System

Abstract

An object of a system according to an embodiment is to efficiently process a large number of unread mails and reflect the unread mails in a schedule.SOLUTION: A system includes an analysis part, a summarization part, and a schedule reflection part. The analysis unit analyzes the content of the mail. The summarizing unit summarizes the content analyzed by the analyzing unit. The schedule reflection unit reflects the content summarized by the summarization unit on the schedule.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem of making it difficult to efficiently process large amounts of unread email and reflect the results in schedules.

[0005] The system according to the embodiment aims to efficiently process a large amount of unread emails and reflect them in a schedule. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, a summarization unit, and a schedule reflection unit. The analysis unit analyzes the content of the email. The summarization unit summarizes the content analyzed by the analysis unit. The schedule reflection unit reflects the content summarized by the summarization unit in the schedule. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently process a large amount of unread emails and reflect them in a schedule. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) An AI concierge system according to an embodiment of the present invention summarizes the contents of unread emails that accumulate after a holiday and manages schedules. The AI ​​concierge system automatically retrieves unread emails, analyzes their contents, and provides summaries when a user connects their email account. Furthermore, important emails and emails related to a schedule are automatically reflected in the schedule. For example, the AI ​​concierge system allows a user to access their email account by entering their email account credentials. The AI ​​concierge system then accesses the user's email account and retrieves a list of unread emails. For example, the AI ​​concierge system retrieves all unread emails that accumulated after a holiday and analyzes their contents. The AI ​​concierge system then analyzes the contents of the unread emails, extracts important points, and creates summaries. For example, the AI ​​concierge system provides the user with summaries of emails containing meeting invitations or important notices. Furthermore, the AI ​​concierge system automatically adds important emails and emails related to a schedule to the schedule. For example, if an email contains a meeting invitation, the AI ​​concierge system automatically adds it to the schedule. This allows users to efficiently process emails and manage their schedules without being overwhelmed by a large number of unread emails. This allows the AI ​​concierge system to efficiently process emails and manage schedules without users being overwhelmed by a large number of unread emails. For example, the AI ​​concierge system can summarize unread emails that have accumulated after a holiday and update important emails in the schedule, allowing users to get to work right away.

[0029] The AI ​​concierge system according to the embodiment includes an analysis unit, a summarization unit, and a schedule reflection unit. The analysis unit analyzes the content of emails. For example, the analysis unit analyzes the content of emails using natural language processing technology. For example, the analysis unit analyzes the grammatical structure of emails using morphological analysis. The analysis unit can also extract important words and phrases using keyword extraction technology. The analysis unit can also understand the content of emails using semantic analysis technology. For example, the analysis unit understands the context of emails and extracts important information. The summarization unit summarizes the content analyzed by the analysis unit. For example, the summarization unit extracts important points to create a summary. For example, the summarization unit extracts important parts of emails and creates a concise summary. The summarization unit can also create a summary using a generation AI. For example, the summarization unit inputs a prompt to the generation AI, such as "Please summarize the main points of this email," and generates a summary. The schedule reflection unit reflects the content summarized by the summarization unit in a schedule. For example, the schedule reflection unit automatically adds important emails and emails related to a schedule to the schedule. For example, the schedule reflection unit automatically adds a meeting invitation email to the schedule. The schedule reflection unit can also manage the schedule in cooperation with a calendar app. For example, the schedule reflection unit cooperates with Google (registered trademark) Calendar or Outlook (registered trademark) Calendar to automatically update the schedule. This allows the AI ​​concierge system according to the embodiment to enable the user to efficiently process emails and manage the schedule.

[0030] Furthermore, the AI ​​concierge system includes a linking unit that links email accounts. The linking unit provides a function for users to link their email accounts. For example, the linking unit allows users to access their email accounts by entering authentication information for the email account. For example, the linking unit allows users to access their email accounts by entering an email address and password. The linking unit can also access email accounts using OAuth authentication. For example, the linking unit allows users to access their email accounts using a Google account or a Microsoft account. This allows users to link their email accounts, allowing the AI ​​concierge to retrieve and analyze emails.

[0031] The AI ​​concierge system also includes an acquisition unit that acquires unread emails. The acquisition unit automatically acquires unread emails. For example, the acquisition unit accesses the user's email account and acquires a list of unread emails. For example, the acquisition unit acquires all unread emails that have accumulated after a holiday and analyzes their contents. The acquisition unit can also acquire unread emails from a specific folder. For example, the acquisition unit acquires unread emails from the inbox or folders with specific labels. The acquisition unit can also acquire unread emails from a certain period of time. For example, the acquisition unit acquires unread emails from the past week. This automatically acquires unread emails, eliminating the need for the user to manually check emails.

[0032] The analysis unit can analyze the content of emails using natural language processing technology. The analysis unit, for example, analyzes the grammatical structure of emails using morphological analysis. For example, the analysis unit breaks down the sentences of an email into words and identifies the part of speech of each word. The analysis unit can also extract important words and phrases using keyword extraction technology. For example, the analysis unit extracts words and phrases that appear frequently in an email and identifies important information based on that. The analysis unit can also understand the content of an email using semantic analysis technology. For example, the analysis unit understands the context of an email and extracts important information. In this way, the content of an email can be accurately analyzed using natural language processing technology.

[0033] The summarization unit can extract important points and create a summary. For example, the summarization unit extracts important parts of an email and creates a concise summary. For example, the summarization unit extracts particularly important information from an email and creates a summary based on that. The summarization unit can also create a summary using a generation AI. For example, the summarization unit inputs a prompt such as "Please summarize the main points of this email" into the generation AI and generates a summary. The summarization unit can also extract important words and phrases using keyword extraction technology and create a summary based on that. For example, the summarization unit extracts words and phrases that appear frequently in an email and creates a summary based on that. This allows users to quickly grasp the information they need by extracting important points.

[0034] The schedule reflection unit can automatically add important emails and emails related to a schedule to the schedule. The schedule reflection unit can automatically add, for example, meeting invitation emails to the schedule. For example, the schedule reflection unit can analyze the content of the email and add the date, time, and location of the meeting to the schedule. The schedule reflection unit can also manage the schedule in cooperation with a calendar app. For example, the schedule reflection unit can cooperate with Google Calendar or Outlook Calendar to automatically update the schedule. The schedule reflection unit can also prioritize reflecting important emails in the schedule. For example, the schedule reflection unit can prioritize adding emails from specific senders or emails containing specific keywords to the schedule. In this way, by automatically adding important emails and emails related to a schedule to the schedule, the user can save time and effort in manually managing the schedule.

[0035] The analysis unit can evaluate the trustworthiness of the email sender and adjust the level of analysis detail based on the trustworthiness. The analysis unit, for example, performs a detailed analysis of emails from highly trusted senders. For example, the analysis unit evaluates trustworthiness based on the frequency of past exchanges and the sender's domain. The analysis unit can also perform a simplified analysis of emails from senders with low trustworthiness. For example, the analysis unit performs a simplified analysis when the sender's domain is unknown or when there has been little past exchange. The analysis unit can also adjust the level of analysis detail based on the content of emails from senders with medium trustworthiness. For example, the analysis unit adjusts the level of analysis detail based on the sender's trustworthiness and the content of the email. In this way, important emails can be analyzed in detail by adjusting the level of analysis detail based on the trustworthiness of the email sender.

[0036] The analysis unit can apply different analysis algorithms based on the content of the email. For example, the analysis unit applies a schedule analysis algorithm to a meeting invitation email. For example, the analysis unit extracts the date, time, and location of the meeting and reflects this in the schedule. The analysis unit can also apply a detailed analysis algorithm to emails containing important notices. For example, the analysis unit analyzes the content of the email in detail and extracts important information. The analysis unit can also apply a simplified analysis algorithm to advertising emails. For example, the analysis unit analyzes the content of advertising emails in a simplified manner and extracts only important information. This allows the analysis accuracy to be improved by applying the optimal analysis algorithm depending on the content of the email.

[0037] The analysis unit classifies the contents of emails by category and can apply different analysis methods to each category. For example, the analysis unit applies a business analysis method to business emails. For example, the analysis unit analyzes the contents of business emails in detail and extracts important information. The analysis unit can also apply a private analysis method to private emails. For example, the analysis unit simply analyzes the contents of private emails and extracts only important information. The analysis unit can also apply an advertising analysis method to advertising emails. For example, the analysis unit simply analyzes the contents of advertising emails and extracts only important information. This allows the analysis accuracy to be improved by applying the optimal analysis method depending on the email category.

[0038] The analysis unit can perform analysis taking into account the geographical location information of the sender of the email. For example, if the sender is nearby, the analysis unit performs analysis with a high level of urgency. For example, the analysis unit identifies geographical location information based on the sender's IP address or GPS data, and prioritizes analysis of emails with a high level of urgency. The analysis unit can also perform normal analysis if the sender is far away. For example, the analysis unit applies a normal analysis method based on the sender's geographical location information. The analysis unit can also select an appropriate analysis method based on the sender's geographical location information. For example, the analysis unit selects the optimal analysis method based on the sender's geographical location information. This makes it possible to prioritize analysis of emails with a high level of urgency by taking into account the geographical location information of the sender.

