system

Abstract

The system according to this embodiment aims to streamline communication using communication tools and prevent important information from being overlooked. [Solution] The system according to the embodiment comprises a confirmation unit, a reply unit, a comment unit, a task unit, and an action unit. The confirmation unit confirms the message addressed to the user. The reply unit considers the content of the reply based on the message confirmed by the confirmation unit. The comment unit looks at the interactions in which the user is participating and suggests an appropriate comment. The task unit summarizes what needs to be done and the deadlines based on the interactions in which the user is involved. The action unit proposes a plan of action for the future.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the interaction in communication tools is complicated, and there is a risk of missing important information.

[0005] The system according to the embodiment aims to streamline the interaction in communication tools and prevent important information from being missed.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a confirmation unit, a reply unit, a comment unit, a task unit, and an action unit. The confirmation unit confirms the message addressed to the user. The reply unit considers the content of the reply based on the message confirmed by the confirmation unit. The comment unit looks at the interactions in which the user is participating and suggests an appropriate comment. The task unit summarizes the tasks and deadlines that need to be done from the interactions in which the user is involved. The action unit proposes a plan of action for the future. [Effects of the Invention]

[0007] The system according to this embodiment can streamline communication using communication tools and prevent important information from being overlooked. [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 numbered 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 reception 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 reception 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 AICA system according to an embodiment of the present invention is a system for streamlining interactions in communication tools. The AICA system checks messages addressed to the user and considers replies based on past interactions. The AICA system looks at interactions in which the user is participating and suggests appropriate comments. The AICA system summarizes tasks and deadlines from the interactions in which the user is involved. The AICA system proposes a future action plan. In this way, the AICA system helps save time in communication tools and prevents important information from being overlooked. Specifically, the AICA system consists of the following steps. First, the AICA system checks messages addressed to the user and considers replies based on past interactions. For example, the AICA system suggests appropriate replies based on the user's previous interactions and information. Next, the AICA system looks at interactions in which the user is participating and suggests appropriate comments. For example, the AICA system suggests appropriate comments based on the interactions in the channels the user is participating in and the content of direct messages. Furthermore, the AICA system summarizes tasks and deadlines from the interactions in which the user is involved. For example, the AICA system summarizes tasks and their deadlines based on the interactions in the channels the user is involved in and the content of direct messages. Finally, the AICA system proposes a future action plan. For example, the AICA system suggests future actions and initiatives based on the user's interactions and direct messages across various channels. This mechanism helps users save time on communication tools and ensures they don't miss important information. For instance, if a user needs to respond to many channels and mentions, the AICA system reduces their burden by reviewing the interactions and suggesting appropriate replies and comments. Furthermore, by summarizing tasks and deadlines, the AICA system makes task management easier and allows users to work more efficiently. In addition, by suggesting future action plans, the AICA system helps users clearly understand what to do next and proceed with their work systematically.This allows the AICA system to streamline user message confirmation, replies, comment suggestions, task management, and action plan proposals.

[0029] The AICA system according to this embodiment comprises a confirmation unit, a reply unit, a comment unit, a task unit, and an action unit. The confirmation unit confirms messages addressed to the user. The confirmation unit can, for example, automatically scan messages received by the user and classify them according to their importance. The confirmation unit can also, for example, analyze the content of messages and identify messages that require a reply. The confirmation unit can also, for example, set priorities based on the sender and content of the messages. The reply unit considers the content of a reply based on the messages confirmed by the confirmation unit. The reply unit can, for example, refer to past interactions and generate appropriate reply content. The reply unit can also, for example, quickly create reply content using a reply template. The reply unit can also, for example, automatically generate reply content and suggest it to the user. The comment unit looks at interactions in which the user is participating and suggests appropriate comments. The comment unit can, for example, analyze the content of channel interactions and DMs and generate appropriate comment content. The comment unit can also, for example, refer to past interactions and suggest appropriate comments. The comment unit can also, for example, quickly create comment content using a comment template. The Task Unit summarizes tasks and deadlines based on user interactions. For example, the Task Unit can analyze channel interactions and DM content to identify tasks and their deadlines. The Task Unit can also set task priorities and notify users. The Task Unit can also manage task progress and provide feedback to users. The Action Unit proposes future action plans. For example, the Action Unit can analyze channel interactions and DM content to propose future actions and initiatives. The Action Unit can also quickly create proposals using action plan templates. The Action Unit can also automatically generate proposals and present them to users. As a result, the AICA system according to this embodiment can streamline user message confirmation, replies, comment suggestions, task management, and action plan proposals.

[0030] The verification unit checks messages addressed to the user. For example, the verification unit can automatically scan messages received by the user and classify them according to their importance. Specifically, the verification unit uses natural language processing technology to analyze the content of messages and determines their importance based on keywords and context. For example, messages from a supervisor or messages related to a project are classified as high importance. On the other hand, messages such as advertisements and spam are classified as low importance. The verification unit can also set priorities based on the sender and content of the message. For example, messages from a specific sender can be set to always be treated as high priority. Furthermore, the verification unit can analyze the content of messages and identify messages that require a reply. For example, messages in the form of questions or messages related to tasks with deadlines are identified as messages that require a reply. This allows users to respond quickly without missing important messages. In addition, when analyzing the content of messages, the verification unit can use machine learning algorithms to learn the user's past behavior patterns and reply history, enabling more accurate classification. This allows the verification unit to achieve flexible message management tailored to the user's needs.

[0031] The reply unit considers the content of the reply based on the message confirmed by the confirmation unit. For example, the reply unit can refer to past exchanges to generate appropriate reply content. Specifically, the reply unit searches the database for the user's past reply history and refers to replies to similar messages. This allows the user to provide consistent replies. The reply unit can also quickly create replies using reply templates. For example, by saving standard phrases for frequently asked questions or business email formats as templates, users can create replies in a short amount of time. Furthermore, the reply unit can automatically generate and suggest replies to the user. For example, it can use AI to analyze the content of the message and generate appropriate replies. The generated replies are sent after the user has reviewed and revised them. This significantly reduces the effort required for the user to reply. The reply unit can learn the user's reply style and tone to generate more natural replies. For example, it can adjust to reply in a friendly tone for casual exchanges and a formal tone for business exchanges. In this way, the reply unit can streamline user communication and support more effective exchanges.

[0032] The comment section observes user interactions and suggests appropriate comments. For example, it can analyze channel conversations and DM content to generate appropriate comments. Specifically, it uses natural language processing technology to understand the context and topic of an interaction and generate corresponding comments. For example, in a conversation about project progress, it can suggest feedback on progress and comments on the next steps. The comment section can also refer to past interactions and suggest appropriate comments. For example, by suggesting similar comments based on similar past interactions, it can maintain consistent communication. Furthermore, the comment section can quickly create comments using comment templates. For example, by saving frequently used phrases and standard expressions as templates, users can create comments in a short amount of time. The comment section can learn the user's comment style and tone to generate more natural comments. For example, it can adjust its tone to be friendly for casual interactions and formal for business interactions. In this way, the comment section can streamline user communication and support more effective interactions.

[0033] The Task Unit compiles tasks and deadlines from user interactions. For example, the Task Unit can analyze channel interactions and DM content to identify tasks and their deadlines. Specifically, it uses natural language processing technology to extract task-related information from message content to identify task details and deadlines. For instance, it can identify the next task and its deadline from interactions regarding project progress. The Task Unit can also set task priorities and notify users. For example, it can classify tasks according to importance and urgency and notify users in order of priority. This allows users to manage tasks efficiently. Furthermore, the Task Unit can manage task progress and provide feedback to users. For example, it can periodically check task completion status and progress and report it to users. This allows users to understand task progress and take action as needed. The Task Unit streamlines user task management and provides support for smooth project progress.

[0034] The Action Department proposes future action plans. For example, the Action Department can analyze channel interactions and direct mail content to propose what needs to be done and what initiatives should be pursued. Specifically, the Action Department uses natural language processing technology to extract information relevant to future actions from the content of interactions and generate action plans. For example, it can propose the next actions and their procedures based on interactions regarding project progress. The Action Department can also quickly create proposals using action plan templates. For example, by saving frequently used action plan formats as templates, users can create action plans in a short amount of time. Furthermore, the Action Department can automatically generate and propose proposals to users. For example, it can use AI to analyze the content of interactions and generate appropriate action plans. The generated action plans are then executed after the user reviews and modifies them. This significantly reduces the effort required for users to create action plans. The Action Department streamlines the user's action plan creation process and provides support to ensure smooth project progress.

[0035] The learning unit learns the user's past interactions and information. For example, the learning unit can analyze the history of past messages and interactions to learn the user's communication patterns. For example, the learning unit can learn specific terms and phrases used by the user and use them as data to generate appropriate replies and comments. For example, the learning unit can analyze the user's past behavior patterns to make predictions about future interactions. In this way, the learning unit can improve the accuracy of its suggestions by learning from past interactions and information. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the history of past messages and interactions into a generative AI, which can then analyze this data and perform learning.

[0036] The proposal unit makes suggestions based on information learned by the learning unit. For example, the proposal unit can suggest appropriate replies or comments based on the user's communication patterns learned by the learning unit. For example, the proposal unit can also predict future interactions and suggest appropriate action plans based on the user's past behavior patterns learned by the learning unit. For example, the proposal unit can make customized suggestions tailored to the user's needs based on the data learned by the learning unit. In this way, the proposal unit can improve the accuracy of its suggestions by making suggestions based on learned information. Some or all of the above processing in the proposal unit may be performed using, for example, generative AI, or not using generative AI. For example, the proposal unit can use generative AI to generate appropriate suggestions based on information learned by the learning unit using generative AI.

[0037] The Efficiency Improvement Unit streamlines user interactions based on the proposals made by the Proposal Unit. For example, the Efficiency Improvement Unit can automatically generate and present replies and comments proposed by the Proposal Unit to the user. For example, the Efficiency Improvement Unit can also automatically execute action plans proposed by the Proposal Unit to support the user's task management. For example, the Efficiency Improvement Unit can apply algorithms to optimize user communication based on the proposals made by the Proposal Unit. In this way, the Efficiency Improvement Unit can streamline user interactions based on the proposals made by the Proposal Unit. Some or all of the above processes in the Efficiency Improvement Unit may be performed using, for example, a generative AI, or not. For example, the Efficiency Improvement Unit can apply an algorithm for efficiency based on the proposals made by the Proposal Unit using a generative AI.

