system

Abstract

Provide a system. 【Solution means】 Means for collecting and analyzing the user's past communication data, Means for training an artificial intelligence model that generates an automatic response based on the communication data, Means for automatically generating and sending a response to newly received information, Means for evaluating urgency and immediately notifying important information, Means for summarizing and reporting the received information, Means for performing sentiment analysis on the response data to improve the inquiry response, Means for saving the automatically generated summary and making it available later, A system including the above.

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, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] During work vacations, users constantly receive email and chat notifications, cannot relax even when setting absence notifications, and further feel depressed about a large number of unprocessed emails after the vacation. In such cases, there is a need for means for users to take vacations with peace of mind.

Means for Solving the Problems

[0005] To address this challenge, the system will implement a mechanism for collecting and analyzing users' past communication data and train an AI model to generate automated responses based on this data. For newly received messages, it will automatically generate responses and send customized responses based on company policies and response templates. Furthermore, it will assess urgency to immediately notify users of important messages, summarize received messages in reports, and send summary reports to support users' swift return to work at the end of their vacation.

[0006] "Communication data" refers to records of emails and chat messages that a user has sent or received in the past.

[0007] "Automated response" refers to a response generated by AI in response to a received message.

[0008] An "AI model" is an algorithm that uses machine learning techniques to learn a user's past response patterns and generate responses appropriate to new situations.

[0009] "Customization" refers to a method of applying company policies or specific templates to standard responses and adjusting the content as needed.

[0010] "Assessing urgency" is the process of determining the importance and priority of a message based on its content.

[0011] A "summary report" refers to a form of information that extracts the main points of multiple messages and presents them concisely.

[0012] "Early return to work for users" means enabling them to smoothly access important information after vacation and quickly return to their normal duties. [Brief explanation of the drawing]

[0013] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [[ID=V37]] [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, a communication I / F (Interface) with a reference number is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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 A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0025] 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.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input 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 device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] The 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.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is a system designed to allow users to relax and enjoy their vacation, automatically responding to emails and chats using the user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. After the trained AI model understands the user's writing style and past reply patterns, it generates responses based on this information.

[0035] The device sends newly received emails and chats to the server, where the server's AI model generates an appropriate response. The response may be adjusted based on the company's policies and templates. Furthermore, the server automatically notifies the user of any particularly urgent messages.

[0036] Furthermore, the server summarizes the content of messages received during vacation and provides a report summarizing this information to the user after their vacation. This allows users to quickly grasp important information upon returning from vacation.

[0037] As a concrete example, consider a scenario where a user receives a project-related inquiry while on vacation. The terminal forwards this inquiry to the server, which, based on similar past data, generates an automated response such as, "The person in charge is currently on vacation, but we will address the issue as soon as they return." This response can also be based on a pre-configured template according to company policy.

[0038] This system allows users to enjoy their vacation without being bothered by communication issues, and upon their return, they can quickly return to work thanks to automatically generated summary reports. In this way, the form of implementation of the invention enables unprecedented improvements in work efficiency and user experience.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server collects users' past email and chat data. This includes securely retrieving login information from email accounts and chat applications that users use regularly and storing it in a database.

[0042] Step 2:

[0043] The server analyzes the collected data and uses natural language processing techniques to train an AI model. In this process, it develops the ability to understand the user's writing style and response patterns, and to generate responses to various scenarios.

[0044] Step 3:

[0045] The device receives new emails and chat messages in real time. Received messages are temporarily stored in the device's storage.

[0046] Step 4:

[0047] The terminal sends the received message to the server. The server passes this to an AI model, which generates an appropriate automated response to the message.

[0048] Step 5:

[0049] The server validates the generated automated response and customizes it as needed, referencing corporate policies and existing response templates. This ensures the consistency and appropriateness of the response.

[0050] Step 6:

[0051] The device receives a customized automated response and replies to the original sender. The sending process is automated via email or chat application.

[0052] Step 7:

[0053] The server analyzes the content of incoming messages and assesses their urgency. Messages deemed highly urgent are immediately notified to the user.

[0054] Step 8:

[0055] The server summarizes and stores all messages received during the holiday period. The summaries are designed to allow users to grasp important information concisely.

