system

Abstract

The system according to the embodiment aims to prevent missed responses to emails and delayed responses, and to achieve efficient email management. [Solution] A system according to an embodiment includes an analysis unit, an identification unit, a resending unit, and an unread return unit. The analysis unit analyzes the content of emails. The identification unit identifies emails that require a response or a response based on the content analyzed by the analysis unit. The resending unit automatically resends emails identified by the identification unit. The unread return unit automatically returns emails identified by the identification unit to unread.

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 technologies have had the problem of making efficient email management difficult, as emails are often left unanswered or responses are delayed.

[0005] The system according to the embodiment aims to prevent missed responses to emails and delayed responses, and to achieve efficient email management. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an identification unit, a retransmission unit, and an unread return unit. The analysis unit analyzes the content of emails. The identification unit identifies emails that require a response or a response based on the content analyzed by the analysis unit. The retransmission unit automatically resends the emails identified by the identification unit. The unread return unit automatically returns the emails identified by the identification unit to unread. [Effects of the Invention]

[0007] The system according to the embodiment can prevent missed responses to emails and delayed responses, and can achieve efficient email management. [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 email management system according to an embodiment of the present invention reads email text or image information and uses AI to perform the following actions. In this email management system, AI first analyzes incoming and outgoing emails and automatically selects emails that require a response. Next, it automatically resends outgoing emails that have not yet received a response, and automatically resets incoming emails that have not yet received a response to unread status. This shortens the time that requests are left unattended. Since this cannot be achieved using scripts alone, it is achieved by combining AI. For example, AI analyzes the content of emails. AI analyzes the text and image information of emails to identify emails that require a reply or that have not yet received a response. For example, if AI analyzes the body of an email and determines that a reply is required, it identifies the email as requiring a response. Next, AI automatically takes action on the identified emails that require a response. For example, it automatically resends outgoing emails that have not yet received a response. This eliminates the need for users to manually resend emails. It also automatically resets incoming emails that have not yet received a response to unread status. This prevents users from overlooking unattended emails. This mechanism shortens the time that requests are left unattended. Users can prevent emails from being overlooked by having AI automatically resend or mark them as unread. Furthermore, because this cannot be achieved with scripts alone, combining it with AI allows for more advanced email management. This allows the email management system to shorten the period of time requested tasks are left unattended.

[0029] An email management system according to an embodiment includes an analysis unit, an identification unit, a resending unit, and an unread return unit. The analysis unit analyzes the content of emails. The analysis unit analyzes, for example, text information and image information of emails. The analysis unit analyzes the email body using, for example, natural language processing technology, and identifies emails that require a reply or emails that have not yet been addressed. The identification unit identifies emails that require a response or emails that have not yet been addressed based on the content analyzed by the analysis unit. The identification unit analyzes the content of emails using, for example, AI to identify emails that require a reply or emails that have not yet been addressed. The identification unit identifies emails that require a response, for example, based on keywords or phrases contained in the email body. The resending unit automatically resends outgoing emails that have not received a response, as identified by the identification unit. The resending unit automatically resends outgoing emails that have not received a reply within a certain period of time, as identified by the identification unit. The resending unit can also resend emails during a specific time period, as identified by the identification unit. The unread return unit automatically returns received emails that have not received a reply, as identified by the identification unit, to unread status. The unread return unit automatically returns received emails that have not been responded to within a certain period of time to the unread status. The unread return unit can also return emails to the unread status within a specific time period. This allows the email management system according to the embodiment to shorten the period for which requested tasks are left unattended.

[0030] The analysis unit can analyze the text information or image information of the email. The analysis unit analyzes, for example, the text information of the email. For example, the analysis unit can analyze the email body, subject, text of attached files, etc. The analysis unit can also analyze the image information of the email. For example, the analysis unit can analyze attached images, embedded images, etc. This enables more accurate analysis by analyzing the text information and image information of the email. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text information of the email to the generation AI and have the generation AI analyze the text information.

[0031] The identification unit can identify emails that require a reply or emails that have not been addressed based on the content analyzed by the analysis unit. The identification unit, for example, identifies emails that require a reply. For example, the identification unit can identify emails that require a reply based on questions or requests contained in the email body. The identification unit can also identify emails that have not been addressed. For example, the identification unit can identify emails that have not been replied to within a certain period of time as emails that have not been addressed. By identifying emails that require a reply or emails that have not been addressed, it is possible to clarify emails that the user should address. Some or all of the above-mentioned processing by the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the content of emails analyzed by the analysis unit into a generation AI and cause the generation AI to identify emails that require a reply or emails that have not been addressed.

[0032] The resending unit can automatically resend a sent email for which a reply identified by the identification unit has not been received. The resending unit, for example, automatically resends a sent email for which no reply has been received within a certain period of time. For example, the resending unit can resend an email if no reply has been received within one week of sending. The resending unit can also resend an email during a specific time period. For example, the resending unit can resend an email during business hours. This can reduce the user's effort by automatically resending a sent email for which a reply has not been received. Some or all of the above-mentioned processing in the resending unit may be performed using, for example, AI, or may be performed without using AI. For example, the resending unit can input the sent email identified by the identification unit into a generation AI and have the generation AI execute the resending.

[0033] The unread return unit can automatically return to unread received emails identified by the identification unit that have not been responded to. The unread return unit, for example, automatically returns to unread received emails that have not been responded to within a certain period of time. For example, the unread return unit can return to unread emails that have not been responded to within one week of receipt. The unread return unit can also return to unread during a specific time period. For example, the unread return unit can return to unread emails during business hours. This prevents users from overlooking unresponded emails by automatically returning to unread received emails that have not been responded to. Some or all of the above-mentioned processing in the unread return unit may be performed, for example, using AI, or may be performed without using AI. For example, the unread return unit can input received emails identified by the identification unit into a generation AI and have the generation AI execute the process of returning the emails to unread.