[0038] The reply function can suggest appropriate replies based on the user's previous interactions and information. For example, the reply function can refer to the user's past interaction history and generate appropriate replies based on past replies. For example, the reply function can learn specific terms and phrases the user has used in the past and generate replies based on them. For example, the reply function can consider the context of the user's previous interactions and suggest appropriate replies. In this way, the reply function can improve the accuracy of its replies by suggesting replies based on previous interactions and information. Some or all of the above processing in the reply function may be performed using, for example, a generative AI, or not using a generative AI. For example, the reply function can input the user's past interaction history into a generative AI, which can then generate appropriate replies.

[0039] The comment section can suggest appropriate comments based on the content of the user's channel interactions and direct messages (DMs). For example, the comment section can analyze the content of channel interactions and DMs and generate appropriate comments. For example, the comment section can suggest appropriate comments by considering the context of the user's interactions. For example, the comment section can refer to the user's interaction history and generate appropriate comments based on past comments. In this way, the comment section can improve the accuracy of comments by suggesting comments based on the content of channels and DMs. Some or all of the above processing in the comment section may be performed using a generation AI, or not. For example, the comment section can input the content of channel interactions and DMs into a generation AI, which can then generate appropriate comments.

[0040] The task unit can consolidate tasks and their deadlines based on the content of channel interactions and direct messages (DMs) in which the user is involved. For example, the task unit can analyze the content of channel interactions and DMs to identify tasks and their deadlines. The task unit can also set task priorities and notify the user. For example, the task unit can manage the progress of tasks and provide feedback to the user. In this way, task management is made more efficient by the task unit consolidating tasks and deadlines based on the content of channels and DMs. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the task unit can input the content of channel interactions and DMs into a generative AI, which can then identify tasks and their deadlines.

[0041] The Action Department can propose future actions and initiatives based on the user's channel interactions and direct mail content. For example, the Action Department can analyze channel interactions and direct mail content to identify future actions and initiatives. The Action Department can also quickly create proposals using action plan templates. For example, the Action Department can automatically generate proposals and present them to users. This enables planned work progress by allowing the Action Department to propose future action plans based on channel and direct mail content. Some or all of the above processes in the Action Department may be performed using, for example, a generative AI, or not. For example, the Action Department can input channel interactions and direct mail content into a generative AI, which can then identify future actions and initiatives.

[0042] The confirmation unit can analyze the user's past behavior patterns when reviewing messages and prioritize the review of high-priority messages. For example, the confirmation unit may prioritize displaying messages from people the user has frequently interacted with in the past. The confirmation unit may also analyze the content of messages the user previously deemed important and prioritize displaying similar messages. The confirmation unit may also prioritize displaying messages the user previously reviewed during specific time periods. In this way, the confirmation unit can prioritize the review of important messages by analyzing past behavior patterns. Some or all of the above processing in the confirmation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the confirmation unit may input the user's past behavior data into a generative AI, which can analyze the behavior patterns and identify high-priority messages.

[0043] The confirmation unit can adjust the confirmation method when confirming a message, taking into account the user's current situation. For example, if the user is in a meeting, the confirmation unit will only notify the user of high-priority messages. For example, if the user is on the move, the confirmation unit can read the messages aloud. For example, if the user is on a break, the confirmation unit can display all messages at once. This allows the confirmation unit to confirm messages in an appropriate manner by considering the current situation. Some or all of the above processing in the confirmation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the confirmation unit can input the user's current situation data into a generative AI, which can analyze the situation and suggest an appropriate confirmation method.

[0044] The confirmation unit can prioritize displaying highly relevant messages by considering the user's geographical location information when confirming messages. For example, if the user is in a specific location, the confirmation unit will prioritize displaying messages related to that location. For example, if the user is traveling, the confirmation unit can also prioritize displaying messages related to the travel destination. For example, if the user is at home, the confirmation unit can also prioritize displaying messages related to home. In this way, the confirmation unit can prioritize displaying highly relevant messages by considering geographical location information. Some or all of the above processing in the confirmation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the confirmation unit can input the user's geographical location information into a generation AI, which can then identify highly relevant messages.

[0045] The verification unit can analyze the user's social media activity when reviewing messages and prioritize the review of relevant messages. For example, the verification unit may prioritize displaying messages from people the user frequently interacts with on specific social media platforms. The verification unit may also prioritize displaying messages related to topics the user is interested in on social media. The verification unit may also prioritize displaying messages from accounts the user follows on social media. In this way, the verification unit can prioritize the review of relevant messages by analyzing social media activity. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the verification unit may input the user's social media activity data into a generative AI, which can then identify relevant messages.

[0046] The reply function can adjust the level of detail in its replies based on the importance of the message when formulating a response. For example, it might suggest a detailed reply for a highly important message. For example, it might suggest a concise reply for a less important message. For example, it might suggest a reply with an appropriate level of detail for a message of moderate importance. This allows the reply function to provide appropriate replies by adjusting the level of detail based on the importance of the message. Some or all of the above processing in the reply function may be performed using, for example, a generative AI, or without a generative AI. For example, the reply function can input message importance data into a generative AI, which can analyze the importance and adjust the level of detail in the reply.

[0047] The reply unit can apply different reply algorithms depending on the message category when considering the content of the reply. For example, the reply unit can apply a formal reply algorithm to business-related messages. For example, the reply unit can apply a casual reply algorithm to private messages. For example, the reply unit can apply a rapid reply algorithm to urgent messages. In this way, the reply unit can provide an appropriate reply by applying a reply algorithm according to the message category. Some or all of the above processing in the reply unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reply unit can input message category data into a generative AI, which can analyze the category and apply an appropriate reply algorithm.

[0048] The reply unit can determine the priority of replies based on when the message was sent when considering the content of the reply. For example, the reply unit may suggest a quick reply to a message sent early in the morning. For example, the reply unit may suggest replying the next morning to a message sent late at night. For example, the reply unit may suggest replying at the beginning of the week to a message sent over the weekend. In this way, the reply unit can provide appropriate replies by determining the priority of replies based on when the message was sent. Some or all of the above processing in the reply unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reply unit can input message sending time data into a generative AI, which can analyze the sending time and determine the priority of replies.

[0049] The reply unit can adjust the order of replies based on the relevance of the messages when considering the content of the reply. For example, the reply unit may suggest prioritizing replies to highly relevant messages. For example, the reply unit may suggest postponing replies to less relevant messages. For example, the reply unit may suggest replying to messages of moderate relevance with an appropriate priority. In this way, the reply unit can provide appropriate replies by adjusting the order of replies based on the relevance of the messages. Some or all of the above processing in the reply unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reply unit can input message relevance data into a generative AI, which can analyze the relevance and adjust the order of replies.

[0050] The comment section can adjust the level of detail of comments based on the importance of the exchange when proposing comments. For example, the comment section will propose detailed comments for high-importance exchanges. For example, the comment section may propose concise comments for low-importance exchanges. For example, the comment section may propose comments with an appropriate level of detail for medium-importance exchanges. In this way, the comment section can provide appropriate comments by adjusting the level of detail of comments based on the importance of the exchange. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or without a generative AI. For example, the comment section can input exchange importance data into a generative AI, which can analyze the importance and adjust the level of detail of the comments.

[0051] The comment section can apply different comment algorithms depending on the category of the interaction when proposing comments. For example, the comment section can apply a formal comment algorithm to business-related interactions. For example, the comment section can apply a casual comment algorithm to private interactions. For example, the comment section can apply a rapid comment algorithm to urgent interactions. This allows the comment section to provide appropriate comments by applying a comment algorithm according to the category of the interaction. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or without a generative AI. For example, the comment section can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate comment algorithm.

[0052] The comment section can determine the priority of comments based on when the exchange was sent when proposing comments. For example, the comment section may suggest a prompt comment for an exchange sent early in the morning. For example, the comment section may suggest commenting the next morning for an exchange sent late at night. For example, the comment section may suggest commenting at the beginning of the week for an exchange sent over the weekend. This allows the comment section to make appropriate comments by prioritizing comments based on when the exchange was sent. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or not using a generative AI. For example, the comment section can input exchange sending time data into a generative AI, which can analyze the sending time and determine the priority of comments.

[0053] The comment section can adjust the order of comments based on the relevance of the exchange when proposing comments. For example, the comment section may suggest prioritizing comments on highly relevant exchanges. For example, the comment section may suggest postponing comments on less relevant exchanges. For example, the comment section may suggest commenting on exchanges of moderate relevance with an appropriate priority. In this way, the comment section can make appropriate comments by adjusting the order of comments based on the relevance of the exchanges. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or not using a generative AI. For example, the comment section can input exchange relevance data into a generative AI, which can analyze the relevance and adjust the order of comments.

[0054] The task unit can adjust the level of detail of tasks based on the importance of the interactions when grouping tasks. For example, the task unit can propose detailed tasks for high-importance interactions. For example, the task unit can propose concise tasks for low-importance interactions. For example, the task unit can propose tasks with an appropriate level of detail for moderately important interactions. In this way, the task unit can manage tasks appropriately by adjusting the level of detail of tasks based on the importance of the interactions. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or without a generative AI. For example, the task unit can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail of the tasks.

[0055] The task unit can apply different task management algorithms depending on the category of the interaction when grouping tasks. For example, the task unit can apply a formal task management algorithm to business-related interactions. For example, the task unit can apply a casual task management algorithm to private interactions. For example, the task unit can apply a rapid task management algorithm to urgent interactions. This allows the task unit to perform appropriate task management by applying a task management algorithm according to the category of the interaction. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or without a generative AI. For example, the task unit can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate task management algorithm.

[0056] The task unit can determine task priorities based on the timing of communication transmissions when grouping tasks. For example, the task unit might suggest urgent tasks for communications sent early in the morning. For example, it might suggest grouping tasks the following morning for communications sent late at night. For example, it might suggest grouping tasks at the beginning of the week for communications sent over the weekend. This allows the task unit to manage tasks effectively by determining task priorities based on the timing of communication transmissions. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or without a generative AI. For example, the task unit can input communication transmission timing data into a generative AI, which can analyze the transmission timing and determine task priorities.

[0057] The task unit can adjust the order of tasks based on the relevance of interactions when grouping tasks. For example, the task unit may suggest prioritizing the grouping of tasks based on highly relevant interactions. For example, the task unit may suggest postponing tasks based on less relevant interactions. For example, the task unit may suggest grouping tasks based on interactions of moderate relevance with an appropriate priority. In this way, the task unit can perform appropriate task management by adjusting the order of tasks based on the relevance of interactions. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the task unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of tasks.

[0058] The action unit can adjust the level of detail of an action plan based on the importance of the interaction when proposing an action plan. For example, the action unit can propose a detailed action plan for high-importance interactions. For example, the action unit can propose a concise action plan for low-importance interactions. For example, the action unit can propose an action plan with an appropriate level of detail for moderately important interactions. In this way, the action unit can create an appropriate action plan by adjusting the level of detail of the action plan based on the importance of the interaction. Some or all of the above processing in the action unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the action unit can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail of the action plan.

