system

Abstract

The system according to this embodiment aims to analyze the content of received emails, generate appropriate reply templates, and flag important emails. [Solution] The system according to the embodiment comprises an analysis unit, a generation unit, and a flagging unit. The analysis unit analyzes the content of the received email. The generation unit generates a reply email template to the received email based on the content analyzed by the analysis unit. The flagging unit flags the received email based on specific criteria based on the content analyzed by the analysis unit.

Description

Technical Field

[0006] , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the content of received emails has not been efficiently analyzed, an appropriate reply template has not been sufficiently generated, and important emails have not been sufficiently flagged, leaving room for improvement.

[0005] The system according to the embodiment aims to analyze the content of received emails, generate an appropriate reply template, and flag important emails.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, a generation unit, and a flagging unit. The analysis unit analyzes the content of the received email. The generation unit generates a reply email template to the received email based on the content analyzed by the analysis unit. The flagging unit flags the received email based on specific criteria based on the content analyzed by the analysis unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze the content of received emails, generate appropriate reply templates, and flag important emails. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of 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), or Bluetooth (registered trademark).

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI assistant for email replies according to an embodiment of the present invention is a system that analyzes the content of received emails and proposes an appropriate reply template. The AI ​​assistant for email replies analyzes the content of received emails and generates a reply email template based on the analyzed content. It also flags received emails based on specific criteria based on the analyzed content. Furthermore, it works in conjunction with a schedule management function to update schedule data based on the analyzed content. Finally, it confirms appointments and suggests changes. For example, the AI ​​assistant for email replies analyzes the body, subject, sender information, etc., of received emails to understand the content of the email. In this case, different analysis algorithms can be applied depending on the content of the email. For example, different analysis algorithms are used for business emails and private emails. Next, it generates a reply email template based on the analyzed content. For example, in the case of business emails, a standard reply template can be generated. It can also estimate the user's emotions and generate a reply email template based on the estimated user emotions. For example, if the user is angry, a reply template with a calm tone is generated. Furthermore, it flags received emails based on specific criteria based on the analyzed content. For example, the system can determine the priority and urgency of emails based on the sender's job title and email content, and flag them accordingly. This ensures that important emails are not missed and allows for quick responses. It also integrates with the schedule management function, updating schedule data based on the analyzed information. For instance, if an incoming email includes appointment confirmation or modification, the schedule data can be automatically updated. This streamlines schedule management. Finally, it can confirm or suggest changes to appointments. For example, if an incoming email includes an appointment confirmation, it can suggest confirmation to the user. It can also suggest changes if necessary. This streamlines appointment management.Thus, the AI ​​assistant for email replies can comprehensively support email replies by analyzing the content of received emails and suggesting appropriate reply templates, as well as flagging important emails, analyzing their urgency, and integrating with schedule management functions to confirm and suggest changes to appointments.

[0029] The email reply support AI assistant according to this embodiment comprises an analysis unit, a generation unit, and a flagging unit. The analysis unit analyzes the content of the received email. The analysis unit analyzes the email body, subject, and sender information using, for example, natural language processing technology to understand the content of the email. The analysis unit can extract important information using, for example, keyword extraction technology. The analysis unit can also analyze the sentiment of the email using sentiment analysis technology. The generation unit generates a reply email template based on the content analyzed by the analysis unit. The generation unit can generate, for example, a standard reply template. The generation unit can also estimate the user's sentiment and generate a reply email template based on the estimated user sentiment. For example, if the user is angry, the generation unit generates a reply template with a calm tone. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can generate a reply email template using a generation AI model that takes the content analyzed by the analysis unit as input and outputs a reply email template. The flagging unit flags received emails based on specific criteria derived from the analysis performed by the analysis unit. For example, the flagging unit can determine the priority and urgency of an email based on the sender's job title or the content of the email, and then flag it accordingly. For example, if the sender holds a high job title, the flagging unit will flag it as important. The flagging unit can also flag an email as urgent if its content is urgent. Some or all of the above-described processes in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes the content analyzed by the analysis unit as input and outputs a flag. This enables the email reply support AI assistant according to the embodiment to analyze the content of received emails, suggest appropriate reply templates, and flag important emails.

[0030] The analysis unit analyzes the content of received emails. For example, it uses natural language processing techniques to analyze the email body, subject, and sender information to understand the email's content. Specifically, it employs natural language processing techniques such as tokenization, morphological analysis, grammatical analysis, and semantic analysis. Tokenization is the process of dividing the email body into words and phrases, while morphological analysis identifies the part of speech and meaning of each token. Grammatical analysis analyzes the sentence structure and clarifies relationships between subjects, predicates, and objects. Semantic analysis understands the meaning of a sentence and provides an appropriate interpretation based on the context. The analysis unit combines these techniques to analyze the email content in detail. For example, it can extract important information from the email body using keyword extraction techniques. Keyword extraction techniques use methods such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec to identify important words and phrases in the email body. It can also analyze the sentiment of an email using sentiment analysis techniques. Sentiment analysis technology categorizes emails into positive, negative, and neutral sentiment categories and evaluates the sentiment of each email. This allows the analysis unit to analyze the content of received emails in detail and grasp important information and emotions. Furthermore, the analysis unit can perform more accurate analyses by utilizing past email data and user behavior history. For example, it can learn patterns associated with specific senders and subject lines based on past email data and use this information to analyze new emails. It can also understand user preferences and tendencies based on user behavior history and reflect them in the analysis results. As a result, the analysis unit can analyze the content of received emails with high accuracy and provide users with useful information.

[0031] The generation unit generates a reply email template based on the content analyzed by the analysis unit. For example, the generation unit can generate standard reply templates. Specifically, it can prepare templates for different situations, such as business emails and casual emails, and select the appropriate template based on the analysis results. The generation unit can also estimate the user's emotions and generate a reply email template based on the estimated emotions. For example, if the user is angry, the generation unit will generate a reply template with a calm tone. Some or all of the above processing in the generation unit may be performed using a generation AI, or without one. For example, the generation unit can generate a reply email template using a generation AI model that takes the content analyzed by the analysis unit as input and outputs a reply email template. The generation AI model can be a large-scale language model such as an LLM. These models have learned from large amounts of text data and are capable of generating natural-sounding sentences. The generation unit uses the generation AI model to generate an appropriate reply email template based on the analysis results. Furthermore, the generation unit can generate a more personalized reply template by considering the user's past reply history and preferences. For example, the system learns expressions and phrases previously used by the user and incorporates them into templates. Furthermore, the generation unit performs grammar and spell checks when generating reply email templates, providing accurate and easy-to-read text. This allows the generation unit to quickly and accurately generate the most suitable reply email templates for the user, streamlining the email reply process.

