system

Abstract

The system according to this embodiment aims to prevent accidental sending of emails and errors in attached files before sending them. [Solution] The system according to the embodiment comprises a checking unit, a notification unit, a holding unit, and a correction unit. The checking unit checks the accuracy of the recipient before sending the email. The notification unit notifies the user of any problems detected by the checking unit via a pop-up alert. The holding unit holds the email until the problems notified by the notification unit are confirmed. The correction unit generates a revised version that includes changes to the email recipient, proposed changes to the email text, and deletion of unnecessary lines in attached files.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a risk of occurrence of personal information leakage accidents due to mis-sending of emails or errors in attached files.

[0005] The system according to the embodiment aims to prevent mis-sending and errors in attached files before email sending.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a checking unit, a notification unit, a holding unit, and a correction unit. The checking unit checks the accuracy of the recipient before sending the email. The notification unit notifies the user of any problems detected by the checking unit via a pop-up alert. The holding unit holds the email until the problems notified by the notification unit are confirmed. The correction unit generates a proposed correction, including changes to the email recipient, changes to the email text, and deletion of unnecessary lines in the attachment. [Effects of the Invention]

[0007] The system according to this embodiment can prevent accidental sending of emails and errors in attached files before sending them. [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 misdelivery prevention system according to an embodiment of the present invention is a system that uses a generating AI agent to prevent misdelivery and incorrect attachments before email is sent. In this system, from the moment the send button is pressed until the email is actually sent, the generating AI agent instantly checks whether "the recipient is correct / whether there are any errors in the attached data." The agent notifies the user of any concerns it detects with a pop-up alert and suspends sending until confirmation is received. This prevents the system from becoming a mere formality (due to complacency) by only displaying pop-ups when a concern is detected, rather than every time an email is sent. Furthermore, the generating AI agent creates proposed corrections such as changing the email recipient, revising the text, and deleting unnecessary lines in attached files, minimizing the effort required for rework. This has the potential to prevent approximately 28.7% of personal information leakage incidents from being caused by misdelivery, and the fact that about one in four people have experience of sending an email to the wrong recipient. For example, from the moment the send button is pressed until the email is actually sent, the generating AI agent instantly checks whether "the recipient is correct / whether there are any errors in the attached data." In this process, the generating AI agent thoroughly analyzes whether the recipient's email address is correct and whether there are any errors in the attachments. For example, it can detect if the recipient's email address differs from the recipient's last name listed in the body of the email, or if the attachment contains hidden cells. Next, the agent notifies the user of any detected concerns via a pop-up alert and withholds sending the email until confirmation is received. This allows the user to review the concerns and make corrections as needed. For example, it notifies the user via a pop-up alert if the recipient's email address is incorrect or if there are errors in the attachments. Furthermore, the generating AI agent creates suggested corrections, such as changing the email recipient, revising the email body, or deleting unnecessary lines in the attachments. This allows the user to respond with minimal effort required to redo the work. For example, the generating AI agent can create suggestions such as changing the recipient's email address to a correct one or deleting unnecessary lines in the attachments. This mechanism has the potential to prevent incidents such as the fact that approximately 28.7% of personal information leaks are due to misdelivery, and that about one in four people have experience misdelivering emails.For example, if the recipient's email address is incorrect or there is an error in the attached file, the AI ​​agent can detect this and notify the user via a pop-up alert, thereby preventing accidental sending or attachments. In this way, the system for preventing accidental sending of emails before they are sent can prevent accidental sending or attachments.

[0029] The email misdelivery prevention system according to the embodiment comprises a checking unit, a notification unit, a holding unit, and a correction unit. The checking unit checks the accuracy of the recipient before sending the email. The checking unit can, for example, detect if the recipient's email address differs from the recipient's last name written in the body of the email. The checking unit can also detect if an attached file contains hidden cells. For example, the checking unit can detect hidden cells or hidden data in an Excel file. The notification unit notifies the user of the problem detected by the checking unit using a pop-up alert. The notification unit can, for example, immediately notify the user of the detected concern. For example, the notification unit displays a pop-up alert to inform the user of the problem. The holding unit holds the email until the problem notified by the notification unit is confirmed. For example, the holding unit holds the email sending until the user confirms the problem and completes the correction. For example, the holding unit temporarily suspends the email sending until the user confirms it. The correction unit generates a correction proposal that includes changing the email recipient, changing the text, and deleting unnecessary rows in the attached file. The correction unit generates, for example, a proposal to change the recipient's email address to an appropriate one. The correction unit can also generate a proposal to delete unnecessary lines in the attachment. For example, the correction unit automatically detects unnecessary lines in the attachment and generates a proposal to delete them. As a result, the email sending error prevention system according to the embodiment can prevent email sending errors and incorrect attachments.

[0030] The checking unit verifies the accuracy of the recipient before sending an email. For example, it can detect if the recipient's email address differs from the recipient's last name listed in the email body. Specifically, the checking unit analyzes the recipient information in the email body and compares it with the domain and username portions of the email address to reduce the risk of sending to the wrong recipient. The checking unit can also detect if an attached file contains hidden cells. For example, it can detect hidden cells and hidden data in Excel files. This involves analyzing the file's metadata and internal structure to identify the presence of hidden cells and hidden data. Furthermore, the checking unit can detect specific keywords and phrases in the email body to determine if confidential information is included. For example, it can detect keywords containing confidential information such as credit card numbers and personal information and warn of the risk of sending to the wrong recipient. In this way, the checking unit can check accuracy from multiple perspectives before sending an email, preventing the risk of sending to the wrong recipient.

[0031] The notification unit notifies users of problems detected by the checking unit via pop-up alerts. For example, the notification unit immediately notifies users of detected concerns. Specifically, the notification unit displays a pop-up window on the user's screen, visually presenting details of the detected problem. For example, the notification unit displays a pop-up alert to inform the user of the problem. The pop-up alert includes the type and specific details of the detected problem, as well as recommended actions. The notification unit can also use additional notification methods such as audio alerts and vibration notifications to draw the user's attention. This allows users to quickly understand problems and take appropriate action before sending emails. Furthermore, the notification unit can continuously improve the accuracy and effectiveness of notifications by recording the user's operation history and referring to past notification content and actions. For example, the notification unit learns how to deal with similar problems in the past and incorporates this into future notifications. This allows the notification unit to provide users with quick and accurate notifications, minimizing the risk of accidental sending.

[0032] The holding unit withholds sending until the issue notified by the notification unit is confirmed. For example, the holding unit withholds sending the email until the user confirms the issue and completes the correction. Specifically, the holding unit temporarily suspends sending the email until the user confirms the issue and completes the correction. For example, the holding unit temporarily suspends sending the email until the user confirms it. The holding unit maintains the suspended state of email sending and withholds sending the email until the user confirms the issue and completes the correction. This allows the user to withhold sending the email until they confirm the issue and complete the correction. Furthermore, the holding unit can withhold sending the email until the user confirms the issue and completes the correction. For example, the holding unit temporarily suspends sending the email until the user confirms it. This allows the user to withhold sending the email until they confirm the issue and complete the correction.