[0034] The analysis unit can improve the accuracy of analysis by referring to past email history. For example, the analysis unit learns the patterns of emails that were previously determined to require a reply and prioritizes analysis of emails with similar patterns. For example, the analysis unit can extract specific keywords or phrases from past email history and perform analysis based on them. The analysis unit can also determine the priority of analysis results by referring to the reply time and frequency of past emails. This improves the accuracy of analysis by referring to past email history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past email history data into the generation AI and have the generation AI improve the analysis accuracy.

[0035] The analysis unit can perform analysis while taking into account attribute information of the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the analysis unit prioritizes the AI's analysis of that email. For example, the analysis unit can perform analysis while taking into account attribute information such as the sender's and recipient's job titles, departments, and past communication history. Furthermore, if there are multiple recipients, the analysis unit can perform analysis while taking into account the job titles and relationships of each recipient. For example, the analysis unit can improve the reliability of the analysis results by referring to past email communications between the sender and recipient. This improves the reliability of the analysis results by taking into account the attribute information of the sender and recipient. Some or all of the above-described processing in the analysis unit can be performed using, or without, AI. For example, the analysis unit can input attribute information of the sender and recipient into the generation AI and have the generation AI perform the analysis.

[0036] The analysis unit can perform analysis taking into account the sending time and receiving time of the email. For example, if the sending time is during business hours, the analysis unit prioritizes the AI's analysis of the email. For example, the analysis unit can determine the urgency of the email based on the sending time and receiving time and reflect this in the analysis results. Furthermore, if the receiving time is late at night, the analysis unit can postpone the AI's analysis of the email. This improves the accuracy of the analysis results by taking the sending time and receiving time into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the sending time and receiving time data of the email into the generation AI and have the generation AI perform the analysis.

[0037] The analysis unit can analyze the contents of email attachments and extract relevant information. For example, if the attachment is a PDF, the analysis unit uses AI to analyze the contents and extract relevant information. For example, if the attachment is an image, the analysis unit can analyze the contents using image recognition technology. Furthermore, if the attachment is a spreadsheet, the analysis unit can analyze the data and extract important information. This makes it easier to extract relevant information by analyzing the contents of the attachment. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the data of the attachment into a generation AI and have the generation AI extract relevant information.

[0038] The identification unit can improve the identification accuracy by referring to past response history. For example, the identification unit learns patterns of emails that have been determined to require a response in the past and identifies emails with similar patterns. For example, the identification unit can extract specific keywords or phrases from the past response history and identify emails that require a response based on those keywords or phrases. The identification unit can also adjust an algorithm for improving the identification accuracy by referring to the past response history. In this way, the identification accuracy is improved by referring to the past response history. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past response history data into a generation AI and cause the generation AI to improve the identification accuracy.

[0039] The identification unit can identify emails that require a response while taking into account the importance of the email content. The identification unit identifies emails that require a response, for example, based on important keywords contained in the email subject or body. For example, if the email content is related to an important project, the identification unit can cause the AI ​​to identify the email as one that requires a response. Furthermore, if the email content is urgent, the identification unit can cause the AI ​​to identify the email as one that requires a response. This makes it easier to identify more important emails by taking the importance of the email content into account. Some or all of the above-described processing in the identification unit may be performed using AI, for example, or may be performed without using AI. For example, the identification unit can input email content data to the generation AI and cause the generation AI to perform identification based on importance.

[0040] The identification unit can identify emails by taking into account the relationship between the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the AI ​​can identify the email as requiring action. For example, the identification unit can identify emails by taking into account relationships such as the sender's and recipient's job titles, departments, and frequency of past interactions. Furthermore, if there are multiple recipients, the identification unit can identify emails requiring action by taking into account the job titles and relationships of each recipient. For example, the identification unit can identify emails requiring action by referring to past email interactions between the sender and recipient. This improves the accuracy of identification by taking into account the relationship between the sender and recipient. Some or all of the above-described processing in the identification unit can be performed using, for example, AI, or without AI. For example, the identification unit can input data on the relationship between the sender and recipient into the generation AI and have the generation AI perform the identification.

[0041] The identification unit can improve the identification accuracy by referring to literature and materials related to the email. For example, the identification unit automatically searches for literature and materials related to the email using an AI and identifies emails requiring action based on their content. For example, if the content of the email is related to a specific project, the identification unit can have the AI ​​refer to materials related to the project to identify emails requiring action. Furthermore, if the content of the email is related to a specific topic, the identification unit can have the AI ​​refer to literature related to the topic to identify emails requiring action. By referring to related literature and materials, the identification accuracy is improved. Some or all of the above-mentioned processing in the identification unit may be performed using, or without, an AI. For example, the identification unit can input related literature and material data into the generation AI and cause the generation AI to improve the identification accuracy.

[0042] The retransmission unit can optimize the retransmission method by referring to past retransmission history. The retransmission unit, for example, learns the timing when retransmission was successful in the past and performs retransmission at that timing. For example, the retransmission unit can preferentially use a specific transmission method (email, messaging app, etc.) based on the past retransmission history. The retransmission unit can also optimize the frequency and timing of retransmission by referring to the past retransmission history. In this way, the retransmission method is optimized by referring to the past retransmission history. Some or all of the above-mentioned processing in the retransmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the retransmission unit can input past retransmission history data to a generation AI and cause the generation AI to optimize the retransmission method.

[0043] The resending unit can adjust the frequency of resending depending on the content of the email. For example, if the content of the email is important, the AI ​​increases the frequency of resending. For example, if the content of the email is urgent, the resending unit can further increase the frequency of resending. Furthermore, if the content of the email is general, the resending unit can decrease the frequency of resending. This allows for more appropriate resending by adjusting the frequency of resending depending on the content of the email. Some or all of the above-mentioned processing in the resending unit may be performed using, for example, AI, or may be performed without using AI. For example, the resending unit can input email content data to the generation AI and have the generation AI adjust the resending frequency.

