system

Abstract

The system according to this embodiment aims to quickly and appropriately create email and chat replies. [Solution] The system according to the embodiment comprises an acquisition unit, a generation unit, a proposal unit, a modification unit, a check unit, and a recommendation unit. The acquisition unit acquires the content of received emails or chats. The generation unit generates a reply to the email or chat whose content has been acquired by the acquisition unit. The proposal unit proposes the reply generated by the generation unit. The modification unit accepts modifications to the reply proposed by the proposal unit and modifies the reply. The check unit checks the grammar and expression of the reply modified by the modification unit. The recommendation unit recommends business terms or business phrases.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it takes time to create replies to emails and chats, which may reduce the efficiency of business communication.

[0005] The system according to the embodiment aims to quickly and appropriately create replies to emails and chats. [[ID=四十ー]]

Means for Solving the Problems

[0006] The system according to the embodiment comprises an acquisition unit, a generation unit, a proposal unit, a modification unit, a checking unit, and a recommendation unit. The acquisition unit acquires the content of received emails or chats. The generation unit generates a reply to the email or chat whose content has been acquired by the acquisition unit. The proposal unit proposes the reply generated by the generation unit. The modification unit accepts modifications to the reply proposed by the proposal unit and modifies the reply. The checking unit checks the grammar and expression of the reply modified by the modification unit. The recommendation unit recommends business terms or business phrases. [Effects of the Invention]

[0007] The system according to this embodiment can quickly and appropriately create email and chat replies. [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, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The business communication support system according to an embodiment of the present invention is a system that analyzes the content of received emails and chats and proposes a quick and appropriate reply. The business communication support system acquires the content of received emails and chats and generates a reply based on the acquired content. The generated reply is proposed to the user, and the user can make revisions. The revised reply is checked for grammar and expression and finally provided to the user. For example, the business communication support system acquires the content of received emails and chats. At this time, the AI ​​analyzes the content and extracts important information. For example, in the case of a business email, the sender's name, company name, and inquiry content are extracted. This organizes the information necessary for the reply. Next, a reply is generated based on the acquired content. The AI ​​recommends business terms and phrases and generates an appropriate reply. For example, a reply can be generated using a template based on a business scenario, such as answering an inquiry or scheduling a meeting. The generated reply is proposed to the user. The user can revise the proposed reply. For example, the user can add additional information or change the expression of the reply generated by the AI. The revised reply is checked for grammar and expression. The AI ​​checks whether the grammar and expression of the reply are appropriate and proposes revisions as necessary. Furthermore, the AI ​​can also check whether the content of replies is legally sound. For example, it can verify that replies containing contractual content or legal advice are legally sound. This reduces the risks associated with business communication. This system improves the efficiency of business communication, enabling quick and appropriate responses. For example, users can select the best reply from multiple replies generated by the AI. It can also generate new replies based on multiple replies selected by the user. This allows users to achieve more effective business communication. As a result, the business communication support system can analyze the content of received emails and chats, suggest quick and appropriate replies, recommend business terminology and phrases, and check grammar and expression.

[0029] The business communication support system according to the embodiment comprises an acquisition unit, a generation unit, a proposal unit, a modification unit, a check unit, and a recommendation unit. The acquisition unit acquires the content of received emails or chats. The acquisition unit can acquire emails or chats in formats such as text format, HTML format, business chat, and personal chat. The generation unit generates replies to emails or chats whose content has been acquired by the acquisition unit. The generation unit can generate replies using, for example, template-based generation or natural language generation technology. The proposal unit proposes replies generated by the generation unit. The proposal unit can make suggestions based on, for example, the user's past reply history or AI-generated suggestions. The modification unit accepts requests for modification of replies proposed by the proposal unit and modifies the replies. The modification unit can make modifications based on, for example, user input or automatic modifications by AI. The check unit checks the grammar and expression of replies modified by the modification unit. The check unit can make checks using, for example, a grammar checker or a style guide. The recommendation unit recommends business terms or business phrases. The recommendation function can, for example, recommend industry-specific terminology or common business phrases. This enables the business communication support system according to the embodiment to analyze the content of received emails and chats, and to quickly suggest appropriate replies, recommend business terms and phrases, and check grammar and expression.

[0030] The retrieval unit retrieves the content of received emails or chats. The retrieval unit can retrieve emails and chats in various formats, such as text, HTML, business chat, and personal chat. Specifically, the retrieval unit works with email and chat servers to automatically detect new messages in the inbox and retrieve their content. For text-formatted emails, it directly retrieves the text data of the body; for HTML-formatted emails, it parses HTML tags to extract text data. For business and personal chats, it retrieves message data via APIs and collects metadata (sender, recipient, timestamp, etc.) as needed. Furthermore, the retrieval unit performs spam filtering and importance assessment, prioritizing the processing of high-priority messages. This allows the retrieval unit to efficiently retrieve the content of emails and chats in diverse formats and provide the data necessary for subsequent processing.

[0031] The generation unit generates replies to emails or chats whose content has been retrieved by the acquisition unit. The generation unit can generate replies using, for example, template-based generation or natural language generation technology. Specifically, in template-based generation, pre-prepared reply templates are used, and the appropriate template is selected according to the content of the retrieved message, with the necessary information filled in. When using natural language generation technology, the generation unit utilizes an AI model to analyze the content of the retrieved message and automatically generate a contextually appropriate reply. For example, the generation unit uses natural language processing technology to understand the intent of the message and construct an appropriate reply. Furthermore, the generation unit can also learn the user's past reply history and style to generate personalized replies. This allows the generation unit to automatically generate quick and appropriate replies, improving the user's communication efficiency.

[0032] The suggestion unit proposes replies generated by the generation unit. The suggestion unit can, for example, make suggestions based on the user's past reply history or AI-generated suggestions. Specifically, the suggestion unit presents the user with multiple reply options generated by the generation unit and assists in selecting the most appropriate reply. It analyzes the user's past reply history and, by referring to past replies in similar situations, prioritizes suggesting the most appropriate reply option. In addition, AI-generated suggestions select the reply that best fits the context and tone from the generated options and present it to the user. Furthermore, the suggestion unit can collect user feedback and continuously improve the accuracy of its suggestions. This allows the suggestion unit to help users select quick and appropriate replies, thereby improving the quality of communication.

[0033] The editing unit receives and modifies replies proposed by the proposal unit. The editing unit can perform modifications based on user input or automated modifications using AI. Specifically, when a user modifies a proposed reply, the editing unit reflects the user's input in real time and saves the modifications. AI-powered automated modifications detect grammatical and stylistic errors and automatically suggest corrections. For example, it can use a grammar checker to detect grammatical errors and suggest appropriate corrections. It can also perform modifications based on style guides to ensure the replies are appropriate for business communication. This allows the editing unit to help users quickly and accurately modify replies, thereby improving the quality of communication.

[0034] The checking unit checks the grammar and expression of the reply corrected by the editing unit. The checking unit can, for example, use a grammar checker or perform checks based on a style guide. Specifically, the checking unit runs the corrected reply through a grammar checker to detect grammatical errors and inappropriate expressions. Furthermore, it verifies, based on a style guide, whether expressions and tones appropriate for business communication are used. For example, it checks for the use of honorifics and the presence of appropriate greetings. The checking unit can also notify the user of any detected problems and suggest corrections. This allows the checking unit to ensure the quality of the reply and improve the reliability of business communication.

[0035] The recommendation system recommends business terms or phrases. For example, it can recommend industry-specific terminology or general business phrases. Specifically, the recommendation system presents appropriate business terms and phrases in real time as the user is composing a reply. For industry-specific terminology, it extracts specialized terms from a database for specific industries or fields and recommends them at the appropriate time. For general business phrases, it presents commonly used expressions and standard phrases to help the user quickly compose a reply. Furthermore, the recommendation system can learn from the user's past usage history and provide personalized recommendations. This allows the recommendation system to help users use appropriate business terms and phrases, improving the quality of communication.