[0033] The editing unit generates suggested revisions, including changes to the email recipient, changes to the email content, and deletion of unnecessary lines in attachments. For example, the editing unit generates a suggestion to change the recipient's email address to an appropriate one. Specifically, the editing unit uses AI to analyze the email content and generates appropriate suggested revisions to the recipient and content. For example, the editing unit analyzes the recipient information in the email body and suggests an appropriate email address. The editing unit can also generate suggestions to delete unnecessary lines in attachments. For example, the editing unit automatically detects unnecessary lines in attachments and generates a suggestion to delete them. This uses technology to analyze the file content and identify unnecessary lines and data. Furthermore, the editing unit can detect typographical errors and grammatical mistakes in the email body and suggest revisions. As a result, the editing unit can analyze the email content from multiple angles and generate appropriate revisions. Thus, the email misdelivery prevention system according to the embodiment can prevent misdelivery and incorrect attachments before they occur.

[0034] The checking unit can detect cases where the recipient's email address differs from the recipient's last name written in the email body. For example, the checking unit can detect cases where the recipient's email address does not match the recipient's last name written in the email body. For example, the checking unit compares the recipient's last name written in the email body with the last name in the email address and displays a warning if they do not match. The checking unit can also detect cases where the domain of the email address is different. For example, the checking unit displays a warning if the domain of the email address does not match the domain written in the email body. This prevents accidental sending by detecting errors in the recipient's email address. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can detect the accuracy of an email address using a generative AI model that takes the email body and email address as input and outputs the accuracy of the email address.

[0035] The checking unit can detect if an attached file contains hidden cells. For example, the checking unit can detect hidden cells in an Excel file. For example, the checking unit can detect hidden cells in an Excel file and display a warning. The checking unit can also detect if hidden data is included. For example, the checking unit can detect hidden data in an Excel file and display a warning. This prevents incorrect attachments by detecting errors in attached files. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can detect hidden cells and hidden data using a generative AI model that takes an Excel file as input and outputs whether or not there are hidden cells or hidden data.

[0036] The notification unit can notify users of detected concerns via pop-up alerts. For example, the notification unit can immediately notify users of detected concerns. For example, the notification unit can display a pop-up alert to inform users of the problem. The notification unit can also adjust the design and timing of the alerts. For example, the notification unit can adjust the timing of the alert display according to the user's work status. This prevents accidental sending or attachment by immediately notifying users of concerns. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can notify users of concerns using a generative AI model that takes detected concerns as input and outputs pop-up alerts.

[0037] The correction unit can generate suggestions for changing the recipient's email address to an appropriate one. For example, the correction unit can generate suggestions for changing the recipient's email address to an appropriate one. For example, the correction unit can suggest an appropriate email address with a matching domain. The correction unit can also suggest an appropriate email address by referring to past sending history. For example, the correction unit can suggest an appropriate email address based on the recipients of emails sent in the past. This prevents accidental sending by generating suggestions for changing to an appropriate email address. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the correction unit can suggest an appropriate email address using a generative AI model that takes an email address as input and outputs an appropriate email address.

[0038] The editing unit can generate suggestions for deleting unnecessary rows in an attached file. For example, the editing unit can generate suggestions for deleting unnecessary rows in an attached file. For example, the editing unit can detect blank rows or duplicate data in an Excel file and propose suggestions for their deletion. The editing unit can also analyze the contents of an attached file and automatically detect unnecessary rows. For example, the editing unit can automatically detect unnecessary rows in an Excel file and generate suggestions for their deletion. This prevents accidental attachment by generating suggestions for deleting unnecessary rows in attached files. Some or all of the above processing in the editing unit may be performed using, for example, a generation AI, or without a generation AI. For example, the editing unit can use a generation AI model that takes an Excel file as input and outputs unnecessary rows to propose suggestions for deleting unnecessary rows.

[0039] The checking unit can cross-check the content of the email body and attachments to confirm consistency. For example, the checking unit can verify whether the data in the email body matches the data in the attachments. For example, the checking unit can verify whether the links in the email body match the links in the attachments. The checking unit can also verify whether the dates and times in the email body match the information in the attachments. For example, the checking unit can verify whether the dates and times in the email body match the information in the attachments. By confirming the consistency between the content of the email body and attachments, it is possible to prevent accidental sending or attachments. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can verify consistency using a generative AI model that takes the email body and attachments as input and outputs consistency of content.

[0040] The checking unit can refer to past sending history and detect similar erroneous sending patterns. For example, the checking unit can learn patterns from emails that have been sent erroneously in the past and detect similar patterns. For example, the checking unit can refer to the recipients of emails that have been sent erroneously in the past and warn against sending to the same recipients. The checking unit can also refer to the content of emails that have been sent erroneously in the past and warn against sending emails with the same content. For example, the checking unit can refer to the content of emails that have been sent erroneously in the past and warn against sending emails with the same content. In this way, by detecting past erroneous sending patterns, erroneous sending can be prevented. Some or all of the above processing in the checking unit may be performed using, for example, generative AI, or without generative AI. For example, the checking unit can detect erroneous sending patterns using a generative AI model that takes past sending history as input and outputs similar erroneous sending patterns.

[0041] The checking unit can adjust its checking criteria based on the recipient's organization and position. For example, if the recipient is a superior, the checking unit will perform a rigorous check. For example, if the recipient is a colleague, the checking unit will perform a standard check. The checking unit can also add particularly important check items if the recipient is an external business partner. For example, the checking unit will add particularly important check items if the recipient is an external business partner. This allows for appropriate checking by adjusting the checking criteria according to the recipient's organization and position. Some or all of the above processing in the checking unit may be performed using, for example, generative AI, or without generative AI. For example, the checking unit can adjust its checking criteria using a generative AI model that takes the recipient's organization and position as input and outputs the checking criteria.

[0042] The checking unit can adjust the frequency of checks based on the time of email transmission. For example, the checking unit checks at a normal frequency during business hours. For example, the checking unit can lower the frequency of checks outside of business hours and check only important items. The checking unit can also increase the frequency of checks in emergencies to perform quick checks. For example, the checking unit can increase the frequency of checks in emergencies to perform quick checks. This allows for appropriate checks by adjusting the frequency of checks according to the time of transmission. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can adjust the frequency of checks using a generative AI model that takes the time of transmission as input and outputs the frequency of checks.

[0043] The notification unit can customize the content of notifications based on the user's past interaction history. For example, the notification unit displays relevant notification content based on concerns the user has previously addressed. For example, the notification unit displays notifications including suggested revisions based on content the user has previously revised. The notification unit can also adjust the importance of notifications by considering notifications the user has previously ignored. For example, the notification unit adjusts the importance of notifications by considering notifications the user has previously ignored. This allows for appropriate notifications to be delivered by customizing the content based on past interaction history. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can customize the content of notifications using a generative AI model that takes past interaction history as input and outputs notification content.

[0044] The notification unit can optimize the timing of notifications according to the user's work status. For example, if the user is concentrating on a task, the notification unit will display a notification after the task is completed. For example, if the user is on a break, the notification unit will display a notification immediately. The notification unit can also display a notification after the meeting has ended if the user is in a meeting. For example, if the user is in a meeting, the notification unit will display a notification after the meeting has ended. In this way, appropriate notifications can be provided by optimizing the timing of notifications according to the user's work status. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can optimize the timing of notifications using a generative AI model that takes the user's work status as input and outputs the timing of notifications.