[0039] The analysis unit can improve the accuracy of the analysis by referring to an external database related to the content of the email. The analysis unit performs the analysis by referring to, for example, an industry database related to the content of the email. For example, the analysis unit acquires related information from the industry database and reflects it in the analysis. The analysis unit can also perform the analysis by referring to a news database related to the content of the email. For example, the analysis unit acquires the latest information from the news database and reflects it in the analysis. The analysis unit can also perform the analysis by referring to an academic database related to the content of the email. For example, the analysis unit acquires related research papers from the academic database and reflects it in the analysis. In this way, the accuracy of the analysis can be improved by referring to an external database.

[0040] The analysis unit can analyze the content of emails in cooperation with other communication channels. The analysis unit, for example, analyzes the content of emails in cooperation with the content of chats. For example, the analysis unit refers to the content of a chat app and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in cooperation with posts on social media. For example, the analysis unit refers to posts on social media and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in cooperation with other communication channels. For example, the analysis unit refers to the content of a chat app or social media and analyzes it in association with the content of emails. In this way, by coordinating with other communication channels, the accuracy of the analysis can be improved.

[0041] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the email. For example, the summarization unit provides a detailed summary for emails of high importance. For example, the summarization unit evaluates the importance based on the job title of the email sender and the content of the email and creates a detailed summary. The summarization unit can also provide a concise summary for emails of low importance. For example, the summarization unit briefly summarizes the content of the email and provides only important information. The summarization unit can also adjust the level of detail of the summary based on the content of the email for emails of medium importance. For example, the summarization unit adjusts the level of detail of the summary based on the content of the email. In this way, by adjusting the level of detail of the summary based on the importance of the email, it is possible to provide a detailed summary of important emails.

[0042] The summarization unit can apply different summarization algorithms depending on the category of email when generating a summary. For example, the summarization unit applies a business summarization algorithm to business emails. For example, the summarization unit summarizes the content of the business email in detail and provides important information. The summarization unit can also apply a private summarization algorithm to private emails. For example, the summarization unit briefly summarizes the content of the private email and provides only important information. The summarization unit can also apply an advertising summarization algorithm to advertising emails. For example, the summarization unit briefly summarizes the content of advertising emails and provides only important information. This allows the accuracy of the summary to be improved by applying the optimal summarization algorithm depending on the category of email.

[0043] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit provides an optimal summary, for example, based on the user's past summarization results. For example, the summarization unit creates a summary based on the accuracy of the past summarizations and user feedback. The summarization unit can also improve the accuracy of the summary from the user's past summarization results. For example, the summarization unit analyzes the past summarization results and improves the accuracy of the summary. The summarization unit can also improve the accuracy of the summary by referring to the user's past summarization results. For example, the summarization unit improves the accuracy of the summary based on the past summarization results. In this way, the accuracy of the summary can be improved by referring to the user's past summarization results.

[0044] When generating a summary, the summarizing unit can determine the priority of the summary based on the time when the email was sent. For example, the summarizing unit prioritizes summarizing the most recently sent email. For example, the summarizing unit prioritizes summarizing the most recent email based on the date and time when the email was sent. The summarizing unit can also postpone summarizing older emails. For example, the summarizing unit postpones summarizing older emails based on the date and time when the email was sent. The summarizing unit can also adjust the priority of the summary based on the time when it was sent. For example, the summarizing unit adjusts the priority of the summary based on the frequency of email sending and the date and time when it was sent. In this way, by determining the priority of the summary based on the time when the email was sent, it is possible to prioritize summarizing the latest information.

[0045] When generating summaries, the summarizing unit can adjust the order of summaries based on the relevance of emails. For example, the summarizing unit prioritizes summarizing highly relevant emails. For example, the summarizing unit prioritizes summarizing highly relevant emails based on the content of the emails and the commonality of senders. The summarizing unit can also postpone summarizing less relevant emails. For example, the summarizing unit postpones summarizing less relevant emails based on the content of the emails and the commonality of senders. The summarizing unit can also adjust the order of summaries based on relevance. For example, the summarizing unit adjusts the order of summaries based on common keywords and the commonality of senders. In this way, by adjusting the order of summaries based on the relevance of emails, it is possible to provide highly relevant information preferentially.

[0046] When generating a summary, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. For example, if the user's level of expertise is high, the summarization unit provides a summary that uses a lot of technical terms. For example, the summarization unit creates a summary that uses a lot of technical terms based on the user's occupation and educational background. Furthermore, if the user's level of expertise is low, the summarization unit can also provide a summary that avoids technical terms. For example, the summarization unit creates a summary that avoids technical terms based on the content of the user's past emails. Furthermore, the summarization unit can also adjust the use of technical terms in the summary according to the user's level of expertise. For example, the summarization unit adjusts the use of technical terms in the summary based on the user's occupation and educational background. In this way, by adjusting the use of technical terms in the summary according to the user's level of expertise, it is possible to provide a summary that is easy for the user to understand.

[0047] The schedule reflection unit can determine the priority of a schedule based on the importance of an email when reflecting a schedule. The schedule reflection unit, for example, preferentially reflects an appointment for an email with a high level of importance in the schedule. For example, the schedule reflection unit evaluates the importance based on the job title of the sender of the email or the content of the email and reflects it in the schedule. The schedule reflection unit can also postpone the appointment for an email with a low level of importance before reflecting it in the schedule. For example, the schedule reflection unit postpones the appointment for an email with a low level of importance before reflecting it in the schedule based on the content of the email. The schedule reflection unit can also adjust the priority of a schedule based on the importance. For example, the schedule reflection unit adjusts the priority of a schedule based on the content of the email or the job title of the sender. In this way, by determining the priority of a schedule based on the importance of an email, it is possible to preferentially reflect important appointments in the schedule.

[0048] The schedule reflection unit can apply different schedule reflection methods depending on the category of email when reflecting the schedule. For example, the schedule reflection unit applies a business schedule reflection method to a business email schedule. For example, the schedule reflection unit applies the business schedule reflection method based on the content of the business email. The schedule reflection unit can also apply a private schedule reflection method to a private email schedule. For example, the schedule reflection unit applies the private schedule reflection method based on the content of the private email. The schedule reflection unit can also apply an advertising schedule reflection method to a promotional email schedule. For example, the schedule reflection unit applies the advertising schedule reflection method based on the content of the promotional email. This allows the accuracy of the schedule to be improved by applying the optimal schedule reflection method depending on the category of email.

[0049] When reflecting a schedule, the schedule reflection unit can improve the accuracy of the schedule by referring to the user's past schedule history. The schedule reflection unit provides an optimal schedule based on, for example, the user's past schedule history. For example, the schedule reflection unit creates a schedule based on the frequency and importance of past appointments. The schedule reflection unit can also improve the accuracy of the schedule from the user's past schedule history. For example, the schedule reflection unit analyzes the past schedule history to improve the accuracy of the schedule. The schedule reflection unit can also improve the accuracy of the schedule by referring to the user's past schedule history. For example, the schedule reflection unit improves the accuracy of the schedule based on the past schedule history. In this way, the accuracy of the schedule can be improved by referring to the user's past schedule history.

[0050] When reflecting a schedule, the schedule reflecting unit can adjust the schedule taking into account the geographical location information of the email sender. For example, if the sender is nearby, the schedule reflecting unit prioritizes reflecting schedules with a high level of urgency. For example, the schedule reflecting unit identifies geographical location information based on the sender's IP address or GPS data, and prioritizes reflecting schedules with a high level of urgency. The schedule reflecting unit can also reflect a regular schedule if the sender is far away. For example, the schedule reflecting unit reflects a regular schedule based on the sender's geographical location information. The schedule reflecting unit can also adjust an appropriate schedule based on the sender's geographical location information. For example, the schedule reflecting unit adjusts an optimal schedule based on the sender's geographical location information. In this way, by taking into account the geographical location information of the email sender, it is possible to prioritize reflecting plans with a high level of urgency in the schedule.

[0051] The schedule reflection unit can improve the accuracy of the schedule by referring to literature related to the email when reflecting the schedule. The schedule reflection unit adjusts the schedule by, for example, referring to industry literature related to the content of the email. For example, the schedule reflection unit acquires related information from industry literature and reflects it in the schedule. The schedule reflection unit can also adjust the schedule by referring to news literature related to the content of the email. For example, the schedule reflection unit acquires the latest information from news literature and reflects it in the schedule. The schedule reflection unit can also adjust the schedule by referring to academic literature related to the content of the email. For example, the schedule reflection unit acquires related research papers from academic literature and reflects them in the schedule. In this way, the accuracy of the schedule can be improved by referring to literature related to the email.

