing a user's social media activity, relevant emails can be prioritized.

[0121] An email management system can estimate a user's emotions and adjust how emails are sent based on that estimation. For example, if a user is stressed, it can prompt for confirmation before sending. If the user is relaxed, it can send immediately. If the user is in a hurry, it can prioritize sending only important emails. This allows emails to be sent in an appropriate manner by adjusting the sending method based on the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0122] An email management system can analyze a user's past email sending history and select the optimal sending method. For example, if a user frequently sent emails during a specific time period in the past, the system can concentrate email sending during that time. If a user previously prioritized sending emails to a specific sender, the system can prioritize sending emails to that sender. Furthermore, if a user previously sent emails using a specific device, the system can send emails using a method optimized for that device. In this way, by analyzing a user's past email sending history, the system can select the most suitable sending method.

[0123] The following briefly describes the processing flow for example form 2.

[0124] Step 1: The retrieval unit retrieves incoming emails. The retrieval unit can retrieve incoming emails from, for example, a mail server. The retrieval unit can communicate with the mail server using protocols such as POP3 or IMAP to retrieve incoming emails. The retrieval unit can access the mail server at specific time intervals to retrieve new emails. The retrieval unit can also retrieve emails manually by the user. Step 2: The classification unit classifies the emails acquired by the acquisition unit. The classification unit can, for example, automatically categorize emails based on their content. The classification unit can analyze the content of emails using natural language processing technology and classify them based on pre-learned categories. For example, the classification unit can automatically move urgent customer inquiry emails to the "Important" folder. The classification unit can also classify routine business communication emails into the "Daily Business" folder. Step 3: The summary generation unit summarizes the content of the emails classified by the classification unit. The summary generation unit can, for example, convert long emails into concise summaries. The summary generation unit can analyze the content of emails using natural language processing technology, extract important points, and generate summaries. The summary generation unit can, for example, display the email headlines and concise summaries. Even with long emails, the summary generation unit allows users to grasp the important points simply by reading the summary. Step 4: The reply generation unit generates a reply to the email summarized by the summary generation unit. The reply generation unit can, for example, analyze the content of the email and past exchanges to generate an appropriate reply. The reply generation unit can analyze the content of the email using natural language processing techniques to generate an appropriate reply. The reply generation unit can, for example, present multiple reply options and allow the user to select or edit one. The reply generation unit can pass the reply selected by the user to the sender. Step 5: The sender sends the reply generated by the reply generation unit. The sender can send the reply, for example, through a mail server. The sender can communicate with the mail server using the SMTP protocol and send the reply. The sender can also send the reply manually by the user.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the acquisition unit, classification unit, summary generation unit, reply generation unit, and transmission unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit is implemented by the processor 46 of the smart device 14 and acquires incoming emails from the mail server. The classification unit is implemented by the identification processing unit 290 of the data processing device 12 and automatically classifies incoming emails. The summary generation unit is implemented by the control unit 46A of the smart device 14 and summarizes the content of the emails. The reply generation unit is implemented by the identification processing unit 290 of the data processing device 12 and generates an appropriate reply. The transmission unit is implemented by the processor 46 of the smart device 14 and transmits 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 modified in various ways.

[0129] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the acquisition unit, classification unit, summary generation unit, reply generation unit, and transmission unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit is implemented by the processor 46 of the smart glasses 214 and acquires incoming emails from the mail server. The classification unit is implemented by the identification processing unit 290 of the data processing device 12 and automatically classifies incoming emails. The summary generation unit is implemented by the control unit 46A of the smart glasses 214 and summarizes the content of the emails. The reply generation unit is implemented by the identification processing unit 290 of the data processing device 12 and generates an appropriate reply. The transmission unit is implemented by the processor 46 of the smart glasses 214 and transmits 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 modified in various ways.

[0145] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the acquisition unit, classification unit, summary generation unit, reply generation unit, and transmission unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the acquisition unit is implemented by the processor 46 of the headset terminal 314 and acquires incoming emails from the mail server. The classification unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically classifies incoming emails. The summary generation unit is implemented by the control unit 46A of the headset terminal 314 and summarizes the content of the emails. The reply generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates an appropriate reply. The transmission unit is implemented by the processor 46 of the headset terminal 314 and transmits 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 modified in various ways.

[0161] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.).

[0174] 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.

[0175] 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.

[0176] 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.