[0044] The resending unit can resend an email while taking into account attribute information of the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the resending unit causes the AI ​​to resend the email as a priority. For example, the resending unit can resend an email while taking into account attribute information such as the sender's and recipient's job title, department, and past communication history. Furthermore, if there are multiple recipients, the resending unit can resend an email while taking into account the job title and relationship of each recipient. For example, the resending unit can determine the resending priority by referring to past email communications between the sender and recipient. This improves the accuracy of resending by taking into account the attribute information of the sender and recipient. Some or all of the above-described processing in the resending unit may be performed using, or without, AI. For example, the resending unit can input attribute information of the sender and recipient into the generation AI and cause the generation AI to execute resending.

[0045] The resending unit can improve the accuracy of resending by referring to literature and materials related to the email. For example, the resending unit automatically searches for literature and materials related to the email using an AI and resends the email based on the content. For example, if the content of the email is related to a specific project, the resending unit can resend the email using the AI ​​by referring to materials related to the project. Furthermore, if the content of the email is related to a specific topic, the resending unit can resend the email using the AI ​​by referring to literature related to the topic. This improves the accuracy of resending by referring to related literature and materials. Some or all of the above-mentioned processing in the resending unit may be performed using, or without, an AI. For example, the resending unit can input related literature and material data into the generation AI and cause the generation AI to improve the accuracy of resending.

[0046] The unread return unit can optimize the unread return method by referring to past unread return history. The unread return unit, for example, learns the timing when unread return was successful in the past and performs unread return at that timing. For example, the unread return unit can preferentially use a specific method (email re-notification, pop-up notification, etc.) based on the past unread return history. The unread return unit can also optimize the frequency and timing of unread return by referring to the past unread return history. In this way, the unread return method is optimized by referring to the past unread return history. Some or all of the above-mentioned processing in the unread return unit may be performed using, for example, AI, or may be performed without using AI. For example, the unread return unit can input past unread return history data to the generation AI and cause the generation AI to optimize the unread return method.

[0047] The unread return unit can adjust the frequency of unread return depending on the content of the email. For example, if the content of the email is important, the AI ​​in the unread return unit increases the frequency of unread return. For example, if the content of the email is urgent, the unread return unit can further increase the frequency of unread return. Furthermore, if the content of the email is general, the unread return unit can decrease the frequency of unread return. This allows for more appropriate unread return by adjusting the frequency of unread return depending on the content of the email. Some or all of the above-mentioned processing in the unread return unit may be performed using AI, for example, or may be performed without using AI. For example, the unread return unit can input email content data to the generation AI and have the generation AI adjust the frequency of unread return.

[0048] The unread return unit can return emails to unread status by taking into account attribute information of the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the AI ​​prioritizes returning the email to unread status. For example, the unread return unit can return emails to unread status by taking into account attribute information such as the sender's and recipient's job titles, departments, and past communication history. Furthermore, if there are multiple recipients, the unread return unit can return emails to unread status by taking into account the job titles and relationships of each recipient. For example, the unread return unit can determine the priority of returning emails to unread status by referring to past email communications between the sender and recipient. This improves the accuracy of returning emails to unread status by taking into account attribute information of the sender and recipient. Some or all of the above-described processing in the unread return unit can be performed using, or without, AI. For example, the unread return unit can input attribute information of the sender and recipient into the generation AI and have the generation AI execute the returning email to unread status.

[0049] The unread return unit can improve the accuracy of unread return by referring to literature and materials related to the email. For example, the unread return unit automatically searches for literature and materials related to the email using an AI and returns the email to unread based on the content. For example, if the content of the email is related to a specific project, the unread return unit can return the email to unread by referring to materials for that project. Also, if the content of the email is related to a specific topic, the unread return unit can return the email to unread by referring to literature related to that topic. This improves the accuracy of unread return by referring to related literature and materials. Some or all of the above-mentioned processing in the unread return unit may be performed using, or without, an AI. For example, the unread return unit can input related literature and material data into the generation AI and cause the generation AI to improve the accuracy of unread return.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] When analyzing the content of an email, the analysis unit can take into account the past behavioral patterns of the email sender and recipient. For example, if emails from a specific sender have been processed with high priority in the past, the analysis unit can also analyze new emails from the same sender with high priority. Also, if a recipient has responded sensitively to a specific keyword in the past, the analysis unit can prioritize analyzing emails containing that keyword. Furthermore, the analysis unit can evaluate the relationship with a specific sender or recipient based on the frequency and content of past email exchanges and determine the priority of analysis. By taking past behavioral patterns into account, the accuracy and efficiency of analysis are improved.

[0052] The retransmission unit can adjust the timing of retransmission based on the user's schedule when automatically retransmitting a sent email for which a response identified by the identification unit has not been received. For example, the retransmission unit can refer to the user's calendar information and perform retransmission during a time when the user is not in a meeting or on vacation. The retransmission unit can also be set to not perform retransmission outside the user's working hours. Furthermore, the retransmission unit can optimize the frequency and timing of retransmission based on the user's schedule. This maximizes the effectiveness of retransmission by taking the user's schedule into consideration.

[0053] The unread return unit can take into consideration the category of the email content when automatically returning to unread the unanswered received email identified by the identification unit. For example, if the content of an email is project-related, the unread return unit can prioritize returning the email to unread. Also, if the content of an email is personal, the unread return unit can reduce the frequency of returning the email to unread. Furthermore, if the content of an email is urgent, the unread return unit can quickly return the email to unread. Thus, by taking into consideration the category of the email content, the accuracy and efficiency of returning email to unread are improved.

[0054] The identification unit can take into account attribute information of the sender and recipient of an email when identifying emails that require a reply or emails that have not yet been addressed based on the content analyzed by the analysis unit. For example, if the sender is a superior or an important business partner, the identification unit will prioritize identifying the email using AI. For example, the identification unit can take into account attribute information such as the sender's and recipient's job title, department, and past communication history when identifying emails. Furthermore, if there are multiple recipients, the identification unit can take into account the AI's job title and relationship with each recipient when identifying emails. For example, the identification unit can improve the accuracy of identification by referring to past email communications between the sender and recipient. This improves the accuracy of identification by taking into account attribute information of the sender and recipient.