[0032] The flagging unit flags received emails based on specific criteria derived from the analysis performed by the analysis unit. For example, the flagging unit can determine the priority and urgency of an email based on the sender's job title or the email's content, and then flag it accordingly. Specifically, if the sender holds a high job title, it will be flagged as important. The flagging unit can also flag emails as urgent if their content is urgent. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can use an AI model that takes the analysis performed by the analysis unit as input and outputs flags. The AI ​​model can use machine learning algorithms such as random forests or support vector machines. These algorithms learn from past email data and generate rules for flagging based on specific criteria. The flagging unit can use these rules to flag received emails appropriately. Furthermore, the flagging unit can customize the flag criteria according to user settings and preferences. For example, it can be configured to always treat emails from a specific sender as important, or to treat emails containing specific keywords as urgent. This allows the flagging unit to quickly identify important emails for the user and prompt appropriate action. Furthermore, the flagging unit can continuously learn flagging methods and criteria, improving its accuracy. For example, it can revise its flagging methods based on user feedback to perform more appropriate flagging. This streamlines the management of incoming emails and reduces the user's workload.

[0033] The flagging unit can determine the priority or urgency of an email based on the sender's job title or the content of the email. For example, the flagging unit can flag an email as important if the sender has a high job title. For example, the flagging unit can flag an email as urgent if the content of the email is urgent. The flagging unit can flag an email as urgent if the content of the email is urgent. This allows for the determination of the priority and urgency of emails, ensuring that important emails are not overlooked. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes the sender's job title and email content as input and outputs priority and urgency.

[0034] The integration unit can work in conjunction with the schedule management function to update schedule data based on the analysis performed by the analysis unit. For example, if an incoming email contains appointment confirmation or changes, the integration unit can automatically update the schedule data. The integration unit can automatically update schedule data if an incoming email contains appointment confirmation. Furthermore, the integration unit can automatically update schedule data if an incoming email contains appointment changes. This automatically updates schedule data and streamlines schedule management. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can update schedule data using an AI model that takes the analysis performed by the analysis unit as input and outputs schedule data.

[0035] The proposal unit can confirm appointments and suggest changes. For example, if an incoming email includes an appointment confirmation, the proposal unit will suggest that the user confirm the appointment. The proposal unit can also suggest changes to appointments if necessary. This automates appointment confirmation and change suggestions, streamlining management. Some or all of the above processes in the proposal unit may be performed using AI or not. For example, the proposal unit can use an AI model that takes the content analyzed by the analysis unit as input and outputs appointment confirmation and change suggestions to make proposals.

[0036] The analysis unit can apply different analysis algorithms depending on the content of the email. For example, the analysis unit uses different analysis algorithms for business emails and personal emails. For example, in the case of business emails, the analysis unit can analyze the content of the email using natural language processing technology. For example, in the case of personal emails, the analysis unit can analyze the content of the email using sentiment analysis technology. This enables optimal analysis according to the content of the email. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can perform analysis using an AI model that takes the content of the email as input and outputs the analysis results.

[0037] The analysis unit can improve the accuracy of its analysis of received emails by considering the time of day and frequency of email transmission. For example, the analysis unit can consider the time of day of email transmission and determine that emails sent during business hours are business-related. For example, the analysis unit can analyze the frequency of email transmission and determine that frequently sent emails are of high importance. Furthermore, the analysis unit can improve the accuracy of its analysis by combining the time of day and frequency of email transmission. Thus, considering the time of day and frequency of email transmission improves the accuracy of the analysis. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the time of day and frequency of email transmission as input and perform analysis using an AI model that improves the accuracy of the analysis.

[0038] The analysis unit can analyze not only the email body but also the contents of attached files during the analysis. For example, the analysis unit can determine the type of attached file and analyze its contents if it is a text file. If the attached file is an image, the analysis unit can analyze its contents using image analysis technology. Furthermore, if there are multiple attached files, the analysis unit can analyze the contents of each and make an overall judgment. By including the contents of attached files in the analysis, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can perform the analysis using an AI model that takes the contents of an attached file as input and outputs the analysis results.

[0039] The analysis unit can improve the accuracy of its analysis by referring to the sender's past email history during the analysis process. For example, the analysis unit can analyze the sender's past email history to find specific patterns. For example, the analysis unit can refer to the content of the sender's past emails and analyze similar content. Furthermore, the analysis unit can determine the importance and urgency of an email based on the sender's past email history. This improves the accuracy of the analysis by referring to the sender's past email history. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the sender's past email history as input and perform the analysis using an AI model that improves the accuracy of the analysis.

[0040] The analysis unit can adjust its analysis algorithm during analysis, taking into account the language and cultural background of the email. For example, the analysis unit can automatically determine the language of the email and select an appropriate analysis algorithm. For example, the analysis unit can analyze specific expressions and phrases, taking into account the cultural background of the email. Furthermore, the analysis unit can improve the accuracy of the analysis by combining the language and cultural background of the email. Thus, considering the language and cultural background of the email improves the accuracy of the analysis. Some or all of the above processes in the analysis unit may be performed using AI, or they may not be performed using AI. For example, the analysis unit can perform analysis using an AI model that takes the language and cultural background of the email as input and adjusts the analysis algorithm.

[0041] The generation unit can reflect the user's past reply history in the reply email template during generation. For example, the generation unit can generate a new template based on a reply template previously used by the user. For example, the generation unit can analyze the user's past reply history and reflect frequently used phrases in the template. The generation unit can also find specific patterns based on the user's past reply history and reflect them in the template. This allows for the generation of more appropriate reply email templates by reflecting the user's past reply history. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can generate templates using a generation AI model that takes the user's past reply history as input and outputs a reply email template.

[0042] The generation unit can automatically attach links and materials related to the reply email template during generation. For example, the generation unit can automatically attach web links related to the content of the reply email. For example, the generation unit can automatically attach materials related to the content of the reply email. In addition, the generation unit can automatically attach past emails related to the content of the reply email. This enriches the reply content by automatically attaching links and materials related to the reply email template. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can attach links and materials using a generation AI model that takes the content of the reply email as input and outputs related links and materials.

[0043] The generation unit can automatically insert the user's signature and standard phrases into the reply email template during generation. For example, the generation unit can automatically insert the user's signature into the reply email template. For example, the generation unit can automatically insert standard phrases that the user frequently uses into the reply email template. Furthermore, the generation unit can combine the user's signature and standard phrases and insert them into the reply email template. This makes replying more efficient by automatically inserting the user's signature and standard phrases into the reply email template. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can use an AI model that takes the user's signature and standard phrases as input and inserts them into the reply email template to insert the signature and standard phrases.

[0044] The generation unit can provide reply options in multiple languages ​​in the reply email template during generation. For example, the generation unit can provide reply options in multiple languages ​​in the reply email template. For example, the generation unit can generate a reply email template in the language selected by the user. The generation unit can also automatically insert reply options in multiple languages ​​into the reply email template. This enables multilingual support by providing reply options in multiple languages. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can provide reply options in multiple languages ​​using a generation AI model that takes multiple languages ​​as input and outputs a reply email template.