[0045] The notification unit can optimize the notification display format according to the user's device. For example, if the user is using a smartphone, the notification unit will display a notification that is sized to fit the screen. For example, if the user is using a tablet, the notification unit will display a notification optimized for a larger screen. The notification unit can also display a concise and highly visible notification if the user is using a smartwatch. For example, if the user is using a smartwatch, the notification unit will display a concise and highly visible notification. In this way, appropriate notifications can be provided by optimizing the notification display format according to the user's device. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can optimize the notification display format using a generative AI model that takes user device information as input and outputs the notification display format.

[0046] The notification unit can translate notification content based on the user's language settings. For example, the notification unit can automatically set the notification language based on the user's device language settings. For example, the notification unit can provide a language switching function if the user uses multiple languages. The notification unit can also display notifications in a specific language if the user selects that language. For example, the notification unit can display notifications in a specific language if the user selects that language. This allows for appropriate notifications to be provided by translating notification content based on the user's language settings. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can translate notification content using a generative AI model that takes the user's language settings as input and translates the notification content.

[0047] The holding section can reflect changes made by the user while the email is on hold in real time. For example, if the user changes the recipient address, the holding section will immediately reflect this change in the email on hold. For example, if the user changes an attachment, the holding section will immediately reflect this change in the email on hold. The holding section can also immediately reflect changes made by the user in the email body. This allows for appropriate corrections to be made by reflecting changes made while the email is on hold in real time. Some or all of the above processing in the holding section may be performed using, for example, a generative AI, or without a generative AI. For example, the holding section can reflect changes in real time using a generative AI model that takes the changes as input and reflects them in the email on hold.

[0048] The holding unit monitors the sending status of other related emails while the email is on hold and can resume sending at an appropriate time. For example, if a related email is sent, the holding unit will immediately send the email that is on hold. For example, if a related email has not been sent, the holding unit will extend the holding period. The holding unit can also determine the optimal sending timing based on the sending status of related emails. This allows sending to resume at the optimal time based on the sending status of related emails. Some or all of the above processing in the holding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the holding unit can determine the sending timing using a generative AI model that takes the sending status of related emails as input and outputs the sending timing.

[0049] The holding section can present appropriate revision suggestions to the user while the request is pending. For example, the holding section can present appropriate revision suggestions when the user modifies the recipient address. For example, the holding section can present appropriate revision suggestions when the user modifies an attachment. The holding section can also present appropriate revision suggestions when the user modifies the body text. This allows the user to make appropriate revisions by presenting appropriate revision suggestions while the request is pending. Some or all of the above processing in the holding section may be performed using, for example, a generative AI, or without a generative AI. For example, the holding section can present revision suggestions using a generative AI model that takes the modification content as input and outputs appropriate revision suggestions.

[0050] The holding unit can propose the optimal sending timing while the message is on hold, taking into account the user's schedule. For example, the holding unit proposes the optimal sending timing based on the user's schedule. For example, if the user is in a meeting, the holding unit proposes a timing to send the message after the meeting ends. Also, if the user is on a break, the holding unit can propose a timing to send the message after the break ends. This allows for appropriate sending by proposing the optimal sending timing based on the user's schedule. Some or all of the above processing in the holding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the holding unit can propose a sending timing using a generative AI model that takes the user's schedule information as input and outputs the optimal sending timing.

[0051] The revision unit can propose the optimal revision by referring to past revision history when generating revision proposals. For example, the revision unit proposes the optimal revision proposal based on content previously revised by the user. For example, the revision unit considers revision proposals that the user previously ignored and adjusts their importance before proposing them. The revision unit can also analyze content previously revised by the user and propose the most effective revision proposal. In this way, the optimal revision proposal can be proposed by referring to past revision history. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or without a generative AI. For example, the revision unit can propose revision proposals using a generative AI model that takes past revision history as input and outputs the optimal revision proposal.

[0052] The revision unit can adjust the email content and attachment content to ensure consistency when generating revised proposals. For example, the revision unit generates revised proposals so that the data in the email body and attachments match. For example, the revision unit generates revised proposals so that the destination of a link in the email body matches the destination of a link in the attachment. The revision unit can also generate revised proposals so that the date and time in the email body match the information in the attachment. This ensures consistency between the email content and attachment content, thereby providing appropriate revised proposals. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or without a generative AI. For example, the revision unit can generate revised proposals using a generative AI model that takes the email body and attachments as input and outputs a consistent revised proposal.

[0053] The correction unit can translate the proposed corrections based on the user's language settings when generating them. For example, the correction unit can automatically set the language of the proposed corrections based on the language settings of the user's device. For example, the correction unit can provide a language switching function if the user uses multiple languages. The correction unit can also provide the proposed corrections in a specific language if the user selects that language. This allows the correction unit to provide appropriate proposed corrections by translating them based on the user's language settings. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the correction unit can translate the proposed corrections using a generative AI model that takes the user's language settings as input and translates the proposed corrections.

[0054] The revision unit can be customized based on the recipient's organization and job title when generating revision proposals. For example, if the recipient is a superior, the revision unit will provide a formal revision proposal. For example, if the recipient is a colleague, the revision unit will provide a casual revision proposal. Furthermore, if the recipient is an external business partner, the revision unit can provide a businesslike revision proposal. In this way, by customizing the revision proposal according to the recipient's organization and job title, it is possible to provide an appropriate revision proposal. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the revision unit can take the recipient's organization and job title as input and generate revision proposals using a generative AI model that customizes the revision proposals.

[0055] The revision unit can be customized based on the recipient's organization and job title when generating revision proposals. For example, if the recipient is a superior, the revision unit will provide a formal revision proposal. For example, if the recipient is a colleague, the revision unit will provide a casual revision proposal. Furthermore, if the recipient is an external business partner, the revision unit can provide a businesslike revision proposal. In this way, by customizing the revision proposal according to the recipient's organization and job title, it is possible to provide an appropriate revision proposal. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the revision unit can take the recipient's organization and job title as input and generate revision proposals using a generative AI model that customizes the revision proposals.

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

[0057] The checking unit can verify whether the recipient of an email has been previously blacklisted. For example, the checking unit can detect addresses that have previously sent spam or phishing emails and display a warning. It can also detect addresses that have been reported for unauthorized access in the past. This allows for the prevention of accidental or unauthorized email transmissions by verifying the security of recipients based on blacklists.

[0058] The checking unit can verify whether the recipient of an email belongs to a specific region or country. For example, the checking unit can detect addresses with domains from a specific country and display a warning. It can also detect addresses belonging to a specific region. This allows for verification of recipient legitimacy based on region and country, preventing accidental or inappropriate email transmissions.

[0059] The checking unit can verify whether the recipient of an email belongs to a specific industry or business. For example, the checking unit can detect addresses with domains belonging to a specific industry and display a warning. It can also detect addresses belonging to a specific business. This allows for verification of recipient appropriateness based on industry and business type, preventing accidental or inappropriate email transmissions.