[0036] The checking unit can check expressions based on the cultural background of the sender of an email or chat. The checking unit checks expressions considering, for example, the sender's nationality, language, religion, and regional customs. This makes it possible to check expressions based on the sender's cultural background. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input data about the sender's cultural background into the AI ​​and have the AI ​​perform the check for appropriate expressions.

[0037] The checking unit can verify whether the content of the reply is legally sound. For example, the checking unit may check the content of the reply based on specific laws and regulations. The checking unit may also review the content of the reply under the supervision of the legal department. This reduces the risks of business communication by checking whether the content of the reply is legally sound. Some or all of the above processes in the checking unit may be performed using AI or not. For example, the checking unit can input the content of the reply into an AI and have the AI ​​check whether there are any legal issues.

[0038] The generation unit generates multiple types of replies, and the suggestion unit can suggest that the user select one or more of the multiple types of replies generated by the generation unit. The generation unit generates multiple types of replies, such as replies with different tones or styles, or replies with different content. The suggestion unit suggests that the user can select from the multiple types of replies generated by the generation unit. This allows for more appropriate replies by generating multiple types of replies and making suggestions that the user can choose from. 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 input prompts to the generation AI and have it generate multiple types of replies.

[0039] The generation unit generates a new reply by combining two or more replies selected by the user from among several types of replies, and the suggestion unit can propose the new reply generated by the generation unit. The generation unit generates the new reply by, for example, combining elements of the selected replies or by AI generation. The suggestion unit proposes the new reply generated by the generation unit to the user. This enables more effective business communication by generating and proposing a new reply based on multiple replies selected by the user. 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 input a prompt to the generation AI and have it generate a new reply based on the selected replies.

[0040] The generation unit can use templates based on business scenarios tailored to the sender of the email or chat. For example, the generation unit generates replies using templates based on business scenarios such as sales emails, support emails, and follow-up emails. This ensures that appropriate replies are generated by using business scenario-based templates tailored to the sender. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input prompts into the generation AI, causing it to generate replies using business scenario-based templates.

[0041] The retrieval unit can analyze the content of received emails and chats and determine the priority of retrieval based on importance. For example, the retrieval unit can prioritize the retrieval of important business-related messages. The retrieval unit can prioritize the retrieval of messages from superiors or important business partners. Based on the content of the messages, the retrieval unit can prioritize the retrieval of messages with high urgency. In this way, by determining the priority of retrieval based on importance, important messages can be retrieved preferentially. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input the content of received emails and chats into AI and have it determine the priority of retrieval based on importance.

[0042] The retrieval unit can extract important information by referring to the sender's past communication history in emails and chats. For example, the retrieval unit can refer to the sender's past communication history and extract and retrieve important keywords. Based on past interactions with the sender, the retrieval unit can prioritize the retrieval of important messages. The retrieval unit can analyze the sender's past communication history and extract and retrieve important information. In this way, important information can be extracted and retrieved by referring to the sender's past communication history. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input the sender's past communication history into AI and have it extract important information.

[0043] The retrieval unit can prioritize the retrieval of highly relevant content based on the geographical location information of the sender of emails and chats. For example, the retrieval unit can prioritize the retrieval of messages from nearby senders based on the sender's geographical location information. The retrieval unit can prioritize the retrieval of messages from senders in the same time zone, taking the sender's geographical location information into consideration. The retrieval unit can prioritize the retrieval of highly relevant messages by referring to the sender's geographical location information. In this way, by considering the sender's geographical location information, highly relevant messages can be prioritized. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input the sender's geographical location information into AI and have it prioritize the retrieval of highly relevant content.

[0044] The acquisition unit can analyze a user's social media activity and retrieve relevant emails and chats. For example, the acquisition unit can analyze a user's social media activity and prioritize the retrieval of relevant messages. The acquisition unit can retrieve relevant emails and chats based on the user's interests on social media. The acquisition unit can refer to a user's social media activity history and prioritize the retrieval of highly relevant messages. In this way, relevant messages can be prioritized by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the user's social media activity data into AI and have it retrieve relevant emails and chats.

[0045] The generation unit can adjust the level of detail in replies based on the importance of the content of emails and chats. For example, the generation unit can generate detailed replies for important emails and chats. For general inquiries, the generation unit can generate concise replies. For urgent messages, the generation unit can generate short messages to allow for quick responses. This ensures that appropriate replies are generated by adjusting the level of detail in replies based on the importance of the content of emails and chats. 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 input the content of emails and chats into a generation AI and have it adjust the level of detail in replies based on their importance.

[0046] The generation unit can apply different reply algorithms depending on the category of the email or chat. For example, the generation unit can generate replies that include business terminology for business-related emails. For casual chats, it can generate replies that include friendly language. For technical inquiries, it can generate replies that include technical terms. In this way, appropriate replies are generated by applying different reply algorithms depending on the category of the email or chat. 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 input the category of the email or chat into a generation AI and have it apply an appropriate reply algorithm.

[0047] The generation unit can determine the priority of replies based on when emails and chats were sent. For example, the generation unit may prioritize replies to recently sent messages. The generation unit may postpone older messages. The generation unit may prioritize replies to messages that are urgent. In this way, appropriate replies are generated by determining the priority of replies based on when emails and chats were sent. 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 input the sending dates of emails and chats into a generation AI and have it determine the priority of replies.

[0048] The generation unit can adjust the order of replies based on the relevance of emails and chats. For example, the generation unit can prioritize replying to highly relevant messages. The generation unit can postpone replying to less relevant messages. The generation unit can prioritize replying to highly relevant messages and reply to other messages later. This allows for the generation of appropriate replies by adjusting the order of replies based on the relevance of emails and chats. 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 input the relevance of emails and chats into a generation AI and have it adjust the order of replies.

[0049] The suggestion unit can select the most suitable suggestion by referring to the user's past reply history. For example, the suggestion unit can refer to the user's past reply history and suggest similar replies. The suggestion unit can suggest the most suitable reply based on the user's past reply history. The suggestion unit can analyze the user's past reply history and suggest the most appropriate reply. In this way, the optimal suggestion is made by referring to the user's past reply history. Some or all of the above processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the user's past reply history into AI and have it select the most suitable suggestion.

[0050] The suggestion department can make suggestions by considering the attribute information of the sender of emails and chats. For example, the suggestion department can consider the sender's job title and position and suggest an appropriate reply. The suggestion department can consider the sender's industry and field of expertise and suggest a reply that includes specialized terminology. The suggestion department can suggest the optimal reply based on the sender's past interactions. In this way, appropriate suggestions are made by considering the sender's attribute information. Some or all of the above processes in the suggestion department may be performed using AI or not. For example, the suggestion department can input the sender's attribute information into AI and have it make appropriate suggestions.

[0051] The suggestion unit can make suggestions considering the geographical distribution of email and chat senders. For example, the suggestion unit can make highly relevant suggestions based on the geographical distribution of senders. The suggestion unit can prioritize displaying suggestions from senders in the same time zone, taking into account the geographical distribution of senders. The suggestion unit can make optimal suggestions by referring to the geographical distribution of senders. As a result, highly relevant suggestions are made by considering the geographical distribution of senders. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the geographical distribution of senders into AI and have it make appropriate suggestions.

[0052] The proposal unit can improve the accuracy of its proposals by referring to relevant literature in emails and chats. For example, the proposal unit can refer to literature related to the content of emails and chats and make the best proposal. The proposal unit can improve the accuracy of its proposals by referring to relevant literature based on the content of emails and chats. The proposal unit can make the best proposal based on literature related to the content of emails and chats. As a result, the accuracy of the proposals is improved by referring to relevant literature. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input relevant literature into AI to improve the accuracy of its proposals.

[0053] The correction unit can select the optimal correction method by referring to the user's past correction history. For example, the correction unit can refer to the user's past correction history and suggest similar corrections. The correction unit can suggest the optimal correction method based on the user's past correction history. The correction unit can analyze the user's past correction history and suggest the most appropriate correction method. In this way, the optimal correction method is selected by referring to the user's past correction history. Some or all of the above processes in the correction unit may be performed using AI or not. For example, the correction unit can input the user's past correction history into AI and have it select the optimal correction method.