[0052] The schedule reflection unit can adjust the schedule by taking into consideration the market value of the email when reflecting the schedule. The schedule reflection unit, for example, preferentially reflects plans for emails with high market value in the schedule. For example, the schedule reflection unit evaluates the market value based on the content of the email and reflects important plans in the schedule preferentially. The schedule reflection unit can also postpone plans for emails with low market value before reflecting them in the schedule. For example, the schedule reflection unit evaluates the market value based on the content of the email and reflects plans with low importance in the schedule preferentially. The schedule reflection unit can also adjust the priority of the schedule based on the market value. For example, the schedule reflection unit adjusts the priority of the schedule based on the content of the email and market research data. In this way, important plans can be reflected in the schedule preferentially by taking into consideration the market value of the email.

[0053] When linking, the linking unit can select the optimal linking method by referring to the user's past linking history. The linking unit provides the optimal linking method, for example, based on the user's past linking history. For example, the linking unit selects the linking method based on the past linking success rate and frequency of linking. The linking unit can also improve the accuracy of linking based on the user's past linking history. For example, the linking unit analyzes the past linking history and improves the accuracy of linking. The linking unit can also select the optimal linking method by referring to the user's past linking history. For example, the linking unit selects the optimal linking method based on the past linking history. In this way, the optimal linking method can be provided by referring to the user's past linking history.

[0054] The collaboration unit can customize the collaboration means at the time of collaboration, taking into account the user's current device information. For example, if the user is using a smartphone, the collaboration unit provides a collaboration means optimized for the smartphone. For example, the collaboration unit customizes the collaboration means based on the type of smartphone and the OS version. Furthermore, if the user is using a tablet, the collaboration unit can also provide a collaboration means optimized for the tablet. For example, the collaboration unit customizes the collaboration means based on the type of tablet and the OS version. Furthermore, if the user is using a desktop, the collaboration unit can also provide a collaboration means optimized for the desktop. For example, the collaboration unit customizes the collaboration means based on the type of desktop and the OS version. In this way, the optimal collaboration means can be provided by taking into account the user's current device information.

[0055] At the time of collaboration, the collaboration unit can select the optimal collaboration method by taking into account the user's geographical location information. For example, if the user is nearby, the collaboration unit provides a direct collaboration method. For example, the collaboration unit identifies geographical location information based on the user's IP address or GPS data and selects the optimal collaboration method. The collaboration unit can also provide a remote collaboration method if the user is far away. For example, the collaboration unit selects a remote collaboration method based on the user's geographical location information. The collaboration unit can also select the optimal collaboration method based on the user's geographical location information. For example, the collaboration unit selects the optimal collaboration method based on the user's geographical location information. In this way, the optimal collaboration method can be provided by taking into account the user's geographical location information.

[0056] At the time of collaboration, the collaboration unit can analyze the user's social media activity and suggest collaboration methods. The collaboration unit, for example, suggests the most appropriate collaboration method based on the user's social media activity. For example, the collaboration unit suggests collaboration methods based on the user's posting frequency and number of followers. The collaboration unit can also improve the accuracy of collaboration based on the user's social media activity. For example, the collaboration unit analyzes the user's social media activity and improves the accuracy of collaboration. The collaboration unit can also analyze the user's social media activity and suggest the most appropriate collaboration method. For example, the collaboration unit suggests the most appropriate collaboration method based on the user's social media activity. In this way, the most appropriate collaboration method can be provided by analyzing the user's social media activity.

[0057] The acquisition unit can analyze the user's past email acquisition history and select the optimal acquisition method. The acquisition unit provides the optimal acquisition method, for example, based on the user's past email acquisition history. For example, the acquisition unit selects the acquisition method based on the past acquisition frequency and acquisition time period. The acquisition unit can also improve the acquisition accuracy based on the user's past email acquisition history. For example, the acquisition unit analyzes the past acquisition history and improves the acquisition accuracy. The acquisition unit can also select the optimal acquisition method by referring to the user's past email acquisition history. For example, the acquisition unit selects the optimal acquisition method based on the past acquisition history. In this way, the optimal acquisition method can be provided by analyzing the user's past email acquisition history.

[0058] When acquiring emails, the acquisition unit can filter emails based on the user's current project or area of ​​interest. The acquisition unit, for example, preferentially acquires emails related to the user's current project. For example, the acquisition unit filters emails based on keywords in the project name or area of ​​interest. The acquisition unit can also preferentially acquire emails related to the user's area of ​​interest. For example, the acquisition unit filters emails based on keywords in the area of ​​interest. The acquisition unit can also filter emails based on the user's current project or area of ​​interest. For example, the acquisition unit filters emails based on keywords in the project name or area of ​​interest. In this way, by filtering emails based on the user's current project or area of ​​interest, it is possible to preferentially acquire highly relevant emails.

[0059] When retrieving email, the retrieval unit can select the optimal retrieval means depending on the user's input method. For example, if the user uses voice input, the retrieval unit provides an retrieval means optimized for voice input. For example, the retrieval unit analyzes the voice input using voice recognition technology and retrieves the email. Furthermore, if the user uses text input, the retrieval unit can also provide an retrieval means optimized for text input. For example, the retrieval unit analyzes the text input using text analysis technology and retrieves the email. Furthermore, if the user uses image input, the retrieval unit can also provide an retrieval means optimized for image input. For example, the retrieval unit analyzes the image input using image recognition technology and retrieves the email. In this way, by selecting the optimal retrieval means depending on the user's input method, it is possible to retrieve email in a manner that is easy for the user to use.

[0060] When retrieving emails, the retrieval unit can prioritize retrieving highly relevant emails by taking into account the user's geographical location information. For example, when the user is nearby, the retrieval unit prioritizes retrieving highly relevant emails. For example, the retrieval unit identifies geographical location information based on the user's IP address or GPS data, and prioritizes retrieving highly relevant emails. The retrieval unit can also retrieve regular emails when the user is far away. For example, the retrieval unit retrieves regular emails based on the user's geographical location information. The retrieval unit can also prioritize retrieving highly relevant emails based on the user's geographical location information. For example, the retrieval unit prioritizes retrieving highly relevant emails based on the user's geographical location information. In this way, it is possible to prioritize retrieving highly relevant emails by taking into account the user's geographical location information.

[0061] When acquiring emails, the acquisition unit can analyze the user's social media activity and acquire related emails. The acquisition unit, for example, acquires related emails based on the user's social media activity. For example, the acquisition unit acquires related emails based on the user's posting frequency and number of followers. The acquisition unit can also improve the accuracy of acquisition based on the user's social media activity. For example, the acquisition unit analyzes the user's social media activity and improves the accuracy of acquisition. The acquisition unit can also analyze the user's social media activity to acquire related emails. For example, the acquisition unit acquires related emails based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to preferentially acquire related emails.

[0062] When retrieving emails, the retrieval unit can customize the retrieval method by reflecting the user's past feedback. The retrieval unit provides an optimal retrieval method, for example, based on the user's past feedback. For example, the retrieval unit customizes the retrieval method based on the content and evaluation of the past feedback. The retrieval unit can also improve the accuracy of retrieval based on the user's past feedback. For example, the retrieval unit analyzes the past feedback and improves the accuracy of retrieval. The retrieval unit can also customize the retrieval method by reflecting the user's past feedback. For example, the retrieval unit customizes the optimal retrieval method based on the past feedback. In this way, the optimal retrieval method can be provided by reflecting the user's past feedback.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The analysis unit can evaluate the trustworthiness of the email sender and adjust the level of analysis detail based on the trustworthiness. For example, emails from highly trusted senders are analyzed in detail. The analysis unit evaluates trustworthiness based on the frequency of past exchanges and the sender's domain. Emails from senders with low trustworthiness can also be analyzed more simply. The analysis unit performs a more simplified analysis when the sender's domain is unknown or there has been little past exchange. Furthermore, for emails from senders with medium trustworthiness, the level of analysis detail can be adjusted according to their content. The analysis unit adjusts the level of analysis detail based on the sender's trustworthiness and the content of the email. In this way, important emails can be analyzed in detail by adjusting the level of analysis detail based on the trustworthiness of the email sender.

[0065] The analysis unit can apply different analysis algorithms based on the content of the email. For example, a schedule analysis algorithm can be applied to a meeting invitation email. The analysis unit extracts the date, time, and location of the meeting and reflects this in the schedule. A detailed analysis algorithm can also be applied to emails containing important notices. The analysis unit analyzes the content of the email in detail and extracts important information. Furthermore, a simplified analysis algorithm can also be applied to advertising emails. The analysis unit simply analyzes the content of advertising emails and extracts only important information. This allows the most appropriate analysis algorithm to be applied depending on the content of the email, improving the accuracy of the analysis.