[0056] Step 9:

[0057] When a user's vacation ends, the server generates a summary report and sends it to their device. This allows the user to quickly understand their situation.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In environments where communication continues even while users are on vacation, it is difficult to ensure they get sufficient rest because they are often interrupted regardless of the urgency of the situation. Furthermore, they face the challenge of having to deal with a large volume of unfinished tasks upon returning to work, leading to increased stress.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for collecting and analyzing the user's past communication information, means for training a generative model, and means for automatically generating and transmitting responses to newly received information. This allows users to rest with peace of mind even while on vacation, and after their vacation ends, they can quickly grasp important information and return to work smoothly.

[0063] "User's past communication information" refers to data related to the history of messages such as emails and chats that the user has previously sent and received.

[0064] A "generative model" is an artificial intelligence model that generates documents using natural language processing techniques and is used to automatically create responses based on specific writing styles and patterns.

[0065] "Newly received information" refers to messages such as emails and chats that a user receives while on vacation.

[0066] A "response template" refers to a standard answer format pre-set by a company or organization, and automatically generated responses based on this template may be adjusted.

[0067] "Assessing urgency and immediately notifying important information" refers to the process of identifying information of high importance and priority from received data and notifying users immediately as needed.

[0068] "Summarizing and reporting" refers to analyzing a large amount of received information, extracting the important parts, and presenting them to the user in an easy-to-understand format.

[0069] This invention is a system that allows users to manage important communications even while on vacation, enabling them to enjoy their holidays with peace of mind. This document provides a detailed explanation of how this system is configured and operates.

[0070] First, the server collects the user's past communication information and stores it in a database. This process utilizes various data retrieval APIs, specifically common mail server APIs and chat service APIs. The collected data is analyzed through text processing and converted into an appropriate format.

[0071] The server uses this data to train a generative AI model. The generative AI model used is one that excels at natural language processing, with a typical example being a "natural language generation model." Through this training, the model becomes able to understand the user's unique writing style and patterns.

[0072] When a terminal detects a newly received message, it sends it to the server. The server uses a trained generative AI model to automatically generate a response to the new message. During the response generation process, it refers to the organization's response templates and customizes them as needed.

[0073] The server also has the ability to determine the urgency of received messages and, through AI models and keyword analysis, immediately notifies users of important messages.

[0074] Furthermore, the server summarizes messages received during the holiday and compiles their contents into a single report. This summarization process utilizes an enhanced text summarization algorithm. The summary report is provided to the user at the end of the holiday to help them quickly grasp the information.

[0075] As a concrete example, consider a scenario where a user on vacation inquires about the progress of a project. Based on past data and response templates, the server automatically generates an appropriate response such as, "The user is currently on vacation, but we will address the issue as soon as the person in charge returns."

[0076] An example of a prompt message would be, "User A has received an inquiry about the project's progress. User A is currently on vacation. Generate an appropriate response for this situation." The AI ​​model would then generate a response based on this prompt.

[0077] Thus, in the embodiment of the present invention, users can efficiently manage their communications during vacation, reduce stress, and quickly return to work after their vacation.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server collects the user's past communication information. This collection is done using email server APIs and chat service APIs. Past communication history is taken as input and stored in a database. Specifically, metadata such as email subject, sender, and body is analyzed and organized.

[0081] Step 2:

[0082] The server trains a generative AI model based on the collected communication information. It utilizes the communication data taken as input. The data is serialized and subjected to text processing, resulting in a format suitable for input to the AI ​​model. The server employs natural language processing techniques to learn the user's writing style and response patterns. The output is the trained generative model.

[0083] Step 3:

[0084] The terminal receives a new message. The reception event occurs in real time, and the message content is sent to the server. The input is the newly received message, which includes the sender, subject, etc. Specifically, the terminal queues the message.

[0085] Step 4:

[0086] The server generates a response based on the received message. The input consists of a generative AI model and the newly received message. The server uses the model to form a prompt and generates an automated response. The output is the generated response message, which may be tailored based on the organization's templates.

[0087] Step 5:

[0088] The terminal sends the generated response back to the sender. The input is the generated response message. The terminal sends the response using the SMTP protocol or chat API. Specifically, it saves a message transmission log.

[0089] Step 6:

[0090] The server evaluates the urgency of received messages. The input is the message body, and it uses AI models and keyword extraction techniques. It detects specific keywords and contexts and notifies the user as needed. The output is notifications to the user for messages deemed highly urgent.