[0045] The flagging unit can improve the accuracy of flagging by referring to the sender's past flagging history when flagging. For example, the flagging unit can analyze the sender's past flagging history and find specific patterns. For example, the flagging unit can determine importance and urgency based on the sender's past flagging history. The flagging unit can also adjust the color and shape of the flag by referring to the sender's past flagging history. This improves the accuracy of flagging by referring to the sender's past flagging history. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can take the sender's past flagging history as input and flag using an AI model that improves flag accuracy.

[0046] The flagging unit can assign different flags to emails depending on the importance of the email content. For example, the flagging unit can assign a red flag if the email content is important. For example, the flagging unit can assign a yellow flag if the email content is urgent. The flagging unit can assign a blue flag if the email content is normal. This allows for the provision of flags according to the importance of the email content. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can assign flags using an AI model that takes the email content as input and outputs flags according to importance.

[0047] The flagging unit can flag emails while considering the geographical location information of the email sender. For example, if the sender is nearby, the flagging unit may determine that the email is urgent and assign a red flag. For example, if the sender is far away, the flagging unit may determine that the email is not urgent and assign a blue flag. The flagging unit can also adjust the color and shape of the flag based on the sender's geographical location information. This improves the accuracy of the flagging by considering the sender's geographical location information. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes the sender's geographical location information as input and outputs a flag.

[0048] The flagging unit can improve the accuracy of flagging by referring to relevant literature and materials related to the email during the flagging process. For example, the flagging unit can refer to literature and materials related to the content of the email to determine its importance. For example, the flagging unit can refer to past emails related to the content of the email to determine its urgency. Furthermore, the flagging unit can adjust the color and shape of the flag based on literature and materials related to the content of the email. This improves the accuracy of flagging by referring to relevant literature and materials. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes relevant literature and materials as input and outputs flags.

[0049] The integration unit can select the optimal update method by referring to the past history of the schedule data during integration. For example, the integration unit can analyze the past history of the schedule data and find specific patterns. For example, the integration unit can select the optimal update frequency based on the past history of the schedule data. Furthermore, the integration unit can refer to the past history of the schedule data and select an update method that suits the user's preferences. In this way, by referring to the past history, the optimal schedule data update method can be provided. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the past history of the schedule data as input and select an update method using an AI model that selects the optimal update method.

[0050] The integration unit can optimize schedule data by considering the user's device information during integration. For example, if the user is using a smartphone, the integration unit can provide a display method for schedule data that is adapted to the screen size. For example, if the user is using a tablet, the integration unit can provide a display method for schedule data optimized for a larger screen. Furthermore, if the user is using a smartwatch, the integration unit can provide a concise and highly visible display method for schedule data. In this way, optimal schedule data can be provided by considering the user's device information. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's device information as input and perform optimization using an AI model that optimizes schedule data.

[0051] The proposal unit can make optimal suggestions by referring to the user's past appointment history. For example, the proposal unit can analyze the user's past appointment history and find specific patterns. For example, the proposal unit can make optimal suggestions based on the user's past appointment history. Furthermore, the proposal unit can refer to the user's past appointment history and make suggestions tailored to the user's preferences. In this way, the optimal suggestion can be provided by referring to the past appointment history. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can make suggestions using an AI model that takes the user's past appointment history as input and outputs the optimal suggestion.

[0052] The proposal unit can suggest the most suitable appointment by considering the user's geographical location information. For example, if the user is nearby, the proposal unit can suggest a high-priority appointment. For example, if the user is far away, the proposal unit can suggest a low-priority appointment. The proposal unit can also suggest the most suitable appointment based on the user's geographical location information. In this way, the optimal appointment can be provided by considering the user's geographical location information. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can make suggestions using an AI model that takes the user's geographical location information as input and outputs the most suitable appointment.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] The analysis unit can improve the accuracy of its analysis of received emails by considering the sender's past behavioral patterns. For example, the analysis unit can analyze what kinds of emails the sender has sent in the past and find specific patterns. For example, the analysis unit can refer to the content of emails the sender has sent in the past and analyze similar content. Furthermore, the analysis unit can determine the importance and urgency of an email based on the sender's past behavioral patterns. This improves the accuracy of the analysis by referring to the sender's past behavioral patterns. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the sender's past behavioral patterns as input and perform the analysis using an AI model that improves the accuracy of the analysis.

[0055] The flagging unit can detect specific keywords based on the content of an email and flag it based on those keywords. For example, if the email content contains keywords such as "urgent" or "important," the flagging unit will flag it as urgent. For example, if the email content contains keywords such as "confirm" or "reply," the flagging unit can flag it as important. Also, if the email content contains keywords such as "meeting" or "appointment," the flagging unit can flag it as schedule-related. This improves the accuracy of flagging by detecting specific keywords based on the content of the email and flagging them accordingly. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can take the email content as input and flag it using an AI model that detects keywords.

[0056] The integration unit, when integrating with the schedule management function, can refer to the user's past schedule data to propose an optimal schedule. For example, the integration unit can analyze the user's past schedule data and find specific patterns. For example, the integration unit can propose an optimal schedule based on the user's past schedule data. Furthermore, the integration unit can refer to the user's past schedule data and propose a schedule tailored to the user's preferences. In this way, by referring to past schedule data, it can provide an optimal schedule. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's past schedule data as input and propose a schedule using an AI model that proposes an optimal schedule.

[0057] The proposal department can adjust its proposals to reflect the user's current situation when confirming or suggesting changes to appointments. For example, if the user is busy, the proposal department can provide concise and to-the-point proposals. If the user is relaxed, the proposal department can provide proposals that include detailed information. If the user is in a hurry, the proposal department can provide proposals that can be addressed quickly. This allows the proposal department to provide content tailored to the user's current situation. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can use an AI model that takes the user's current situation as input and adjusts the proposal content accordingly.

[0058] The generation unit can optimize the content of reply email templates by referring to the user's past reply history when generating reply email templates. For example, the generation unit can generate a new template based on reply templates previously used by the user. For example, the generation unit can analyze the user's past reply history and reflect frequently used phrases in the template. The generation unit can also find specific patterns based on the user's past reply history and reflect them in the template. This allows for the generation of more appropriate reply email templates by reflecting the user's past reply history. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can generate templates using a generation AI model that takes the user's past reply history as input and outputs reply email templates.

[0059] The integration unit can optimize schedule data by considering the user's device information when integrating with the schedule management function. For example, if the user is using a smartphone, the integration unit can provide a display method for schedule data that is adapted to the screen size. For example, if the user is using a tablet, the integration unit can provide a display method for schedule data optimized for a larger screen. Furthermore, if the user is using a smartwatch, the integration unit can provide a concise and highly visible display method for schedule data. In this way, optimal schedule data can be provided by considering the user's device information. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's device information as input and perform optimization using an AI model that optimizes schedule data.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The analysis unit analyzes the content of the received email. The analysis unit uses natural language processing technology to analyze the email body, subject, and sender information to understand the email's content. For example, it can use keyword extraction technology to extract important information and sentiment analysis technology to analyze the sentiment of the email. Step 2: The generation unit generates a reply email template based on the analysis performed by the analysis unit. The generation unit can generate standard reply templates, and can also estimate the user's emotions and generate a reply email template based on those emotions. For example, if the user is angry, it will generate a reply template with a calm tone. Processing in the generation unit may also be performed using generation AI. Step 3: The flagging unit flags incoming emails based on specific criteria derived from the analysis performed by the analysis unit. The flagging unit can determine the priority and urgency of emails based on the sender's job title and the content of the email, and then flag them accordingly. For example, if the sender has a high job title, it will be flagged as important, and if the content of the email is urgent, it will be flagged as urgent. Processing in the flagging unit may also be performed using AI.