[0055] The unread return unit can take into account the relationship between the sender and recipient of an email when automatically returning unread an unanswered received email identified by the identification unit. For example, if the sender is a superior or an important business partner, the unread return unit will prioritize returning the email to unread with AI. For example, the unread return unit can return emails to unread by taking into account relationships such as the sender's and recipient's job titles, departments, and frequency of past interactions. Furthermore, if there are multiple recipients, the unread return unit can return emails to unread with AI taking into account each recipient's job title and relationship. For example, the unread return unit can determine the priority of returning emails to unread by referring to past email interactions between the sender and recipient. This improves the accuracy of returning emails to unread by taking into account the relationship between the sender and recipient.

[0056] The identification unit can take into account the importance of the email content when identifying emails that require a reply or emails that have not yet been addressed, based on the content analyzed by the analysis unit. For example, the identification unit identifies emails that require a response based on important keywords contained in the email subject or body. For example, if the email content is related to an important project, the identification unit can use AI to identify the email as one that requires a response. Furthermore, if the email content is urgent, the identification unit can use AI to identify the email as one that requires a response. In this way, by taking the importance of the email content into account, it becomes easier to identify more important emails.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The analysis unit analyzes the content of the email. For example, the analysis unit analyzes the text information and image information of the email and analyzes the email body using natural language processing technology. Step 2: The identification unit identifies emails that require a response or a response based on the content analyzed by the analysis unit. The identification unit analyzes the content of the email using AI, for example, and identifies emails that require a response based on keywords and phrases contained in the email body. Step 3: The resending unit automatically resends the outgoing email for which a reply has not been received, as identified by the identifying unit. The resending unit can, for example, automatically resend the outgoing email for which no reply has been received within a certain period of time, and can also resend the email during a specific time period. Step 4: The unread return unit automatically returns the received email identified by the identification unit to unread if no response has been made. For example, the unread return unit can automatically return received emails that have not been responded to within a certain period of time to unread, or can return them to unread within a specific time period.

[0059] (Example 2) An email management system according to an embodiment of the present invention reads email text or image information and uses AI to perform the following actions. In this email management system, AI first analyzes incoming and outgoing emails and automatically selects emails that require a response. Next, it automatically resends outgoing emails that have not yet received a response, and automatically resets incoming emails that have not yet received a response to unread status. This shortens the time that requests are left unattended. Since this cannot be achieved using scripts alone, it is achieved by combining AI. For example, AI analyzes the content of emails. AI analyzes the text and image information of emails to identify emails that require a reply or that have not yet received a response. For example, if AI analyzes the body of an email and determines that a reply is required, it identifies the email as requiring a response. Next, AI automatically takes action on the identified emails that require a response. For example, it automatically resends outgoing emails that have not yet received a response. This eliminates the need for users to manually resend emails. It also automatically resets incoming emails that have not yet received a response to unread status. This prevents users from overlooking unattended emails. This mechanism shortens the time that requests are left unattended. Users can prevent emails from being overlooked by having AI automatically resend or mark them as unread. Furthermore, because this cannot be achieved with scripts alone, combining it with AI allows for more advanced email management. This allows the email management system to shorten the period of time requested tasks are left unattended.

[0060] An email management system according to an embodiment includes an analysis unit, an identification unit, a resending unit, and an unread return unit. The analysis unit analyzes the content of emails. The analysis unit analyzes, for example, text information and image information of emails. The analysis unit analyzes the email body using, for example, natural language processing technology, and identifies emails that require a reply or emails that have not yet been addressed. The identification unit identifies emails that require a response or emails that have not yet been addressed based on the content analyzed by the analysis unit. The identification unit analyzes the content of emails using, for example, AI to identify emails that require a reply or emails that have not yet been addressed. The identification unit identifies emails that require a response, for example, based on keywords or phrases contained in the email body. The resending unit automatically resends outgoing emails that have not received a response, as identified by the identification unit. The resending unit automatically resends outgoing emails that have not received a reply within a certain period of time, as identified by the identification unit. The resending unit can also resend emails during a specific time period, as identified by the identification unit. The unread return unit automatically returns received emails that have not received a reply, as identified by the identification unit, to unread status. The unread return unit automatically returns received emails that have not been responded to within a certain period of time to the unread status. The unread return unit can also return emails to the unread status within a specific time period. This allows the email management system according to the embodiment to shorten the period for which requested tasks are left unattended.

[0061] The analysis unit can analyze the text information or image information of the email. The analysis unit analyzes, for example, the text information of the email. For example, the analysis unit can analyze the email body, subject, text of attached files, etc. The analysis unit can also analyze the image information of the email. For example, the analysis unit can analyze attached images, embedded images, etc. This enables more accurate analysis by analyzing the text information and image information of the email. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the text information of the email to the generation AI and have the generation AI analyze the text information.

[0062] The identification unit can identify emails that require a reply or emails that have not been addressed based on the content analyzed by the analysis unit. The identification unit, for example, identifies emails that require a reply. For example, the identification unit can identify emails that require a reply based on questions or requests contained in the email body. The identification unit can also identify emails that have not been addressed. For example, the identification unit can identify emails that have not been replied to within a certain period of time as emails that have not been addressed. By identifying emails that require a reply or emails that have not been addressed, it is possible to clarify emails that the user should address. Some or all of the above-mentioned processing by the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input the content of emails analyzed by the analysis unit into a generation AI and cause the generation AI to identify emails that require a reply or emails that have not been addressed.

[0063] The resending unit can automatically resend a sent email for which a reply identified by the identification unit has not been received. The resending unit, for example, automatically resends a sent email for which no reply has been received within a certain period of time. For example, the resending unit can resend an email if no reply has been received within one week of sending. The resending unit can also resend an email during a specific time period. For example, the resending unit can resend an email during business hours. This can reduce the user's effort by automatically resending a sent email for which a reply has not been received. Some or all of the above-mentioned processing in the resending unit may be performed using, for example, AI, or may be performed without using AI. For example, the resending unit can input the sent email identified by the identification unit into a generation AI and have the generation AI execute the resending.