[0091] Step 7:

[0092] The server generates a summary report. The input is all messages received during the vacation. The server uses a text summarization algorithm to aggregate the information and create a report that is easy for the user to understand. The output is a summary report that the user can access and review after the vacation.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In recent years, there has been an increasing demand for quick and appropriate responses from users while they are on vacation and away from work. However, providing immediate responses to all inquiries increases the burden on vacationers and makes it difficult to return to work efficiently. To solve this problem, automated responses to messages received during vacation and notifications of organized information are needed. Accurate sentiment analysis and customized responses to individual inquiries are also crucial.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an artificial intelligence model that generates automatic responses based on that communication data, means for automatically generating and transmitting responses to newly received information, means for evaluating urgency and immediately notifying important information, means for summarizing and reporting the received information, means for performing sentiment analysis on response data to improve inquiry responses, and means for saving the automatically generated summaries and making them available for later use. This allows users to rest with peace of mind during their vacation and to return to work efficiently after their vacation.

[0098] "Communication data" refers to records of electronic information exchanges that users have previously engaged in, including messages such as emails and chats.

[0099] An "artificial intelligence model" is a program based on machine learning algorithms designed to perform a specific task, in this case, one that generates automated responses.

[0100] "Newly received information" refers to any new messages or inquiries that the user has not yet responded to.

[0101] A "means for assessing urgency" is a system that determines the importance and urgency of received information and prompts immediate action as needed.

[0102] "Methods for summarizing and reporting" refer to the process of concisely summarizing received information so that users can easily understand its content.

[0103] "Sentiment analysis" is a process that analyzes the emotional tone and reactions of a received message in order to derive an appropriate response.

[0104] An "automatically generated summary" is a short document created by artificial intelligence processing data, which concisely conveys the essence of the information.

[0105] "Means of saving and making available later" refers to methods for managing generated information and making it accessible to users when needed.

[0106] In this embodiment of the invention, the system is mainly composed of a server and a terminal. The server first collects the user's past communication data into cloud storage and manages the data using Amazon S3 or similar services. Then, it uses AWS® SageMaker to train an AI model based on this data. The trained artificial intelligence model creates automated responses that reflect the user's writing style and past response patterns.

[0107] The device has a means to send newly received emails and chat messages to a server, where an AI model generates appropriate responses. Furthermore, sentiment analysis using Amazon Comprehend assesses the urgency of incoming messages, and important information is immediately notified via Amazon SNS. High-priority messages are notified to the user, while others are handled by automated responses.

[0108] At this time, the server uses natural language processing techniques such as BERT to generate summaries of received messages and saves the automatically generated summaries to storage as needed. After the vacation ends, users can easily review these summarized reports.

[0109] For example, if a user is a freelance writer and receives inquiry messages from multiple publishers while on vacation, the AI ​​model will automatically send responses such as "I am currently on vacation. I will respond later." Furthermore, messages deemed urgent can receive push notifications on the user's smartphone. The generating AI model is prompted with phrases like "Create the optimal response based on past communication history."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects the user's past communication data from cloud storage. User identification information is required as input. It collects email and chat history data stored in Amazon S3 and prepares it as a dataset for the next processing step. The output is training data for a generative AI model.

[0113] Step 2:

[0114] The server uses AWS SageMaker to train a generative AI model based on the collected communication data. The input is the dataset prepared in Step 1. Using this dataset, the AI ​​model learns the user's writing style and past response patterns. The output is an AI model with user-specific response generation patterns.

[0115] Step 3:

[0116] When the device receives a new message, it sends that message to the server. The input is a newly received email or chat message. The information the server receives includes the sender and the content of the message. The output is a notification that the message has been successfully sent to the server.

[0117] Step 4:

[0118] The server analyzes new messages and performs sentiment analysis using AWS Comprehend. The input is the message received in step 3. The server analyzes the emotional tone of the message and assesses its urgency as needed. The output is the urgency assessment result for the message.

[0119] Step 5:

[0120] For messages deemed highly urgent, the server sends a notification to the user via Amazon SNS. The input is the urgency assessment result from step 4. The server generates a push notification and sends it immediately to the user's smartphone. The output is the notification sending completion status.

[0121] Step 6:

[0122] For low-priority messages, the server generates an automated response using a trained AI model. The input is a new message and the AI ​​model. The AI ​​model generates the response using the prompt "Create the optimal response based on past communication history." The output is the generated automated response.