[0054] The editing unit can apply different editing algorithms depending on the content of the email or chat. For example, it can suggest edits that include business terminology for business-related emails, friendly language for casual chats, and technical terminology for technical inquiries. By applying different editing algorithms depending on the content of the email or chat, appropriate edits are made. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input the content of the email or chat into an AI and have it apply an appropriate editing algorithm.

[0055] The editing unit can make corrections while considering the geographical location information of the sender of the email or chat. For example, the editing unit can make highly relevant corrections based on the sender's geographical location information. The editing unit can consider the sender's geographical location information and prioritize correcting messages from senders in the same time zone. The editing unit can refer to the sender's geographical location information and make the most appropriate corrections. This ensures that highly relevant corrections are made by considering the sender's geographical location information. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input the sender's geographical location information into AI and have it make appropriate corrections.

[0056] The editing unit can improve the accuracy of its corrections by referring to relevant literature in emails and chats. For example, the editing unit can refer to literature related to the content of emails and chats and make the optimal corrections. The editing unit can improve the accuracy of its corrections by referring to relevant literature based on the content of emails and chats. The editing unit can make the optimal corrections based on literature related to the content of emails and chats. As a result, the accuracy of the corrections is improved by referring to relevant literature. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input relevant literature into AI to improve the accuracy of its corrections.

[0057] The checking unit can check expressions based on the cultural background of the sender of emails and chats. For example, the checking unit can check for appropriate expressions considering the sender's cultural background. The checking unit can check for expressions that are not likely to cause misunderstandings based on the sender's cultural background. The checking unit can refer to the sender's cultural background and check for the most appropriate expression. This makes it possible to check expressions based on the sender's cultural background. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input data on the sender's cultural background into AI and have the AI ​​perform the check for appropriate expressions.

[0058] The checking unit can verify whether the content of emails and chats is legally compliant. For example, the checking unit can check the content of emails and chats based on specific laws and regulations. The checking unit can also review the content of emails and chats under the supervision of the legal department. This reduces the risks of business communication by checking whether the content of emails and chats is legally compliant. Some or all of the above processes in the checking unit may be performed using AI or not. For example, the checking unit can input the content of emails and chats into an AI and have the AI ​​check whether there are any legal issues.

[0059] The checking unit can perform checks while considering the geographical location information of the sender of emails and chats. For example, the checking unit can perform highly relevant checks based on the sender's geographical location information. The checking unit can prioritize checking messages from senders in the same time zone, taking the sender's geographical location information into consideration. The checking unit can refer to the sender's geographical location information to perform optimal checks. As a result, highly relevant checks are performed by considering the sender's geographical location information. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input the sender's geographical location information into AI and have it perform appropriate checks.

[0060] The checking unit can improve the accuracy of its checks by referring to relevant literature for emails and chats. For example, the checking unit can refer to literature related to the content of emails and chats and perform optimal checks. The checking unit can improve the accuracy of its checks by referring to relevant literature based on the content of emails and chats. The checking unit can perform optimal checks based on literature related to the content of emails and chats. As a result, the accuracy of the checks is improved by referring to relevant literature. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input relevant literature into AI to improve the accuracy of its checks.

[0061] The recommendation system can select the most appropriate business terms and phrases based on the content of emails and chats. For example, the recommendation system can recommend appropriate business terms and phrases based on the content of emails and chats. The recommendation system can recommend business terms and phrases related to the content of emails and chats. This ensures that appropriate recommendations are made by selecting the most appropriate business terms and phrases based on the content of emails and chats. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input the content of emails and chats into AI and have it select the most appropriate business terms and phrases.

[0062] The recommendation system can recommend the most suitable business terms and phrases by referring to the user's past usage history. For example, the recommendation system can refer to the user's past usage history and recommend similar business terms and phrases. The recommendation system can recommend the most suitable business terms and phrases based on the user's past usage history. The recommendation system can analyze the user's past usage history and recommend the most appropriate business terms and phrases. As a result, the most suitable business terms and phrases are recommended by referring to the user's past usage history. Some or all of the above processes in the recommendation system may be performed using AI or not. For example, the recommendation system can input the user's past usage history into AI and have it recommend the most suitable business terms and phrases.

[0063] The recommendation system can recommend the most appropriate business terms and phrases by considering the geographical location of the sender of an email or chat message. For example, the recommendation system can recommend highly relevant business terms and phrases based on the sender's geographical location. The recommendation system can also prioritize recommending business terms and phrases from senders in the same time zone, taking the sender's geographical location into consideration. The recommendation system can recommend the most appropriate business terms and phrases by referring to the sender's geographical location. This ensures that highly relevant business terms and phrases are recommended by considering the sender's geographical location. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input the sender's geographical location into AI and have it recommend the most appropriate business terms and phrases.

[0064] The recommendation system can improve the accuracy of business terms and phrases by referring to relevant literature in emails and chats. For example, the recommendation system can refer to literature related to the content of emails and chats and recommend the most appropriate business terms and phrases. The recommendation system can improve the accuracy of business terms and phrases by referring to relevant literature based on the content of emails and chats. The recommendation system can recommend the most appropriate business terms and phrases based on literature related to the content of emails and chats. This improves the accuracy of business terms and phrases by referring to relevant literature. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input relevant literature into AI to improve the accuracy of business terms and phrases.

[0065] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0066] Business communication support systems can further analyze a user's past reply history and suggest the most suitable reply template. For example, based on phrases and expressions frequently used by the user in the past, the system can suggest a suitable reply template. Furthermore, if the user communicates within a specific industry or field, the system can suggest templates that include industry-specific terminology and phrases. This allows users to quickly generate optimal replies based on their past communication style.

[0067] Business communication support systems can further generate replies by considering the sender's attribute information in emails and chats. For example, they can generate replies using appropriate honorifics and expressions, taking into account the sender's job title and position. They can also generate replies that include specialized terminology, taking into account the sender's industry and field of expertise. Furthermore, they can generate optimal replies based on the sender's past interactions. As a result, appropriate replies that take the sender's attribute information into account are generated, improving the quality of business communication.

[0068] Business communication support systems can further consider the geographical location of email and chat senders when generating replies. For example, they can generate replies containing highly relevant information based on the sender's geographical location. They can also prioritize replies from senders in the same time zone, taking the sender's geographical location into consideration. Furthermore, they can generate optimal replies by referencing the sender's geographical location. This results in the generation of appropriate replies that take the sender's geographical location into account, improving the quality of business communication.

[0069] The business communication support system can further generate replies by referencing relevant literature for email and chat content. For example, it can refer to industry guidelines and regulations related to the content of the email or chat and generate replies based on them. It can also refer to technical literature related to the content of the email or chat and generate replies that include specialized information. Furthermore, it can refer to past cases related to the content of the email or chat and generate optimal replies. This results in the generation of highly accurate replies that refer to relevant literature, improving the quality of business communication.

[0070] The business communication support system can further prioritize replies based on when emails and chats were sent. For example, it can prioritize replies to recently sent messages, while older messages can be postponed. Furthermore, it can prioritize replies to messages that are considered urgent. This ensures that replies are prioritized based on when emails and chats were sent, generating appropriate responses.

[0071] The following briefly describes the processing flow for example form 1.

[0072] Step 1: The retrieval unit retrieves the content of received emails or chats. The retrieval unit can retrieve emails and chats in various formats, such as text format, HTML format, business chat, and personal chat. Step 2: The generation unit generates a reply to the email or chat whose content was retrieved by the acquisition unit. The generation unit can generate the reply using, for example, template-based generation or natural language generation technology. Step 3: The suggestion unit proposes the reply generated by the generation unit. The suggestion unit can, for example, make suggestions based on the user's past reply history or AI-generated suggestions. Step 4: The revision unit receives and makes revisions to the response proposed by the proposal unit. The revision unit can, for example, make revisions based on user input or automated revisions by AI. Step 5: The checking unit checks the grammar and expression of the reply corrected by the editing unit. The checking unit can, for example, use a grammar checker or perform checks based on a style guide. Step 6: The recommendation team recommends business terms or phrases. For example, the recommendation team may recommend industry-specific terms or general business phrases.