[0064] The unread return unit can automatically return to unread received emails identified by the identification unit that have not been responded to. The unread return unit, for example, automatically returns to unread received emails that have not been responded to within a certain period of time. For example, the unread return unit can return to unread emails that have not been responded to within one week of receipt. The unread return unit can also return to unread during a specific time period. For example, the unread return unit can return to unread emails during business hours. This prevents users from overlooking unresponded emails by automatically returning to unread received emails that have not been responded to. Some or all of the above-mentioned processing in the unread return unit may be performed, for example, using AI, or may be performed without using AI. For example, the unread return unit can input received emails identified by the identification unit into a generation AI and have the generation AI execute the process of returning the emails to unread.

[0065] The analysis unit can estimate the user's emotions and adjust the email analysis method based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit uses AI to prioritize email importance and display only important emails. For example, the analysis unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, if the user is relaxed, the analysis unit can use AI to perform a detailed analysis and analyze the contents of all emails. For example, the analysis unit can adjust the email analysis method based on the user's emotions. This enables more appropriate analysis by adjusting the analysis method according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into the generation AI and cause the generation AI to adjust the analysis method based on the emotion.

[0066] The analysis unit can improve the accuracy of analysis by referring to past email history. For example, the analysis unit learns the patterns of emails that were previously determined to require a reply and prioritizes analysis of emails with similar patterns. For example, the analysis unit can extract specific keywords or phrases from past email history and perform analysis based on them. The analysis unit can also determine the priority of analysis results by referring to the reply time and frequency of past emails. This improves the accuracy of analysis by referring to past email history. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input past email history data into the generation AI and have the generation AI improve the analysis accuracy.

[0067] The analysis unit can perform analysis while taking into account attribute information of the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the analysis unit prioritizes the AI's analysis of that email. For example, the analysis unit can perform analysis while taking into account attribute information such as the sender's and recipient's job titles, departments, and past communication history. Furthermore, if there are multiple recipients, the analysis unit can perform analysis while taking into account the job titles and relationships of each recipient. For example, the analysis unit can improve the reliability of the analysis results by referring to past email communications between the sender and recipient. This improves the reliability of the analysis results by taking into account the attribute information of the sender and recipient. Some or all of the above-described processing in the analysis unit can be performed using, or without, AI. For example, the analysis unit can input attribute information of the sender and recipient into the generation AI and have the generation AI perform the analysis.

[0068] 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 nervous, the analysis unit can provide a simple, highly visible display method. For example, the analysis unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. For example, the analysis unit can adjust the display method of the analysis results based on the user's emotions. This enables more appropriate display by adjusting the display method according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's emotion data into a generation AI and cause the generation AI to adjust the display method based on the emotion.

[0069] The analysis unit can perform analysis taking into account the sending time and receiving time of the email. For example, if the sending time is during business hours, the analysis unit prioritizes the AI's analysis of the email. For example, the analysis unit can determine the urgency of the email based on the sending time and receiving time and reflect this in the analysis results. Furthermore, if the receiving time is late at night, the analysis unit can postpone the AI's analysis of the email. This improves the accuracy of the analysis results by taking the sending time and receiving time into consideration. Some or all of the above-mentioned processing in the analysis unit may be performed using, or without, AI. For example, the analysis unit can input the sending time and receiving time data of the email into the generation AI and have the generation AI perform the analysis.

[0070] The analysis unit can analyze the contents of email attachments and extract relevant information. For example, if the attachment is a PDF, the analysis unit uses AI to analyze the contents and extract relevant information. For example, if the attachment is an image, the analysis unit can analyze the contents using image recognition technology. Furthermore, if the attachment is a spreadsheet, the analysis unit can analyze the data and extract important information. This makes it easier to extract relevant information by analyzing the contents of the attachment. Some or all of the above-described processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the data of the attachment into a generation AI and have the generation AI extract relevant information.

[0071] The identification unit can estimate the user's emotions and adjust the criteria for identifying emails that require action based on the estimated user emotions. For example, when the user is feeling stressed, the identification unit uses AI to identify only emails with high importance as emails that require action. For example, the identification unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, when the user is relaxed, the identification unit can identify emails that require action using detailed criteria. For example, the identification unit can adjust the criteria for identifying emails that require action based on the user's emotions. This allows for more appropriate identification of emails that require action. Some or all of the above-described processing in the identification unit may be performed using AI, for example, or may be performed without using AI. For example, the identification unit can input user emotion data into the generation AI and cause the generation AI to adjust the criteria for identifying based on the emotion.

[0072] The identification unit can improve the identification accuracy by referring to past response history. For example, the identification unit learns patterns of emails that have been determined to require a response in the past and identifies emails with similar patterns. For example, the identification unit can extract specific keywords or phrases from the past response history and identify emails that require a response based on those keywords or phrases. The identification unit can also adjust an algorithm for improving the identification accuracy by referring to the past response history. In this way, the identification accuracy is improved by referring to the past response history. Some or all of the above-mentioned processing in the identification unit may be performed using, for example, AI, or may be performed without using AI. For example, the identification unit can input past response history data into a generation AI and cause the generation AI to improve the identification accuracy.

[0073] The identification unit can identify emails that require a response while taking into account the importance of the email content. The identification unit identifies emails that require a response, for example, based on important keywords contained in the email subject or body. For example, if the email content is related to an important project, the identification unit can cause the AI ​​to identify the email as one that requires a response. Furthermore, if the email content is urgent, the identification unit can cause the AI ​​to identify the email as one that requires a response. This makes it easier to identify more important emails by taking the importance of the email content into account. Some or all of the above-described processing in the identification unit may be performed using AI, for example, or may be performed without using AI. For example, the identification unit can input email content data to the generation AI and cause the generation AI to perform identification based on importance.

[0074] The identification unit can estimate the user's emotions and prioritize the identified emails based on the estimated user emotions. For example, when the user is feeling stressed, the identification unit uses AI to prioritize emails that are highly important. For example, the identification unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, when the user is relaxed, the identification unit can prioritize emails using detailed criteria. For example, the identification unit can prioritize the identified emails based on the user's emotions. This enables more appropriate email management by determining the priority according to the user's emotions. Some or all of the above-described processing in the identification unit may be performed using AI, for example, or without AI. For example, the identification unit can input user emotion data into the generation AI and cause the generation AI to determine the priority based on emotions.