[0062] (Example of form 2) An AI assistant for email replies according to an embodiment of the present invention is a system that analyzes the content of received emails and proposes an appropriate reply template. The AI ​​assistant for email replies analyzes the content of received emails and generates a reply email template based on the analyzed content. It also flags received emails based on specific criteria based on the analyzed content. Furthermore, it works in conjunction with a schedule management function to update schedule data based on the analyzed content. Finally, it confirms appointments and suggests changes. For example, the AI ​​assistant for email replies analyzes the body, subject, sender information, etc., of received emails to understand the content of the email. In this case, different analysis algorithms can be applied depending on the content of the email. For example, different analysis algorithms are used for business emails and private emails. Next, it generates a reply email template based on the analyzed content. For example, in the case of business emails, a standard reply template can be generated. It can also estimate the user's emotions and generate a reply email template based on the estimated user emotions. For example, if the user is angry, a reply template with a calm tone is generated. Furthermore, it flags received emails based on specific criteria based on the analyzed content. For example, the system can determine the priority and urgency of emails based on the sender's job title and email content, and flag them accordingly. This ensures that important emails are not missed and allows for quick responses. It also integrates with the schedule management function, updating schedule data based on the analyzed information. For instance, if an incoming email includes appointment confirmation or modification, the schedule data can be automatically updated. This streamlines schedule management. Finally, it can confirm or suggest changes to appointments. For example, if an incoming email includes an appointment confirmation, it can suggest confirmation to the user. It can also suggest changes if necessary. This streamlines appointment management.Thus, the AI ​​assistant for email replies can comprehensively support email replies by analyzing the content of received emails and suggesting appropriate reply templates, as well as flagging important emails, analyzing their urgency, and integrating with schedule management functions to confirm and suggest changes to appointments.

[0063] The email reply support AI assistant according to this embodiment comprises an analysis unit, a generation unit, and a flagging unit. The analysis unit analyzes the content of the received email. The analysis unit analyzes the email body, subject, and sender information using, for example, natural language processing technology to understand the content of the email. The analysis unit can extract important information using, for example, keyword extraction technology. The analysis unit can also analyze the sentiment of the email using sentiment analysis technology. The generation unit generates a reply email template based on the content analyzed by the analysis unit. The generation unit can generate, for example, a standard reply template. The generation unit can also estimate the user's sentiment and generate a reply email template based on the estimated user sentiment. For example, if the user is angry, the generation unit generates a reply template with a calm tone. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the generation unit can generate a reply email template using a generation AI model that takes the content analyzed by the analysis unit as input and outputs a reply email template. The flagging unit flags received emails based on specific criteria derived from the analysis performed by the analysis unit. For example, the flagging unit can determine the priority and urgency of an email based on the sender's job title or the content of the email, and then flag it accordingly. For example, if the sender holds a high job title, the flagging unit will flag it as important. The flagging unit can also flag an email as urgent if its content is urgent. Some or all of the above-described processes in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes the content analyzed by the analysis unit as input and outputs a flag. This enables the email reply support AI assistant according to the embodiment to analyze the content of received emails, suggest appropriate reply templates, and flag important emails.

[0064] The analysis unit analyzes the content of received emails. For example, it uses natural language processing techniques to analyze the email body, subject, and sender information to understand the email's content. Specifically, it employs natural language processing techniques such as tokenization, morphological analysis, grammatical analysis, and semantic analysis. Tokenization is the process of dividing the email body into words and phrases, while morphological analysis identifies the part of speech and meaning of each token. Grammatical analysis analyzes the sentence structure and clarifies relationships between subjects, predicates, and objects. Semantic analysis understands the meaning of a sentence and provides an appropriate interpretation based on the context. The analysis unit combines these techniques to analyze the email content in detail. For example, it can extract important information from the email body using keyword extraction techniques. Keyword extraction techniques use methods such as TF-IDF (Term Frequency-Inverse Document Frequency) and Word2Vec to identify important words and phrases in the email body. It can also analyze the sentiment of an email using sentiment analysis techniques. Sentiment analysis technology categorizes emails into positive, negative, and neutral sentiment categories and evaluates the sentiment of each email. This allows the analysis unit to analyze the content of received emails in detail and grasp important information and emotions. Furthermore, the analysis unit can perform more accurate analyses by utilizing past email data and user behavior history. For example, it can learn patterns associated with specific senders and subject lines based on past email data and use this information to analyze new emails. It can also understand user preferences and tendencies based on user behavior history and reflect them in the analysis results. As a result, the analysis unit can analyze the content of received emails with high accuracy and provide users with useful information.

[0065] The generation unit generates a reply email template based on the content analyzed by the analysis unit. For example, the generation unit can generate standard reply templates. Specifically, it can prepare templates for different situations, such as business emails and casual emails, and select the appropriate template based on the analysis results. The generation unit can also estimate the user's emotions and generate a reply email template based on the estimated emotions. For example, if the user is angry, the generation unit will generate a reply template with a calm tone. Some or all of the above processing in the generation unit may be performed using a generation AI, or without one. For example, the generation unit can generate a reply email template using a generation AI model that takes the content analyzed by the analysis unit as input and outputs a reply email template. The generation AI model can be a large-scale language model such as an LLM. These models have learned from large amounts of text data and are capable of generating natural-sounding sentences. The generation unit uses the generation AI model to generate an appropriate reply email template based on the analysis results. Furthermore, the generation unit can generate a more personalized reply template by considering the user's past reply history and preferences. For example, the system learns expressions and phrases previously used by the user and incorporates them into templates. Furthermore, the generation unit performs grammar and spell checks when generating reply email templates, providing accurate and easy-to-read text. This allows the generation unit to quickly and accurately generate the most suitable reply email templates for the user, streamlining the email reply process.

[0066] The flagging unit flags received emails based on specific criteria derived from the analysis performed by the analysis unit. For example, the flagging unit can determine the priority and urgency of an email based on the sender's job title or the email's content, and then flag it accordingly. Specifically, if the sender holds a high job title, it will be flagged as important. The flagging unit can also flag emails as urgent if their content is urgent. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can use an AI model that takes the analysis performed by the analysis unit as input and outputs flags. The AI ​​model can use machine learning algorithms such as random forests or support vector machines. These algorithms learn from past email data and generate rules for flagging based on specific criteria. The flagging unit can use these rules to flag received emails appropriately. Furthermore, the flagging unit can customize the flag criteria according to user settings and preferences. For example, it can be configured to always treat emails from a specific sender as important, or to treat emails containing specific keywords as urgent. This allows the flagging unit to quickly identify important emails for the user and prompt appropriate action. Furthermore, the flagging unit can continuously learn flagging methods and criteria, improving its accuracy. For example, it can revise its flagging methods based on user feedback to perform more appropriate flagging. This streamlines the management of incoming emails and reduces the user's workload.