[0123] Step 7:

[0124] The server generates automated responses and summaries, which are then notified to the user or saved for later use. Input is the automated response and message content generated by the AI ​​model. Output is the automated response notification to the user and the status of data storage completion in Amazon S3.

[0125] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0126] This invention combines an emotion engine with a system that automatically responds to emails and chats using a user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. This activity includes analyzing the user's tone of voice and response patterns. The emotion engine then extracts and analyzes emotional data from past communication history to understand the user's emotional tendencies.

[0127] For newly received emails and chat messages, the device receives them in real time and sends them to the server. When the server generates an automated response using an AI model, it incorporates an evaluation of the emotional aspects by an emotion engine and adjusts the tone of the response. In addition, if the emotion engine determines that the content of the received message may cause the user significant stress, it immediately notifies the user of this fact.

[0128] For example, consider a scenario where a user receives an inquiry about a highly debated project while on vacation. The terminal forwards this inquiry to the server, where an AI model generates a response stating, "I am currently on vacation and will address this upon my return." Simultaneously, an emotion engine recognizes signs of tension or anxiety from the communication regarding the project and adjusts the response tone to be more gentle.

[0129] Furthermore, the server summarizes all messages received during the vacation and creates a report that includes emotional feedback analyzed by the sentiment engine, which is then provided to the user upon their return. This allows the user to quickly grasp the situation, including important information and emotional impact.

[0130] In this way, systems that incorporate an emotion engine reduce the psychological burden on users while improving work efficiency and response quality.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server collects users' past email and chat data. This data includes message content, sending date and time, and sender information.

[0134] Step 2:

[0135] The server analyzes the collected data and trains an AI model. In this process, it systematically learns the user's writing style and response patterns.

[0136] Step 3:

[0137] The server uses an emotion engine to extract emotional data from past communication history and analyze it to understand the user's emotional tendencies.

[0138] Step 4:

[0139] The device receives newly arrived emails and chat messages in real time and sends them to the server.

[0140] Step 5:

[0141] The server inputs the received message into an AI model and generates an automated response. The tone of the generated response is then adjusted using the results of the emotion engine's analysis.

[0142] Step 6:

[0143] The server's sentiment engine evaluates whether an incoming message might cause stress to the user, and if so, immediately notifies the user.

[0144] Step 7:

[0145] The terminal receives a pre-arranged automated response sent from the server and automatically replies to the sender.

[0146] Step 8:

[0147] The server compiles messages received during the holiday and creates a summary report that includes changes in emotions.

[0148] Step 9:

[0149] When a user returns from vacation, the device receives a summary report from the server, allowing the user to quickly understand the situation.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] Existing electronic communication systems face challenges such as the cumbersome manual handling of the large number of messages users receive, leading to increased psychological burden. Furthermore, the failure to immediately notify users of urgent messages creates a risk of missing important information. Additionally, responses that disregard the user's emotional state can hinder smooth communication. Therefore, there is a need to automate message handling while ensuring responses that are sensitive to the user's emotions.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an intelligent algorithm that generates automatic responses based on that communication data, and means for understanding the user's emotional tendencies and adjusting the tone of the response using that information. As a result, the user can receive responses that have been automatically adjusted based on past data, enabling efficient, emotionally sensitive, and smooth communication.

[0155] "Communication data" refers to digital information, including messages and associated information, that a user has previously sent or received.

[0156] An "intelligent algorithm" refers to a computational method used to analyze data and generate automated responses, and specifically refers to a program that possesses learning capabilities.

[0157] "Adjusting the tone of responses" refers to the process of changing the tone and style of generated responses according to the user's emotional state.

[0158] "Urgency" is a criterion for evaluating whether a received message requires immediate attention.

[0159] "Summarizing and reporting" is the process of presenting a concise summary of the received message to the user.

[0160] "Organizational regulations" refer to guidelines and policies established by a company or organization, and serve as the basis for decision-making and actions.

[0161] A "response template" is a template that shows a standard response pattern used in specific situations.

[0162] "Emotional tendencies" refer to the patterns and tendencies of emotions that a user has shown in past communications.

[0163] This invention is an automated response system designed to effectively utilize user communication data and reduce the burden on users. This system is primarily operated by a server and terminals.