[0075] The identification unit can identify emails by taking into account the relationship between the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the AI ​​can identify the email as requiring action. For example, the identification unit can identify emails by taking into account relationships such as the sender's and recipient's job titles, departments, and frequency of past interactions. Furthermore, if there are multiple recipients, the identification unit can identify emails requiring action by taking into account the job titles and relationships of each recipient. For example, the identification unit can identify emails requiring action by referring to past email interactions between the sender and recipient. This improves the accuracy of identification by taking into account the relationship between the sender and recipient. Some or all of the above-described processing in the identification unit can be performed using, for example, AI, or without AI. For example, the identification unit can input data on the relationship between the sender and recipient into the generation AI and have the generation AI perform the identification.

[0076] The identification unit can improve the identification accuracy by referring to literature and materials related to the email. For example, the identification unit automatically searches for literature and materials related to the email using an AI and identifies emails requiring action based on their content. For example, if the content of the email is related to a specific project, the identification unit can have the AI ​​refer to materials related to the project to identify emails requiring action. Furthermore, if the content of the email is related to a specific topic, the identification unit can have the AI ​​refer to literature related to the topic to identify emails requiring action. By referring to related literature and materials, the identification accuracy is improved. Some or all of the above-mentioned processing in the identification unit may be performed using, or without, an AI. For example, the identification unit can input related literature and material data into the generation AI and cause the generation AI to improve the identification accuracy.

[0077] The retransmission unit can estimate the user's emotions and adjust the timing of retransmission based on the estimated user's emotions. For example, if the user is feeling stressed, the AI ​​in the retransmission unit delays the timing of retransmission. For example, the retransmission unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, the retransmission unit can advance the timing of retransmission if the user is relaxed. For example, the retransmission unit can adjust the timing of retransmission based on the user's emotions. This enables more appropriate retransmission by adjusting the timing of retransmission according to the user's emotions. Some or all of the above-described processing in the retransmission unit may be performed using, or without, AI. For example, the retransmission unit can input user emotion data into the generation AI and cause the generation AI to adjust the timing of retransmission based on the emotion.

[0078] The retransmission unit can optimize the retransmission method by referring to past retransmission history. The retransmission unit, for example, learns the timing when retransmission was successful in the past and performs retransmission at that timing. For example, the retransmission unit can preferentially use a specific transmission method (email, messaging app, etc.) based on the past retransmission history. The retransmission unit can also optimize the frequency and timing of retransmission by referring to the past retransmission history. In this way, the retransmission method is optimized by referring to the past retransmission history. Some or all of the above-mentioned processing in the retransmission unit may be performed using, for example, AI, or may be performed without using AI. For example, the retransmission unit can input past retransmission history data to a generation AI and cause the generation AI to optimize the retransmission method.

[0079] The resending unit can adjust the frequency of resending depending on the content of the email. For example, if the content of the email is important, the AI ​​increases the frequency of resending. For example, if the content of the email is urgent, the resending unit can further increase the frequency of resending. Furthermore, if the content of the email is general, the resending unit can decrease the frequency of resending. This allows for more appropriate resending by adjusting the frequency of resending depending on the content of the email. Some or all of the above-mentioned processing in the resending unit may be performed using, for example, AI, or may be performed without using AI. For example, the resending unit can input email content data to the generation AI and have the generation AI adjust the resending frequency.

[0080] The resending unit can estimate the user's emotions and determine the priority of emails to be resent based on the estimated user emotions. For example, when the user is feeling stressed, the resending unit uses AI to prioritize resending of emails with high importance. For example, the resending unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, when the user is relaxed, the resending unit can determine the priority of emails to be resent using detailed criteria. For example, the resending unit can determine the priority of emails to be resent based on the user's emotions. This enables more appropriate resending by determining the priority of emails to be resent based on the user's emotions. Some or all of the above-described processing in the resending unit may be performed using AI, for example, or without AI. For example, the resending unit can input user emotion data into the generation AI and cause the generation AI to determine the resending priority based on the emotion.

[0081] The resending unit can resend an email while taking into account attribute information of the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the resending unit causes the AI ​​to resend the email as a priority. For example, the resending unit can resend an email while taking into account attribute information such as the sender's and recipient's job title, department, and past communication history. Furthermore, if there are multiple recipients, the resending unit can resend an email while taking into account the job title and relationship of each recipient. For example, the resending unit can determine the resending priority by referring to past email communications between the sender and recipient. This improves the accuracy of resending by taking into account the attribute information of the sender and recipient. Some or all of the above-described processing in the resending unit may be performed using, or without, AI. For example, the resending unit can input attribute information of the sender and recipient into the generation AI and cause the generation AI to execute resending.

[0082] The resending unit can improve the accuracy of resending by referring to literature and materials related to the email. For example, the resending unit automatically searches for literature and materials related to the email using an AI and resends the email based on the content. For example, if the content of the email is related to a specific project, the resending unit can resend the email using the AI ​​by referring to materials related to the project. Furthermore, if the content of the email is related to a specific topic, the resending unit can resend the email using the AI ​​by referring to literature related to the topic. This improves the accuracy of resending by referring to related literature and materials. Some or all of the above-mentioned processing in the resending unit may be performed using, or without, an AI. For example, the resending unit can input related literature and material data into the generation AI and cause the generation AI to improve the accuracy of resending.

[0083] The unread return unit can estimate the user's emotions and adjust the timing of unread return based on the estimated user's emotions. For example, if the user is feeling stressed, the unread return unit delays the timing of unread return. For example, the unread return unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, if the user is relaxed, the unread return unit can advance the timing of unread return. For example, the unread return unit can adjust the timing of unread return based on the user's emotions. This enables more appropriate unread return by adjusting the timing of unread return according to the user's emotions. Some or all of the above-described processing in the unread return unit may be performed using, or without, AI. For example, the unread return unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the timing of unread return based on the emotion.