[0067] The flagging unit can determine the priority or urgency of an email based on the sender's job title or the content of the email. For example, the flagging unit can flag an email as important if the sender has a high job title. For example, the flagging unit can flag an email as urgent if the content of the email is urgent. The flagging unit can flag an email as urgent if the content of the email is urgent. This allows for the determination of the priority and urgency of emails, ensuring that important emails are not overlooked. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes the sender's job title and email content as input and outputs priority and urgency.

[0068] The integration unit can work in conjunction with the schedule management function to update schedule data based on the analysis performed by the analysis unit. For example, if an incoming email contains appointment confirmation or changes, the integration unit can automatically update the schedule data. The integration unit can automatically update schedule data if an incoming email contains appointment confirmation. Furthermore, the integration unit can automatically update schedule data if an incoming email contains appointment changes. This automatically updates schedule data and streamlines schedule management. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can update schedule data using an AI model that takes the analysis performed by the analysis unit as input and outputs schedule data.

[0069] The proposal unit can confirm appointments and suggest changes. For example, if an incoming email includes an appointment confirmation, the proposal unit will suggest that the user confirm the appointment. The proposal unit can also suggest changes to appointments if necessary. This automates appointment confirmation and change suggestions, streamlining management. Some or all of the above processes in the proposal unit may be performed using AI or not. For example, the proposal unit can use an AI model that takes the content analyzed by the analysis unit as input and outputs appointment confirmation and change suggestions to make proposals.

[0070] The generation unit can estimate the user's emotions and generate a reply email template based on the estimated emotions. For example, if the user is angry, the generation unit can generate a reply template in a calm tone. For example, if the user is relaxed, the generation unit can generate a reply template in a friendly tone. Furthermore, if the user is in a hurry, the generation unit can generate a concise and to-the-point reply template. This allows for the generation of reply email templates that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using a generative AI or not. For example, the generation unit can generate a reply email template using a generative AI model that takes the user's emotions as input and outputs a reply email template.

[0071] The analysis unit can apply different analysis algorithms depending on the content of the email. For example, the analysis unit uses different analysis algorithms for business emails and personal emails. For example, in the case of business emails, the analysis unit can analyze the content of the email using natural language processing technology. For example, in the case of personal emails, the analysis unit can analyze the content of the email using sentiment analysis technology. This enables optimal analysis according to the content of the email. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can perform analysis using an AI model that takes the content of the email as input and outputs the analysis results.

[0072] The analysis unit can estimate the user's emotions and select an analysis algorithm based on the estimated emotions. For example, if the user is stressed, the analysis unit can select a simple analysis algorithm and perform a quick analysis. If the user is relaxed, for example, the analysis unit can select a detailed analysis algorithm and perform a deeper analysis. Furthermore, if the user is in a hurry, the analysis unit can select an algorithm to produce results in the shortest possible time. This allows for the selection of an analysis algorithm that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can select an analysis algorithm using an AI model that takes the user's emotions as input and selects an analysis algorithm.

[0073] The analysis unit can improve the accuracy of its analysis of received emails by considering the time of day and frequency of email transmission. For example, the analysis unit can consider the time of day of email transmission and determine that emails sent during business hours are business-related. For example, the analysis unit can analyze the frequency of email transmission and determine that frequently sent emails are of high importance. Furthermore, the analysis unit can improve the accuracy of its analysis by combining the time of day and frequency of email transmission. Thus, considering the time of day and frequency of email transmission improves the accuracy of the analysis. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the time of day and frequency of email transmission as input and perform analysis using an AI model that improves the accuracy of the analysis.

[0074] The analysis unit can analyze not only the email body but also the contents of attached files during the analysis. For example, the analysis unit can determine the type of attached file and analyze its contents if it is a text file. If the attached file is an image, the analysis unit can analyze its contents using image analysis technology. Furthermore, if there are multiple attached files, the analysis unit can analyze the contents of each and make an overall judgment. By including the contents of attached files in the analysis, the accuracy of the analysis is improved. Some or all of the above processing in the analysis unit may be performed using AI or not. For example, the analysis unit can perform the analysis using an AI model that takes the contents of an attached file as input and outputs the analysis results.

[0075] 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 and highly visible display method. For example, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that gets straight to the point. This allows for the display of analysis results to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using AI or not. For example, the analysis unit can adjust the display method using an AI model that takes the user's emotions as input and adjusts the display method of the analysis results.

[0076] The analysis unit can improve the accuracy of its analysis by referring to the sender's past email history during the analysis process. For example, the analysis unit can analyze the sender's past email history to find specific patterns. For example, the analysis unit can refer to the content of the sender's past emails and analyze similar content. Furthermore, the analysis unit can determine the importance and urgency of an email based on the sender's past email history. This improves the accuracy of the analysis by referring to the sender's past email history. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the sender's past email history as input and perform the analysis using an AI model that improves the accuracy of the analysis.

[0077] The analysis unit can adjust its analysis algorithm during analysis, taking into account the language and cultural background of the email. For example, the analysis unit can automatically determine the language of the email and select an appropriate analysis algorithm. For example, the analysis unit can analyze specific expressions and phrases, taking into account the cultural background of the email. Furthermore, the analysis unit can improve the accuracy of the analysis by combining the language and cultural background of the email. Thus, considering the language and cultural background of the email improves the accuracy of the analysis. Some or all of the above processes in the analysis unit may be performed using AI, or they may not be performed using AI. For example, the analysis unit can perform analysis using an AI model that takes the language and cultural background of the email as input and adjusts the analysis algorithm.

[0078] The generation unit can estimate the user's emotions and adjust the tone of the reply email template based on the estimated emotions. For example, if the user is angry, the generation unit can generate a reply template with a calm and polite tone. For example, if the user is relaxed, the generation unit can generate a reply template with a friendly tone. Also, if the user is in a hurry, the generation unit can generate a reply template with a concise and to-the-point tone. This allows for the generation of reply email templates with a tone appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generative AI or not. For example, the generation unit can take the user's emotions as input and adjust the tone of the reply email template using an AI model.

[0079] The generation unit can reflect the user's past reply history in the reply email template during generation. For example, the generation unit can generate a new template based on a reply template previously used by the user. For example, the generation unit can analyze the user's past reply history and reflect frequently used phrases in the template. The generation unit can also find specific patterns based on the user's past reply history and reflect them in the template. This allows for the generation of more appropriate reply email templates by reflecting the user's past reply history. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can generate templates using a generation AI model that takes the user's past reply history as input and outputs a reply email template.