[0059] The Action Unit can apply different action plan algorithms depending on the category of the interaction when proposing an action plan. For example, the Action Unit can apply a formal action plan algorithm to business-related interactions. For example, the Action Unit can apply a casual action plan algorithm to private interactions. For example, the Action Unit can apply a rapid action plan algorithm to urgent interactions. This allows the Action Unit to create an appropriate action plan by applying an action plan algorithm according to the category of the interaction. Some or all of the above processing in the Action Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Action Unit can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate action plan algorithm.

[0060] The Action Unit can prioritize action plans based on when the communications were sent when proposing action plans. For example, the Action Unit might propose a rapid action plan for communications sent early in the morning. For communications sent late at night, the Action Unit might propose compiling an action plan the following morning. For communications sent over the weekend, the Action Unit might propose compiling an action plan at the beginning of the following week. This allows the Action Unit to create appropriate action plans by prioritizing action plans based on when the communications were sent. Some or all of the above processing in the Action Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Action Unit can input the communication sending time data into a generative AI, which can then analyze the sending time and determine the priority of action plans.

[0061] The Action Unit can adjust the order of action plans based on the relevance of interactions when proposing an action plan. For example, the Action Unit may suggest prioritizing action plans for highly relevant interactions. For example, the Action Unit may suggest postponing actions for less relevant interactions. For example, the Action Unit may suggest compiling action plans with appropriate priority for interactions of moderate relevance. In this way, the Action Unit can create an appropriate action plan by adjusting the order of action plans based on the relevance of interactions. Some or all of the above processing in the Action Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Action Unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of action plans.

[0062] The learning unit can optimize its learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also apply algorithms that improve learning efficiency from past learning data. The learning unit can also analyze past learning data and apply algorithms that improve learning accuracy. As a result, the learning unit improves learning accuracy by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input past learning data into a generative AI, which can then analyze the data and optimize the learning algorithm.

[0063] The learning unit can weight the training data based on the transmission timing of the interactions during training. For example, the learning unit can assign a high weight to interactions sent in the early morning. It can also assign a low weight to interactions sent late at night. It can also assign a medium weight to interactions sent on weekends. This allows the learning unit to perform appropriate training by weighting the training data based on the transmission timing of the interactions. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the transmission timing data of the interactions into a generative AI, which can then analyze the transmission timing and weight the training data.

[0064] The proposal department can adjust the level of detail of its proposals based on the importance of the interactions when considering the content of the proposals. For example, the proposal department can provide detailed proposals for high-importance interactions. For example, it can provide concise proposals for low-importance interactions. For example, it can provide proposals with an appropriate level of detail for moderately important interactions. In this way, the proposal department can provide appropriate proposals by adjusting the level of detail of the proposals based on the importance of the interactions. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal department can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail of the proposals.

[0065] The proposal unit can apply different proposal algorithms depending on the category of the interaction when considering proposal content. For example, the proposal unit can apply a formal proposal algorithm to business-related interactions. For example, the proposal unit can apply a casual proposal algorithm to private interactions. For example, the proposal unit can apply a rapid proposal algorithm to urgent interactions. In this way, the proposal unit can make appropriate proposals by applying a proposal algorithm according to the category of the interaction. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate proposal algorithm.

[0066] The proposal department can determine the priority of proposals based on the timing of communication transmissions when considering proposal content. For example, the proposal department can make prompt proposals for communication transmitted early in the morning. For example, the proposal department can propose making a proposal the following morning for communication transmitted late at night. For example, the proposal department can propose making a proposal at the beginning of the week for communication transmitted over the weekend. In this way, the proposal department can make appropriate proposals by determining the priority of proposals based on the timing of communication transmissions. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input communication transmission timing data into a generative AI, which can analyze the transmission timing and determine the priority of proposals.

[0067] The proposal unit can adjust the order of proposals based on the relevance of the interactions when considering the content of the proposals. For example, the proposal unit can propose prioritizing proposals for highly relevant interactions. For example, the proposal unit can propose postponing proposals for less relevant interactions. For example, the proposal unit can propose making proposals with an appropriate priority for interactions of moderate relevance. In this way, the proposal unit can make appropriate proposals by adjusting the order of proposals based on the relevance of the interactions. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of proposals.

[0068] The efficiency improvement unit can adjust the level of detail in its efficiency improvements based on the importance of the interaction. For example, the efficiency improvement unit can propose detailed efficiency improvements for high-importance interactions. For example, it can propose concise efficiency improvements for low-importance interactions. For example, it can propose efficiency improvements with an appropriate level of detail for moderately important interactions. In this way, the efficiency improvement unit can achieve appropriate efficiency improvements by adjusting the level of detail in its efficiency improvements based on the importance of the interaction. Some or all of the above processing in the efficiency improvement unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the efficiency improvement unit can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail in its efficiency improvements.

[0069] The efficiency unit can apply different efficiency algorithms depending on the category of the interaction when performing efficiency improvements. For example, the efficiency unit can apply a formal efficiency algorithm to business-related interactions. For example, it can apply a casual efficiency algorithm to private interactions. For example, it can apply a rapid efficiency algorithm to urgent interactions. In this way, the efficiency unit can achieve appropriate efficiency by applying an efficiency algorithm according to the category of the interaction. Some or all of the above processing in the efficiency unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the efficiency unit can input interaction category data into a generative AI, the generative AI can analyze the categories, and apply an appropriate efficiency algorithm.

[0070] The efficiency improvement unit can determine the priority of efficiency improvements based on the timing of communication transmissions when implementing efficiency improvements. For example, the efficiency improvement unit can propose quick efficiency improvements for communications sent early in the morning. For communications sent late at night, the efficiency improvement unit can also propose compiling efficiency improvements the following morning. For communications sent over the weekend, the efficiency improvement unit can also propose compiling efficiency improvements at the beginning of the following week. This allows the efficiency improvement unit to implement appropriate efficiency improvements by determining the priority of efficiency improvements based on the timing of communication transmissions. Some or all of the above processing in the efficiency improvement unit may be performed using, for example, a generative AI, or without a generative AI. For example, the efficiency improvement unit can input communication transmission timing data into a generative AI, which can analyze the transmission timing and determine the priority of efficiency improvements.

[0071] The efficiency optimization unit can adjust the order of optimization based on the relevance of interactions when performing optimization. For example, the efficiency optimization unit may suggest prioritizing the grouping of optimization methods for highly relevant interactions. For example, the efficiency optimization unit may suggest postponing less relevant interactions. For example, the efficiency optimization unit may suggest grouping optimization methods with an appropriate priority for interactions of moderate relevance. In this way, the efficiency optimization unit can achieve appropriate optimization by adjusting the order of optimization based on the relevance of interactions. Some or all of the above processing in the efficiency optimization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the efficiency optimization unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of optimization.

[0072] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0073] The AICA system can analyze a user's past behavior patterns and prioritize the display of high-priority messages. For example, it can prioritize displaying messages from people the user has frequently interacted with in the past. It can also analyze the content of messages the user previously deemed important and prioritize the display of similar messages. Furthermore, it can prioritize the display of messages the user previously viewed during specific time periods. This allows users to prioritize the display of important messages based on their past behavior patterns. Some or all of the above processing in the confirmation unit may be performed using generative AI, or it may be performed without using generative AI.

[0074] The AICA system can adjust how messages are viewed, taking into account the user's current situation. For example, if the user is in a meeting, only high-priority messages can be notified. If the user is on the move, messages can be read aloud. Furthermore, if the user is on a break, all messages can be displayed at once. This allows the user to view messages in an appropriate manner according to their current situation. Some or all of the above processing in the confirmation unit may be performed using generative AI, or it may be performed without using generative AI.

[0075] The AICA system can prioritize displaying highly relevant messages by taking into account the user's geographical location. For example, if the user is in a specific location, messages related to that location can be displayed preferentially. Similarly, if the user is traveling, messages related to their travel destination can be displayed preferentially. Furthermore, if the user is at home, messages related to their home can be displayed preferentially. This allows the user to prioritize displaying highly relevant messages based on their geographical location. Some or all of the above processing in the verification unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0076] The AICA system can analyze a user's social media activity and prioritize the display of relevant messages. For example, it can prioritize displaying messages from people the user frequently interacts with on a particular social media platform. It can also prioritize displaying messages related to topics the user is interested in on social media. Furthermore, it can prioritize displaying messages from accounts the user follows on social media. This allows users to prioritize the display of relevant messages based on their social media activity. Some or all of the above processing in the verification unit may be performed using generative AI, or it may be performed without using generative AI.

[0077] The AICA system can adjust the level of detail in a reply based on the importance of the message when formulating a response. For example, it can suggest a detailed reply for a highly important message, a concise reply for a less important message, and a reply of moderate detail for a message of moderate importance. This allows users to send replies with appropriate detail according to the importance of the message. Some or all of the above processing in the reply section may be performed using generative AI, or it may be performed without using generative AI.

[0078] The AICA system can apply different reply algorithms depending on the message category when considering reply content. For example, a formal reply algorithm can be applied to business-related messages, a casual reply algorithm to private messages, and a rapid reply algorithm to urgent messages. This allows users to apply the appropriate reply algorithm according to the message category. Some or all of the above processing in the reply section may be performed using generative AI, or it may be performed without using generative AI.

[0079] The AICA system can determine the priority of replies based on when the message was sent when considering the content of the reply. For example, it can suggest a quick reply to a message sent early in the morning. It can also suggest replying the following morning to a message sent late at night. Furthermore, it can suggest replying at the beginning of the week to a message sent over the weekend. This allows users to reply with appropriate priority based on when the message was sent. Some or all of the above processing in the reply section may be performed using generative AI, or it may be performed without using generative AI.

[0080] The following briefly describes the processing flow for example form 1.

[0081] Step 1: The verification unit checks messages addressed to the user. For example, it can automatically scan messages received by the user and classify them according to their importance. It can also analyze the content of messages and identify those that require a reply. Furthermore, it can set priorities based on the sender and content of the messages. Step 2: The reply section considers the reply content based on the message confirmed by the confirmation section. For example, it can refer to past exchanges to generate appropriate reply content. It can also use reply templates to quickly create reply content. Furthermore, it can automatically generate reply content and suggest it to the user. Step 3: The comment section observes the user's interactions and suggests appropriate comments. For example, it can analyze channel conversations and DM content to generate appropriate comments. It can also refer to past interactions to suggest appropriate comments. Furthermore, it can quickly create comments using comment templates. Step 4: The task manager compiles tasks and deadlines based on user interactions. For example, they can analyze channel conversations and direct messages to identify tasks and their deadlines. They can also prioritize tasks and notify users. Furthermore, they can manage task progress and provide feedback to users. Step 5: The Actions Department proposes future action plans. For example, they can analyze channel interactions and direct mail content to propose what needs to be done and what initiatives should be pursued. They can also use action plan templates to quickly create proposals. Furthermore, they can automatically generate proposals and present them to users.