[0164] The server first collects the user's past communication data. This includes extracting data from email servers. The server processes this data to generate a dataset for the intelligent algorithm to learn from. This learning process uses the Python programming language to provide data to the intelligent algorithm. Deep learning frameworks such as Tensorflow® and PyTorch are particularly used.

[0165] In parallel, the server utilizes an emotion engine to perform sentiment analysis. This emotion engine employs an API for analyzing emotional tone. This API extracts emotional tone from text within communication data to understand the user's emotional tendencies.

[0166] When a terminal receives a new message, it immediately sends that information to the server. This information is securely transmitted using encryption technology. The server uses this information to input prompts into an AI model, which then generates a response. An example of a prompt sent at this time would be, "Generate an appropriate reply while maintaining the user's tone."

[0167] As a concrete example, consider a scenario where a user receives a work-related message while on vacation. Upon receiving this message, the server automatically sends a response such as, "The user is currently on vacation; we will address this upon their return." This response is generated by an intelligent algorithm and verified by an emotion engine.

[0168] This system configuration allows users to maintain communication automatically and in an emotionally sensitive manner while reducing their psychological burden.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server collects the user's past communication data from the email server. This collection retrieves email text and metadata associated with a specific user ID via a database connection. The inputs collected in this process include email body, sending and receiving date and time, and sender information. This data is converted into a structured data format for use in subsequent data analysis steps. The output is a dataset in a parseable format.

[0172] Step 2:

[0173] The server trains a generative AI model using the dataset obtained in Step 1. The input data here consists of text data and metadata. The server preprocesses the data, converting the text into an appropriate format such as vector format, and then supplies it to the intelligent algorithm. The intelligent algorithm uses machine learning techniques to train a response generation model. The output is a model that has learned user response patterns.

[0174] Step 3:

[0175] The server analyzes the dataset obtained from Step 1 using an emotion engine. The input data is email text data. The emotion engine extracts emotional tones from the text using, for example, natural language processing techniques to understand the user's emotional tendencies. The output is the user's emotion profile. This profile is used in subsequent response generation.

[0176] Step 4:

[0177] The terminal detects newly received messages and forwards the data to the server. This process uses the content of the new message, sender information, and the date and time of receipt as input. The terminal securely transmits the data to the server using an encryption protocol. The output is the new message information received by the server.

[0178] Step 5:

[0179] The server generates an automated response based on the new message information obtained in step 4. A generation AI model is used for this process. The input consists of the new message information and the trained AI model, and the server provides the model with the prompt "Generate an appropriate response while maintaining the user's tone." Furthermore, the response is adjusted based on a previously analyzed sentiment profile. The output is an automated response with an appropriate emotional tone.

[0180] Step 6:

[0181] The server immediately responds to incoming messages by sending a generated automated response. It also notifies the user if the message is important or stressful, based on the sentiment engine's evaluation. The input here is the generated response message, which the server uses to execute the appropriate message sending procedure. The output is the sent response message and notification.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In today's information environment, the diversification of communication methods has led to an increase in the amount of information users receive, making it more complex to select important messages and manage stress within that information. Furthermore, the impact of psychological stress on users' work efficiency and health cannot be ignored. In this context, there is a need for methods that enable users to efficiently receive and respond to appropriate information without experiencing excessive burden.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for collecting and analyzing the user's past information exchange data, means for evaluating the emotional impact of received messages using an emotion engine, and for detecting and notifying psychological stress based on that evaluation, and means for immediately notifying important messages and providing summary information including the emotion evaluation results. This enables users to efficiently manage messages, reduce psychological burden, and improve their quality of work and life.

[0187] A "user" is an individual or organization that uses the system to exchange information.

[0188] "Information exchange data" refers to the content of communications such as emails and chats that users have previously exchanged.

[0189] An "artificial intelligence model" is an algorithm or system that is trained to generate automated responses based on information exchange data.

[0190] An "emotion engine" is an engine or system that analyzes the emotional impact of a received message and evaluates the results.

[0191] "Psychological stress" refers to the mental burden and tension caused by the content of messages that users encounter.

[0192] "Summary information" is a concise summary of the entire content of a received message, extracting the key points that are important to the user.

[0193] "Instant notification" is a means of communication that quickly informs users of important messages.

[0194] A "template" refers to a standard response format based on organizational regulations.