[0066] The analysis unit classifies the contents of emails by category and can apply different analysis methods to each category. For example, a business analysis method is applied to business emails. The analysis unit analyzes the contents of business emails in detail and extracts important information. A private analysis method can also be applied to private emails. The analysis unit simply analyzes the contents of private emails and extracts only important information. Furthermore, an advertising analysis method can also be applied to advertising emails. The analysis unit simply analyzes the contents of advertising emails and extracts only important information. This allows the analysis accuracy to be improved by applying the most appropriate analysis method according to the email category.

[0067] The analysis unit can perform analysis taking into account the geographical location information of the sender of the email. For example, if the sender is nearby, it performs analysis with a high level of urgency. The analysis unit identifies the geographical location information based on the sender's IP address or GPS data, and prioritizes analysis of emails with a high level of urgency. In addition, if the sender is far away, it can also perform normal analysis. The analysis unit applies normal analysis methods based on the sender's geographical location information. Furthermore, it can also select an appropriate analysis method based on the sender's geographical location information. The analysis unit selects the optimal analysis method based on the sender's geographical location information. In this way, it is possible to prioritize analysis of emails with a high level of urgency by taking into account the geographical location information of the sender.

[0068] The analysis unit can improve the accuracy of the analysis by referring to an external database related to the content of the email. For example, the analysis is performed by referring to an industry database related to the content of the email. The analysis unit obtains related information from the industry database and reflects it in the analysis. The analysis unit can also perform the analysis by referring to a news database related to the content of the email. The analysis unit obtains the latest information from the news database and reflects it in the analysis. Furthermore, the analysis can also perform the analysis by referring to an academic database related to the content of the email. The analysis unit obtains related research papers from the academic database and reflects them in the analysis. In this way, the accuracy of the analysis can be improved by referring to external databases.

[0069] The analysis unit can analyze the content of emails in conjunction with other communication channels. For example, the analysis unit analyzes the content of emails in conjunction with the content of chats. The analysis unit refers to the content of chat apps and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in conjunction with posts on social media. The analysis unit refers to posts on social media and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in conjunction with other communication channels. The analysis unit refers to the content of chat apps and social media and analyzes it in association with the content of emails. This makes it possible to improve the accuracy of the analysis by linking with other communication channels.

[0070] When generating a summary, the summarization unit can adjust the level of detail in the summary based on the importance of the email. For example, a detailed summary is provided for emails with high importance. The summarization unit evaluates the importance based on the job title of the email sender and the content of the email, and creates a detailed summary. It can also provide a concise summary for emails with low importance. The summarization unit briefly summarizes the content of the email and provides only important information. Furthermore, for emails with medium importance, the level of detail in the summary can be adjusted according to the content. The summarization unit adjusts the level of detail in the summary based on the content of the email. In this way, by adjusting the level of detail in the summary based on the importance of the email, it is possible to provide a detailed summary of important emails.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The analysis unit analyzes the content of the email. The analysis unit analyzes the content of the email using, for example, natural language processing technology. Specifically, it uses morphological analysis to analyze the grammatical structure of the email and keyword extraction technology to extract important words and phrases. It also uses semantic analysis technology to understand the content of the email, grasp the context, and extract important information. Step 2: The summarization unit summarizes the content analyzed by the analysis unit. For example, the summarization unit extracts key points to create a summary. Specifically, it extracts the important parts of the email and creates a concise summary. It is also possible to create summaries using generative AI, which generates summaries by entering prompts. Step 3: The schedule reflection unit reflects the content summarized by the summarization unit in the schedule. For example, the schedule reflection unit automatically adds important emails and emails related to the schedule to the schedule. Specifically, it automatically adds meeting invitation emails to the schedule and manages the schedule in cooperation with a calendar app. For example, it cooperates with Google Calendar or Outlook Calendar to automatically update the schedule.

[0073] (Example 2) An AI concierge system according to an embodiment of the present invention summarizes the contents of unread emails that accumulate after a holiday and manages schedules. The AI ​​concierge system automatically retrieves unread emails, analyzes their contents, and provides summaries when a user connects their email account. Furthermore, important emails and emails related to a schedule are automatically reflected in the schedule. For example, the AI ​​concierge system allows a user to access their email account by entering their email account credentials. The AI ​​concierge system then accesses the user's email account and retrieves a list of unread emails. For example, the AI ​​concierge system retrieves all unread emails that accumulated after a holiday and analyzes their contents. The AI ​​concierge system then analyzes the contents of the unread emails, extracts important points, and creates summaries. For example, the AI ​​concierge system provides the user with summaries of emails containing meeting invitations or important notices. Furthermore, the AI ​​concierge system automatically adds important emails and emails related to a schedule to the schedule. For example, if an email contains a meeting invitation, the AI ​​concierge system automatically adds it to the schedule. This allows users to efficiently process emails and manage their schedules without being overwhelmed by a large number of unread emails. This allows the AI ​​concierge system to efficiently process emails and manage schedules without users being overwhelmed by a large number of unread emails. For example, the AI ​​concierge system can summarize unread emails that have accumulated after a holiday and update important emails in the schedule, allowing users to get to work right away.

[0074] The AI ​​concierge system according to the embodiment includes an analysis unit, a summarization unit, and a schedule reflection unit. The analysis unit analyzes the content of emails. For example, the analysis unit analyzes the content of emails using natural language processing technology. For example, the analysis unit analyzes the grammatical structure of emails using morphological analysis. The analysis unit can also extract important words and phrases using keyword extraction technology. The analysis unit can also understand the content of emails using semantic analysis technology. For example, the analysis unit understands the context of emails and extracts important information. The summarization unit summarizes the content analyzed by the analysis unit. For example, the summarization unit extracts important points to create a summary. For example, the summarization unit extracts important parts of emails and creates a concise summary. The summarization unit can also create a summary using a generation AI. For example, the summarization unit inputs a prompt to the generation AI, such as "Please summarize the main points of this email," and generates a summary. The schedule reflection unit reflects the content summarized by the summarization unit in a schedule. For example, the schedule reflection unit automatically adds important emails and emails related to a schedule to the schedule. For example, the schedule reflection unit automatically adds a meeting invitation email to the schedule. The schedule reflection unit can also manage the schedule in cooperation with a calendar app. For example, the schedule reflection unit cooperates with Google Calendar or Outlook Calendar to automatically update the schedule. This allows the AI ​​concierge system according to the embodiment to enable the user to efficiently process emails and manage the schedule.

[0075] Furthermore, the AI ​​concierge system includes a linking unit that links email accounts. The linking unit provides a function for users to link their email accounts. For example, the linking unit allows users to access their email accounts by entering authentication information for the email account. For example, the linking unit allows users to access their email accounts by entering an email address and password. The linking unit can also access email accounts using OAuth authentication. For example, the linking unit allows users to access their email accounts using a Google account or a Microsoft account. This allows users to link their email accounts, allowing the AI ​​concierge to retrieve and analyze emails.

[0076] The AI ​​concierge system also includes an acquisition unit that acquires unread emails. The acquisition unit automatically acquires unread emails. For example, the acquisition unit accesses the user's email account and acquires a list of unread emails. For example, the acquisition unit acquires all unread emails that have accumulated after a holiday and analyzes their contents. The acquisition unit can also acquire unread emails from a specific folder. For example, the acquisition unit acquires unread emails from the inbox or folders with specific labels. The acquisition unit can also acquire unread emails from a certain period of time. For example, the acquisition unit acquires unread emails from the past week. This automatically acquires unread emails, eliminating the need for the user to manually check emails.

[0077] The analysis unit can analyze the content of emails using natural language processing technology. The analysis unit, for example, analyzes the grammatical structure of emails using morphological analysis. For example, the analysis unit breaks down the sentences of an email into words and identifies the part of speech of each word. The analysis unit can also extract important words and phrases using keyword extraction technology. For example, the analysis unit extracts words and phrases that appear frequently in an email and identifies important information based on that. The analysis unit can also understand the content of an email using semantic analysis technology. For example, the analysis unit understands the context of an email and extracts important information. In this way, the content of an email can be accurately analyzed using natural language processing technology.

[0078] The summarization unit can extract important points and create a summary. For example, the summarization unit extracts important parts of an email and creates a concise summary. For example, the summarization unit extracts particularly important information from an email and creates a summary based on that. The summarization unit can also create a summary using a generation AI. For example, the summarization unit inputs a prompt such as "Please summarize the main points of this email" into the generation AI and generates a summary. The summarization unit can also extract important words and phrases using keyword extraction technology and create a summary based on that. For example, the summarization unit extracts words and phrases that appear frequently in an email and creates a summary based on that. This allows users to quickly grasp the information they need by extracting important points.

[0079] The schedule reflection unit can automatically add important emails and emails related to a schedule to the schedule. The schedule reflection unit can automatically add, for example, meeting invitation emails to the schedule. For example, the schedule reflection unit can analyze the content of the email and add the date, time, and location of the meeting to the schedule. The schedule reflection unit can also manage the schedule in cooperation with a calendar app. For example, the schedule reflection unit can cooperate with Google Calendar or Outlook Calendar to automatically update the schedule. The schedule reflection unit can also prioritize reflecting important emails in the schedule. For example, the schedule reflection unit can prioritize adding emails from specific senders or emails containing specific keywords to the schedule. In this way, by automatically adding important emails and emails related to a schedule to the schedule, the user can save time and effort in manually managing the schedule.