[0082] (Example of form 2) The AICA system according to an embodiment of the present invention is a system for streamlining interactions in communication tools. The AICA system checks messages addressed to the user and considers replies based on past interactions. The AICA system looks at interactions in which the user is participating and suggests appropriate comments. The AICA system summarizes tasks and deadlines from the interactions in which the user is involved. The AICA system proposes a future action plan. In this way, the AICA system helps save time in communication tools and prevents important information from being overlooked. Specifically, the AICA system consists of the following steps. First, the AICA system checks messages addressed to the user and considers replies based on past interactions. For example, the AICA system suggests appropriate replies based on the user's previous interactions and information. Next, the AICA system looks at interactions in which the user is participating and suggests appropriate comments. For example, the AICA system suggests appropriate comments based on the interactions in the channels the user is participating in and the content of direct messages. Furthermore, the AICA system summarizes tasks and deadlines from the interactions in which the user is involved. For example, the AICA system summarizes tasks and their deadlines based on the interactions in the channels the user is involved in and the content of direct messages. Finally, the AICA system proposes a future action plan. For example, the AICA system suggests future actions and initiatives based on the user's interactions and direct messages across various channels. This mechanism helps users save time on communication tools and ensures they don't miss important information. For instance, if a user needs to respond to many channels and mentions, the AICA system reduces their burden by reviewing the interactions and suggesting appropriate replies and comments. Furthermore, by summarizing tasks and deadlines, the AICA system makes task management easier and allows users to work more efficiently. In addition, by suggesting future action plans, the AICA system helps users clearly understand what to do next and proceed with their work systematically.This allows the AICA system to streamline user message confirmation, replies, comment suggestions, task management, and action plan proposals.

[0083] The AICA system according to this embodiment comprises a confirmation unit, a reply unit, a comment unit, a task unit, and an action unit. The confirmation unit confirms messages addressed to the user. The confirmation unit can, for example, automatically scan messages received by the user and classify them according to their importance. The confirmation unit can also, for example, analyze the content of messages and identify messages that require a reply. The confirmation unit can also, for example, set priorities based on the sender and content of the messages. The reply unit considers the content of a reply based on the messages confirmed by the confirmation unit. The reply unit can, for example, refer to past interactions and generate appropriate reply content. The reply unit can also, for example, quickly create reply content using a reply template. The reply unit can also, for example, automatically generate reply content and suggest it to the user. The comment unit looks at interactions in which the user is participating and suggests appropriate comments. The comment unit can, for example, analyze the content of channel interactions and DMs and generate appropriate comment content. The comment unit can also, for example, refer to past interactions and suggest appropriate comments. The comment unit can also, for example, quickly create comment content using a comment template. The Task Unit summarizes tasks and deadlines based on user interactions. For example, the Task Unit can analyze channel interactions and DM content to identify tasks and their deadlines. The Task Unit can also set task priorities and notify users. The Task Unit can also manage task progress and provide feedback to users. The Action Unit proposes future action plans. For example, the Action Unit can analyze channel interactions and DM content to propose future actions and initiatives. The Action Unit can also quickly create proposals using action plan templates. The Action Unit can also automatically generate proposals and present them to users. As a result, the AICA system according to this embodiment can streamline user message confirmation, replies, comment suggestions, task management, and action plan proposals.

[0084] The verification unit checks messages addressed to the user. For example, the verification unit can automatically scan messages received by the user and classify them according to their importance. Specifically, the verification unit uses natural language processing technology to analyze the content of messages and determines their importance based on keywords and context. For example, messages from a supervisor or messages related to a project are classified as high importance. On the other hand, messages such as advertisements and spam are classified as low importance. The verification unit can also set priorities based on the sender and content of the message. For example, messages from a specific sender can be set to always be treated as high priority. Furthermore, the verification unit can analyze the content of messages and identify messages that require a reply. For example, messages in the form of questions or messages related to tasks with deadlines are identified as messages that require a reply. This allows users to respond quickly without missing important messages. In addition, when analyzing the content of messages, the verification unit can use machine learning algorithms to learn the user's past behavior patterns and reply history, enabling more accurate classification. This allows the verification unit to achieve flexible message management tailored to the user's needs.

[0085] The reply unit considers the content of the reply based on the message confirmed by the confirmation unit. For example, the reply unit can refer to past exchanges to generate appropriate reply content. Specifically, the reply unit searches the database for the user's past reply history and refers to replies to similar messages. This allows the user to provide consistent replies. The reply unit can also quickly create replies using reply templates. For example, by saving standard phrases for frequently asked questions or business email formats as templates, users can create replies in a short amount of time. Furthermore, the reply unit can automatically generate and suggest replies to the user. For example, it can use AI to analyze the content of the message and generate appropriate replies. The generated replies are sent after the user has reviewed and revised them. This significantly reduces the effort required for the user to reply. The reply unit can learn the user's reply style and tone to generate more natural replies. For example, it can adjust to reply in a friendly tone for casual exchanges and a formal tone for business exchanges. In this way, the reply unit can streamline user communication and support more effective exchanges.

[0086] The comment section observes user interactions and suggests appropriate comments. For example, it can analyze channel conversations and DM content to generate appropriate comments. Specifically, it uses natural language processing technology to understand the context and topic of an interaction and generate corresponding comments. For example, in a conversation about project progress, it can suggest feedback on progress and comments on the next steps. The comment section can also refer to past interactions and suggest appropriate comments. For example, by suggesting similar comments based on similar past interactions, it can maintain consistent communication. Furthermore, the comment section can quickly create comments using comment templates. For example, by saving frequently used phrases and standard expressions as templates, users can create comments in a short amount of time. The comment section can learn the user's comment style and tone to generate more natural comments. For example, it can adjust its tone to be friendly for casual interactions and formal for business interactions. In this way, the comment section can streamline user communication and support more effective interactions.

[0087] The Task Unit compiles tasks and deadlines from user interactions. For example, the Task Unit can analyze channel interactions and DM content to identify tasks and their deadlines. Specifically, it uses natural language processing technology to extract task-related information from message content to identify task details and deadlines. For instance, it can identify the next task and its deadline from interactions regarding project progress. The Task Unit can also set task priorities and notify users. For example, it can classify tasks according to importance and urgency and notify users in order of priority. This allows users to manage tasks efficiently. Furthermore, the Task Unit can manage task progress and provide feedback to users. For example, it can periodically check task completion status and progress and report it to users. This allows users to understand task progress and take action as needed. The Task Unit streamlines user task management and provides support for smooth project progress.

[0088] The Action Department proposes future action plans. For example, the Action Department can analyze channel interactions and direct mail content to propose what needs to be done and what initiatives should be pursued. Specifically, the Action Department uses natural language processing technology to extract information relevant to future actions from the content of interactions and generate action plans. For example, it can propose the next actions and their procedures based on interactions regarding project progress. The Action Department can also quickly create proposals using action plan templates. For example, by saving frequently used action plan formats as templates, users can create action plans in a short amount of time. Furthermore, the Action Department can automatically generate and propose proposals to users. For example, it can use AI to analyze the content of interactions and generate appropriate action plans. The generated action plans are then executed after the user reviews and modifies them. This significantly reduces the effort required for users to create action plans. The Action Department streamlines the user's action plan creation process and provides support to ensure smooth project progress.

[0089] The learning unit learns the user's past interactions and information. For example, the learning unit can analyze the history of past messages and interactions to learn the user's communication patterns. For example, the learning unit can learn specific terms and phrases used by the user and use them as data to generate appropriate replies and comments. For example, the learning unit can analyze the user's past behavior patterns to make predictions about future interactions. In this way, the learning unit can improve the accuracy of its suggestions by learning from past interactions and information. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can input the history of past messages and interactions into a generative AI, which can then analyze this data and perform learning.

[0090] The proposal unit makes suggestions based on information learned by the learning unit. For example, the proposal unit can suggest appropriate replies or comments based on the user's communication patterns learned by the learning unit. For example, the proposal unit can also predict future interactions and suggest appropriate action plans based on the user's past behavior patterns learned by the learning unit. For example, the proposal unit can make customized suggestions tailored to the user's needs based on the data learned by the learning unit. In this way, the proposal unit can improve the accuracy of its suggestions by making suggestions based on learned information. Some or all of the above processing in the proposal unit may be performed using, for example, generative AI, or not using generative AI. For example, the proposal unit can use generative AI to generate appropriate suggestions based on information learned by the learning unit using generative AI.

[0091] The Efficiency Improvement Unit streamlines user interactions based on the proposals made by the Proposal Unit. For example, the Efficiency Improvement Unit can automatically generate and present replies and comments proposed by the Proposal Unit to the user. For example, the Efficiency Improvement Unit can also automatically execute action plans proposed by the Proposal Unit to support the user's task management. For example, the Efficiency Improvement Unit can apply algorithms to optimize user communication based on the proposals made by the Proposal Unit. In this way, the Efficiency Improvement Unit can streamline user interactions based on the proposals made by the Proposal Unit. Some or all of the above processes in the Efficiency Improvement Unit may be performed using, for example, a generative AI, or not. For example, the Efficiency Improvement Unit can apply an algorithm for efficiency based on the proposals made by the Proposal Unit using a generative AI.

[0092] The reply function can suggest appropriate replies based on the user's previous interactions and information. For example, the reply function can refer to the user's past interaction history and generate appropriate replies based on past replies. For example, the reply function can learn specific terms and phrases the user has used in the past and generate replies based on them. For example, the reply function can consider the context of the user's previous interactions and suggest appropriate replies. In this way, the reply function can improve the accuracy of its replies by suggesting replies based on previous interactions and information. Some or all of the above processing in the reply function may be performed using, for example, a generative AI, or not using a generative AI. For example, the reply function can input the user's past interaction history into a generative AI, which can then generate appropriate replies.

[0093] The comment section can suggest appropriate comments based on the content of the user's channel interactions and direct messages (DMs). For example, the comment section can analyze the content of channel interactions and DMs and generate appropriate comments. For example, the comment section can suggest appropriate comments by considering the context of the user's interactions. For example, the comment section can refer to the user's interaction history and generate appropriate comments based on past comments. In this way, the comment section can improve the accuracy of comments by suggesting comments based on the content of channels and DMs. Some or all of the above processing in the comment section may be performed using a generation AI, or not. For example, the comment section can input the content of channel interactions and DMs into a generation AI, which can then generate appropriate comments.