[0080] The generation unit can automatically attach links and materials related to the reply email template during generation. For example, the generation unit can automatically attach web links related to the content of the reply email. For example, the generation unit can automatically attach materials related to the content of the reply email. In addition, the generation unit can automatically attach past emails related to the content of the reply email. This enriches the reply content by automatically attaching links and materials related to the reply email template. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can attach links and materials using a generation AI model that takes the content of the reply email as input and outputs related links and materials.

[0081] The generation unit can estimate the user's emotions and adjust the length of the reply email template based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate a short, to-the-point reply template. If the user is relaxed, the generation unit can generate a longer reply template that includes detailed explanations. If the user is excited, the generation unit can generate a reply template with visually stimulating effects. This allows for the generation of reply email templates of appropriate length according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the generation unit may be performed using a generative AI or not. For example, the generation unit can take the user's emotions as input and adjust the length of the reply email template using an AI model that adjusts the length of the template.

[0082] The generation unit can automatically insert the user's signature and standard phrases into the reply email template during generation. For example, the generation unit can automatically insert the user's signature into the reply email template. For example, the generation unit can automatically insert standard phrases that the user frequently uses into the reply email template. Furthermore, the generation unit can combine the user's signature and standard phrases and insert them into the reply email template. This makes replying more efficient by automatically inserting the user's signature and standard phrases into the reply email template. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can use an AI model that takes the user's signature and standard phrases as input and inserts them into the reply email template to insert the signature and standard phrases.

[0083] The generation unit can provide reply options in multiple languages ​​in the reply email template during generation. For example, the generation unit can provide reply options in multiple languages ​​in the reply email template. For example, the generation unit can generate a reply email template in the language selected by the user. The generation unit can also automatically insert reply options in multiple languages ​​into the reply email template. This enables multilingual support by providing reply options in multiple languages. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can provide reply options in multiple languages ​​using a generation AI model that takes multiple languages ​​as input and outputs a reply email template.

[0084] The flagging unit can estimate the user's emotions and adjust the color and shape of the flag based on the estimated emotions. For example, if the user is stressed, the flagging unit can use a simple color and shape of flag. If the user is relaxed, the flagging unit can use a colorful and visually appealing flag. If the user is in a hurry, the flagging unit can use a flag with a conspicuous color and shape. This allows the flag color and shape to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can adjust the flag using an AI model that takes the user's emotions as input and adjusts the color and shape of the flag.

[0085] The flagging unit can improve the accuracy of flagging by referring to the sender's past flagging history when flagging. For example, the flagging unit can analyze the sender's past flagging history and find specific patterns. For example, the flagging unit can determine importance and urgency based on the sender's past flagging history. The flagging unit can also adjust the color and shape of the flag by referring to the sender's past flagging history. This improves the accuracy of flagging by referring to the sender's past flagging history. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can take the sender's past flagging history as input and flag using an AI model that improves flag accuracy.

[0086] The flagging unit can assign different flags to emails depending on the importance of the email content. For example, the flagging unit can assign a red flag if the email content is important. For example, the flagging unit can assign a yellow flag if the email content is urgent. The flagging unit can assign a blue flag if the email content is normal. This allows for the provision of flags according to the importance of the email content. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can assign flags using an AI model that takes the email content as input and outputs flags according to importance.

[0087] The flagging unit can estimate the user's emotions and adjust the display order of flags based on the estimated emotions. For example, if the user is stressed, the flagging unit will display important flags at the top. If the user is relaxed, the flagging unit can allow the user to freely customize the display order of flags. Also, if the user is in a hurry, the flagging unit can display urgent flags at the top. This provides a display order of flags that corresponds to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can take the user's emotions as input and adjust the display order using an AI model that adjusts the display order of flags.

[0088] The flagging unit can flag emails while considering the geographical location information of the email sender. For example, if the sender is nearby, the flagging unit may determine that the email is urgent and assign a red flag. For example, if the sender is far away, the flagging unit may determine that the email is not urgent and assign a blue flag. The flagging unit can also adjust the color and shape of the flag based on the sender's geographical location information. This improves the accuracy of the flagging by considering the sender's geographical location information. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes the sender's geographical location information as input and outputs a flag.

[0089] The flagging unit can improve the accuracy of flagging by referring to relevant literature and materials related to the email during the flagging process. For example, the flagging unit can refer to literature and materials related to the content of the email to determine its importance. For example, the flagging unit can refer to past emails related to the content of the email to determine its urgency. Furthermore, the flagging unit can adjust the color and shape of the flag based on literature and materials related to the content of the email. This improves the accuracy of flagging by referring to relevant literature and materials. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can flag emails using an AI model that takes relevant literature and materials as input and outputs flags.

[0090] The integration unit can estimate the user's emotions and adjust the update frequency of the schedule data based on the estimated emotions. For example, if the user is stressed, the integration unit can lower the update frequency of the schedule data. For example, if the user is relaxed, the integration unit can increase the update frequency of the schedule data. Furthermore, if the user is in a hurry, the integration unit can optimize the update frequency of the schedule data. This allows for the provision of schedule data updates that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's emotions as input and adjust the update frequency of the schedule data using an AI model that adjusts the update frequency.

[0091] The integration unit can select the optimal update method by referring to the past history of the schedule data during integration. For example, the integration unit can analyze the past history of the schedule data and find specific patterns. For example, the integration unit can select the optimal update frequency based on the past history of the schedule data. Furthermore, the integration unit can refer to the past history of the schedule data and select an update method that suits the user's preferences. In this way, by referring to the past history, the optimal schedule data update method can be provided. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the past history of the schedule data as input and select an update method using an AI model that selects the optimal update method.

[0092] The integration unit can estimate the user's emotions and adjust the display method of schedule data based on the estimated user emotions. For example, if the user is stressed, the integration unit can provide a simple and highly visible display method. For example, if the user is relaxed, the integration unit can provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the integration unit can provide a concise display method. This allows for the display of schedule data to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can adjust the display method using an AI model that takes the user's emotions as input and adjusts the display method of schedule data.

[0093] The integration unit can optimize schedule data by considering the user's device information during integration. For example, if the user is using a smartphone, the integration unit can provide a display method for schedule data that is adapted to the screen size. For example, if the user is using a tablet, the integration unit can provide a display method for schedule data optimized for a larger screen. Furthermore, if the user is using a smartwatch, the integration unit can provide a concise and highly visible display method for schedule data. In this way, optimal schedule data can be provided by considering the user's device information. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's device information as input and perform optimization using an AI model that optimizes schedule data.

[0094] The suggestion unit can estimate the user's emotions and adjust the appointment suggestion method based on the estimated emotions. For example, if the user is nervous, the suggestion unit can provide a simple and highly visible suggestion method. For example, if the user is relaxed, the suggestion unit can provide a suggestion method that includes detailed information. Furthermore, if the user is in a hurry, the suggestion unit can provide a concise suggestion method. This allows for the provision of appointment suggestion methods that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can take the user's emotions as input and adjust the suggestion method using an AI model that adjusts the appointment suggestion method.