[0080] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit prioritizes analyzing emails of high importance. For example, the analysis unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, the analysis unit can analyze all emails equally. For example, the analysis unit records the user's voice and estimates the user's emotions using voice analysis technology. Alternatively, if the user is in a hurry, the analysis unit can prioritize analyzing emails containing meetings or urgent notices. For example, the analysis unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the system to adjust the analysis priority according to the user's emotions, thereby reducing the user's stress and efficiently processing emails. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0081] The analysis unit can evaluate the trustworthiness of the email sender and adjust the level of analysis detail based on the trustworthiness. The analysis unit, for example, performs a detailed analysis of emails from highly trusted senders. For example, the analysis unit evaluates trustworthiness based on the frequency of past exchanges and the sender's domain. The analysis unit can also perform a simplified analysis of emails from senders with low trustworthiness. For example, the analysis unit performs a simplified analysis when the sender's domain is unknown or when there has been little past exchange. The analysis unit can also adjust the level of analysis detail based on the content of emails from senders with medium trustworthiness. For example, the analysis unit adjusts the level of analysis detail based on the sender's trustworthiness and the content of the email. In this way, important emails can be analyzed in detail by adjusting the level of analysis detail based on the trustworthiness of the email sender.

[0082] The analysis unit can apply different analysis algorithms based on the content of the email. For example, the analysis unit applies a schedule analysis algorithm to a meeting invitation email. For example, the analysis unit extracts the date, time, and location of the meeting and reflects this in the schedule. The analysis unit can also apply a detailed analysis algorithm to emails containing important notices. For example, the analysis unit analyzes the content of the email in detail and extracts important information. The analysis unit can also apply a simplified analysis algorithm to advertising emails. For example, the analysis unit analyzes the content of advertising emails in a simplified manner and extracts only important information. This allows the analysis accuracy to be improved by applying the optimal analysis algorithm depending on the content of the email.

[0083] The analysis unit classifies the contents of emails by category and can apply different analysis methods to each category. For example, the analysis unit applies a business analysis method to business emails. For example, the analysis unit analyzes the contents of business emails in detail and extracts important information. The analysis unit can also apply a private analysis method to private emails. For example, the analysis unit simply analyzes the contents of private emails and extracts only important information. The analysis unit can also apply an advertising analysis method to advertising emails. For example, the analysis unit simply analyzes the contents of advertising emails and extracts only important information. This allows the analysis accuracy to be improved by applying the optimal analysis method depending on the email category.

[0084] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit provides a concise display method. For example, the analysis unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. The analysis unit can also provide a detailed display method if the user is relaxed. For example, the analysis unit records the user's voice and estimates the user's emotions using voice analysis technology. The analysis unit can also provide a more concise display method if the user is in a hurry. For example, the analysis unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the display method of the analysis results to be adjusted according to the user's emotions, allowing the user to view the analysis results without feeling stressed. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0085] The analysis unit can perform analysis taking into account the geographical location information of the sender of the email. For example, if the sender is nearby, the analysis unit performs analysis with a high level of urgency. For example, the analysis unit identifies geographical location information based on the sender's IP address or GPS data, and prioritizes analysis of emails with a high level of urgency. The analysis unit can also perform normal analysis if the sender is far away. For example, the analysis unit applies a normal analysis method based on the sender's geographical location information. The analysis unit can also select an appropriate analysis method based on the sender's geographical location information. For example, the analysis unit selects the optimal analysis method based on the sender's geographical location information. This makes it possible to prioritize analysis of emails with a high level of urgency by taking into account the geographical location information of the sender.

[0086] The analysis unit can improve the accuracy of the analysis by referring to an external database related to the content of the email. The analysis unit performs the analysis by referring to, for example, an industry database related to the content of the email. For example, the analysis unit acquires related information from the industry database and reflects it in the analysis. The analysis unit can also perform the analysis by referring to a news database related to the content of the email. For example, the analysis unit acquires the latest information from the news database and reflects it in the analysis. The analysis unit can also perform the analysis by referring to an academic database related to the content of the email. For example, the analysis unit acquires related research papers from the academic database and reflects it in the analysis. In this way, the accuracy of the analysis can be improved by referring to an external database.

[0087] The analysis unit can analyze the content of emails in cooperation with other communication channels. The analysis unit, for example, analyzes the content of emails in cooperation with the content of chats. For example, the analysis unit refers to the content of a chat app and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in cooperation with posts on social media. For example, the analysis unit refers to posts on social media and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in cooperation with other communication channels. For example, the analysis unit refers to the content of a chat app or social media and analyzes it in association with the content of emails. In this way, by coordinating with other communication channels, the accuracy of the analysis can be improved.

[0088] The summarization unit can estimate the user's emotions and adjust the presentation style of the summary based on the estimated user emotions. For example, if the user is feeling stressed, the summarization unit provides a concise summary. For example, the summarization unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. The summarization unit can also provide a detailed summary if the user is relaxed. For example, the summarization unit records the user's voice and estimates the user's emotions using voice analysis technology. The summarization unit can also provide a summary that focuses on the main points if the user is in a hurry. For example, the summarization unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the user to view the summary without feeling stressed by adjusting the presentation style of the summary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] When generating a summary, the summarization unit can adjust the level of detail of the summary based on the importance of the email. For example, the summarization unit provides a detailed summary for emails of high importance. For example, the summarization unit evaluates the importance based on the job title of the email sender and the content of the email and creates a detailed summary. The summarization unit can also provide a concise summary for emails of low importance. For example, the summarization unit briefly summarizes the content of the email and provides only important information. The summarization unit can also adjust the level of detail of the summary based on the content of the email for emails of medium importance. For example, the summarization unit adjusts the level of detail of the summary based on the content of the email. In this way, by adjusting the level of detail of the summary based on the importance of the email, it is possible to provide a detailed summary of important emails.

[0090] The summarization unit can apply different summarization algorithms depending on the category of email when generating a summary. For example, the summarization unit applies a business summarization algorithm to business emails. For example, the summarization unit summarizes the content of the business email in detail and provides important information. The summarization unit can also apply a private summarization algorithm to private emails. For example, the summarization unit briefly summarizes the content of the private email and provides only important information. The summarization unit can also apply an advertising summarization algorithm to advertising emails. For example, the summarization unit briefly summarizes the content of advertising emails and provides only important information. This allows the accuracy of the summary to be improved by applying the optimal summarization algorithm depending on the category of email.

[0091] When generating a summary, the summarization unit can improve the accuracy of the summary by referring to the user's past summarization results. The summarization unit provides an optimal summary, for example, based on the user's past summarization results. For example, the summarization unit creates a summary based on the accuracy of the past summarizations and user feedback. The summarization unit can also improve the accuracy of the summary from the user's past summarization results. For example, the summarization unit analyzes the past summarization results and improves the accuracy of the summary. The summarization unit can also improve the accuracy of the summary by referring to the user's past summarization results. For example, the summarization unit improves the accuracy of the summary based on the past summarization results. In this way, the accuracy of the summary can be improved by referring to the user's past summarization results.

[0092] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated user emotions. For example, if the user is feeling stressed, the summarization unit provides a short summary. For example, the summarization unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. The summarization unit can also provide a longer summary if the user is relaxed. For example, the summarization unit records the user's voice and estimates the user's emotions using voice analysis technology. The summarization unit can also provide a short summary that focuses on the main points if the user is in a hurry. For example, the summarization unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the user to view the summary without feeling stressed by adjusting the length of the summary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] When generating a summary, the summarizing unit can determine the priority of the summary based on the time when the email was sent. For example, the summarizing unit prioritizes summarizing the most recently sent email. For example, the summarizing unit prioritizes summarizing the most recent email based on the date and time when the email was sent. The summarizing unit can also postpone summarizing older emails. For example, the summarizing unit postpones summarizing older emails based on the date and time when the email was sent. The summarizing unit can also adjust the priority of the summary based on the time when it was sent. For example, the summarizing unit adjusts the priority of the summary based on the frequency of email sending and the date and time when it was sent. In this way, by determining the priority of the summary based on the time when the email was sent, it is possible to prioritize summarizing the latest information.

[0094] When generating summaries, the summarizing unit can adjust the order of summaries based on the relevance of emails. For example, the summarizing unit prioritizes summarizing highly relevant emails. For example, the summarizing unit prioritizes summarizing highly relevant emails based on the content of the emails and the commonality of senders. The summarizing unit can also postpone summarizing less relevant emails. For example, the summarizing unit postpones summarizing less relevant emails based on the content of the emails and the commonality of senders. The summarizing unit can also adjust the order of summaries based on relevance. For example, the summarizing unit adjusts the order of summaries based on common keywords and the commonality of senders. In this way, by adjusting the order of summaries based on the relevance of emails, it is possible to provide highly relevant information preferentially.