[0060] The checking unit can verify whether the email recipient's address is one that should be receiving emails during a specific time period. For example, the checking unit can detect addresses receiving emails outside of business hours and display a warning. It can also detect addresses that should be receiving emails during specific time periods. This allows for verification of recipient appropriateness based on the time of day, preventing accidental or inappropriate email transmissions.

[0061] The checking unit can verify whether the recipient of an email is an address associated with a specific project or task. For example, the checking unit can detect addresses associated with a specific project and display a warning. It can also detect addresses associated with specific tasks. This allows for verification of recipient appropriateness based on projects and tasks, preventing accidental or inappropriate email transmissions.

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

[0063] Step 1: The checking unit verifies the accuracy of the recipient before sending the email. For example, it detects if the recipient's email address differs from the last name of the recipient listed in the email body, or if the attached file contains cells that have been hidden. Step 2: The notification unit notifies the user of any issues detected by the checking unit via a pop-up alert. For example, it immediately notifies the user of any detected concerns and displays a pop-up alert to inform the user of the problem. Step 3: The holding unit withholds sending until the issue notified by the notification unit is confirmed. For example, it withholds sending the email until the user confirms the issue and completes the fix, or it pauses sending the email until the user confirms it. Step 4: The revision section generates proposed revisions, including changes to the email recipient, changes to the email content, and deletion of unnecessary lines in the attachment file. For example, it generates proposals to change the recipient's email address to an appropriate one, or to delete unnecessary lines in the attachment file.

[0064] (Example of form 2) The email misdelivery prevention system according to an embodiment of the present invention is a system that uses a generating AI agent to prevent misdelivery and incorrect attachments before email is sent. In this system, from the moment the send button is pressed until the email is actually sent, the generating AI agent instantly checks whether "the recipient is correct / whether there are any errors in the attached data." The agent notifies the user of any concerns it detects with a pop-up alert and suspends sending until confirmation is received. This prevents the system from becoming a mere formality (due to complacency) by only displaying pop-ups when a concern is detected, rather than every time an email is sent. Furthermore, the generating AI agent creates proposed corrections such as changing the email recipient, revising the text, and deleting unnecessary lines in attached files, minimizing the effort required for rework. This has the potential to prevent approximately 28.7% of personal information leakage incidents from being caused by misdelivery, and the fact that about one in four people have experience of sending an email to the wrong recipient. For example, from the moment the send button is pressed until the email is actually sent, the generating AI agent instantly checks whether "the recipient is correct / whether there are any errors in the attached data." In this process, the generating AI agent thoroughly analyzes whether the recipient's email address is correct and whether there are any errors in the attachments. For example, it can detect if the recipient's email address differs from the recipient's last name listed in the body of the email, or if the attachment contains hidden cells. Next, the agent notifies the user of any detected concerns via a pop-up alert and withholds sending the email until confirmation is received. This allows the user to review the concerns and make corrections as needed. For example, it notifies the user via a pop-up alert if the recipient's email address is incorrect or if there are errors in the attachments. Furthermore, the generating AI agent creates suggested corrections, such as changing the email recipient, revising the email body, or deleting unnecessary lines in the attachments. This allows the user to respond with minimal effort required to redo the work. For example, the generating AI agent can create suggestions such as changing the recipient's email address to a correct one or deleting unnecessary lines in the attachments. This mechanism has the potential to prevent incidents such as the fact that approximately 28.7% of personal information leaks are due to misdelivery, and that about one in four people have experience misdelivering emails.For example, if the recipient's email address is incorrect or there is an error in the attached file, the AI ​​agent can detect this and notify the user via a pop-up alert, thereby preventing accidental sending or attachments. In this way, the system for preventing accidental sending of emails before they are sent can prevent accidental sending or attachments.

[0065] The email misdelivery prevention system according to the embodiment comprises a checking unit, a notification unit, a holding unit, and a correction unit. The checking unit checks the accuracy of the recipient before sending the email. The checking unit can, for example, detect if the recipient's email address differs from the recipient's last name written in the body of the email. The checking unit can also detect if an attached file contains hidden cells. For example, the checking unit can detect hidden cells or hidden data in an Excel file. The notification unit notifies the user of the problem detected by the checking unit using a pop-up alert. The notification unit can, for example, immediately notify the user of the detected concern. For example, the notification unit displays a pop-up alert to inform the user of the problem. The holding unit holds the email until the problem notified by the notification unit is confirmed. For example, the holding unit holds the email sending until the user confirms the problem and completes the correction. For example, the holding unit temporarily suspends the email sending until the user confirms it. The correction unit generates a correction proposal that includes changing the email recipient, changing the text, and deleting unnecessary rows in the attached file. The correction unit generates, for example, a proposal to change the recipient's email address to an appropriate one. The correction unit can also generate a proposal to delete unnecessary lines in the attachment. For example, the correction unit automatically detects unnecessary lines in the attachment and generates a proposal to delete them. As a result, the email sending error prevention system according to the embodiment can prevent email sending errors and incorrect attachments.

[0066] The checking unit verifies the accuracy of the recipient before sending an email. For example, it can detect if the recipient's email address differs from the recipient's last name listed in the email body. Specifically, the checking unit analyzes the recipient information in the email body and compares it with the domain and username portions of the email address to reduce the risk of sending to the wrong recipient. The checking unit can also detect if an attached file contains hidden cells. For example, it can detect hidden cells and hidden data in Excel files. This involves analyzing the file's metadata and internal structure to identify the presence of hidden cells and hidden data. Furthermore, the checking unit can detect specific keywords and phrases in the email body to determine if confidential information is included. For example, it can detect keywords containing confidential information such as credit card numbers and personal information and warn of the risk of sending to the wrong recipient. In this way, the checking unit can check accuracy from multiple perspectives before sending an email, preventing the risk of sending to the wrong recipient.

[0067] The notification unit notifies users of problems detected by the checking unit via pop-up alerts. For example, the notification unit immediately notifies users of detected concerns. Specifically, the notification unit displays a pop-up window on the user's screen, visually presenting details of the detected problem. For example, the notification unit displays a pop-up alert to inform the user of the problem. The pop-up alert includes the type and specific details of the detected problem, as well as recommended actions. The notification unit can also use additional notification methods such as audio alerts and vibration notifications to draw the user's attention. This allows users to quickly understand problems and take appropriate action before sending emails. Furthermore, the notification unit can continuously improve the accuracy and effectiveness of notifications by recording the user's operation history and referring to past notification content and actions. For example, the notification unit learns how to deal with similar problems in the past and incorporates this into future notifications. This allows the notification unit to provide users with quick and accurate notifications, minimizing the risk of accidental sending.

[0068] The holding unit withholds sending until the issue notified by the notification unit is confirmed. For example, the holding unit withholds sending the email until the user confirms the issue and completes the correction. Specifically, the holding unit temporarily suspends sending the email until the user confirms the issue and completes the correction. For example, the holding unit temporarily suspends sending the email until the user confirms it. The holding unit maintains the suspended state of email sending and withholds sending the email until the user confirms the issue and completes the correction. This allows the user to withhold sending the email until they confirm the issue and complete the correction. Furthermore, the holding unit can withhold sending the email until the user confirms the issue and completes the correction. For example, the holding unit temporarily suspends sending the email until the user confirms it. This allows the user to withhold sending the email until they confirm the issue and complete the correction.