[0073] (Example of form 2) The business communication support system according to an embodiment of the present invention is a system that analyzes the content of received emails and chats and proposes a quick and appropriate reply. The business communication support system acquires the content of received emails and chats and generates a reply based on the acquired content. The generated reply is proposed to the user, and the user can make revisions. The revised reply is checked for grammar and expression and finally provided to the user. For example, the business communication support system acquires the content of received emails and chats. At this time, the AI ​​analyzes the content and extracts important information. For example, in the case of a business email, the sender's name, company name, and inquiry content are extracted. This organizes the information necessary for the reply. Next, a reply is generated based on the acquired content. The AI ​​recommends business terms and phrases and generates an appropriate reply. For example, a reply can be generated using a template based on a business scenario, such as answering an inquiry or scheduling a meeting. The generated reply is proposed to the user. The user can revise the proposed reply. For example, the user can add additional information or change the expression of the reply generated by the AI. The revised reply is checked for grammar and expression. The AI ​​checks whether the grammar and expression of the reply are appropriate and proposes revisions as necessary. Furthermore, the AI ​​can also check whether the content of replies is legally sound. For example, it can verify that replies containing contractual content or legal advice are legally sound. This reduces the risks associated with business communication. This system improves the efficiency of business communication, enabling quick and appropriate responses. For example, users can select the best reply from multiple replies generated by the AI. It can also generate new replies based on multiple replies selected by the user. This allows users to achieve more effective business communication. As a result, the business communication support system can analyze the content of received emails and chats, suggest quick and appropriate replies, recommend business terminology and phrases, and check grammar and expression.

[0074] The business communication support system according to the embodiment comprises an acquisition unit, a generation unit, a proposal unit, a modification unit, a check unit, and a recommendation unit. The acquisition unit acquires the content of received emails or chats. The acquisition unit can acquire emails or chats in formats such as text format, HTML format, business chat, and personal chat. The generation unit generates replies to emails or chats whose content has been acquired by the acquisition unit. The generation unit can generate replies using, for example, template-based generation or natural language generation technology. The proposal unit proposes replies generated by the generation unit. The proposal unit can make suggestions based on, for example, the user's past reply history or AI-generated suggestions. The modification unit accepts requests for modification of replies proposed by the proposal unit and modifies the replies. The modification unit can make modifications based on, for example, user input or automatic modifications by AI. The check unit checks the grammar and expression of replies modified by the modification unit. The check unit can make checks using, for example, a grammar checker or a style guide. The recommendation unit recommends business terms or business phrases. The recommendation function can, for example, recommend industry-specific terminology or common business phrases. This enables the business communication support system according to the embodiment to analyze the content of received emails and chats, and to quickly suggest appropriate replies, recommend business terms and phrases, and check grammar and expression.

[0075] The retrieval unit retrieves the content of received emails or chats. The retrieval unit can retrieve emails and chats in various formats, such as text, HTML, business chat, and personal chat. Specifically, the retrieval unit works with email and chat servers to automatically detect new messages in the inbox and retrieve their content. For text-formatted emails, it directly retrieves the text data of the body; for HTML-formatted emails, it parses HTML tags to extract text data. For business and personal chats, it retrieves message data via APIs and collects metadata (sender, recipient, timestamp, etc.) as needed. Furthermore, the retrieval unit performs spam filtering and importance assessment, prioritizing the processing of high-priority messages. This allows the retrieval unit to efficiently retrieve the content of emails and chats in diverse formats and provide the data necessary for subsequent processing.

[0076] The generation unit generates replies to emails or chats whose content has been retrieved by the acquisition unit. The generation unit can generate replies using, for example, template-based generation or natural language generation technology. Specifically, in template-based generation, pre-prepared reply templates are used, and the appropriate template is selected according to the content of the retrieved message, with the necessary information filled in. When using natural language generation technology, the generation unit utilizes an AI model to analyze the content of the retrieved message and automatically generate a contextually appropriate reply. For example, the generation unit uses natural language processing technology to understand the intent of the message and construct an appropriate reply. Furthermore, the generation unit can also learn the user's past reply history and style to generate personalized replies. This allows the generation unit to automatically generate quick and appropriate replies, improving the user's communication efficiency.

[0077] The suggestion unit proposes replies generated by the generation unit. The suggestion unit can, for example, make suggestions based on the user's past reply history or AI-generated suggestions. Specifically, the suggestion unit presents the user with multiple reply options generated by the generation unit and assists in selecting the most appropriate reply. It analyzes the user's past reply history and, by referring to past replies in similar situations, prioritizes suggesting the most appropriate reply option. In addition, AI-generated suggestions select the reply that best fits the context and tone from the generated options and present it to the user. Furthermore, the suggestion unit can collect user feedback and continuously improve the accuracy of its suggestions. This allows the suggestion unit to help users select quick and appropriate replies, thereby improving the quality of communication.

[0078] The editing unit receives and modifies replies proposed by the proposal unit. The editing unit can perform modifications based on user input or automated modifications using AI. Specifically, when a user modifies a proposed reply, the editing unit reflects the user's input in real time and saves the modifications. AI-powered automated modifications detect grammatical and stylistic errors and automatically suggest corrections. For example, it can use a grammar checker to detect grammatical errors and suggest appropriate corrections. It can also perform modifications based on style guides to ensure the replies are appropriate for business communication. This allows the editing unit to help users quickly and accurately modify replies, thereby improving the quality of communication.

[0079] The checking unit checks the grammar and expression of the reply corrected by the editing unit. The checking unit can, for example, use a grammar checker or perform checks based on a style guide. Specifically, the checking unit runs the corrected reply through a grammar checker to detect grammatical errors and inappropriate expressions. Furthermore, it verifies, based on a style guide, whether expressions and tones appropriate for business communication are used. For example, it checks for the use of honorifics and the presence of appropriate greetings. The checking unit can also notify the user of any detected problems and suggest corrections. This allows the checking unit to ensure the quality of the reply and improve the reliability of business communication.

[0080] The recommendation system recommends business terms or phrases. For example, it can recommend industry-specific terminology or general business phrases. Specifically, the recommendation system presents appropriate business terms and phrases in real time as the user is composing a reply. For industry-specific terminology, it extracts specialized terms from a database for specific industries or fields and recommends them at the appropriate time. For general business phrases, it presents commonly used expressions and standard phrases to help the user quickly compose a reply. Furthermore, the recommendation system can learn from the user's past usage history and provide personalized recommendations. This allows the recommendation system to help users use appropriate business terms and phrases, improving the quality of communication.

[0081] The checking unit can check expressions based on the cultural background of the sender of an email or chat. The checking unit checks expressions considering, for example, the sender's nationality, language, religion, and regional customs. This makes it possible to check expressions based on the sender's cultural background. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input data about the sender's cultural background into the AI ​​and have the AI ​​perform the check for appropriate expressions.

[0082] The checking unit can verify whether the content of the reply is legally sound. For example, the checking unit may check the content of the reply based on specific laws and regulations. The checking unit may also review the content of the reply under the supervision of the legal department. This reduces the risks of business communication by checking whether the content of the reply is legally sound. Some or all of the above processes in the checking unit may be performed using AI or not. For example, the checking unit can input the content of the reply into an AI and have the AI ​​check whether there are any legal issues.

[0083] The generation unit generates multiple types of replies, and the suggestion unit can suggest that the user select one or more of the multiple types of replies generated by the generation unit. The generation unit generates multiple types of replies, such as replies with different tones or styles, or replies with different content. The suggestion unit suggests that the user can select from the multiple types of replies generated by the generation unit. This allows for more appropriate replies by generating multiple types of replies and making suggestions that the user can choose from. 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 input prompts to the generation AI and have it generate multiple types of replies.