[0084] The unread return unit can optimize the unread return method by referring to past unread return history. The unread return unit, for example, learns the timing when unread return was successful in the past and performs unread return at that timing. For example, the unread return unit can preferentially use a specific method (email re-notification, pop-up notification, etc.) based on the past unread return history. The unread return unit can also optimize the frequency and timing of unread return by referring to the past unread return history. In this way, the unread return method is optimized by referring to the past unread return history. Some or all of the above-mentioned processing in the unread return unit may be performed using, for example, AI, or may be performed without using AI. For example, the unread return unit can input past unread return history data to the generation AI and cause the generation AI to optimize the unread return method.

[0085] The unread return unit can adjust the frequency of unread return depending on the content of the email. For example, if the content of the email is important, the AI ​​in the unread return unit increases the frequency of unread return. For example, if the content of the email is urgent, the unread return unit can further increase the frequency of unread return. Furthermore, if the content of the email is general, the unread return unit can decrease the frequency of unread return. This allows for more appropriate unread return by adjusting the frequency of unread return depending on the content of the email. Some or all of the above-mentioned processing in the unread return unit may be performed using AI, for example, or may be performed without using AI. For example, the unread return unit can input email content data to the generation AI and have the generation AI adjust the frequency of unread return.

[0086] The unread return unit can estimate the user's emotions and prioritize the unread emails to be returned based on the estimated user emotions. For example, when the user is feeling stressed, the unread return unit uses AI to prioritize emails of high importance. For example, the unread return unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, when the user is relaxed, the unread return unit can prioritize the unread emails to be returned using detailed criteria. For example, the unread return unit can prioritize the unread emails to be returned based on the user's emotions. This enables more appropriate unread return by prioritizing the unread emails to be returned based on the user's emotions. Some or all of the above-described processing in the unread return unit may be performed using AI, for example, or without AI. For example, the unread return unit can input the user's emotion data into the generation AI and cause the generation AI to determine the unread return priority based on the emotion.

[0087] The unread return unit can return emails to unread status by taking into account attribute information of the sender and recipient of the email. For example, if the sender is a superior or an important business partner, the AI ​​prioritizes returning the email to unread status. For example, the unread return unit can return emails to unread status by taking into account attribute information such as the sender's and recipient's job titles, departments, and past communication history. Furthermore, if there are multiple recipients, the unread return unit can return emails to unread status by taking into account the job titles and relationships of each recipient. For example, the unread return unit can determine the priority of returning emails to unread status by referring to past email communications between the sender and recipient. This improves the accuracy of returning emails to unread status by taking into account attribute information of the sender and recipient. Some or all of the above-described processing in the unread return unit can be performed using, or without, AI. For example, the unread return unit can input attribute information of the sender and recipient into the generation AI and have the generation AI execute the returning email to unread status.

[0088] The unread return unit can improve the accuracy of unread return by referring to literature and materials related to the email. For example, the unread return unit automatically searches for literature and materials related to the email using an AI and returns the email to unread based on the content. For example, if the content of the email is related to a specific project, the unread return unit can return the email to unread by referring to materials for that project. Also, if the content of the email is related to a specific topic, the unread return unit can return the email to unread by referring to literature related to that topic. This improves the accuracy of unread return by referring to related literature and materials. Some or all of the above-mentioned processing in the unread return unit may be performed using, or without, an AI. For example, the unread return unit can input related literature and material data into the generation AI and cause the generation AI to improve the accuracy of unread return. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, identification unit, retransmission unit, and unread return unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart device 14 and analyzes text information and image information of emails. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies emails requiring a response or response based on the analyzed content. The retransmission unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and automatically resends sent emails for which no response has been received. The unread return unit is realized, for example, by the control unit 46A of the smart device 14 and automatically returns received emails for which no response has been received to unread status. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, identification unit, retransmission unit, and unread return unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the smart glasses 214 and analyzes text information and image information of emails. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies emails requiring a response or a response based on the analyzed content. The retransmission unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and automatically resends sent emails for which no response has been received. The unread return unit is realized, for example, by the control unit 46A of the smart glasses 214 and automatically returns received emails for which no response has been received to unread status. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, identification unit, retransmission unit, and unread return unit is realized, for example, 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 processor 46 of the headset type terminal 314 and analyzes text information and image information of emails. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies emails requiring a response or a response based on the analyzed content. The retransmission unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and automatically resends sent emails for which no response has been received. The unread return unit is realized, for example, by the control unit 46A of the headset type terminal 314 and automatically returns received emails for which no response has been received to unread status. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, identification unit, retransmission unit, and unread return unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the processor 46 of the robot 414 and analyzes text information and image information of emails. The identification unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and identifies emails requiring a response or a response based on the analyzed content. The retransmission unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and automatically resends sent emails for which no response has been received. The unread return unit is realized, for example, by the control unit 46A of the robot 414 and automatically returns received emails for which no response has been received to unread status.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] When analyzing the content of an email, the analysis unit can take into account the past behavioral patterns of the email sender and recipient. For example, if emails from a specific sender have been processed with high priority in the past, the analysis unit can also analyze new emails from the same sender with high priority. Also, if a recipient has responded sensitively to a specific keyword in the past, the analysis unit can prioritize analyzing emails containing that keyword. Furthermore, the analysis unit can evaluate the relationship with a specific sender or recipient based on the frequency and content of past email exchanges and determine the priority of analysis. By taking past behavioral patterns into account, the accuracy and efficiency of analysis are improved.

[0091] The identification unit can take into account the emotional tone of the email content when identifying emails that require a reply or emails that have not yet been addressed based on the content analyzed by the analysis unit. For example, the identification unit can analyze emotional expressions contained in the body of an email to determine its urgency or importance. Furthermore, if the email content indicates positive emotions, the identification unit can identify the email as having a low priority. Furthermore, the identification unit can prioritize emails that indicate negative emotions and classify them as emails that require a prompt response. This makes it possible to identify more appropriate emails by taking emotional tone into account.