[0069] The editing unit generates suggested revisions, including changes to the email recipient, changes to the email content, and deletion of unnecessary lines in attachments. For example, the editing unit generates a suggestion to change the recipient's email address to an appropriate one. Specifically, the editing unit uses AI to analyze the email content and generates appropriate suggested revisions to the recipient and content. For example, the editing unit analyzes the recipient information in the email body and suggests an appropriate email address. The editing unit can also generate suggestions to delete unnecessary lines in attachments. For example, the editing unit automatically detects unnecessary lines in attachments and generates a suggestion to delete them. This uses technology to analyze the file content and identify unnecessary lines and data. Furthermore, the editing unit can detect typographical errors and grammatical mistakes in the email body and suggest revisions. As a result, the editing unit can analyze the email content from multiple angles and generate appropriate revisions. Thus, the email misdelivery prevention system according to the embodiment can prevent misdelivery and incorrect attachments before they occur.

[0070] The checking unit can detect cases where the recipient's email address differs from the recipient's last name written in the email body. For example, the checking unit can detect cases where the recipient's email address does not match the recipient's last name written in the email body. For example, the checking unit compares the recipient's last name written in the email body with the last name in the email address and displays a warning if they do not match. The checking unit can also detect cases where the domain of the email address is different. For example, the checking unit displays a warning if the domain of the email address does not match the domain written in the email body. This prevents accidental sending by detecting errors in the recipient's email address. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can detect the accuracy of an email address using a generative AI model that takes the email body and email address as input and outputs the accuracy of the email address.

[0071] The checking unit can detect if an attached file contains hidden cells. For example, the checking unit can detect hidden cells in an Excel file. For example, the checking unit can detect hidden cells in an Excel file and display a warning. The checking unit can also detect if hidden data is included. For example, the checking unit can detect hidden data in an Excel file and display a warning. This prevents incorrect attachments by detecting errors in attached files. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can detect hidden cells and hidden data using a generative AI model that takes an Excel file as input and outputs whether or not there are hidden cells or hidden data.

[0072] The notification unit can notify users of detected concerns via pop-up alerts. For example, the notification unit can immediately notify users of detected concerns. For example, the notification unit can display a pop-up alert to inform users of the problem. The notification unit can also adjust the design and timing of the alerts. For example, the notification unit can adjust the timing of the alert display according to the user's work status. This prevents accidental sending or attachment by immediately notifying users of concerns. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can notify users of concerns using a generative AI model that takes detected concerns as input and outputs pop-up alerts.

[0073] The correction unit can generate suggestions for changing the recipient's email address to an appropriate one. For example, the correction unit can generate suggestions for changing the recipient's email address to an appropriate one. For example, the correction unit can suggest an appropriate email address with a matching domain. The correction unit can also suggest an appropriate email address by referring to past sending history. For example, the correction unit can suggest an appropriate email address based on the recipients of emails sent in the past. This prevents accidental sending by generating suggestions for changing to an appropriate email address. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the correction unit can suggest an appropriate email address using a generative AI model that takes an email address as input and outputs an appropriate email address.

[0074] The editing unit can generate suggestions for deleting unnecessary rows in an attached file. For example, the editing unit can generate suggestions for deleting unnecessary rows in an attached file. For example, the editing unit can detect blank rows or duplicate data in an Excel file and propose suggestions for their deletion. The editing unit can also analyze the contents of an attached file and automatically detect unnecessary rows. For example, the editing unit can automatically detect unnecessary rows in an Excel file and generate suggestions for their deletion. This prevents accidental attachment by generating suggestions for deleting unnecessary rows in attached files. Some or all of the above processing in the editing unit may be performed using, for example, a generation AI, or without a generation AI. For example, the editing unit can use a generation AI model that takes an Excel file as input and outputs unnecessary rows to propose suggestions for deleting unnecessary rows.

[0075] The checking unit can estimate the user's emotions and adjust the rigor of the checks based on the estimated emotions. For example, if the user is stressed, the checking unit can ease the rigor of the checks and provide results quickly. For example, if the user is relaxed, the checking unit can perform a more detailed check and detect more concerns. Also, if the user is in a hurry, the checking unit can focus on important check items and provide results quickly. This allows for appropriate checks by adjusting the rigor of the checks according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using a generative AI, or not. For example, the checking unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0076] The checking unit can cross-check the content of the email body and attachments to confirm consistency. For example, the checking unit can verify whether the data in the email body matches the data in the attachments. For example, the checking unit can verify whether the links in the email body match the links in the attachments. The checking unit can also verify whether the dates and times in the email body match the information in the attachments. For example, the checking unit can verify whether the dates and times in the email body match the information in the attachments. By confirming the consistency between the content of the email body and attachments, it is possible to prevent accidental sending or attachments. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can verify consistency using a generative AI model that takes the email body and attachments as input and outputs consistency of content.

[0077] The checking unit can refer to past sending history and detect similar erroneous sending patterns. For example, the checking unit can learn patterns from emails that have been sent erroneously in the past and detect similar patterns. For example, the checking unit can refer to the recipients of emails that have been sent erroneously in the past and warn against sending to the same recipients. The checking unit can also refer to the content of emails that have been sent erroneously in the past and warn against sending emails with the same content. For example, the checking unit can refer to the content of emails that have been sent erroneously in the past and warn against sending emails with the same content. In this way, by detecting past erroneous sending patterns, erroneous sending can be prevented. Some or all of the above processing in the checking unit may be performed using, for example, generative AI, or without generative AI. For example, the checking unit can detect erroneous sending patterns using a generative AI model that takes past sending history as input and outputs similar erroneous sending patterns.

[0078] The checking unit can estimate the user's emotions and determine the priority of checks based on the estimated emotions. For example, if the user is nervous, the checking unit will prioritize checking important items. For example, if the user is relaxed, the checking unit will check all items equally. Also, if the user is in a hurry, the checking unit can prioritize checking the most important items. In this way, by determining the priority of checks according to the user's emotions, appropriate checks can be performed. 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 checking unit may be performed using a generative AI, or not using a generative AI. For example, the checking unit can input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0079] The checking unit can adjust its checking criteria based on the recipient's organization and position. For example, if the recipient is a superior, the checking unit will perform a rigorous check. For example, if the recipient is a colleague, the checking unit will perform a standard check. The checking unit can also add particularly important check items if the recipient is an external business partner. For example, the checking unit will add particularly important check items if the recipient is an external business partner. This allows for appropriate checking by adjusting the checking criteria according to the recipient's organization and position. Some or all of the above processing in the checking unit may be performed using, for example, generative AI, or without generative AI. For example, the checking unit can adjust its checking criteria using a generative AI model that takes the recipient's organization and position as input and outputs the checking criteria.

[0080] The checking unit can adjust the frequency of checks based on the time of email transmission. For example, the checking unit checks at a normal frequency during business hours. For example, the checking unit can lower the frequency of checks outside of business hours and check only important items. The checking unit can also increase the frequency of checks in emergencies to perform quick checks. For example, the checking unit can increase the frequency of checks in emergencies to perform quick checks. This allows for appropriate checks by adjusting the frequency of checks according to the time of transmission. Some or all of the above processing in the checking unit may be performed using, for example, a generative AI, or without a generative AI. For example, the checking unit can adjust the frequency of checks using a generative AI model that takes the time of transmission as input and outputs the frequency of checks.