[0084] The generation unit generates a new reply by combining two or more replies selected by the user from among several types of replies, and the suggestion unit can propose the new reply generated by the generation unit. The generation unit generates the new reply by, for example, combining elements of the selected replies or by AI generation. The suggestion unit proposes the new reply generated by the generation unit to the user. This enables more effective business communication by generating and proposing a new reply based on multiple replies selected by the user. 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 input a prompt to the generation AI and have it generate a new reply based on the selected replies.

[0085] The generation unit can use templates based on business scenarios tailored to the sender of the email or chat. For example, the generation unit generates replies using templates based on business scenarios such as sales emails, support emails, and follow-up emails. This ensures that appropriate replies are generated by using business scenario-based templates tailored to the sender. Some or all of the above-described processes in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input prompts into the generation AI, causing it to generate replies using business scenario-based templates.

[0086] The retrieval unit can estimate the user's emotions and dynamically adjust the timing of email and chat retrieval based on the estimated emotions. For example, if the user is stressed, the retrieval unit will prioritize retrieving only important emails and chats, delaying other messages. If the user is relaxed, the retrieval unit can retrieve all emails and chats as usual. If the user is in a hurry, the retrieval unit can prioritize retrieving high-priority messages, retrieving other messages later. This reduces the user's burden by adjusting the timing of email and chat retrieval based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input user emotion data into AI and have the AI ​​adjust the retrieval timing.

[0087] The retrieval unit can analyze the content of received emails and chats and determine the priority of retrieval based on importance. For example, the retrieval unit can prioritize the retrieval of important business-related messages. The retrieval unit can prioritize the retrieval of messages from superiors or important business partners. Based on the content of the messages, the retrieval unit can prioritize the retrieval of messages with high urgency. In this way, by determining the priority of retrieval based on importance, important messages can be retrieved preferentially. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input the content of received emails and chats into AI and have it determine the priority of retrieval based on importance.

[0088] The retrieval unit can extract important information by referring to the sender's past communication history in emails and chats. For example, the retrieval unit can refer to the sender's past communication history and extract and retrieve important keywords. Based on past interactions with the sender, the retrieval unit can prioritize the retrieval of important messages. The retrieval unit can analyze the sender's past communication history and extract and retrieve important information. In this way, important information can be extracted and retrieved by referring to the sender's past communication history. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input the sender's past communication history into AI and have it extract important information.

[0089] The retrieval unit can estimate the user's emotions and dynamically determine the priority of emails and chats to retrieve based on the estimated emotions. For example, if the user is stressed, the retrieval unit will prioritize retrieving only important emails and chats, and postpone other messages. If the user is relaxed, the retrieval unit can retrieve all emails and chats as usual. If the user is in a hurry, the retrieval unit can prioritize retrieving high-priority messages, and retrieve other messages later. This reduces the user's burden by determining the priority of emails and chats to retrieve based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input user emotion data into an AI to determine the priority of emails and chats to retrieve.

[0090] The retrieval unit can prioritize the retrieval of highly relevant content based on the geographical location information of the sender of emails and chats. For example, the retrieval unit can prioritize the retrieval of messages from nearby senders based on the sender's geographical location information. The retrieval unit can prioritize the retrieval of messages from senders in the same time zone, taking the sender's geographical location information into consideration. The retrieval unit can prioritize the retrieval of highly relevant messages by referring to the sender's geographical location information. In this way, by considering the sender's geographical location information, highly relevant messages can be prioritized. Some or all of the above processing in the retrieval unit may be performed using AI or not. For example, the retrieval unit can input the sender's geographical location information into AI and have it prioritize the retrieval of highly relevant content.

[0091] The acquisition unit can analyze a user's social media activity and retrieve relevant emails and chats. For example, the acquisition unit can analyze a user's social media activity and prioritize the retrieval of relevant messages. The acquisition unit can retrieve relevant emails and chats based on the user's interests on social media. The acquisition unit can refer to a user's social media activity history and prioritize the retrieval of highly relevant messages. In this way, relevant messages can be prioritized by analyzing the user's social media activity. Some or all of the above processing in the acquisition unit may be performed using AI or not. For example, the acquisition unit can input the user's social media activity data into AI and have it retrieve relevant emails and chats.

[0092] The generation unit can estimate the user's emotions and adjust the wording of the reply based on the estimated emotions. For example, if the user is stressed, the generation unit can generate a concise and clear reply. If the user is relaxed, the generation unit can generate a reply that includes detailed information. If the user is in a hurry, the generation unit can generate a short message that allows for a quick reply. This allows for the generation of more appropriate replies by adjusting the wording of the reply based on 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 or without a generative AI. For example, the generation unit can input user emotion data into a generative AI and have it adjust the wording of the reply.

[0093] The generation unit can adjust the level of detail in replies based on the importance of the content of emails and chats. For example, the generation unit can generate detailed replies for important emails and chats. For general inquiries, the generation unit can generate concise replies. For urgent messages, the generation unit can generate short messages to allow for quick responses. This ensures that appropriate replies are generated by adjusting the level of detail in replies based on the importance of the content of emails and chats. 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 input the content of emails and chats into a generation AI and have it adjust the level of detail in replies based on their importance.

[0094] The generation unit can apply different reply algorithms depending on the category of the email or chat. For example, the generation unit can generate replies that include business terminology for business-related emails. For casual chats, it can generate replies that include friendly language. For technical inquiries, it can generate replies that include technical terms. In this way, appropriate replies are generated by applying different reply algorithms depending on the category of the email or chat. 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 input the category of the email or chat into a generation AI and have it apply an appropriate reply algorithm.

[0095] The generation unit can estimate the user's emotions and adjust the length of the reply based on the estimated emotions. For example, if the user is stressed, the generation unit can generate a short, to-the-point reply. If the user is relaxed, the generation unit can generate a longer reply that includes more detailed information. If the user is in a hurry, the generation unit can generate a short message that allows for a quick reply. By adjusting the length of the reply based on the user's emotions, a more appropriate reply is generated. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation 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 or without a generation AI. For example, the generation unit can input user emotion data into a generation AI and have it adjust the length of the reply.

[0096] The generation unit can determine the priority of replies based on when emails and chats were sent. For example, the generation unit may prioritize replies to recently sent messages. The generation unit may postpone older messages. The generation unit may prioritize replies to messages that are urgent. In this way, appropriate replies are generated by determining the priority of replies based on when emails and chats were sent. 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 input the sending dates of emails and chats into a generation AI and have it determine the priority of replies.

[0097] The generation unit can adjust the order of replies based on the relevance of emails and chats. For example, the generation unit can prioritize replying to highly relevant messages. The generation unit can postpone replying to less relevant messages. The generation unit can prioritize replying to highly relevant messages and reply to other messages later. This allows for the generation of appropriate replies by adjusting the order of replies based on the relevance of emails and chats. 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 input the relevance of emails and chats into a generation AI and have it adjust the order of replies.

[0098] The suggestion unit can estimate the user's emotions and adjust how suggestions are displayed based on those emotions. For example, if the user is stressed, the suggestion unit can provide a simple and highly visible display method. If the user is relaxed, the suggestion unit can provide a display method that includes detailed information. If the user is in a hurry, the suggestion unit can provide a display method that gets straight to the point. By adjusting how suggestions are displayed based on the user's emotions, more appropriate suggestions are made. 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 suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into AI and have it adjust how suggestions are displayed.

[0099] The suggestion unit can select the most suitable suggestion by referring to the user's past reply history. For example, the suggestion unit can refer to the user's past reply history and suggest similar replies. The suggestion unit can suggest the most suitable reply based on the user's past reply history. The suggestion unit can analyze the user's past reply history and suggest the most appropriate reply. In this way, the optimal suggestion is made by referring to the user's past reply history. Some or all of the above processes in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the user's past reply history into AI and have it select the most suitable suggestion.