[0092] The retransmission unit can adjust the timing of retransmission based on the user's schedule when automatically retransmitting a sent email for which a response identified by the identification unit has not been received. For example, the retransmission unit can refer to the user's calendar information and perform retransmission during a time when the user is not in a meeting or on vacation. The retransmission unit can also be set to not perform retransmission outside the user's working hours. Furthermore, the retransmission unit can optimize the frequency and timing of retransmission based on the user's schedule. This maximizes the effectiveness of retransmission by taking the user's schedule into consideration.

[0093] The unread return unit can take into consideration the category of the email content when automatically returning to unread the unanswered received email identified by the identification unit. For example, if the content of an email is project-related, the unread return unit can prioritize returning the email to unread. Also, if the content of an email is personal, the unread return unit can reduce the frequency of returning the email to unread. Furthermore, if the content of an email is urgent, the unread return unit can quickly return the email to unread. Thus, by taking into consideration the category of the email content, the accuracy and efficiency of returning email to unread are improved.

[0094] The analysis unit can estimate the user's emotions and adjust the email analysis method based on the estimated user's emotions. For example, if the user is feeling stressed, the analysis unit uses AI to prioritize the importance of emails and display only important emails. For example, the analysis unit can use technologies such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, if the user is relaxed, the analysis unit can use AI to perform a detailed analysis and analyze the contents of all emails. For example, the analysis unit can adjust the email analysis method based on the user's emotions. This allows for more appropriate analysis by adjusting the analysis method according to the user's emotions.

[0095] The identification unit can take into account attribute information of the sender and recipient of an email when identifying emails that require a reply or emails that have not yet been addressed based on the content analyzed by the analysis unit. For example, if the sender is a superior or an important business partner, the identification unit will prioritize identifying the email using AI. For example, the identification unit can take into account attribute information such as the sender's and recipient's job title, department, and past communication history when identifying emails. Furthermore, if there are multiple recipients, the identification unit can take into account the AI's job title and relationship with each recipient when identifying emails. For example, the identification unit can improve the accuracy of identification by referring to past email communications between the sender and recipient. This improves the accuracy of identification by taking into account attribute information of the sender and recipient.

[0096] When automatically resending a sent email for which a reply identified by the identification unit has not been received, the resending unit can adjust the timing of the resend based on the user's emotions. For example, if the user is feeling stressed, the resending unit delays the timing of the resend using the AI. For example, the resending unit can use techniques such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, if the user is relaxed, the resending unit can advance the timing of the resend using the AI. For example, the resending unit can adjust the timing of the resend based on the user's emotions. This allows for more appropriate resends by adjusting the timing of the resend according to the user's emotions.

[0097] The unread return unit can take into account the relationship between the sender and recipient of an email when automatically returning unread an unanswered received email identified by the identification unit. For example, if the sender is a superior or an important business partner, the unread return unit will prioritize returning the email to unread with AI. For example, the unread return unit can return emails to unread by taking into account relationships such as the sender's and recipient's job titles, departments, and frequency of past interactions. Furthermore, if there are multiple recipients, the unread return unit can return emails to unread with AI taking into account each recipient's job title and relationship. For example, the unread return unit can determine the priority of returning emails to unread by referring to past email interactions between the sender and recipient. This improves the accuracy of returning emails to unread by taking into account the relationship between the sender and recipient.

[0098] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user's emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. For example, the analysis unit can use techniques such as text analysis, facial expression analysis, and voice analysis to estimate the user's emotions. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. For example, the analysis unit can adjust the display method of the analysis results based on the user's emotions. This allows for a more appropriate display by adjusting the display method according to the user's emotions.

[0099] The identification unit can take into account the importance of the email content when identifying emails that require a reply or emails that have not yet been addressed, based on the content analyzed by the analysis unit. For example, the identification unit identifies emails that require a response based on important keywords contained in the email subject or body. For example, if the email content is related to an important project, the identification unit can use AI to identify the email as one that requires a response. Furthermore, if the email content is urgent, the identification unit can use AI to identify the email as one that requires a response. In this way, by taking the importance of the email content into account, it becomes easier to identify more important emails.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The analysis unit analyzes the content of the email. For example, the analysis unit analyzes the text information and image information of the email and analyzes the email body using natural language processing technology. Step 2: The identification unit identifies emails that require a response or a response based on the content analyzed by the analysis unit. The identification unit analyzes the content of the email using AI, for example, and identifies emails that require a response based on keywords and phrases contained in the email body. Step 3: The resending unit automatically resends the outgoing email for which a reply has not been received, as identified by the identifying unit. The resending unit can, for example, automatically resend the outgoing email for which no reply has been received within a certain period of time, and can also resend the email during a specific time period. Step 4: The unread return unit automatically returns the received email identified by the identification unit to unread if no response has been made. For example, the unread return unit can automatically return received emails that have not been responded to within a certain period of time to unread, or can return them to unread within a specific time period.

[0102] 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.

[0103] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0104] 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.

[0105] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0120] 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.

[0121] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0136] 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.

[0137] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] [Explanation of symbols]

[0174] 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; an identification unit that identifies emails requiring a response or response based on the content analyzed by the analysis unit; a retransmission unit that automatically retransmits the email identified by the identification unit; an unread return unit that automatically returns the email identified by the identification unit to an unread state; A system characterized by:

2. The analysis unit Analyze the text or image information of the email 2. The system of claim 1.

3. The identification unit Based on the content analyzed by the analysis unit, emails that require a reply or unaddressed emails are identified.

2. The system of claim 1.

4. The retransmission unit Automatically resending the outgoing email for which the reply specified by the specifying unit has not been received.

2. The system of claim 1.

5. The unread return unit The received email that has not been answered and that has been identified by the identifying unit is automatically returned to unread.

2. The system of claim 1.

6. The analysis unit Infer user sentiment and adjust email analysis based on the inferred sentiment 2. The system of claim 1.

7. The analysis unit Improve analysis accuracy by referencing past email history 2. The system of claim 1.

8. The analysis unit Analyzes emails by taking into account the attributes of the sender and recipient 2. The system of claim 1.

Images