[0094] The task unit can consolidate tasks and their deadlines based on the content of channel interactions and direct messages (DMs) in which the user is involved. For example, the task unit can analyze the content of channel interactions and DMs to identify tasks and their deadlines. The task unit can also set task priorities and notify the user. For example, the task unit can manage the progress of tasks and provide feedback to the user. In this way, task management is made more efficient by the task unit consolidating tasks and deadlines based on the content of channels and DMs. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the task unit can input the content of channel interactions and DMs into a generative AI, which can then identify tasks and their deadlines.

[0095] The Action Department can propose future actions and initiatives based on the user's channel interactions and direct mail content. For example, the Action Department can analyze channel interactions and direct mail content to identify future actions and initiatives. The Action Department can also quickly create proposals using action plan templates. For example, the Action Department can automatically generate proposals and present them to users. This enables planned work progress by allowing the Action Department to propose future action plans based on channel and direct mail content. Some or all of the above processes in the Action Department may be performed using, for example, a generative AI, or not. For example, the Action Department can input channel interactions and direct mail content into a generative AI, which can then identify future actions and initiatives.

[0096] The confirmation unit can estimate the user's emotions and adjust the order in which messages are viewed based on the estimated emotions. For example, if the user is stressed, the confirmation unit will prioritize displaying high-importance messages. For example, if the user is relaxed, the confirmation unit can also display messages in chronological order. For example, if the user is in a hurry, the confirmation unit can also display high-urgency messages first. In this way, the confirmation unit can prioritize important messages by adjusting the order in which messages are viewed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the confirmation unit may be performed using a generative AI, or not using a generative AI. For example, the confirmation unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the order in which messages are viewed.

[0097] The confirmation unit can analyze the user's past behavior patterns when reviewing messages and prioritize the review of high-priority messages. For example, the confirmation unit may prioritize displaying messages from people the user has frequently interacted with in the past. The confirmation unit may also analyze the content of messages the user previously deemed important and prioritize displaying similar messages. The confirmation unit may also prioritize displaying messages the user previously reviewed during specific time periods. In this way, the confirmation unit can prioritize the review of important messages by analyzing past behavior patterns. Some or all of the above processing in the confirmation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the confirmation unit may input the user's past behavior data into a generative AI, which can analyze the behavior patterns and identify high-priority messages.

[0098] The confirmation unit can adjust the confirmation method when confirming a message, taking into account the user's current situation. For example, if the user is in a meeting, the confirmation unit will only notify the user of high-priority messages. For example, if the user is on the move, the confirmation unit can read the messages aloud. For example, if the user is on a break, the confirmation unit can display all messages at once. This allows the confirmation unit to confirm messages in an appropriate manner by considering the current situation. Some or all of the above processing in the confirmation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the confirmation unit can input the user's current situation data into a generative AI, which can analyze the situation and suggest an appropriate confirmation method.

[0099] The confirmation unit can estimate the user's emotions and adjust the message display method based on the estimated emotions. For example, if the user is nervous, the confirmation unit can provide a simple and highly visible display method. For example, if the user is relaxed, the confirmation unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the confirmation unit can also provide a display method that gets straight to the point. In this way, the confirmation unit improves visibility by adjusting the message display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 confirmation unit may be performed using a generative AI, or not using a generative AI. For example, the confirmation unit can input user emotion data into a generative AI, which can estimate the emotion and adjust the message display method.

[0100] The confirmation unit can prioritize displaying highly relevant messages by considering the user's geographical location information when confirming messages. For example, if the user is in a specific location, the confirmation unit will prioritize displaying messages related to that location. For example, if the user is traveling, the confirmation unit can also prioritize displaying messages related to the travel destination. For example, if the user is at home, the confirmation unit can also prioritize displaying messages related to home. In this way, the confirmation unit can prioritize displaying highly relevant messages by considering geographical location information. Some or all of the above processing in the confirmation unit may be performed using, for example, a generation AI, or without a generation AI. For example, the confirmation unit can input the user's geographical location information into a generation AI, which can then identify highly relevant messages.

[0101] The verification unit can analyze the user's social media activity when reviewing messages and prioritize the review of relevant messages. For example, the verification unit may prioritize displaying messages from people the user frequently interacts with on specific social media platforms. The verification unit may also prioritize displaying messages related to topics the user is interested in on social media. The verification unit may also prioritize displaying messages from accounts the user follows on social media. In this way, the verification unit can prioritize the review of relevant messages by analyzing social media activity. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the verification unit may input the user's social media activity data into a generative AI, which can then identify relevant messages.

[0102] The reply unit can estimate the user's emotions and adjust the tone of the reply based on the estimated emotions. For example, if the user is angry, the reply unit may suggest a calm and polite reply. For example, if the user is happy, the reply unit may suggest a bright and positive reply. For example, if the user is sad, the reply unit may suggest a comforting reply. In this way, the reply unit can provide an appropriate reply by adjusting the tone of the reply based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reply unit may be performed using a generative AI, or not using a generative AI. For example, the reply unit can input user emotion data into a generative AI, which can estimate the emotion and adjust the tone of the reply.

[0103] The reply function can adjust the level of detail in its replies based on the importance of the message when formulating a response. For example, it might suggest a detailed reply for a highly important message. For example, it might suggest a concise reply for a less important message. For example, it might suggest a reply with an appropriate level of detail for a message of moderate importance. This allows the reply function to provide appropriate replies by adjusting the level of detail based on the importance of the message. Some or all of the above processing in the reply function may be performed using, for example, a generative AI, or without a generative AI. For example, the reply function can input message importance data into a generative AI, which can analyze the importance and adjust the level of detail in the reply.

[0104] The reply unit can apply different reply algorithms depending on the message category when considering the content of the reply. For example, the reply unit can apply a formal reply algorithm to business-related messages. For example, the reply unit can apply a casual reply algorithm to private messages. For example, the reply unit can apply a rapid reply algorithm to urgent messages. In this way, the reply unit can provide an appropriate reply by applying a reply algorithm according to the message category. Some or all of the above processing in the reply unit may be performed using, for example, a generative AI, or without a generative AI. For example, the reply unit can input message category data into a generative AI, which can analyze the category and apply an appropriate reply algorithm.

[0105] The reply 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 in a hurry, the reply unit may suggest a short, to-the-point reply. If the user is relaxed, the reply unit may suggest a longer reply with a detailed explanation. If the user is excited, the reply unit may suggest a reply with visually stimulating effects. This allows the reply unit to provide an appropriate reply by adjusting the length of the reply 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 reply unit may be performed using a generative AI, or not. For example, the reply unit can input user emotion data into a generative AI, which can estimate the emotion and adjust the length of the reply.

[0106] The reply unit can determine the priority of replies based on when the message was sent when considering the content of the reply. For example, the reply unit may suggest a quick reply to a message sent early in the morning. For example, the reply unit may suggest replying the next morning to a message sent late at night. For example, the reply unit may suggest replying at the beginning of the week to a message sent over the weekend. In this way, the reply unit can provide appropriate replies by determining the priority of replies based on when the message was sent. Some or all of the above processing in the reply unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reply unit can input message sending time data into a generative AI, which can analyze the sending time and determine the priority of replies.

[0107] The reply unit can adjust the order of replies based on the relevance of the messages when considering the content of the reply. For example, the reply unit may suggest prioritizing replies to highly relevant messages. For example, the reply unit may suggest postponing replies to less relevant messages. For example, the reply unit may suggest replying to messages of moderate relevance with an appropriate priority. In this way, the reply unit can provide appropriate replies by adjusting the order of replies based on the relevance of the messages. Some or all of the above processing in the reply unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reply unit can input message relevance data into a generative AI, which can analyze the relevance and adjust the order of replies.

[0108] The comment section can estimate the user's emotions and adjust the way the comment is expressed based on the estimated emotions. For example, if the user is angry, the comment section may suggest a calm and polite comment. For example, if the user is happy, the comment section may suggest a bright and positive comment. For example, if the user is sad, the comment section may suggest a comforting comment. In this way, the comment section can provide appropriate comments by adjusting the way the comment is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the comment section may be performed using a generative AI, or not using a generative AI. For example, the comment section can input user emotion data into a generative AI, which can estimate the emotion and adjust the way the comment is expressed.

[0109] The comment section can adjust the level of detail of comments based on the importance of the exchange when proposing comments. For example, the comment section will propose detailed comments for high-importance exchanges. For example, the comment section may propose concise comments for low-importance exchanges. For example, the comment section may propose comments with an appropriate level of detail for medium-importance exchanges. In this way, the comment section can provide appropriate comments by adjusting the level of detail of comments based on the importance of the exchange. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or without a generative AI. For example, the comment section can input exchange importance data into a generative AI, which can analyze the importance and adjust the level of detail of the comments.

[0110] The comment section can apply different comment algorithms depending on the category of the interaction when proposing comments. For example, the comment section can apply a formal comment algorithm to business-related interactions. For example, the comment section can apply a casual comment algorithm to private interactions. For example, the comment section can apply a rapid comment algorithm to urgent interactions. This allows the comment section to provide appropriate comments by applying a comment algorithm according to the category of the interaction. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or without a generative AI. For example, the comment section can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate comment algorithm.

[0111] The comment section can estimate the user's emotions and adjust the length of the comment based on the estimated emotions. For example, if the user is in a hurry, the comment section may suggest a short, to-the-point comment. If the user is relaxed, the comment section may suggest a longer comment with detailed explanations. If the user is excited, the comment section may suggest a comment with visually stimulating effects. This allows the comment section to provide appropriate comments by adjusting the length of the comment 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 comment section may be performed using a generative AI, or not. For example, the comment section can input user emotion data into a generative AI, which can estimate the emotion and adjust the length of the comment.

[0112] The comment section can determine the priority of comments based on when the exchange was sent when proposing comments. For example, the comment section may suggest a prompt comment for an exchange sent early in the morning. For example, the comment section may suggest commenting the next morning for an exchange sent late at night. For example, the comment section may suggest commenting at the beginning of the week for an exchange sent over the weekend. This allows the comment section to make appropriate comments by prioritizing comments based on when the exchange was sent. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or not using a generative AI. For example, the comment section can input exchange sending time data into a generative AI, which can analyze the sending time and determine the priority of comments.