[0081] The notification unit can estimate the user's emotions and adjust how notifications are displayed based on the estimated emotions. For example, if the user is tense, the notification unit displays a simple and highly visible notification. For example, if the user is relaxed, the notification unit displays a notification containing detailed information. Also, if the user is in a hurry, the notification unit can display a concise notification that gets straight to the point. In this way, appropriate notifications can be provided by adjusting how notifications are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using a generative AI, or not using a generative AI. For example, the notification unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0082] The notification unit can customize the content of notifications based on the user's past interaction history. For example, the notification unit displays relevant notification content based on concerns the user has previously addressed. For example, the notification unit displays notifications including suggested revisions based on content the user has previously revised. The notification unit can also adjust the importance of notifications by considering notifications the user has previously ignored. For example, the notification unit adjusts the importance of notifications by considering notifications the user has previously ignored. This allows for appropriate notifications to be delivered by customizing the content based on past interaction history. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can customize the content of notifications using a generative AI model that takes past interaction history as input and outputs notification content.

[0083] The notification unit can optimize the timing of notifications according to the user's work status. For example, if the user is concentrating on a task, the notification unit will display a notification after the task is completed. For example, if the user is on a break, the notification unit will display a notification immediately. The notification unit can also display a notification after the meeting has ended if the user is in a meeting. For example, if the user is in a meeting, the notification unit will display a notification after the meeting has ended. In this way, appropriate notifications can be provided by optimizing the timing of notifications according to the user's work status. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can optimize the timing of notifications using a generative AI model that takes the user's work status as input and outputs the timing of notifications.

[0084] The notification unit can estimate the user's emotions and determine the priority of notifications based on the estimated emotions. For example, if the user is stressed, the notification unit will prioritize displaying important notifications. For example, if the user is relaxed, the notification unit will display all notifications equally. Also, if the user is in a hurry, the notification unit can prioritize displaying the most important notifications. In this way, appropriate notifications can be provided by determining the priority of notifications according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the notification unit may be performed using a generative AI, or not using a generative AI. For example, the notification unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0085] The notification unit can optimize the notification display format according to the user's device. For example, if the user is using a smartphone, the notification unit will display a notification that is sized to fit the screen. For example, if the user is using a tablet, the notification unit will display a notification optimized for a larger screen. The notification unit can also display a concise and highly visible notification if the user is using a smartwatch. For example, if the user is using a smartwatch, the notification unit will display a concise and highly visible notification. In this way, appropriate notifications can be provided by optimizing the notification display format according to the user's device. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can optimize the notification display format using a generative AI model that takes user device information as input and outputs the notification display format.

[0086] The notification unit can translate notification content based on the user's language settings. For example, the notification unit can automatically set the notification language based on the user's device language settings. For example, the notification unit can provide a language switching function if the user uses multiple languages. The notification unit can also display notifications in a specific language if the user selects that language. For example, the notification unit can display notifications in a specific language if the user selects that language. This allows for appropriate notifications to be provided by translating notification content based on the user's language settings. Some or all of the above processing in the notification unit may be performed using, for example, generative AI, or without generative AI. For example, the notification unit can translate notification content using a generative AI model that takes the user's language settings as input and translates the notification content.

[0087] The hold function can estimate the user's emotions and adjust the hold period based on the estimated emotions. For example, if the user is nervous, the hold function can set a short hold period. For example, if the user is relaxed, the hold function can set a standard hold period. The hold function can also set the shortest hold period if the user is in a hurry. This allows for appropriate holding by adjusting the hold period according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the hold function may be performed using a generative AI, or not using a generative AI. For example, the hold function can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0088] The holding section can reflect changes made by the user while the email is on hold in real time. For example, if the user changes the recipient address, the holding section will immediately reflect this change in the email on hold. For example, if the user changes an attachment, the holding section will immediately reflect this change in the email on hold. The holding section can also immediately reflect changes made by the user in the email body. This allows for appropriate corrections to be made by reflecting changes made while the email is on hold in real time. Some or all of the above processing in the holding section may be performed using, for example, a generative AI, or without a generative AI. For example, the holding section can reflect changes in real time using a generative AI model that takes the changes as input and reflects them in the email on hold.

[0089] The holding unit monitors the sending status of other related emails while the email is on hold and can resume sending at an appropriate time. For example, if a related email is sent, the holding unit will immediately send the email that is on hold. For example, if a related email has not been sent, the holding unit will extend the holding period. The holding unit can also determine the optimal sending timing based on the sending status of related emails. This allows sending to resume at the optimal time based on the sending status of related emails. Some or all of the above processing in the holding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the holding unit can determine the sending timing using a generative AI model that takes the sending status of related emails as input and outputs the sending timing.

[0090] The holding unit can estimate the user's emotions and determine the priority of holding emails based on the estimated emotions. For example, if the user is stressed, the holding unit will prioritize holding important emails. For example, if the user is relaxed, the holding unit will hold all emails equally. Also, if the user is in a hurry, the holding unit can prioritize holding the most important emails. In this way, appropriate holding can be performed by determining the priority of holding emails according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the holding unit may be performed using a generative AI, or not using a generative AI. For example, the holding unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0091] The holding section can present appropriate revision suggestions to the user while the request is pending. For example, the holding section can present appropriate revision suggestions when the user modifies the recipient address. For example, the holding section can present appropriate revision suggestions when the user modifies an attachment. The holding section can also present appropriate revision suggestions when the user modifies the body text. This allows the user to make appropriate revisions by presenting appropriate revision suggestions while the request is pending. Some or all of the above processing in the holding section may be performed using, for example, a generative AI, or without a generative AI. For example, the holding section can present revision suggestions using a generative AI model that takes the modification content as input and outputs appropriate revision suggestions.

[0092] The holding unit can propose the optimal sending timing while the message is on hold, taking into account the user's schedule. For example, the holding unit proposes the optimal sending timing based on the user's schedule. For example, if the user is in a meeting, the holding unit proposes a timing to send the message after the meeting ends. Also, if the user is on a break, the holding unit can propose a timing to send the message after the break ends. This allows for appropriate sending by proposing the optimal sending timing based on the user's schedule. Some or all of the above processing in the holding unit may be performed using, for example, a generative AI, or without a generative AI. For example, the holding unit can propose a sending timing using a generative AI model that takes the user's schedule information as input and outputs the optimal sending timing.

[0093] The editing unit can estimate the user's emotions and adjust the presentation of the suggested revisions based on the estimated emotions. For example, if the user is tense, the editing unit can provide a simple and highly visible revised revision. For example, if the user is relaxed, the editing unit can provide a revised revision that includes detailed information. Furthermore, if the user is in a hurry, the editing unit can provide a concise revised revision that gets straight to the point. In this way, by adjusting the presentation of the revised revisions according to the user's emotions, an appropriate revised revision can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using a generative AI, or not using a generative AI. For example, the editing unit can input the user's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0094] The revision unit can propose the optimal revision by referring to past revision history when generating revision proposals. For example, the revision unit proposes the optimal revision proposal based on content previously revised by the user. For example, the revision unit considers revision proposals that the user previously ignored and adjusts their importance before proposing them. The revision unit can also analyze content previously revised by the user and propose the most effective revision proposal. In this way, the optimal revision proposal can be proposed by referring to past revision history. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or without a generative AI. For example, the revision unit can propose revision proposals using a generative AI model that takes past revision history as input and outputs the optimal revision proposal.