[0095] When generating a summary, the summarization unit can adjust the use of technical terms in the summary according to the user's level of expertise. For example, if the user's level of expertise is high, the summarization unit provides a summary that uses a lot of technical terms. For example, the summarization unit creates a summary that uses a lot of technical terms based on the user's occupation and educational background. Furthermore, if the user's level of expertise is low, the summarization unit can also provide a summary that avoids technical terms. For example, the summarization unit creates a summary that avoids technical terms based on the content of the user's past emails. Furthermore, the summarization unit can also adjust the use of technical terms in the summary according to the user's level of expertise. For example, the summarization unit adjusts the use of technical terms in the summary based on the user's occupation and educational background. In this way, by adjusting the use of technical terms in the summary according to the user's level of expertise, it is possible to provide a summary that is easy for the user to understand.

[0096] The schedule reflection unit can estimate the user's emotions and adjust the schedule reflection method based on the estimated user emotions. For example, if the user is feeling stressed, the schedule reflection unit reflects only important events in the schedule. For example, the schedule reflection unit captures the user's facial expressions with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the schedule reflection unit can also reflect all events in the schedule. For example, the schedule reflection unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the schedule reflection unit can prioritize the most urgent events in the schedule. For example, the schedule reflection unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the user to manage their schedule without feeling stressed by adjusting the schedule reflection method according to the user's emotions. Emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0097] The schedule reflection unit can determine the priority of a schedule based on the importance of an email when reflecting a schedule. The schedule reflection unit, for example, preferentially reflects an appointment for an email with a high level of importance in the schedule. For example, the schedule reflection unit evaluates the importance based on the job title of the sender of the email or the content of the email and reflects it in the schedule. The schedule reflection unit can also postpone the appointment for an email with a low level of importance before reflecting it in the schedule. For example, the schedule reflection unit postpones the appointment for an email with a low level of importance before reflecting it in the schedule based on the content of the email. The schedule reflection unit can also adjust the priority of a schedule based on the importance. For example, the schedule reflection unit adjusts the priority of a schedule based on the content of the email or the job title of the sender. In this way, by determining the priority of a schedule based on the importance of an email, it is possible to preferentially reflect important appointments in the schedule.

[0098] The schedule reflection unit can apply different schedule reflection methods depending on the category of email when reflecting the schedule. For example, the schedule reflection unit applies a business schedule reflection method to a business email schedule. For example, the schedule reflection unit applies the business schedule reflection method based on the content of the business email. The schedule reflection unit can also apply a private schedule reflection method to a private email schedule. For example, the schedule reflection unit applies the private schedule reflection method based on the content of the private email. The schedule reflection unit can also apply an advertising schedule reflection method to a promotional email schedule. For example, the schedule reflection unit applies the advertising schedule reflection method based on the content of the promotional email. This allows the accuracy of the schedule to be improved by applying the optimal schedule reflection method depending on the category of email.

[0099] When reflecting a schedule, the schedule reflection unit can improve the accuracy of the schedule by referring to the user's past schedule history. The schedule reflection unit provides an optimal schedule based on, for example, the user's past schedule history. For example, the schedule reflection unit creates a schedule based on the frequency and importance of past appointments. The schedule reflection unit can also improve the accuracy of the schedule from the user's past schedule history. For example, the schedule reflection unit analyzes the past schedule history to improve the accuracy of the schedule. The schedule reflection unit can also improve the accuracy of the schedule by referring to the user's past schedule history. For example, the schedule reflection unit improves the accuracy of the schedule based on the past schedule history. In this way, the accuracy of the schedule can be improved by referring to the user's past schedule history.

[0100] The schedule reflecting unit can estimate the user's emotions and adjust the schedule display method based on the estimated user emotions. For example, if the user is feeling stressed, the schedule reflecting unit can provide a concise display method. For example, the schedule reflecting unit can capture the user's facial expression with a camera and estimate the user's emotions using an emotion estimation algorithm. Furthermore, if the user is relaxed, the schedule reflecting unit can provide a detailed display method. For example, the schedule reflecting unit can record the user's voice and estimate the user's emotions using voice analysis technology. Furthermore, if the user is in a hurry, the schedule reflecting unit can provide a display method that focuses on the key points. For example, the schedule reflecting unit can collect the user's biometric data (heart rate and electrodermal activity) using a sensor and estimate the user's emotions using an emotion estimation algorithm. This allows the user to check the schedule without feeling stressed by adjusting the schedule display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0101] When reflecting a schedule, the schedule reflecting unit can adjust the schedule taking into account the geographical location information of the email sender. For example, if the sender is nearby, the schedule reflecting unit prioritizes reflecting schedules with a high level of urgency. For example, the schedule reflecting unit identifies geographical location information based on the sender's IP address or GPS data, and prioritizes reflecting schedules with a high level of urgency. The schedule reflecting unit can also reflect a regular schedule if the sender is far away. For example, the schedule reflecting unit reflects a regular schedule based on the sender's geographical location information. The schedule reflecting unit can also adjust an appropriate schedule based on the sender's geographical location information. For example, the schedule reflecting unit adjusts an optimal schedule based on the sender's geographical location information. In this way, by taking into account the geographical location information of the email sender, it is possible to prioritize reflecting plans with a high level of urgency in the schedule.

[0102] The schedule reflection unit can improve the accuracy of the schedule by referring to literature related to the email when reflecting the schedule. The schedule reflection unit adjusts the schedule by, for example, referring to industry literature related to the content of the email. For example, the schedule reflection unit acquires related information from industry literature and reflects it in the schedule. The schedule reflection unit can also adjust the schedule by referring to news literature related to the content of the email. For example, the schedule reflection unit acquires the latest information from news literature and reflects it in the schedule. The schedule reflection unit can also adjust the schedule by referring to academic literature related to the content of the email. For example, the schedule reflection unit acquires related research papers from academic literature and reflects them in the schedule. In this way, the accuracy of the schedule can be improved by referring to literature related to the email.

[0103] The schedule reflection unit can adjust the schedule by taking into consideration the market value of the email when reflecting the schedule. The schedule reflection unit, for example, preferentially reflects plans for emails with high market value in the schedule. For example, the schedule reflection unit evaluates the market value based on the content of the email and reflects important plans in the schedule preferentially. The schedule reflection unit can also postpone plans for emails with low market value before reflecting them in the schedule. For example, the schedule reflection unit evaluates the market value based on the content of the email and reflects plans with low importance in the schedule preferentially. The schedule reflection unit can also adjust the priority of the schedule based on the market value. For example, the schedule reflection unit adjusts the priority of the schedule based on the content of the email and market research data. In this way, important plans can be reflected in the schedule preferentially by taking into consideration the market value of the email.

[0104] The collaboration unit can estimate the user's emotions and adjust the collaboration method based on the estimated user emotions. For example, if the user is feeling stressed, the collaboration unit provides a simple collaboration method. For example, the collaboration unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, if the user is relaxed, the collaboration unit can provide a detailed collaboration method. For example, the collaboration unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, if the user is in a hurry, the collaboration unit can provide a quick collaboration method. For example, the collaboration unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This allows the collaboration method to be adjusted according to the user's emotions, enabling collaboration without stress for the user. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0105] When linking, the linking unit can select the optimal linking method by referring to the user's past linking history. The linking unit provides the optimal linking method, for example, based on the user's past linking history. For example, the linking unit selects the linking method based on the past linking success rate and frequency of linking. The linking unit can also improve the accuracy of linking based on the user's past linking history. For example, the linking unit analyzes the past linking history and improves the accuracy of linking. The linking unit can also select the optimal linking method by referring to the user's past linking history. For example, the linking unit selects the optimal linking method based on the past linking history. In this way, the optimal linking method can be provided by referring to the user's past linking history.

[0106] The collaboration unit can customize the collaboration means at the time of collaboration, taking into account the user's current device information. For example, if the user is using a smartphone, the collaboration unit provides a collaboration means optimized for the smartphone. For example, the collaboration unit customizes the collaboration means based on the type of smartphone and the OS version. Furthermore, if the user is using a tablet, the collaboration unit can also provide a collaboration means optimized for the tablet. For example, the collaboration unit customizes the collaboration means based on the type of tablet and the OS version. Furthermore, if the user is using a desktop, the collaboration unit can also provide a collaboration means optimized for the desktop. For example, the collaboration unit customizes the collaboration means based on the type of desktop and the OS version. In this way, the optimal collaboration means can be provided by taking into account the user's current device information.