[0113] The comment section can adjust the order of comments based on the relevance of the exchange when proposing comments. For example, the comment section may suggest prioritizing comments on highly relevant exchanges. For example, the comment section may suggest postponing comments on less relevant exchanges. For example, the comment section may suggest commenting on exchanges of moderate relevance with an appropriate priority. In this way, the comment section can make appropriate comments by adjusting the order of comments based on the relevance of the exchanges. Some or all of the above processing in the comment section may be performed using, for example, a generative AI, or not using a generative AI. For example, the comment section can input exchange relevance data into a generative AI, which can analyze the relevance and adjust the order of comments.

[0114] The task unit can estimate the user's emotions and determine task priorities based on those emotions. For example, if the user is stressed, the task unit will prioritize displaying high-priority tasks. If the user is relaxed, the task unit can also display tasks in chronological order. If the user is in a hurry, the task unit can also display high-urgency tasks first. This allows the task unit to prioritize important tasks by determining task priorities 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 task unit may be performed using or without a generative AI. For example, the task unit can input user emotion data into a generative AI, which can estimate the emotions and determine task priorities.

[0115] The task unit can adjust the level of detail of tasks based on the importance of the interactions when grouping tasks. For example, the task unit can propose detailed tasks for high-importance interactions. For example, the task unit can propose concise tasks for low-importance interactions. For example, the task unit can propose tasks with an appropriate level of detail for moderately important interactions. In this way, the task unit can manage tasks appropriately by adjusting the level of detail of tasks based on the importance of the interactions. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or without a generative AI. For example, the task unit can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail of the tasks.

[0116] The task unit can apply different task management algorithms depending on the category of the interaction when grouping tasks. For example, the task unit can apply a formal task management algorithm to business-related interactions. For example, the task unit can apply a casual task management algorithm to private interactions. For example, the task unit can apply a rapid task management algorithm to urgent interactions. This allows the task unit to perform appropriate task management by applying a task management algorithm according to the category of the interaction. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or without a generative AI. For example, the task unit can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate task management algorithm.

[0117] The task unit can estimate the user's emotions and adjust the task display method based on the estimated user emotions. For example, if the user is nervous, the task unit can provide a simple and highly visible display method. For example, if the user is relaxed, the task unit can also provide a display method that includes detailed information. For example, if the user is in a hurry, the task unit can provide a display method that gets straight to the point. In this way, the task unit improves visibility by adjusting the task display method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the task unit may be performed using a generative AI, or not using a generative AI. For example, the task unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the task display method.

[0118] The task unit can determine task priorities based on the timing of communication transmissions when grouping tasks. For example, the task unit might suggest urgent tasks for communications sent early in the morning. For example, it might suggest grouping tasks the following morning for communications sent late at night. For example, it might suggest grouping tasks at the beginning of the week for communications sent over the weekend. This allows the task unit to manage tasks effectively by determining task priorities based on the timing of communication transmissions. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or without a generative AI. For example, the task unit can input communication transmission timing data into a generative AI, which can analyze the transmission timing and determine task priorities.

[0119] The task unit can adjust the order of tasks based on the relevance of interactions when grouping tasks. For example, the task unit may suggest prioritizing the grouping of tasks based on highly relevant interactions. For example, the task unit may suggest postponing tasks based on less relevant interactions. For example, the task unit may suggest grouping tasks based on interactions of moderate relevance with an appropriate priority. In this way, the task unit can perform appropriate task management by adjusting the order of tasks based on the relevance of interactions. Some or all of the above processing in the task unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the task unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of tasks.

[0120] The action unit can estimate the user's emotions and adjust how it proposes action plans based on those emotions. For example, if the user is stressed, the action unit will propose a concise and easy-to-follow action plan. If the user is relaxed, the action unit may propose a more detailed action plan. If the user is in a hurry, the action unit may propose an action plan that can be implemented quickly. This allows the action unit to provide appropriate action plans by adjusting how it proposes action plans 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-described processes in the action unit may be performed using or without a generative AI. For example, the action unit can input user emotion data into a generative AI, which will estimate the emotions and adjust how it proposes action plans.

[0121] The action unit can adjust the level of detail of an action plan based on the importance of the interaction when proposing an action plan. For example, the action unit can propose a detailed action plan for high-importance interactions. For example, the action unit can propose a concise action plan for low-importance interactions. For example, the action unit can propose an action plan with an appropriate level of detail for moderately important interactions. In this way, the action unit can create an appropriate action plan by adjusting the level of detail of the action plan based on the importance of the interaction. Some or all of the above processing in the action unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the action unit can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail of the action plan.

[0122] The Action Unit can apply different action plan algorithms depending on the category of the interaction when proposing an action plan. For example, the Action Unit can apply a formal action plan algorithm to business-related interactions. For example, the Action Unit can apply a casual action plan algorithm to private interactions. For example, the Action Unit can apply a rapid action plan algorithm to urgent interactions. This allows the Action Unit to create an appropriate action plan by applying an action plan algorithm according to the category of the interaction. Some or all of the above processing in the Action Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Action Unit can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate action plan algorithm.

[0123] The action unit can estimate the user's emotions and prioritize action plans based on those emotions. For example, if the user is stressed, the action unit will prioritize displaying high-priority action plans. If the user is relaxed, the action unit can also display action plans in chronological order. If the user is in a hurry, the action unit can also prioritize displaying high-urgency action plans first. This allows the action unit to prioritize important action plans 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 action unit may be performed using or without a generative AI. For example, the action unit can input user emotion data into a generative AI, which can estimate the emotions and determine the priority of action plans.

[0124] The Action Unit can prioritize action plans based on when the communications were sent when proposing action plans. For example, the Action Unit might propose a rapid action plan for communications sent early in the morning. For communications sent late at night, the Action Unit might propose compiling an action plan the following morning. For communications sent over the weekend, the Action Unit might propose compiling an action plan at the beginning of the following week. This allows the Action Unit to create appropriate action plans by prioritizing action plans based on when the communications were sent. Some or all of the above processing in the Action Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Action Unit can input the communication sending time data into a generative AI, which can then analyze the sending time and determine the priority of action plans.

[0125] The Action Unit can adjust the order of action plans based on the relevance of interactions when proposing an action plan. For example, the Action Unit may suggest prioritizing action plans for highly relevant interactions. For example, the Action Unit may suggest postponing actions for less relevant interactions. For example, the Action Unit may suggest compiling action plans with appropriate priority for interactions of moderate relevance. In this way, the Action Unit can create an appropriate action plan by adjusting the order of action plans based on the relevance of interactions. Some or all of the above processing in the Action Unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the Action Unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of action plans.

[0126] The learning unit can estimate the user's emotions and select training data based on the estimated emotions. For example, if the user is stressed, the learning unit will select simple and easy-to-execute training data. If the user is relaxed, the learning unit can also select detailed training data. If the user is in a hurry, the learning unit can also select data that allows for quick learning. This enables appropriate learning by selecting training data 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 learning unit may be performed using a generative AI, or not. For example, the learning unit can input user emotion data into a generative AI, which can estimate the emotions and select training data.

[0127] The learning unit can optimize its learning algorithm by referring to past learning data during the learning process. For example, the learning unit can select the optimal learning algorithm based on past learning data. The learning unit can also apply algorithms that improve learning efficiency from past learning data. The learning unit can also analyze past learning data and apply algorithms that improve learning accuracy. As a result, the learning unit improves learning accuracy by optimizing the learning algorithm by referring to past learning data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input past learning data into a generative AI, which can then analyze the data and optimize the learning algorithm.

[0128] The learning unit can estimate the user's emotions and adjust the learning frequency based on the estimated emotions. For example, if the user is stressed, the learning unit can reduce the learning frequency. For example, if the user is relaxed, the learning unit can increase the learning frequency. For example, if the user is in a hurry, the learning unit can adjust the learning frequency. This allows the learning unit to perform appropriate learning by adjusting the learning frequency based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The 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 learning unit may be performed using a generative AI, or not using a generative AI. For example, the learning unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the learning frequency.

[0129] The learning unit can weight the training data based on the transmission timing of the interactions during training. For example, the learning unit can assign a high weight to interactions sent in the early morning. It can also assign a low weight to interactions sent late at night. It can also assign a medium weight to interactions sent on weekends. This allows the learning unit to perform appropriate training by weighting the training data based on the transmission timing of the interactions. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input the transmission timing data of the interactions into a generative AI, which can then analyze the transmission timing and weight the training data.

[0130] The suggestion unit can estimate the user's emotions and adjust the way the suggestion is expressed based on the estimated emotions. For example, if the user is angry, the suggestion unit can make calm and polite suggestions. If the user is happy, the suggestion unit can also make bright and positive suggestions. If the user is sad, the suggestion unit can also make comforting suggestions. In this way, the suggestion unit can make appropriate suggestions by adjusting the way the suggestion is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the suggestion unit may be performed using a generative AI, or not using a generative AI. For example, the suggestion unit can input user emotion data into a generative AI, which can estimate the emotion and adjust the way the suggestion is expressed.

[0131] The proposal department can adjust the level of detail of its proposals based on the importance of the interactions when considering the content of the proposals. For example, the proposal department can provide detailed proposals for high-importance interactions. For example, it can provide concise proposals for low-importance interactions. For example, it can provide proposals with an appropriate level of detail for moderately important interactions. In this way, the proposal department can provide appropriate proposals by adjusting the level of detail of the proposals based on the importance of the interactions. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal department can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail of the proposals.

[0132] The proposal unit can apply different proposal algorithms depending on the category of the interaction when considering proposal content. For example, the proposal unit can apply a formal proposal algorithm to business-related interactions. For example, the proposal unit can apply a casual proposal algorithm to private interactions. For example, the proposal unit can apply a rapid proposal algorithm to urgent interactions. In this way, the proposal unit can make appropriate proposals by applying a proposal algorithm according to the category of the interaction. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input interaction category data into a generative AI, which can analyze the categories and apply an appropriate proposal algorithm.

[0133] The suggestion unit can estimate the user's emotions and adjust the length of the suggestion based on the estimated emotions. For example, if the user is in a hurry, the suggestion unit will provide a short, to-the-point suggestion. If the user is relaxed, the suggestion unit may provide a longer suggestion with detailed explanations. If the user is excited, the suggestion unit may provide a suggestion with visually stimulating effects. This allows the suggestion unit to provide appropriate suggestions by adjusting the length of the suggestion 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 suggestion unit may be performed using or without a generative AI. For example, the suggestion unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the length of the suggestion.