[0095] The revision unit can adjust the email content and attachment content to ensure consistency when generating revised proposals. For example, the revision unit generates revised proposals so that the data in the email body and attachments match. For example, the revision unit generates revised proposals so that the destination of a link in the email body matches the destination of a link in the attachment. The revision unit can also generate revised proposals so that the date and time in the email body match the information in the attachment. This ensures consistency between the email content and attachment content, thereby providing appropriate revised proposals. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or without a generative AI. For example, the revision unit can generate revised proposals using a generative AI model that takes the email body and attachments as input and outputs a consistent revised proposal.

[0096] The editing unit can estimate the user's emotions and prioritize the suggested revisions based on those emotions. For example, if the user is tense, the editing unit will prioritize suggesting important revisions. For example, if the user is relaxed, the editing unit will suggest all revisions equally. Also, if the user is in a hurry, the editing unit can prioritize suggesting the most important revisions. In this way, by prioritizing revisions according to the user's emotions, appropriate revisions can be provided. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using a generative AI, or not using a generative AI. For example, the editing unit can input user facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0097] The correction unit can translate the proposed corrections based on the user's language settings when generating them. For example, the correction unit can automatically set the language of the proposed corrections based on the language settings of the user's device. For example, the correction unit can provide a language switching function if the user uses multiple languages. The correction unit can also provide the proposed corrections in a specific language if the user selects that language. This allows the correction unit to provide appropriate proposed corrections by translating them based on the user's language settings. Some or all of the above processing in the correction unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the correction unit can translate the proposed corrections using a generative AI model that takes the user's language settings as input and translates the proposed corrections.

[0098] The revision unit can be customized based on the recipient's organization and job title when generating revision proposals. For example, if the recipient is a superior, the revision unit will provide a formal revision proposal. For example, if the recipient is a colleague, the revision unit will provide a casual revision proposal. Furthermore, if the recipient is an external business partner, the revision unit can provide a businesslike revision proposal. In this way, by customizing the revision proposal according to the recipient's organization and job title, it is possible to provide an appropriate revision proposal. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the revision unit can take the recipient's organization and job title as input and generate revision proposals using a generative AI model that customizes the revision proposals.

[0099] The revision unit can be customized based on the recipient's organization and job title when generating revision proposals. For example, if the recipient is a superior, the revision unit will provide a formal revision proposal. For example, if the recipient is a colleague, the revision unit will provide a casual revision proposal. Furthermore, if the recipient is an external business partner, the revision unit can provide a businesslike revision proposal. In this way, by customizing the revision proposal according to the recipient's organization and job title, it is possible to provide an appropriate revision proposal. Some or all of the above processing in the revision unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the revision unit can take the recipient's organization and job title as input and generate revision proposals using a generative AI model that customizes the revision proposals.

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

[0101] The checking unit can verify whether the recipient of an email has been previously blacklisted. For example, the checking unit can detect addresses that have previously sent spam or phishing emails and display a warning. It can also detect addresses that have been reported for unauthorized access in the past. This allows for the prevention of accidental or unauthorized email transmissions by verifying the security of recipients based on blacklists.

[0102] The checking unit can verify whether the recipient of an email belongs to a specific region or country. For example, the checking unit can detect addresses with domains from a specific country and display a warning. It can also detect addresses belonging to a specific region. This allows for verification of recipient legitimacy based on region and country, preventing accidental or inappropriate email transmissions.

[0103] The checking unit can verify whether the recipient of an email belongs to a specific industry or business. For example, the checking unit can detect addresses with domains belonging to a specific industry and display a warning. It can also detect addresses belonging to a specific business. This allows for verification of recipient appropriateness based on industry and business type, preventing accidental or inappropriate email transmissions.

[0104] The checking unit can verify whether the email recipient's address is one that should be receiving emails during a specific time period. For example, the checking unit can detect addresses receiving emails outside of business hours and display a warning. It can also detect addresses that should be receiving emails during specific time periods. This allows for verification of recipient appropriateness based on the time of day, preventing accidental or inappropriate email transmissions.

[0105] The checking unit can verify whether the recipient of an email is an address associated with a specific project or task. For example, the checking unit can detect addresses associated with a specific project and display a warning. It can also detect addresses associated with specific tasks. This allows for verification of recipient appropriateness based on projects and tasks, preventing accidental or inappropriate email transmissions.

[0106] The checking unit can estimate the user's emotions and adjust the email content based on that estimation. For example, if the user is stressed, the checking unit will simplify the email content, leaving only essential information. Conversely, if the user is relaxed, it can create an email that includes detailed information. This allows for the sending of appropriate emails by adjusting the content according to the user's emotions.

[0107] The checking unit can estimate the user's emotions and adjust the email sending timing based on the estimated emotions. For example, if the user is nervous, the checking unit will delay sending the email and wait until the user calms down. Conversely, if the user is relaxed, it can send the email immediately. In this way, by adjusting the sending timing according to the user's emotions, emails can be sent at the appropriate time.

[0108] The checking unit can estimate the user's emotions and adjust the email recipients based on that estimation. For example, if the user is stressed, the checking unit will reduce the number of recipients, leaving only the important ones. Conversely, if the user is relaxed, it can send the email to all recipients. This allows the email to be sent to the appropriate recipients by adjusting the recipients according to the user's emotions.

[0109] The checking unit can estimate the user's emotions and adjust email attachments based on that estimation. For example, if the user is stressed, the unit will reduce the number of attachments, leaving only the essential files. Conversely, if the user is relaxed, it can attach all files. This allows the system to send emails with appropriate attachments by adjusting them according to the user's emotions.

[0110] The checking unit can estimate the user's emotions and adjust the email text based on that estimation. For example, if the user is stressed, the checking unit will simplify the text and leave only essential information. Conversely, if the user is relaxed, it can create a text that includes detailed information. This allows for the sending of appropriate emails by adjusting the text according to the user's emotions.