[0107] The collaboration unit can estimate the user's emotions and determine the priority of collaborations based on the estimated user emotions. For example, when the user is feeling stressed, the collaboration unit prioritizes important collaborations. For example, the collaboration unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. Furthermore, when the user is relaxed, the collaboration unit can equally perform all collaborations. For example, the collaboration unit records the user's voice and estimates the emotion using voice analysis technology. Furthermore, when the user is in a hurry, the collaboration unit can prioritize collaborations with high urgency. For example, the collaboration unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates the emotion using an emotion estimation algorithm. This allows collaboration prioritization based on the user's emotions, thereby prioritizing important collaborations. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0108] At the time of collaboration, the collaboration unit can select the optimal collaboration method by taking into account the user's geographical location information. For example, if the user is nearby, the collaboration unit provides a direct collaboration method. For example, the collaboration unit identifies geographical location information based on the user's IP address or GPS data and selects the optimal collaboration method. The collaboration unit can also provide a remote collaboration method if the user is far away. For example, the collaboration unit selects a remote collaboration method based on the user's geographical location information. The collaboration unit can also select the optimal collaboration method based on the user's geographical location information. For example, the collaboration unit selects the optimal collaboration method based on the user's geographical location information. In this way, the optimal collaboration method can be provided by taking into account the user's geographical location information.

[0109] At the time of collaboration, the collaboration unit can analyze the user's social media activity and suggest collaboration methods. The collaboration unit, for example, suggests the most appropriate collaboration method based on the user's social media activity. For example, the collaboration unit suggests collaboration methods based on the user's posting frequency and number of followers. The collaboration unit can also improve the accuracy of collaboration based on the user's social media activity. For example, the collaboration unit analyzes the user's social media activity and improves the accuracy of collaboration. The collaboration unit can also analyze the user's social media activity and suggest the most appropriate collaboration method. For example, the collaboration unit suggests the most appropriate collaboration method based on the user's social media activity. In this way, the most appropriate collaboration method can be provided by analyzing the user's social media activity.

[0110] The acquisition unit can estimate the user's emotions and adjust the timing of email retrieval based on the estimated user emotions. For example, when the user is feeling stressed, the acquisition unit prioritizes retrieving only important emails. For example, the acquisition unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, when the user is relaxed, the acquisition unit can equally retrieve all emails. For example, the acquisition unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, when the user is in a hurry, the acquisition unit can prioritize retrieving emails with a high level of urgency. For example, the acquisition unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. This allows the user to retrieve emails without feeling stressed by adjusting the timing of email retrieval based on the user's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0111] The acquisition unit can analyze the user's past email acquisition history and select the optimal acquisition method. The acquisition unit provides the optimal acquisition method, for example, based on the user's past email acquisition history. For example, the acquisition unit selects the acquisition method based on the past acquisition frequency and acquisition time period. The acquisition unit can also improve the acquisition accuracy based on the user's past email acquisition history. For example, the acquisition unit analyzes the past acquisition history and improves the acquisition accuracy. The acquisition unit can also select the optimal acquisition method by referring to the user's past email acquisition history. For example, the acquisition unit selects the optimal acquisition method based on the past acquisition history. In this way, the optimal acquisition method can be provided by analyzing the user's past email acquisition history.

[0112] When acquiring emails, the acquisition unit can filter emails based on the user's current project or area of ​​interest. The acquisition unit, for example, preferentially acquires emails related to the user's current project. For example, the acquisition unit filters emails based on keywords in the project name or area of ​​interest. The acquisition unit can also preferentially acquire emails related to the user's area of ​​interest. For example, the acquisition unit filters emails based on keywords in the area of ​​interest. The acquisition unit can also filter emails based on the user's current project or area of ​​interest. For example, the acquisition unit filters emails based on keywords in the project name or area of ​​interest. In this way, by filtering emails based on the user's current project or area of ​​interest, it is possible to preferentially acquire highly relevant emails.

[0113] When retrieving email, the retrieval unit can select the optimal retrieval means depending on the user's input method. For example, if the user uses voice input, the retrieval unit provides an retrieval means optimized for voice input. For example, the retrieval unit analyzes the voice input using voice recognition technology and retrieves the email. Furthermore, if the user uses text input, the retrieval unit can also provide an retrieval means optimized for text input. For example, the retrieval unit analyzes the text input using text analysis technology and retrieves the email. Furthermore, if the user uses image input, the retrieval unit can also provide an retrieval means optimized for image input. For example, the retrieval unit analyzes the image input using image recognition technology and retrieves the email. In this way, by selecting the optimal retrieval means depending on the user's input method, it is possible to retrieve email in a manner that is easy for the user to use.

[0114] The acquisition unit can estimate the user's emotions and determine the priority of emails to be retrieved based on the estimated user emotions. For example, when the user is feeling stressed, the acquisition unit prioritizes retrieving important emails. For example, the acquisition unit captures the user's facial expression with a camera and estimates the user's emotions using an emotion estimation algorithm. Furthermore, when the user is relaxed, the acquisition unit can equally retrieve all emails. For example, the acquisition unit records the user's voice and estimates the user's emotions using voice analysis technology. Furthermore, when the user is in a hurry, the acquisition unit can prioritize retrieving emails with a high level of urgency. For example, the acquisition unit collects the user's biometric data (heart rate and electrodermal activity) using a sensor and estimates the user's emotions using an emotion estimation algorithm. Thus, by determining the priority of emails to be retrieved based on the user's emotions, important emails can be prioritized for retrieval. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0115] When retrieving emails, the retrieval unit can prioritize retrieving highly relevant emails by taking into account the user's geographical location information. For example, when the user is nearby, the retrieval unit prioritizes retrieving highly relevant emails. For example, the retrieval unit identifies geographical location information based on the user's IP address or GPS data, and prioritizes retrieving highly relevant emails. The retrieval unit can also retrieve regular emails when the user is far away. For example, the retrieval unit retrieves regular emails based on the user's geographical location information. The retrieval unit can also prioritize retrieving highly relevant emails based on the user's geographical location information. For example, the retrieval unit prioritizes retrieving highly relevant emails based on the user's geographical location information. In this way, it is possible to prioritize retrieving highly relevant emails by taking into account the user's geographical location information.

[0116] When acquiring emails, the acquisition unit can analyze the user's social media activity and acquire related emails. The acquisition unit, for example, acquires related emails based on the user's social media activity. For example, the acquisition unit acquires related emails based on the user's posting frequency and number of followers. The acquisition unit can also improve the accuracy of acquisition based on the user's social media activity. For example, the acquisition unit analyzes the user's social media activity and improves the accuracy of acquisition. The acquisition unit can also analyze the user's social media activity to acquire related emails. For example, the acquisition unit acquires related emails based on the user's social media activity. In this way, by analyzing the user's social media activity, it is possible to preferentially acquire related emails.

[0117] When retrieving emails, the retrieval unit can customize the retrieval method by reflecting the user's past feedback. The retrieval unit provides an optimal retrieval method, for example, based on the user's past feedback. For example, the retrieval unit customizes the retrieval method based on the content and evaluation of the past feedback. The retrieval unit can also improve the accuracy of retrieval based on the user's past feedback. For example, the retrieval unit analyzes the past feedback and improves the accuracy of retrieval. The retrieval unit can also customize the retrieval method by reflecting the user's past feedback. For example, the retrieval unit customizes the optimal retrieval method based on the past feedback. In this way, the optimal retrieval method can be provided by reflecting the user's past feedback. === Hard Collateral 1-1 === For example, each of the multiple elements including the analysis unit, summarization unit, schedule reflection unit, linking unit, and acquisition unit is realized by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of email. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the analyzed content. The schedule reflection unit is realized by the specific processing unit 290 of the data processing device 12 and reflects the summarized content in the schedule. The linking unit is realized by the control unit 46A of the smart device 14 and provides a function for the user to link email accounts. The acquisition unit is realized by the control unit 46A of the smart device 14 and automatically acquires unread emails. === Hard Collateral 1-2 === For example, each of the multiple elements including the analysis unit, summarization unit, schedule reflection unit, linking unit, and acquisition unit is realized by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of emails. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the analyzed content. The schedule reflection unit is realized by the specific processing unit 290 of the data processing device 12 and reflects the summarized content in the schedule. The linking unit is realized by the control unit 46A of the smart glasses 214 and provides a function for a user to link email accounts. The acquisition unit is realized by the control unit 46A of the smart glasses 214 and automatically acquires unread emails. === Hard Collateral 1-3 === For example, each of the multiple elements including the analysis unit, summarization unit, schedule reflection unit, linking unit, and acquisition unit is realized by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of email. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the analyzed content. The schedule reflection unit is realized by the specific processing unit 290 of the data processing device 12 and reflects the summarized content in the schedule. The linking unit is realized by the control unit 46A of the headset type terminal 314 and provides a function for the user to link email accounts. The acquisition unit is realized by the control unit 46A of the headset type terminal 314 and automatically acquires unread emails. === Hard Collateral 1-4 === For example, each of the multiple elements including the analysis unit, summarization unit, schedule reflection unit, linking unit, and acquisition unit is realized by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the content of email. The summarization unit is realized by the specific processing unit 290 of the data processing device 12 and summarizes the analyzed content. The schedule reflection unit is realized by the specific processing unit 290 of the data processing device 12 and reflects the summarized content in the schedule. The linking unit is realized by the control unit 46A of the robot 414 and provides a function for a user to link email accounts. The acquisition unit is realized by the control unit 46A of the robot 414 and automatically acquires unread emails.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] The analysis unit can estimate the user's emotions and adjust the analysis priority based on the estimated user emotions. For example, if the user is feeling stressed, it prioritizes analyzing emails of high importance. The analysis unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. Alternatively, if the user is relaxed, it can analyze all emails equally. The analysis unit records the user's voice and estimates their emotions using voice analysis technology. Furthermore, if the user is in a hurry, it can prioritize analyzing emails containing meetings or urgent notices. The analysis unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. This allows the analysis priority to be adjusted according to the user's emotions, reducing stress and enabling efficient email processing.