[0100] The suggestion department can make suggestions by considering the attribute information of the sender of emails and chats. For example, the suggestion department can consider the sender's job title and position and suggest an appropriate reply. The suggestion department can consider the sender's industry and field of expertise and suggest a reply that includes specialized terminology. The suggestion department can suggest the optimal reply based on the sender's past interactions. In this way, appropriate suggestions are made by considering the sender's attribute information. Some or all of the above processes in the suggestion department may be performed using AI or not. For example, the suggestion department can input the sender's attribute information into AI and have it make appropriate suggestions.

[0101] The suggestion unit can estimate the user's emotions and prioritize suggestions based on those emotions. For example, if the user is stressed, the suggestion unit will prioritize displaying important suggestions. If the user is relaxed, the suggestion unit can display all suggestions normally. If the user is in a hurry, the suggestion unit can prioritize displaying suggestions of high urgency. This ensures that important suggestions are prioritized by prioritizing suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input user emotion data into an AI to determine the priority of suggestions.

[0102] The suggestion unit can make suggestions considering the geographical distribution of email and chat senders. For example, the suggestion unit can make highly relevant suggestions based on the geographical distribution of senders. The suggestion unit can prioritize displaying suggestions from senders in the same time zone, taking into account the geographical distribution of senders. The suggestion unit can make optimal suggestions by referring to the geographical distribution of senders. As a result, highly relevant suggestions are made by considering the geographical distribution of senders. Some or all of the above processing in the suggestion unit may be performed using AI or not. For example, the suggestion unit can input the geographical distribution of senders into AI and have it make appropriate suggestions.

[0103] The proposal unit can improve the accuracy of its proposals by referring to relevant literature in emails and chats. For example, the proposal unit can refer to literature related to the content of emails and chats and make the best proposal. The proposal unit can improve the accuracy of its proposals by referring to relevant literature based on the content of emails and chats. The proposal unit can make the best proposal based on literature related to the content of emails and chats. As a result, the accuracy of the proposals is improved by referring to relevant literature. Some or all of the above processing in the proposal unit may be performed using AI or not. For example, the proposal unit can input relevant literature into AI to improve the accuracy of its proposals.

[0104] The correction unit can estimate the user's emotions and adjust the correction method based on the estimated emotions. For example, if the user is stressed, the correction unit can provide concise and clear correction suggestions. If the user is relaxed, the correction unit can provide detailed correction suggestions. If the user is in a hurry, the correction unit can provide short suggestions for quick correction. This allows for more appropriate corrections by adjusting the correction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the correction unit may be performed using AI or not. For example, the correction unit can input user emotion data into AI and have it adjust the correction method.

[0105] The correction unit can select the optimal correction method by referring to the user's past correction history. For example, the correction unit can refer to the user's past correction history and suggest similar corrections. The correction unit can suggest the optimal correction method based on the user's past correction history. The correction unit can analyze the user's past correction history and suggest the most appropriate correction method. In this way, the optimal correction method is selected by referring to the user's past correction history. Some or all of the above processes in the correction unit may be performed using AI or not. For example, the correction unit can input the user's past correction history into AI and have it select the optimal correction method.

[0106] The editing unit can apply different editing algorithms depending on the content of the email or chat. For example, it can suggest edits that include business terminology for business-related emails, friendly language for casual chats, and technical terminology for technical inquiries. By applying different editing algorithms depending on the content of the email or chat, appropriate edits are made. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input the content of the email or chat into an AI and have it apply an appropriate editing algorithm.

[0107] The editing unit can estimate the user's emotions and determine the priority of corrections based on the estimated emotions. For example, if the user is stressed, the editing unit will prioritize important corrections. If the user is relaxed, the editing unit can perform all corrections as usual. If the user is in a hurry, the editing unit can prioritize corrections of high urgency. In this way, important corrections are prioritized by determining the priority of corrections based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input user emotion data into an AI and have it determine the priority of corrections.

[0108] The editing unit can make corrections while considering the geographical location information of the sender of the email or chat. For example, the editing unit can make highly relevant corrections based on the sender's geographical location information. The editing unit can consider the sender's geographical location information and prioritize correcting messages from senders in the same time zone. The editing unit can refer to the sender's geographical location information and make the most appropriate corrections. This ensures that highly relevant corrections are made by considering the sender's geographical location information. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input the sender's geographical location information into AI and have it make appropriate corrections.

[0109] The editing unit can improve the accuracy of its corrections by referring to relevant literature in emails and chats. For example, the editing unit can refer to literature related to the content of emails and chats and make the optimal corrections. The editing unit can improve the accuracy of its corrections by referring to relevant literature based on the content of emails and chats. The editing unit can make the optimal corrections based on literature related to the content of emails and chats. As a result, the accuracy of the corrections is improved by referring to relevant literature. Some or all of the above processing in the editing unit may be performed using AI or not. For example, the editing unit can input relevant literature into AI to improve the accuracy of its corrections.

[0110] The checking unit can estimate the user's emotions and adjust the grammar and expression checking method based on the estimated user emotions. For example, if the user is stressed, the checking unit can perform a concise and clear check. If the user is relaxed, the checking unit can perform a detailed check. If the user is in a hurry, the checking unit can provide short suggestions to allow for a quick check. This allows for more appropriate checking by adjusting the grammar and expression checking method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input user emotion data into AI and have it adjust the grammar and expression checking method.

[0111] The checking unit can check expressions based on the cultural background of the sender of emails and chats. For example, the checking unit can check for appropriate expressions considering the sender's cultural background. The checking unit can check for expressions that are not likely to cause misunderstandings based on the sender's cultural background. The checking unit can refer to the sender's cultural background and check for the most appropriate expression. This makes it possible to check expressions based on the sender's cultural background. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input data on the sender's cultural background into AI and have the AI ​​perform the check for appropriate expressions.

[0112] The checking unit can verify whether the content of emails and chats is legally compliant. For example, the checking unit can check the content of emails and chats based on specific laws and regulations. The checking unit can also review the content of emails and chats under the supervision of the legal department. This reduces the risks of business communication by checking whether the content of emails and chats is legally compliant. Some or all of the above processes in the checking unit may be performed using AI or not. For example, the checking unit can input the content of emails and chats into an AI and have the AI ​​check whether there are any legal issues.

[0113] The checking unit can estimate the user's emotions and determine the priority of grammatical and phrasal checks based on the estimated emotions. For example, if the user is stressed, the checking unit will prioritize important checks. If the user is relaxed, the checking unit can perform all checks as usual. If the user is in a hurry, the checking unit can prioritize high-urgency checks. This ensures that important checks are prioritized by determining the priority of grammatical and phrasal checks based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input user emotion data into an AI to determine the priority of grammatical and phrasal checks.

[0114] The checking unit can perform checks while considering the geographical location information of the sender of emails and chats. For example, the checking unit can perform highly relevant checks based on the sender's geographical location information. The checking unit can prioritize checking messages from senders in the same time zone, taking the sender's geographical location information into consideration. The checking unit can refer to the sender's geographical location information to perform optimal checks. As a result, highly relevant checks are performed by considering the sender's geographical location information. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input the sender's geographical location information into AI and have it perform appropriate checks.

[0115] The checking unit can improve the accuracy of its checks by referring to relevant literature for emails and chats. For example, the checking unit can refer to literature related to the content of emails and chats and perform optimal checks. The checking unit can improve the accuracy of its checks by referring to relevant literature based on the content of emails and chats. The checking unit can perform optimal checks based on literature related to the content of emails and chats. As a result, the accuracy of the checks is improved by referring to relevant literature. Some or all of the above processing in the checking unit may be performed using AI or not. For example, the checking unit can input relevant literature into AI to improve the accuracy of its checks.