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

[0112] Step 1: The checking unit verifies the accuracy of the recipient before sending the email. For example, it detects if the recipient's email address differs from the last name of the recipient listed in the email body, or if the attached file contains cells that have been hidden. Step 2: The notification unit notifies the user of any issues detected by the checking unit via a pop-up alert. For example, it immediately notifies the user of any detected concerns and displays a pop-up alert to inform the user of the problem. Step 3: The holding unit withholds sending until the issue notified by the notification unit is confirmed. For example, it withholds sending the email until the user confirms the issue and completes the fix, or it pauses sending the email until the user confirms it. Step 4: The revision section generates proposed revisions, including changes to the email recipient, changes to the email content, and deletion of unnecessary lines in the attachment file. For example, it generates proposals to change the recipient's email address to an appropriate one, or to delete unnecessary lines in the attachment file.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0115] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] Each of the multiple elements described above, including the checking unit, notification unit, holding unit, and correction unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the checking unit is implemented by the control unit 46A of the smart device 14 and checks the accuracy of the recipient before sending the email. The notification unit is implemented by the identification processing unit 290 of the data processing unit 12 and notifies the recipient of any detected problems via a pop-up alert. The holding unit is implemented by the control unit 46A of the smart device 14 and holds the email until the problem is confirmed. The correction unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates proposed corrections, including changes to the email recipient, proposed changes to the text, and deletion of unnecessary lines in attached files. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

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

[0118] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0123] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0124] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0125] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0126] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0127] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0129] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0132] Each of the multiple elements described above, including the checking unit, notification unit, holding unit, and correction unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the checking unit is implemented by the control unit 46A of the smart glasses 214 and checks the accuracy of the recipient before sending the email. The notification unit is implemented by the identification processing unit 290 of the data processing unit 12 and notifies the recipient of any detected problems with a pop-up alert. The holding unit is implemented by the control unit 46A of the smart glasses 214 and holds the email until the problem is confirmed. The correction unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a correction proposal that includes changing the email recipient, changing the text, and deleting unnecessary lines in the attachment. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0134] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0135] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0136] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0137] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0138] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0139] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0140] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0141] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0142] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0143] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0144] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0145] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0146] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0147] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0148] Each of the multiple elements described above, including the checking unit, notification unit, holding unit, and correction unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the checking unit is implemented by the control unit 46A of the headset terminal 314 and checks the accuracy of the recipient before sending the email. The notification unit is implemented by the identification processing unit 290 of the data processing unit 12 and notifies the recipient of any detected problems via a pop-up alert. The holding unit is implemented by the control unit 46A of the headset terminal 314 and holds the email until the problem is confirmed. The correction unit is implemented by the identification processing unit 290 of the data processing unit 12 and generates a correction proposal that includes changing the email recipient, changing the text, and deleting unnecessary lines in the attachment. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

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

[0150] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0151] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0152] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0153] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0154] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0155] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0156] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0157] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0158] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0159] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0160] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0161] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0162] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0163] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0164] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0165] Each of the multiple elements described above, including the checking unit, notification unit, holding unit, and correction unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the checking unit is implemented by the control unit 46A of the robot 414 and checks the accuracy of the recipient before sending the email. The notification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and notifies the detected problem with a pop-up alert. The holding unit is implemented by, for example, the control unit 46A of the robot 414 and holds the email until the problem is confirmed. The correction unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and generates a correction proposal that includes changing the email recipient, changing the text, and deleting unnecessary lines in the attachment. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0166] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0167] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0168] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0169] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0170] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0171] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0172] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0173] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0174] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0175] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0176] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0177] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0178] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0179] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0180] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0181] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0182] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0183] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0184] (Note 1) A checking unit that verifies the accuracy of the recipient before sending the email, A notification unit that notifies the user of the problem detected by the aforementioned checking unit via a pop-up alert, A holding unit that withholds delivery until the problem notified by the aforementioned notification unit is confirmed, It includes a correction unit that generates proposed revisions, including changes to the email recipient, changes to the email text, and deletion of unnecessary lines in attachments. A system characterized by the following features. (Note 2) The aforementioned checking unit is Detects cases where the recipient's email address differs from the last name of the recipient listed in the email body. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned checking unit is Detects if an attached file contains hidden cells. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned notification unit, Detected concerns will be notified via pop-up alerts. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned modification section is, Generate a proposal to change the recipient's email address to an appropriate one. The system described in Appendix 1, characterized by the features described herein. (Note 6) The system described in Appendix 1 is characterized in that the modification unit generates a proposal to delete unnecessary lines in the attached file. (Note 7) The aforementioned checking unit is The system estimates the user's emotions and adjusts the strictness of the checks based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned checking unit is Cross-check the email body and attached file contents to ensure consistency. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned checking unit is Referencing past transmission history, similar erroneous transmission patterns are detected. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned checking unit is The system estimates the user's emotions and determines the priority of checks based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned checking unit is Adjust the review criteria based on the organization and job title of the recipient of the email. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned checking unit is Adjust the frequency of checks based on the time of day the email was sent. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned notification unit, It estimates the user's emotions and adjusts how notifications are displayed based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned notification unit, Customize notification content based on the user's past interaction history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The notification unit is characterized by adjusting the timing of notifications according to the user's work status, as described in Appendix 1. (Note 16) The aforementioned notification unit, It estimates the user's emotions and prioritizes notifications based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned notification unit, Optimize the notification display format according to the user's device. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned notification unit, Translate the notification content based on the user's language settings. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned retaining portion is The system estimates the user's emotions and adjusts the hold period based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned retaining portion is The system reflects user modifications made while the project is pending in real time. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned retaining portion is The system reflects user modifications made while the project is pending in real time. The system described in Appendix 1, characterized by the features described herein. (Note 22) The system described in Appendix 1, characterized in that the holding unit monitors the sending status of other related emails while they are on hold and resumes sending at the optimal timing. (Note 23) The aforementioned retaining portion is It estimates the user's emotions and determines the priority of holding the item based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned retaining portion is While the application is pending, present the user with appropriate suggested fixes. The system described in Appendix 1, characterized by the features described herein. (Note 25) The system according to Appendix 1, characterized in that the holding unit proposes the optimal transmission timing while the user's schedule is in consideration during the holding period. (Note 26) The aforementioned modification section is, The system estimates the user's emotions and adjusts the way the proposed revisions are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned modification section is, When generating revised proposals, we refer to past revision history to suggest the most suitable option. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned modification section is, When generating revised proposals, adjust the content of the email and the attached files to ensure consistency. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned modification section is, The system estimates user sentiment and prioritizes proposed revisions based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned modification section is, When generating revised proposals, translate them based on the user's language settings. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned modification section is, When generating revised proposals, customize them based on the organization and job title of the email recipient. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0185] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A checking unit that verifies the accuracy of the recipient before sending the email, A notification unit that notifies the user of the problem detected by the aforementioned checking unit via a pop-up alert, A holding unit that withholds delivery until the problem notified by the aforementioned notification unit is confirmed, It includes a correction unit that generates proposed revisions, including changes to the email recipient, changes to the email text, and deletion of unnecessary lines in attachments. A system characterized by the following features.

2. The aforementioned checking unit is Detects cases where the recipient's email address differs from the last name of the recipient listed in the email body. The system according to feature 1.

3. The aforementioned checking unit is Detects if an attached file contains hidden cells. The system according to feature 1.

4. The aforementioned notification unit, Detected concerns will be notified via pop-up alerts. The system according to feature 1.

5. The aforementioned modification section is, Generate a proposal to change the recipient's email address to an appropriate one. The system according to feature 1.

6. The system according to claim 1, characterized in that the modification unit generates a proposal to delete unnecessary lines in the attached file.

7. The aforementioned checking unit is The system estimates the user's emotions and adjusts the strictness of the checks based on those estimated emotions. The system according to feature 1.

8. The aforementioned checking unit is Cross-check the email body and attached file contents to ensure consistency. The system according to feature 1.

Images