[0095] The proposal unit can make optimal suggestions by referring to the user's past appointment history. For example, the proposal unit can analyze the user's past appointment history and find specific patterns. For example, the proposal unit can make optimal suggestions based on the user's past appointment history. Furthermore, the proposal unit can refer to the user's past appointment history and make suggestions tailored to the user's preferences. In this way, the optimal suggestion can be provided by referring to the past appointment history. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can make suggestions using an AI model that takes the user's past appointment history as input and outputs the optimal suggestion.

[0096] The suggestion unit can estimate the user's emotions and determine appointment priorities based on those emotions. For example, if the user is nervous, the suggestion unit can display important appointments at the top. If the user is relaxed, the suggestion unit can allow the user to freely customize appointment priorities. Also, if the user is in a hurry, the suggestion unit can display urgent appointments at the top. This provides appointment priorities that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can take the user's emotions as input and determine priorities using an AI model that determines appointment priorities.

[0097] The proposal unit can suggest the most suitable appointment by considering the user's geographical location information. For example, if the user is nearby, the proposal unit can suggest a high-priority appointment. For example, if the user is far away, the proposal unit can suggest a low-priority appointment. The proposal unit can also suggest the most suitable appointment based on the user's geographical location information. In this way, the optimal appointment can be provided by considering the user's geographical location information. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can make suggestions using an AI model that takes the user's geographical location information as input and outputs the most suitable appointment.

[0098] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0099] The analysis unit can improve the accuracy of its analysis of received emails by considering the sender's past behavioral patterns. For example, the analysis unit can analyze what kinds of emails the sender has sent in the past and find specific patterns. For example, the analysis unit can refer to the content of emails the sender has sent in the past and analyze similar content. Furthermore, the analysis unit can determine the importance and urgency of an email based on the sender's past behavioral patterns. This improves the accuracy of the analysis by referring to the sender's past behavioral patterns. Some or all of the above processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the sender's past behavioral patterns as input and perform the analysis using an AI model that improves the accuracy of the analysis.

[0100] The generation unit can estimate the user's emotions and adjust the format of the reply email template based on the estimated emotions. For example, if the user is angry, the generation unit can generate a simple and highly visible reply template. For example, if the user is relaxed, the generation unit can generate a reply template with detailed information. Furthermore, if the user is in a hurry, the generation unit can generate a reply template with a concise format. This allows for the generation of reply email templates with formats that match the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generative AI or not. For example, the generation unit can take the user's emotions as input and adjust the format of the reply email template using an AI model.

[0101] The flagging unit can detect specific keywords based on the content of an email and flag it based on those keywords. For example, if the email content contains keywords such as "urgent" or "important," the flagging unit will flag it as urgent. For example, if the email content contains keywords such as "confirm" or "reply," the flagging unit can flag it as important. Also, if the email content contains keywords such as "meeting" or "appointment," the flagging unit can flag it as schedule-related. This improves the accuracy of flagging by detecting specific keywords based on the content of the email and flagging them accordingly. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can take the email content as input and flag it using an AI model that detects keywords.

[0102] The integration unit, when integrating with the schedule management function, can refer to the user's past schedule data to propose an optimal schedule. For example, the integration unit can analyze the user's past schedule data and find specific patterns. For example, the integration unit can propose an optimal schedule based on the user's past schedule data. Furthermore, the integration unit can refer to the user's past schedule data and propose a schedule tailored to the user's preferences. In this way, by referring to past schedule data, it can provide an optimal schedule. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's past schedule data as input and propose a schedule using an AI model that proposes an optimal schedule.

[0103] The proposal department can adjust its proposals to reflect the user's current situation when confirming or suggesting changes to appointments. For example, if the user is busy, the proposal department can provide concise and to-the-point proposals. If the user is relaxed, the proposal department can provide proposals that include detailed information. If the user is in a hurry, the proposal department can provide proposals that can be addressed quickly. This allows the proposal department to provide content tailored to the user's current situation. Some or all of the above processing in the proposal department may be performed using AI or not. For example, the proposal department can use an AI model that takes the user's current situation as input and adjusts the proposal content accordingly.

[0104] The analysis unit can estimate the sender's emotions when analyzing the content of an incoming email and adjust the analysis algorithm based on those emotions. For example, if the sender is angry, the analysis unit can select an algorithm that performs a rapid analysis. For example, if the sender is relaxed, the analysis unit can select an algorithm that performs a detailed analysis. Furthermore, if the sender is in a hurry, the analysis unit can select an algorithm that produces results in the shortest possible time. This allows for the selection of an analysis algorithm that corresponds to the sender's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the analysis unit may be performed using AI or not. For example, the analysis unit can take the sender's emotions as input and adjust the algorithm using an AI model that adjusts the analysis algorithm.

[0105] The generation unit can optimize the content of reply email templates by referring to the user's past reply history when generating reply email templates. For example, the generation unit can generate a new template based on reply templates previously used by the user. For example, the generation unit can analyze the user's past reply history and reflect frequently used phrases in the template. The generation unit can also find specific patterns based on the user's past reply history and reflect them in the template. This allows for the generation of more appropriate reply email templates by reflecting the user's past reply history. Some or all of the above processing in the generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the generation unit can generate templates using a generation AI model that takes the user's past reply history as input and outputs reply email templates.

[0106] The flagging unit can estimate the user's emotions and adjust the color and shape of the flag based on the estimated emotions. For example, if the user is stressed, the flagging unit can use a simple color and shape of flag. If the user is relaxed, the flagging unit can use a colorful and visually appealing flag. If the user is in a hurry, the flagging unit can use a flag with a conspicuous color and shape. This allows the flag color and shape to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the flagging unit may be performed using AI or not. For example, the flagging unit can adjust the flag using an AI model that takes the user's emotions as input and adjusts the color and shape of the flag.

[0107] The integration unit can optimize schedule data by considering the user's device information when integrating with the schedule management function. For example, if the user is using a smartphone, the integration unit can provide a display method for schedule data that is adapted to the screen size. For example, if the user is using a tablet, the integration unit can provide a display method for schedule data optimized for a larger screen. Furthermore, if the user is using a smartwatch, the integration unit can provide a concise and highly visible display method for schedule data. In this way, optimal schedule data can be provided by considering the user's device information. Some or all of the above processing in the integration unit may be performed using AI or not. For example, the integration unit can take the user's device information as input and perform optimization using an AI model that optimizes schedule data.

[0108] The proposal unit can estimate the user's emotions when confirming or suggesting changes to appointments, and adjust the proposal content based on the estimated emotions. For example, if the user is nervous, the proposal unit can provide a simple and highly visible proposal method. For example, if the user is relaxed, the proposal unit can provide a proposal method that includes detailed information. Furthermore, if the user is in a hurry, the proposal unit can provide a proposal method that gets straight to the point. This allows for the provision of appointment proposal methods that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can take the user's emotions as input and adjust the proposal method using an AI model that adjusts the appointment proposal method.