[0116] The recommendation system can estimate the user's emotions and adjust its recommendation method for business terms and phrases based on those emotions. For example, if the user is stressed, the recommendation system will recommend concise and clear business terms and phrases. If the user is relaxed, it can recommend detailed business terms and phrases. If the user is in a hurry, it can recommend short business terms and phrases that can be used quickly. This allows for more appropriate recommendations by adjusting the recommendation method for business terms and phrases based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input user emotion data into an AI to adjust its recommendation method for business terms and phrases.

[0117] The recommendation system can select the most appropriate business terms and phrases based on the content of emails and chats. For example, the recommendation system can recommend appropriate business terms and phrases based on the content of emails and chats. The recommendation system can recommend business terms and phrases related to the content of emails and chats. This ensures that appropriate recommendations are made by selecting the most appropriate business terms and phrases based on the content of emails and chats. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input the content of emails and chats into AI and have it select the most appropriate business terms and phrases.

[0118] The recommendation system can recommend the most suitable business terms and phrases by referring to the user's past usage history. For example, the recommendation system can refer to the user's past usage history and recommend similar business terms and phrases. The recommendation system can recommend the most suitable business terms and phrases based on the user's past usage history. The recommendation system can analyze the user's past usage history and recommend the most appropriate business terms and phrases. As a result, the most suitable business terms and phrases are recommended by referring to the user's past usage history. Some or all of the above processes in the recommendation system may be performed using AI or not. For example, the recommendation system can input the user's past usage history into AI and have it recommend the most suitable business terms and phrases.

[0119] The recommendation system can estimate the user's emotions and prioritize business terms and phrases based on those emotions. For example, if the user is stressed, the recommendation system will prioritize recommending important business terms and phrases. If the user is relaxed, the recommendation system can recommend all business terms and phrases as usual. If the user is in a hurry, the recommendation system can prioritize recommending business terms and phrases of high urgency. This ensures that important terms and phrases are recommended preferentially by prioritizing them based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the recommendation system may be performed using AI or not. For example, the recommendation system can input user emotion data into an AI to determine the priority of business terms and phrases.

[0120] The recommendation system can recommend the most appropriate business terms and phrases by considering the geographical location of the sender of an email or chat message. For example, the recommendation system can recommend highly relevant business terms and phrases based on the sender's geographical location. The recommendation system can also prioritize recommending business terms and phrases from senders in the same time zone, taking the sender's geographical location into consideration. The recommendation system can recommend the most appropriate business terms and phrases by referring to the sender's geographical location. This ensures that highly relevant business terms and phrases are recommended by considering the sender's geographical location. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input the sender's geographical location into AI and have it recommend the most appropriate business terms and phrases.

[0121] The recommendation system can improve the accuracy of business terms and phrases by referring to relevant literature in emails and chats. For example, the recommendation system can refer to literature related to the content of emails and chats and recommend the most appropriate business terms and phrases. The recommendation system can improve the accuracy of business terms and phrases by referring to relevant literature based on the content of emails and chats. The recommendation system can recommend the most appropriate business terms and phrases based on literature related to the content of emails and chats. This improves the accuracy of business terms and phrases by referring to relevant literature. Some or all of the above processing in the recommendation system may be performed using AI or not. For example, the recommendation system can input relevant literature into AI to improve the accuracy of business terms and phrases.

[0122] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0123] Business communication support systems can further estimate the user's emotions and adjust the tone of their replies based on those estimates. For example, if a user is stressed, the system can generate a reply with a calmer, more reassuring tone. If a user is relaxed, the system can generate a reply with a more casual and friendly tone. If a user is in a hurry, the system can generate a concise and quick reply. This ensures that replies are delivered in an appropriate tone according to the user's emotions, improving the quality of business communication.

[0124] Business communication support systems can further analyze a user's past reply history and suggest the most suitable reply template. For example, based on phrases and expressions frequently used by the user in the past, the system can suggest a suitable reply template. Furthermore, if the user communicates within a specific industry or field, the system can suggest templates that include industry-specific terminology and phrases. This allows users to quickly generate optimal replies based on their past communication style.

[0125] Business communication support systems can further estimate the user's emotions and adjust the content of their replies based on those estimates. For example, if a user is stressed, the system can generate a concise reply summarizing important information. If the user is relaxed, the system can generate a reply containing detailed information. Furthermore, if the user is in a hurry, the system can generate a short message to allow for a quick response. This ensures that replies are appropriate to the user's emotions, improving the efficiency of business communication.

[0126] Business communication support systems can further generate replies by considering the sender's attribute information in emails and chats. For example, they can generate replies using appropriate honorifics and expressions, taking into account the sender's job title and position. They can also generate replies that include specialized terminology, taking into account the sender's industry and field of expertise. Furthermore, they can generate optimal replies based on the sender's past interactions. As a result, appropriate replies that take the sender's attribute information into account are generated, improving the quality of business communication.

[0127] The business communication support system can further estimate the user's emotions and prioritize replies based on those emotions. For example, if the user is stressed, the system can prioritize important replies and postpone others. If the user is relaxed, the system can generate all replies as usual. Also, if the user is in a hurry, the system can prioritize high-priority replies. This ensures that replies are prioritized based on the user's emotions, and important replies are delivered quickly.

[0128] Business communication support systems can further consider the geographical location of email and chat senders when generating replies. For example, they can generate replies containing highly relevant information based on the sender's geographical location. They can also prioritize replies from senders in the same time zone, taking the sender's geographical location into consideration. Furthermore, they can generate optimal replies by referencing the sender's geographical location. This results in the generation of appropriate replies that take the sender's geographical location into account, improving the quality of business communication.

[0129] The business communication support system can further estimate the user's emotions and adjust how replies are displayed based on those emotions. For example, if the user is stressed, the system can provide a simple and easy-to-read display. If the user is relaxed, the system can provide a display that includes detailed information. If the user is in a hurry, the system can provide a display that gets straight to the point. This adjusts how replies are displayed based on the user's emotions, resulting in more appropriate suggestions.

[0130] The business communication support system can further generate replies by referencing relevant literature for email and chat content. For example, it can refer to industry guidelines and regulations related to the content of the email or chat and generate replies based on them. It can also refer to technical literature related to the content of the email or chat and generate replies that include specialized information. Furthermore, it can refer to past cases related to the content of the email or chat and generate optimal replies. This results in the generation of highly accurate replies that refer to relevant literature, improving the quality of business communication.

[0131] The business communication support system can further estimate the user's emotions and adjust the length of the reply based on those emotions. For example, if the user is stressed, the system can generate a short, to-the-point reply. If the user is relaxed, the system can generate a longer reply that includes more detailed information. Also, if the user is in a hurry, the system can generate a short message to allow for a quick response. This adjusts the reply length based on the user's emotions, resulting in more appropriate replies.

[0132] The business communication support system can further prioritize replies based on when emails and chats were sent. For example, it can prioritize replies to recently sent messages, while older messages can be postponed. Furthermore, it can prioritize replies to messages that are considered urgent. This ensures that replies are prioritized based on when emails and chats were sent, generating appropriate responses.

[0133] The following briefly describes the processing flow for example form 2.