[0177] Each of the multiple elements described above, including the acquisition unit, classification unit, summary generation unit, reply generation unit, and transmission unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the acquisition unit is implemented by the processor 46 of the robot 414 and acquires incoming emails from the mail server. The classification unit is implemented by the identification processing unit 290 of the data processing unit 12 and automatically classifies incoming emails. The summary generation unit is implemented by the control unit 46A of the robot 414 and summarizes the content of the emails. The reply generation unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates an appropriate reply. The transmission unit is implemented by the processor 46 of the robot 414 and transmits 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 modified in various ways.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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."

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] (Note 1) The retrieval unit retrieves received emails, A classification unit that classifies the emails acquired by the acquisition unit, A summary generation unit that summarizes the content of emails classified by the classification unit, A reply generation unit that generates a reply to the email summarized by the summary generation unit, The system includes a sending unit that sends the reply generated by the reply generation unit. A system characterized by the following features. (Note 2) The aforementioned classification unit is The system automatically categorizes emails based on their content. The system described in Appendix 1, characterized by the features described herein. (Note 3) The summary generation unit, Convert long emails into concise summaries. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned reply generation unit, The system analyzes email content and past correspondence to generate appropriate replies. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned reply generation unit, Present multiple response options and allow the user to select or edit one. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned transmitting unit Send the generated reply The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned classification unit is It learns user behavior patterns and performs more accurate classification and prioritization over time. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition 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 acquisition unit is, Analyze the user's past email retrieval history and select the optimal retrieval method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition 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 acquisition 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 acquisition 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 acquisition 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 aforementioned classification unit is It estimates the user's emotions and adjusts the classification criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned classification unit is When classifying emails, consider the relationships between them to improve classification accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned classification unit is When classifying emails, the sender's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned classification unit is It estimates the user's emotions and adjusts the order in which the classification results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned classification unit is When classifying emails, the geographical distribution of the emails should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned classification unit is During classification, we refer to related literature in emails to improve the accuracy of the classification. The system described in Appendix 1, characterized by the features described herein. (Note 20) The summary generation unit, It estimates the user's emotions and adjusts the way the summary is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The summary generation unit, 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 22) The summary generation unit, 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 23) The summary generation unit, It estimates the user's sentiment and adjusts the length of the summary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 24) The summary generation unit, When generating summaries, prioritize summaries based on when the emails were sent. The system described in Appendix 1, characterized by the features described herein. (Note 25) The summary generation unit, 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 26) The aforementioned reply generation unit, It estimates the user's emotions and adjusts the way it expresses its replies based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned reply generation unit, When generating a reply, adjust the level of detail in the reply based on the importance of the email. The system described in Appendix 1, characterized by the features described herein. (Note 28) 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 29) The aforementioned reply generation unit, It estimates the user's emotions and adjusts the length of the reply based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned reply generation unit, When generating a reply, the system prioritizes replies based on when the email was sent. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned reply generation unit, When generating replies, the order of replies is adjusted based on the relevance of the emails. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned transmitting unit It estimates the user's emotions and adjusts the timing of sending messages based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned transmitting unit When sending an email, the system prioritizes sending it based on its importance. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned transmitting unit When sending an email, the sender's attribute information is taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned transmitting unit It estimates the user's emotions and adjusts the sending method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned transmitting unit When sending emails, the system takes into account the geographical distribution of the emails. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned transmitting unit When sending an email, we refer to related literature to improve the accuracy of the transmission. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0197] 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. The retrieval unit retrieves received emails, A classification unit that classifies the emails acquired by the acquisition unit, A summary generation unit that summarizes the content of emails classified by the classification unit, A reply generation unit that generates a reply to the email summarized by the summary generation unit, The system includes a sending unit that sends the reply generated by the reply generation unit. A system characterized by the following features.

2. The aforementioned classification unit is The system automatically categorizes emails based on their content. The system according to feature 1.

3. The summary generation unit, Convert long emails into concise summaries. The system according to feature 1.

4. The aforementioned reply generation unit, The system analyzes email content and past correspondence to generate appropriate replies. The system according to feature 1.

5. The aforementioned reply generation unit, Present multiple response options and allow the user to select or edit one. The system according to feature 1.

6. The aforementioned transmitting unit Send the generated reply The system according to feature 1.

7. The aforementioned classification unit is It learns user behavior patterns and performs more accurate classification and prioritization over time. The system according to feature 1.

8. The acquisition 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.

9. The acquisition unit is, Analyze the user's past email retrieval history and select the optimal retrieval method. The system according to feature 1.

10. The acquisition unit is, When retrieving emails, filtering is performed based on the user's current projects and areas of interest. The system according to feature 1.

Images