[0134] The proposal department can determine the priority of proposals based on the timing of communication transmissions when considering proposal content. For example, the proposal department can make prompt proposals for communication transmitted early in the morning. For example, the proposal department can propose making a proposal the following morning for communication transmitted late at night. For example, the proposal department can propose making a proposal at the beginning of the week for communication transmitted over the weekend. In this way, the proposal department can make appropriate proposals by determining the priority of proposals based on the timing of communication transmissions. Some or all of the above processing in the proposal department may be performed using, for example, a generative AI, or not using a generative AI. For example, the proposal department can input communication transmission timing data into a generative AI, which can analyze the transmission timing and determine the priority of proposals.

[0135] The proposal unit can adjust the order of proposals based on the relevance of the interactions when considering the content of the proposals. For example, the proposal unit can propose prioritizing proposals for highly relevant interactions. For example, the proposal unit can propose postponing proposals for less relevant interactions. For example, the proposal unit can propose making proposals with an appropriate priority for interactions of moderate relevance. In this way, the proposal unit can make appropriate proposals by adjusting the order of proposals based on the relevance of the interactions. Some or all of the above processing in the proposal unit may be performed using, for example, a generative AI, or without a generative AI. For example, the proposal unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of proposals.

[0136] The efficiency unit can estimate the user's emotions and adjust the efficiency method based on the estimated emotions. For example, if the user is stressed, the efficiency unit can suggest a simple and easy-to-implement efficiency method. For example, if the user is relaxed, the efficiency unit can suggest a detailed efficiency method. For example, if the user is in a hurry, the efficiency unit can suggest an efficiency method that can be implemented quickly. In this way, the efficiency unit can achieve appropriate efficiency by adjusting the efficiency method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the efficiency unit may be performed using a generative AI, or not using a generative AI. For example, the efficiency unit can input user emotion data into a generative AI, which can estimate the emotions and adjust the efficiency method.

[0137] The efficiency improvement unit can adjust the level of detail in its efficiency improvements based on the importance of the interaction. For example, the efficiency improvement unit can propose detailed efficiency improvements for high-importance interactions. For example, it can propose concise efficiency improvements for low-importance interactions. For example, it can propose efficiency improvements with an appropriate level of detail for moderately important interactions. In this way, the efficiency improvement unit can achieve appropriate efficiency improvements by adjusting the level of detail in its efficiency improvements based on the importance of the interaction. Some or all of the above processing in the efficiency improvement unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the efficiency improvement unit can input interaction importance data into a generative AI, which can analyze the importance and adjust the level of detail in its efficiency improvements.

[0138] The efficiency unit can apply different efficiency algorithms depending on the category of the interaction when performing efficiency improvements. For example, the efficiency unit can apply a formal efficiency algorithm to business-related interactions. For example, it can apply a casual efficiency algorithm to private interactions. For example, it can apply a rapid efficiency algorithm to urgent interactions. In this way, the efficiency unit can achieve appropriate efficiency by applying an efficiency algorithm according to the category of the interaction. Some or all of the above processing in the efficiency unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the efficiency unit can input interaction category data into a generative AI, the generative AI can analyze the categories, and apply an appropriate efficiency algorithm.

[0139] The efficiency unit can estimate the user's emotions and determine efficiency priorities based on those emotions. For example, if the user is stressed, the efficiency unit will prioritize displaying efficiency methods of high importance. If the user is relaxed, the efficiency unit can also display efficiency methods in chronological order. If the user is in a hurry, the efficiency unit can also display efficiency methods of high urgency first. This allows the efficiency unit to perform appropriate efficiency improvements by determining efficiency priorities 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 efficiency unit may be performed using a generative AI, or not. For example, the efficiency unit can input user emotion data into a generative AI, which can estimate the emotions and determine efficiency priorities.

[0140] The efficiency improvement unit can determine the priority of efficiency improvements based on the timing of communication transmissions when implementing efficiency improvements. For example, the efficiency improvement unit can propose quick efficiency improvements for communications sent early in the morning. For communications sent late at night, the efficiency improvement unit can also propose compiling efficiency improvements the following morning. For communications sent over the weekend, the efficiency improvement unit can also propose compiling efficiency improvements at the beginning of the following week. This allows the efficiency improvement unit to implement appropriate efficiency improvements by determining the priority of efficiency improvements based on the timing of communication transmissions. Some or all of the above processing in the efficiency improvement unit may be performed using, for example, a generative AI, or without a generative AI. For example, the efficiency improvement unit can input communication transmission timing data into a generative AI, which can analyze the transmission timing and determine the priority of efficiency improvements.

[0141] The efficiency optimization unit can adjust the order of optimization based on the relevance of interactions when performing optimization. For example, the efficiency optimization unit may suggest prioritizing the grouping of optimization methods for highly relevant interactions. For example, the efficiency optimization unit may suggest postponing less relevant interactions. For example, the efficiency optimization unit may suggest grouping optimization methods with an appropriate priority for interactions of moderate relevance. In this way, the efficiency optimization unit can achieve appropriate optimization by adjusting the order of optimization based on the relevance of interactions. Some or all of the above processing in the efficiency optimization unit may be performed using, for example, a generative AI, or without a generative AI. For example, the efficiency optimization unit can input interaction relevance data into a generative AI, which can analyze the relevance and adjust the order of optimization.

[0142] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0143] The AICA system can estimate the user's emotions and adjust message priority based on those emotions. For example, if the user is stressed, high-importance messages can be displayed preferentially. If the user is relaxed, messages can be displayed in chronological order. Furthermore, if the user is in a hurry, urgent messages can be displayed first. This allows the user to check messages optimally according to their current emotions. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the processing described above in the confirmation unit may be performed using generative AI or not.

[0144] The AICA system can analyze a user's past behavior patterns and prioritize the display of high-priority messages. For example, it can prioritize displaying messages from people the user has frequently interacted with in the past. It can also analyze the content of messages the user previously deemed important and prioritize the display of similar messages. Furthermore, it can prioritize the display of messages the user previously viewed during specific time periods. This allows users to prioritize the display of important messages based on their past behavior patterns. Some or all of the above processing in the confirmation unit may be performed using generative AI, or it may be performed without using generative AI.

[0145] The AICA system can adjust how messages are viewed, taking into account the user's current situation. For example, if the user is in a meeting, only high-priority messages can be notified. If the user is on the move, messages can be read aloud. Furthermore, if the user is on a break, all messages can be displayed at once. This allows the user to view messages in an appropriate manner according to their current situation. Some or all of the above processing in the confirmation unit may be performed using generative AI, or it may be performed without using generative AI.

[0146] The AICA system can prioritize displaying highly relevant messages by taking into account the user's geographical location. For example, if the user is in a specific location, messages related to that location can be displayed preferentially. Similarly, if the user is traveling, messages related to their travel destination can be displayed preferentially. Furthermore, if the user is at home, messages related to their home can be displayed preferentially. This allows the user to prioritize displaying highly relevant messages based on their geographical location. Some or all of the above processing in the verification unit may be performed using a generation AI, or it may be performed without using a generation AI.

[0147] The AICA system can analyze a user's social media activity and prioritize the display of relevant messages. For example, it can prioritize displaying messages from people the user frequently interacts with on a particular social media platform. It can also prioritize displaying messages related to topics the user is interested in on social media. Furthermore, it can prioritize displaying messages from accounts the user follows on social media. This allows users to prioritize the display of relevant messages based on their social media activity. Some or all of the above processing in the verification unit may be performed using generative AI, or it may be performed without using generative AI.

[0148] The AICA system can estimate the user's emotions and adjust the tone of its response based on those emotions. For example, if the user is angry, it can suggest a calm and polite response. If the user is happy, it can suggest a bright and positive response. Furthermore, if the user is sad, it can suggest a comforting response. This allows the user to respond with an appropriate tone according to their emotions at the time. Emotion estimation is achieved using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the response section may be performed using generative AI or not.

[0149] The AICA system can adjust the level of detail in a reply based on the importance of the message when formulating a response. For example, it can suggest a detailed reply for a highly important message, a concise reply for a less important message, and a reply of moderate detail for a message of moderate importance. This allows users to send replies with appropriate detail according to the importance of the message. Some or all of the above processing in the reply section may be performed using generative AI, or it may be performed without using generative AI.

[0150] The AICA system can apply different reply algorithms depending on the message category when considering reply content. For example, a formal reply algorithm can be applied to business-related messages, a casual reply algorithm to private messages, and a rapid reply algorithm to urgent messages. This allows users to apply the appropriate reply algorithm according to the message category. Some or all of the above processing in the reply section may be performed using generative AI, or it may be performed without using generative AI.

[0151] The AICA system can estimate the user's emotions and adjust the length of the reply based on the estimated emotion. For example, if the user is in a hurry, it can suggest a short, to-the-point reply. If the user is relaxed, it can suggest a longer reply with detailed explanations. Furthermore, if the user is excited, it can suggest a reply with visually stimulating effects. This allows the user to reply with an appropriate length according to their emotions at the time. Emotion estimation is achieved using an emotion engine or generative AI, etc. Generative AI includes, but is not limited to, text generation AI or multimodal generation AI. Some or all of the above processing in the reply section may be performed using generative AI or not.

[0152] The AICA system can determine the priority of replies based on when the message was sent when considering the content of the reply. For example, it can suggest a quick reply to a message sent early in the morning. It can also suggest replying the following morning to a message sent late at night. Furthermore, it can suggest replying at the beginning of the week to a message sent over the weekend. This allows users to reply with appropriate priority based on when the message was sent. Some or all of the above processing in the reply section may be performed using generative AI, or it may be performed without using generative AI.

[0153] The following briefly describes the processing flow for example form 2.

[0154] Step 1: The verification unit checks messages addressed to the user. For example, it can automatically scan messages received by the user and classify them according to their importance. It can also analyze the content of messages and identify those that require a reply. Furthermore, it can set priorities based on the sender and content of the messages. Step 2: The reply section considers the reply content based on the message confirmed by the confirmation section. For example, it can refer to past exchanges to generate appropriate reply content. It can also use reply templates to quickly create reply content. Furthermore, it can automatically generate reply content and suggest it to the user. Step 3: The comment section observes the user's interactions and suggests appropriate comments. For example, it can analyze channel conversations and DM content to generate appropriate comments. It can also refer to past interactions to suggest appropriate comments. Furthermore, it can quickly create comments using comment templates. Step 4: The task manager compiles tasks and deadlines based on user interactions. For example, they can analyze channel conversations and direct messages to identify tasks and their deadlines. They can also prioritize tasks and notify users. Furthermore, they can manage task progress and provide feedback to users. Step 5: The Actions Department proposes future action plans. For example, they can analyze channel interactions and direct mail content to propose what needs to be done and what initiatives should be pursued. They can also use action plan templates to quickly create proposals. Furthermore, they can automatically generate proposals and present them to users.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the confirmation unit, reply unit, comment unit, task unit, action unit, learning unit, proposal unit, and efficiency unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the confirmation unit is implemented by the control unit 46A of the smart device 14 and confirms the message addressed to the user. The reply unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates reply content by referring to past interactions. The comment unit is implemented by the control unit 46A of the smart device 14 and proposes appropriate comments by looking at the interactions in which the user is participating. The task unit is implemented by the specific processing unit 290 of the data processing unit 12 and summarizes what needs to be done and by when. The action unit is implemented by the control unit 46A of the smart device 14 and proposes a future action plan. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's past interactions and information. The proposal unit is implemented by the control unit 46A of the smart device 14 and makes proposals based on the learned information. The efficiency improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and streamlines user interaction based on the proposed content. 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.