[0109] The following briefly describes the processing flow for example form 2.

[0110] Step 1: The analysis unit analyzes the content of the received email. The analysis unit uses natural language processing technology to analyze the email body, subject, and sender information to understand the email's content. For example, it can use keyword extraction technology to extract important information and sentiment analysis technology to analyze the sentiment of the email. Step 2: The generation unit generates a reply email template based on the analysis performed by the analysis unit. The generation unit can generate standard reply templates, and can also estimate the user's emotions and generate a reply email template based on those emotions. For example, if the user is angry, it will generate a reply template with a calm tone. Processing in the generation unit may also be performed using generation AI. Step 3: The flagging unit flags incoming emails based on specific criteria derived from the analysis performed by the analysis unit. The flagging unit can determine the priority and urgency of emails based on the sender's job title and the content of the email, and then flag them accordingly. For example, if the sender has a high job title, it will be flagged as important, and if the content of the email is urgent, it will be flagged as urgent. Processing in the flagging unit may also be performed using AI.

[0111] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0112] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0113] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0114] For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can also be implemented by the control unit 46A of the smart device 14. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit can also be implemented by the control unit 46A of the smart device 14. The flagging unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the flagging unit can also be implemented by the control unit 46A of the smart device 14. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0115] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0116] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0117] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0118] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0119] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0120] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0121] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0122] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0123] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0124] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0125] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0126] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0128] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0129] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0130] For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can also be implemented by the control unit 46A of the smart glasses 214. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit can also be implemented by the control unit 46A of the smart glasses 214. The flagging unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the flagging unit can also be implemented by the control unit 46A of the smart glasses 214. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0131] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0132] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0134] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0135] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0137] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0138] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0139] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0140] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0141] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0142] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0146] For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can also be implemented by the control unit 46A of the headset terminal 314. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit can also be implemented by the control unit 46A of the headset terminal 314. The flagging unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the flagging unit can also be implemented by the control unit 46A of the headset terminal 314. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0147] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0148] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0149] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0151] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0153] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0154] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0155] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0156] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0157] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0158] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0160] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0163] For example, the analysis unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the analysis unit can also be implemented by the control unit 46A of the robot 414. The generation unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the generation unit can also be implemented by the control unit 46A of the robot 414. The flagging unit is implemented by the specific processing unit 290 of the data processing device 12. For example, the flagging unit can also be implemented by the control unit 46A of the robot 414. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0164] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0165] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0166] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0167] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0168] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0169] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0170] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0171] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0172] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0173] 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.

[0174] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0175] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0176] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0177] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0178] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0179] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0180] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0181] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0182] (Note 1) An analysis unit that analyzes the content of received emails, A generation unit generates a template for a reply email to the received email based on the content analyzed by the analysis unit, The system includes a flagging unit that flags received emails based on specific criteria derived from the analysis performed by the aforementioned analysis unit. A system characterized by the following features. (Note 2) The aforementioned flagging unit is Determine the priority or urgency of an email specifically based on the sender's job title or the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 3) It integrates with the schedule management function, The system further includes a linking unit that specifically updates the schedule data based on the analysis performed by the aforementioned analysis unit. The system described in Appendix 1, characterized by the features described herein. (Note 4) We also have a proposal department that handles appointment confirmations and specific change proposals. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is It estimates the user's emotions and generates a reply email template based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, Apply a specific analysis algorithm based on the content of the email. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, The system estimates the user's emotions and selects an analysis algorithm based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, When analyzing the content of received emails, we improve the accuracy of the analysis by specifically considering the time of day and frequency of email transmission. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, During the analysis, not only the email body but also the contents of attached files will be specifically included in the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During analysis, the sender's past email history is specifically referenced to improve analysis accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned analysis unit, During analysis, the analysis algorithm is adjusted to specifically consider the language and cultural background of the email. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is It estimates the user's emotions and adjusts the tone of the reply email template based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is When generating the reply email template, the user's past reply history will be reflected. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating the reply email template, it automatically attaches relevant links and documents. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is It estimates the user's sentiment and adjusts the length of the reply email template based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is During generation, the user's signature and pre-written phrases are automatically inserted into the reply email template. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is When generating, provide reply options in multiple languages ​​for the reply email template. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned flagging unit is It estimates the user's emotions and adjusts the color and shape of the flag based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned flagging unit is When flagging emails, the accuracy of the flagging is improved by referencing the sender's past flagging history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned flagging unit is When flagging emails, assign different flags depending on the importance of the email content. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned flagging unit is It estimates the user's emotions and adjusts the display order of flags based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned flagging unit is When flagging emails, the sender's geographical location information should be specifically considered. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned flagging unit is When flagging emails, specifically referencing related literature and materials improves the accuracy of the flagging process. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned linkage unit is, It estimates the user's emotions and adjusts the frequency of schedule data updates based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned linkage unit is, During integration, the system selects the optimal update method by referring to the historical history of the schedule data. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned linkage unit is, It estimates the user's emotions and adjusts how schedule data is displayed based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned linkage unit is, When integrating, the system optimizes schedule data by taking into account the user's device information. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned proposal section is, It estimates the user's emotions and adjusts the appointment proposal method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 30) The aforementioned proposal section is, When making a proposal, we refer to the user's past appointment history to make the most suitable proposal. The system described in Appendix 3, characterized by the features described herein. (Note 31) The aforementioned proposal section is, It estimates the user's emotions and determines appointment priorities based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 32) The aforementioned proposal section is, When making a proposal, we take the user's geographical location into consideration to suggest the most suitable appointment. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0183] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. An analysis unit that analyzes the content of received emails, A generation unit generates a template for a reply email to the received email based on the content analyzed by the analysis unit, The system includes a flagging unit that flags the received emails based on specific criteria derived from the analysis performed by the analysis unit. A system characterized by the following features.

2. The aforementioned flagging unit is Determine the priority or urgency of an email specifically based on the sender's job title or the content of the email. The system according to feature 1.

3. It integrates with the schedule management function, The system further includes a linking unit that specifically updates the schedule data based on the analysis performed by the aforementioned analysis unit. The system according to feature 1.

4. We also have a proposal department that handles appointment confirmations and specific change proposals. The system according to feature 1.

5. The generating unit is It estimates the user's emotions and generates a reply email template based on the estimated emotions. The system according to feature 1.

6. The aforementioned analysis unit, Apply a specific analysis algorithm based on the content of the email. The system according to feature 1.

7. The aforementioned analysis unit, The system estimates the user's emotions and selects an analysis algorithm based on those estimated emotions. The system according to feature 1.

8. The aforementioned analysis unit, When analyzing the content of the received emails, the accuracy of the analysis will be improved by specifically considering the time of day and frequency of email transmission. The system according to feature 1.

9. The aforementioned analysis unit, During the analysis, not only the email body but also the contents of attached files will be specifically included in the analysis. The system according to feature 1.

Images