[0120] The analysis unit can evaluate the trustworthiness of the email sender and adjust the level of analysis detail based on the trustworthiness. For example, emails from highly trusted senders are analyzed in detail. The analysis unit evaluates trustworthiness based on the frequency of past exchanges and the sender's domain. Emails from senders with low trustworthiness can also be analyzed more simply. The analysis unit performs a more simplified analysis when the sender's domain is unknown or there has been little past exchange. Furthermore, for emails from senders with medium trustworthiness, the level of analysis detail can be adjusted according to their content. The analysis unit adjusts the level of analysis detail based on the sender's trustworthiness and the content of the email. In this way, important emails can be analyzed in detail by adjusting the level of analysis detail based on the trustworthiness of the email sender.

[0121] The analysis unit can apply different analysis algorithms based on the content of the email. For example, a schedule analysis algorithm can be applied to a meeting invitation email. The analysis unit extracts the date, time, and location of the meeting and reflects this in the schedule. A detailed analysis algorithm can also be applied to emails containing important notices. The analysis unit analyzes the content of the email in detail and extracts important information. Furthermore, a simplified analysis algorithm can also be applied to advertising emails. The analysis unit simply analyzes the content of advertising emails and extracts only important information. This allows the most appropriate analysis algorithm to be applied depending on the content of the email, improving the accuracy of the analysis.

[0122] The analysis unit classifies the contents of emails by category and can apply different analysis methods to each category. For example, a business analysis method is applied to business emails. The analysis unit analyzes the contents of business emails in detail and extracts important information. A private analysis method can also be applied to private emails. The analysis unit simply analyzes the contents of private emails and extracts only important information. Furthermore, an advertising analysis method can also be applied to advertising emails. The analysis unit simply analyzes the contents of advertising emails and extracts only important information. This allows the analysis accuracy to be improved by applying the most appropriate analysis method according to the email category.

[0123] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is feeling stressed, a concise display method is provided. The analysis unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also provide a detailed display method if the user is relaxed. The analysis unit records the user's voice and estimates their emotions using voice analysis technology. It can also provide a display method that focuses on the main points if the user is in a hurry. The analysis unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. By adjusting the display method of the analysis results according to the user's emotions, the user can check the analysis results without feeling stressed.

[0124] The analysis unit can perform analysis taking into account the geographical location information of the sender of the email. For example, if the sender is nearby, it performs analysis with a high level of urgency. The analysis unit identifies the geographical location information based on the sender's IP address or GPS data, and prioritizes analysis of emails with a high level of urgency. In addition, if the sender is far away, it can also perform normal analysis. The analysis unit applies normal analysis methods based on the sender's geographical location information. Furthermore, it can also select an appropriate analysis method based on the sender's geographical location information. The analysis unit selects the optimal analysis method based on the sender's geographical location information. In this way, it is possible to prioritize analysis of emails with a high level of urgency by taking into account the geographical location information of the sender.

[0125] The analysis unit can improve the accuracy of the analysis by referring to an external database related to the content of the email. For example, the analysis is performed by referring to an industry database related to the content of the email. The analysis unit obtains related information from the industry database and reflects it in the analysis. The analysis unit can also perform the analysis by referring to a news database related to the content of the email. The analysis unit obtains the latest information from the news database and reflects it in the analysis. Furthermore, the analysis can also perform the analysis by referring to an academic database related to the content of the email. The analysis unit obtains related research papers from the academic database and reflects them in the analysis. In this way, the accuracy of the analysis can be improved by referring to external databases.

[0126] The analysis unit can analyze the content of emails in conjunction with other communication channels. For example, the analysis unit analyzes the content of emails in conjunction with the content of chats. The analysis unit refers to the content of chat apps and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in conjunction with posts on social media. The analysis unit refers to posts on social media and analyzes it in association with the content of emails. The analysis unit can also analyze the content of emails in conjunction with other communication channels. The analysis unit refers to the content of chat apps and social media and analyzes it in association with the content of emails. This makes it possible to improve the accuracy of the analysis by linking with other communication channels.

[0127] The summarization unit can estimate the user's emotions and adjust the presentation style of the summary based on the estimated user emotions. For example, if the user is feeling stressed, a concise summary is provided. The summarization unit captures the user's facial expressions with a camera and estimates their emotions using an emotion estimation algorithm. It can also provide a detailed summary if the user is relaxed. The summarization unit records the user's voice and estimates their emotions using voice analysis technology. Furthermore, if the user is in a hurry, it can provide a summary that focuses on the main points. The summarization unit collects the user's biometric data (heart rate and electrodermal activity) with a sensor and estimates their emotions using an emotion estimation algorithm. This allows the summary presentation style to be adjusted according to the user's emotions, allowing the user to view the summary without feeling stressed.

[0128] When generating a summary, the summarization unit can adjust the level of detail in the summary based on the importance of the email. For example, a detailed summary is provided for emails with high importance. The summarization unit evaluates the importance based on the job title of the email sender and the content of the email, and creates a detailed summary. It can also provide a concise summary for emails with low importance. The summarization unit briefly summarizes the content of the email and provides only important information. Furthermore, for emails with medium importance, the level of detail in the summary can be adjusted according to the content. The summarization unit adjusts the level of detail in the summary based on the content of the email. In this way, by adjusting the level of detail in the summary based on the importance of the email, it is possible to provide a detailed summary of important emails.

[0129] The processing flow of the second embodiment will be briefly explained below.

[0130] Step 1: The analysis unit analyzes the content of the email. The analysis unit analyzes the content of the email using, for example, natural language processing technology. Specifically, it uses morphological analysis to analyze the grammatical structure of the email and keyword extraction technology to extract important words and phrases. It also uses semantic analysis technology to understand the content of the email, grasp the context, and extract important information. Step 2: The summarization unit summarizes the content analyzed by the analysis unit. For example, the summarization unit extracts key points to create a summary. Specifically, it extracts the important parts of the email and creates a concise summary. It is also possible to create summaries using generative AI, which generates summaries by entering prompts. Step 3: The schedule reflection unit reflects the content summarized by the summarization unit in the schedule. For example, the schedule reflection unit automatically adds important emails and emails related to the schedule to the schedule. Specifically, it automatically adds meeting invitation emails to the schedule and manages the schedule in cooperation with a calendar app. For example, it cooperates with Google Calendar or Outlook Calendar to automatically update the schedule.

[0131] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0132] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0133] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0134] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0142] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0143] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0144] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0145] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0147] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0148] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0149] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0150] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0153] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0154] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0155] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0157] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0158] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0159] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0160] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0162] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0163] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0164] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0165] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 7, a 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.

[0169] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0170] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0171] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0173] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0174] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0175] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0176] 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0177] The storage 32 stores a data generation model 58 and an 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0178] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0179] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0180] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0181] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0182] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0183] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0184] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0185] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0186] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0187] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0188] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0189] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0191] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0192] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0193] 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.

[0194] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0195] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0196] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0197] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0198] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0199] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0200] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0201] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0202] [Explanation of symbols]

[0203] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the content of the email; a summarizing unit that summarizes the content analyzed by the analyzing unit; a schedule reflecting unit that reflects the content summarized by the summarizing unit in a schedule; Equipped with A system characterized by:

2. Equipped with a linking section that links email accounts 2. The system of claim 1.

3. Equipped with an acquisition unit that acquires unread emails 2. The system of claim 1.

4. The analysis unit Analyzing email content using natural language processing technology 2. The system of claim 1.

5. The summary section Extract key points and create a summary 2. The system of claim 1.

6. The schedule reflecting unit Automatically add important or schedule-related emails to your schedule 2. The system of claim 1.

7. The analysis unit Estimate user emotions and adjust analysis priorities based on the estimated user emotions 2. The system of claim 1.

8. The analysis unit Evaluate the trustworthiness of email senders and adjust the depth of analysis based on that trustworthiness 2. The system of claim 1.

9. The analysis unit Apply different analysis algorithms based on the content of the email 2. The system of claim 1.

10. The analysis unit Categorize email content and apply different analysis techniques to each category 2. The system of claim 1.

Images