[0159] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.).

[0171] 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.

[0172] 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.

[0173] 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.

[0174] Each of the multiple elements described above, including the confirmation unit, reply unit, comment unit, task unit, action unit, learning unit, suggestion unit, and efficiency unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the confirmation unit is implemented by the control unit 46A of the smart glasses 214 and confirms the message addressed to the user. The reply unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates reply content by referring to past interactions. The comment unit is implemented by the control unit 46A of the smart glasses 214 and suggests appropriate comments by looking at the interactions the user is participating in. The task unit is implemented by the specific processing unit 290 of the data processing unit 12 and summarizes what needs to be done and by when. The action unit is implemented by the control unit 46A of the smart glasses 214 and suggests a future action plan. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's past interactions and information. The suggestion unit is implemented, for example, by the control unit 46A of the smart glasses 214, and makes suggestions based on learned information. The efficiency improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and improves the efficiency of user interaction based on the suggested content. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0175] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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).

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.).

[0187] 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.

[0188] 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.

[0189] 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.

[0190] Each of the multiple elements described above, including the confirmation unit, reply unit, comment unit, task unit, action unit, learning unit, proposal unit, and efficiency unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the confirmation unit is implemented by the control unit 46A of the headset terminal 314 and confirms the message addressed to the user. The reply unit is implemented by the specific processing unit 290 of the data processing unit 12 and generates reply content by referring to past interactions. The comment unit is implemented by the control unit 46A of the headset terminal 314 and proposes appropriate comments by looking at the interactions in which the user is participating. The task unit is implemented by the specific processing unit 290 of the data processing unit 12 and summarizes what needs to be done and by when. The action unit is implemented by the control unit 46A of the headset terminal 314 and proposes a future action plan. The learning unit is implemented by the specific processing unit 290 of the data processing unit 12 and learns the user's past interactions and information. The suggestion unit is implemented, for example, by the control unit 46A of the headset terminal 314, and makes suggestions based on the learned information. The efficiency improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and improves the efficiency of user interaction based on the suggested content. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0191] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.).

[0204] 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.

[0205] 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.

[0206] 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.

[0207] Each of the multiple elements described above, including the confirmation unit, reply unit, comment unit, task unit, action unit, learning unit, proposal unit, and efficiency unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the confirmation unit is implemented by the control unit 46A of the robot 414 and confirms the message addressed to the user. The reply unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and generates reply content by referring to past interactions. The comment unit is implemented by, for example, the control unit 46A of the robot 414 and proposes appropriate comments by looking at the interactions in which the user is participating. The task unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and summarizes what needs to be done and by when. The action unit is implemented by, for example, the control unit 46A of the robot 414 and proposes a future action plan. The learning unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and learns the user's past interactions and information. The proposal unit is implemented by, for example, the control unit 46A of the robot 414 and makes proposals based on the learned information. The efficiency improvement unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and streamlines user interaction based on the proposed content. 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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."

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] (Note 1) A confirmation section for checking messages addressed to the user, A reply unit considers the content of the reply based on the message confirmed by the confirmation unit, The comment section observes user interactions and suggests appropriate comments, The task department compiles tasks and deadlines based on the interactions the user is involved in, It includes an Action Department that proposes future action plans, A system characterized by the following features. (Note 2) It includes a learning unit that learns from the user's past interactions and Confluence information. The system described in Appendix 1, characterized by the features described herein. (Note 3) The system includes a proposal unit that makes suggestions based on the information learned by the aforementioned learning unit. The system described in Appendix 2, characterized by the features described herein. (Note 4) The aforementioned proposal section is, It features an efficiency unit that streamlines user interactions. The system described in Appendix 3, characterized by the features described herein. (Note 5) The aforementioned reply section is, Based on the user's previous interactions and Confluence information, we suggest appropriate replies. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned comment section is, Based on the user's interactions in the channels they participate in and the content of their direct messages, we suggest appropriate comments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned task unit is Based on the user's interactions in the channels and the content of direct messages, summarize the tasks that need to be done and their deadlines. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned action unit is Based on the user's interactions and DM content across various channels, we propose future actions and initiatives. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned verification unit is It estimates the user's emotions and adjusts the message review order based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned verification unit is When reviewing messages, the system analyzes the user's past behavior patterns and prioritizes reviewing high-priority messages. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned verification unit is When checking messages, the checking method is adjusted to take into account the user's current situation. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned verification unit is It estimates the user's emotions and adjusts how messages are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned verification unit is When reviewing messages, the system prioritizes displaying the most relevant messages by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned verification unit is When reviewing messages, the system analyzes the user's social media activity and prioritizes reviewing relevant messages. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned reply section is, It estimates the user's emotions and adjusts the tone of the response based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned reply section is, When formulating a reply, adjust the level of detail based on the importance of the message. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned reply section is, When formulating a reply, we apply different reply algorithms depending on the message category. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned reply section is, It estimates the user's emotions and adjusts the length of the reply based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned reply section is, When considering what to reply to, prioritize replies based on when the message was sent. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned reply section is, When considering what to reply to, adjust the order of replies based on the relevance of the messages. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned comment section is, It estimates the user's emotions and adjusts the way comments are expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned comment section is, When suggesting comments, adjust the level of detail based on the importance of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned comment section is, When suggesting comments, different comment algorithms are applied depending on the category of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned comment section is, It estimates the user's sentiment and adjusts the length of comments based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned comment section is, When suggesting comments, prioritize them based on when they were sent. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned comment section is, When suggesting comments, adjust the order of comments based on their relevance to the conversation. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned task unit is It estimates the user's emotions and determines task priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned task unit is When compiling tasks, adjust the level of detail based on the importance of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned task unit is When grouping tasks, apply different task management algorithms depending on the category of interaction. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned task unit is It estimates the user's emotions and adjusts how tasks are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned task unit is When compiling tasks, prioritize them based on when the communication was sent. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned task unit is When compiling tasks, adjust the order of tasks based on the relevance of the interactions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned action unit is We estimate the user's emotions and adjust how we propose action plans based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned action unit is When proposing an action plan, adjust the level of detail in the plan based on the importance of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned action unit is When proposing an action plan, different action plan algorithms are applied depending on the category of the interaction. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned action unit is Estimate user emotions and prioritize action plans based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned action unit is When proposing an action plan, prioritize the action plan based on when the communication was sent. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned action unit is When proposing an action plan, adjust the order of the action plan based on the relevance of the interactions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned learning unit, The system estimates the user's emotions and selects training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Supplementary Note 40) The learning unit optimizes the learning algorithm by referring to past learning data during learning. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 41) The learning unit estimates the user's emotion and adjusts the learning frequency based on the estimated user's emotion. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 42) The learning unit weights the learning data based on the transmission time of the interaction during learning. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 43) The proposal unit estimates the user's emotion and adjusts the expression method of the proposed content based on the estimated user's emotion. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 44) The proposal unit adjusts the detail level of the proposal based on the importance of the interaction when considering the proposed content. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 45) The proposal unit applies different proposal algorithms according to the category of the interaction when considering the proposed content. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 46) The proposal unit estimates the user's emotion and adjusts the length of the proposal based on the estimated user's emotion. The system according to Supplementary Note 1, characterized in that. (Supplementary Note 47) The proposal unit determines the priority of the proposal based on the transmission time of the interaction when considering the proposed content. [[ID=6T3]]The system according to Supplementary Note 1, characterized in that. (Supplementary Note 48) The aforementioned proposal section is, When considering proposals, adjust the order of proposals based on the relevance of the interactions. The system described in Appendix 1, characterized by the features described herein. (Note 49) The aforementioned efficiency improvement unit is It estimates the user's emotions and adjusts the optimization method based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 50) The aforementioned efficiency improvement unit is When implementing efficiency improvements, adjust the level of detail based on the importance of the interaction. The system described in Appendix 3, characterized by the features described herein. (Note 51) The aforementioned efficiency improvement unit is When implementing efficiency improvements, different efficiency algorithms are applied depending on the category of the interaction. The system described in Appendix 3, characterized by the features described herein. (Note 52) The aforementioned efficiency improvement unit is It estimates user emotions and determines efficiency priorities based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 53) The aforementioned efficiency improvement unit is When implementing efficiency improvements, prioritize them based on the timing of communication transmissions. The system described in Appendix 3, characterized by the features described herein. (Note 54) The aforementioned efficiency improvement unit is When implementing efficiency improvements, adjust the order of improvements based on the relevance of the interactions. The system described in Appendix 3, characterized by the features described herein. [Explanation of symbols]

[0227] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A confirmation section for checking messages addressed to the user, A reply unit considers the content of the reply based on the message confirmed by the confirmation unit, The comment section observes user interactions and suggests appropriate comments, The task department compiles tasks and deadlines based on the interactions the user is involved in, It includes an Action Department that proposes future action plans, A system characterized by the following features.

2. It includes a learning unit that learns from the user's past interactions. The system according to feature 1.

3. The system includes a proposal unit that makes suggestions based on the information learned by the aforementioned learning unit. The system according to feature 2.

4. The aforementioned proposal section is, It features an efficiency unit that streamlines user interactions. The system according to claim 3.

5. The aforementioned reply section is, Based on the user's previous interactions and Confluence information, we suggest appropriate replies. The system according to feature 1.

6. The aforementioned comment section is, Based on the user's interactions in the channels they participate in and the content of their direct messages, we suggest appropriate comments. The system according to feature 1.

7. The aforementioned task unit is Based on the user's interactions in the channels and the content of direct messages, summarize the tasks that need to be done and their deadlines. The system according to feature 1.

8. The aforementioned action unit is Based on the user's interactions and DM content across various channels, we propose future actions and initiatives. The system according to feature 1.

9. The aforementioned verification unit is It estimates the user's emotions and adjusts the message review order based on the estimated emotions. The system according to feature 1.

Images