[0134] Step 1: The retrieval unit retrieves the content of received emails or chats. The retrieval unit can retrieve emails and chats in various formats, such as text format, HTML format, business chat, and personal chat. Step 2: The generation unit generates a reply to the email or chat whose content was retrieved by the acquisition unit. The generation unit can generate the reply using, for example, template-based generation or natural language generation technology. Step 3: The suggestion unit proposes the reply generated by the generation unit. The suggestion unit can, for example, make suggestions based on the user's past reply history or AI-generated suggestions. Step 4: The revision unit receives and makes revisions to the response proposed by the proposal unit. The revision unit can, for example, make revisions based on user input or automated revisions by AI. Step 5: The checking unit checks the grammar and expression of the reply corrected by the editing unit. The checking unit can, for example, use a grammar checker or perform checks based on a style guide. Step 6: The recommendation team recommends business terms or phrases. For example, the recommendation team may recommend industry-specific terms or general business phrases.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] For example, the acquisition unit is implemented by the computer 36 of the smart device 14 and acquires the content of received emails and chats. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a reply based on the acquired content. The proposal unit is implemented by the control unit 46A of the smart device 14 and proposes the generated reply to the user. The modification unit is implemented by the control unit 46A of the smart device 14 and modifies the user's proposed reply. The checking unit is implemented by the specific processing unit 290 of the data processing device 12 and checks the grammar and expression of the modified reply. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12 and recommends business terms and phrases. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0139] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] For example, the acquisition unit is implemented by the computer 36 of the smart glasses 214 and acquires the content of received emails and chats. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a reply based on the acquired content. The suggestion unit is implemented by the control unit 46A of the smart glasses 214 and suggests the generated reply to the user. The modification unit is implemented by the control unit 46A of the smart glasses 214 and modifies the user's suggested reply. The checking unit is implemented by the specific processing unit 290 of the data processing device 12 and checks the grammar and expression of the modified reply. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12 and recommends business terms and phrases. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0155] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] For example, the acquisition unit is implemented by the computer 36 of the headset terminal 314 and acquires the content of received emails and chats. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a reply based on the acquired content. The suggestion unit is implemented by the control unit 46A of the headset terminal 314 and suggests the generated reply to the user. The modification unit is implemented by the control unit 46A of the headset terminal 314 and modifies the user's suggested reply. The checking unit is implemented by the specific processing unit 290 of the data processing device 12 and checks the grammar and expression of the modified reply. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12 and recommends business terms and phrases. The correspondence between each unit and the device and control unit is not limited to the example described above and can be modified in various ways.

[0171] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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).

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.).

[0184] 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.

[0185] 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.

[0186] 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.

[0187] For example, the acquisition unit is implemented by the computer 36 of the robot 414 and acquires the content of received emails and chats. The generation unit is implemented by the specific processing unit 290 of the data processing device 12 and generates a reply based on the acquired content. The proposal unit is implemented by the control unit 46A of the robot 414 and proposes the generated reply to the user. The modification unit is implemented by the control unit 46A of the robot 414 and modifies the user's proposed reply. The checking unit is implemented by the specific processing unit 290 of the data processing device 12 and checks the grammar and expression of the modified reply. The recommendation unit is implemented by the specific processing unit 290 of the data processing device 12 and recommends business terms and phrases. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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."

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] (Note 1) An acquisition unit that retrieves the content of received emails or chats, A generation unit generates a reply to an email or chat whose content has been acquired by the acquisition unit, A proposal unit that proposes the reply generated by the generation unit, A revision unit that receives and performs revisions to the reply proposed by the proposal unit, A checking unit that checks the grammar and expression of the reply corrected by the correction unit, A system comprising a recommendation section that recommends business terms or business phrases. (Note 2) The aforementioned checking unit is Check the language used in emails or chats based on the cultural background of the sender. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned checking unit is Check whether the content of the reply is legally sound. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate multiple types of replies, The aforementioned proposal section is, We propose that the user be able to select one or more of the multiple types of replies generated by the generation unit. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is If the user selects two or more of the multiple types of replies, It generates a new reply by combining two or more replies selected by the user. The aforementioned proposal section is, The new reply generated by the aforementioned generation unit proposes The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is Use templates based on business scenarios tailored to the sender of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 7) The acquisition unit is, To estimate the user's emotions, Dynamically adjust the timing of email and chat retrieval based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 8) The acquisition unit is, The content of received emails and chats is analyzed, Prioritize acquisition based on importance. The system described in Appendix 1, characterized by the features described herein. (Note 9) The acquisition unit is, By referring to the past communication history of the email or chat sender, Extract important information The system described in Appendix 1, characterized by the features described herein. (Note 10) The acquisition unit is, To estimate the user's emotions, Dynamically prioritize emails and chats to retrieve based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The acquisition unit is, Prioritize retrieving highly relevant content based on the geographical location of the email or chat sender. The system described in Appendix 1, characterized by the features described herein. (Note 12) The acquisition unit is, Analyze users' social media activity, Retrieve related emails and chats The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is To estimate the user's emotions, The way replies are expressed is adjusted based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is The level of detail in replies is adjusted based on the importance of the content of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is Apply different reply algorithms depending on the category of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is To estimate the user's emotions, Adjust the length of the reply based on the estimated user's sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The generating unit is Prioritize replies based on when emails and chats were sent. The system described in Appendix 1, characterized by the features described herein. (Note 18) The generating unit is The order of replies will be adjusted based on the relevance of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned proposal section is, To estimate the user's emotions, Adjust how suggestions are displayed based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned proposal section is, The system selects the most suitable proposal by referring to the user's past reply history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned proposal section is, The suggestions are made considering the attribute information of the sender of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned proposal section is, To estimate the user's emotions, Prioritize suggestions based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, The proposal takes into account the geographical distribution of email and chat senders. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned proposal section is, Referencing relevant literature in emails and chats improves the accuracy of proposals. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned modification section is, To estimate the user's emotions, Adjust the correction method based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned modification section is, Refer to the user's past revision history to select the most suitable correction method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned modification section is, Apply different correction algorithms depending on the content of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned modification section is, To estimate the user's emotions, Prioritize fixes based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned modification section is, The system will be modified to take into account the geographical location of the sender of the email or chat message. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned modification section is, Referencing relevant documents from emails and chats improves the accuracy of corrections. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned checking unit is To estimate the user's emotions, We adjust grammar and expression checking methods based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned checking unit is Check the language used in emails and chats based on the cultural background of the sender. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned checking unit is Check whether the content of emails and chats is legally permissible. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned checking unit is To estimate the user's emotions, Prioritize grammar and expression checks based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned checking unit is The system checks for the sender's geographical location, including the sender's location in emails and chats. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned checking unit is Improve the accuracy of checks by referring to relevant literature in emails and chats. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned recommendation department, To estimate the user's emotions, We adjust how we recommend business terms and phrases based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned recommendation department, Select the most appropriate business terms and phrases based on the content of the email or chat. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned recommendation department, The system recommends the most suitable business terms and phrases by referencing the user's past usage history. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned recommendation department, To estimate the user's emotions, Prioritize business terms and phrases based on estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned recommendation department, The system recommends the most appropriate business terms and phrases, taking into account the geographical location of the email or chat sender. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned recommendation department, Improve the accuracy of business terminology and phrases by referring to relevant literature on email and chat. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0207] 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 acquisition unit that retrieves the content of received emails or chats, A generation unit generates a reply to an email or chat whose content has been acquired by the acquisition unit, A proposal unit that proposes the reply generated by the generation unit, A revision unit that receives and performs revisions to the reply proposed by the proposal unit, A checking unit that checks the grammar and expression of the reply corrected by the correction unit, A system comprising a recommendation section that recommends business terms or business phrases.

2. The aforementioned checking unit is Check the language used in emails or chats based on the cultural background of the sender. The system according to feature 1.

3. The aforementioned checking unit is Check whether the content of the reply is legally sound. The system according to feature 1.

4. The generating unit is Generate multiple types of replies, The aforementioned proposal section is, We propose that the user be able to select one or more of the multiple types of replies generated by the generation unit. The system according to feature 1.

5. The generating unit is If the user selects two or more of the multiple types of replies, It generates a new reply by combining two or more replies selected by the user. The aforementioned proposal section is, The new reply generated by the aforementioned generation unit proposes The system according to feature 1.

6. The generating unit is Use templates based on business scenarios tailored to the sender of the email or chat. The system according to feature 1.

7. The acquisition unit is, To estimate the user's emotions, Dynamically adjust the timing of email and chat retrieval based on estimated user sentiment. The system according to feature 1.

8. The acquisition unit is, The content of received emails and chats is analyzed, Prioritize acquisition based on importance. The system according to feature 1.

9. The acquisition unit is, By referring to the past communication history of the email or chat sender, Extract important information The system according to feature 1.

Images