[0195] "Organizational regulations" refer to a set of rules or guidelines established by a company or organization.

[0196] The system that realizes this invention consists of a server, a terminal, and a user. The server first collects and analyzes the user's past information exchange data. This analysis includes natural language processing to understand the user's language use and response patterns.

[0197] The system processes data using computing resources on the cloud (e.g., AWS EC2). The server uses Python and libraries such as Scikit-learn and Hugging Face Transformers to train an artificial intelligence model based on user communication data. This model analyzes the user's tone of voice and word choice, contributing to the generation of automated responses.

[0198] The terminal operates on smartphones and tablets and is responsible for sending newly received messages to the server. The server analyzes data in real time using TensorFlow Lite and Firebase Realtime Database, and generates automated responses using artificial intelligence models. In this process, the emotion engine evaluates the emotional impact of the received messages, and if psychological burden is detected, it immediately notifies the user and the organization's security team.

[0199] For example, if a user receives work-related messages while on vacation, the server analyzes the stress indicators contained in those messages and generates an appropriate response. At the same time, it provides summary information of the received messages in preparation for when the user returns after their vacation.

[0200] Examples of prompt statements for a generative AI model are as follows:

[0201] "Please enter your email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations."

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] The server collects past information exchange data from users. Emails and chat logs are provided as input, and this data is stored in a database. This collected data is then used in subsequent training processes.

[0205] Step 2:

[0206] The server uses the collected data to train an artificial intelligence model. It analyzes user response patterns and tone using NLP techniques, employing Python's Scikit-learn and Hugging Face Transformers. The input is information exchange data, and the output is a model related to user response generation.

[0207] Step 3:

[0208] The terminal sends a newly received message to the server. This message is the input, and the server receives it and prepares to generate the next automated response.

[0209] Step 4:

[0210] The server uses an artificial intelligence model to generate an automated response to incoming messages. The input is a new message, and the output is the automated response text. This automated response is enhanced in terms of individuality and relevance because it is based on the user's past data.

[0211] Step 5:

[0212] The server uses an emotion engine to evaluate the emotional impact of incoming messages. The input is the incoming message, the calculation involves sentiment analysis, and the output is a psychological stress index. Based on this evaluation, immediate notification is provided if necessary.

[0213] Step 6:

[0214] The server selects important messages and immediately notifies users. It also generates summary information, including sentiment evaluation results. The input is the sentiment evaluation result and the message content, and the output is summary information. This enables the rapid communication of important information to users.

[0215] Step 7:

[0216] The user inputs information using prompts directed to the generating AI model. The prompt, "Please enter email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations," simplifies the processing of necessary information.

[0217] 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.

[0218] Data generation model 58 is a 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> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] 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.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0224] 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.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0226] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] 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.

[0228] 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 using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The 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.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0233] This invention is a system designed to allow users to relax and enjoy their vacation, automatically responding to emails and chats using the user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. After the trained AI model understands the user's writing style and past reply patterns, it generates responses based on this information.

[0234] The device sends newly received emails and chats to the server, where the server's AI model generates an appropriate response. The response may be adjusted based on the company's policies and templates. Furthermore, the server automatically notifies the user of any particularly urgent messages.

[0235] Furthermore, the server summarizes the content of messages received during vacation and provides a report summarizing this information to the user after their vacation. This allows users to quickly grasp important information upon returning from vacation.

[0236] As a concrete example, consider a scenario where a user receives a project-related inquiry while on vacation. The terminal forwards this inquiry to the server, which, based on similar past data, generates an automated response such as, "The person in charge is currently on vacation, but we will address the issue as soon as they return." This response can also be based on a pre-configured template according to company policy.

[0237] This system allows users to enjoy their vacation without being bothered by communication issues, and upon their return, they can quickly return to work thanks to automatically generated summary reports. In this way, the form of implementation of the invention enables unprecedented improvements in work efficiency and user experience.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server collects users' past email and chat data. This includes securely retrieving login information from email accounts and chat applications that users use regularly and storing it in a database.

[0241] Step 2:

[0242] The server analyzes the collected data and uses natural language processing techniques to train an AI model. In this process, it develops the ability to understand the user's writing style and response patterns, and to generate responses to various scenarios.

[0243] Step 3:

[0244] The device receives new emails and chat messages in real time. Received messages are temporarily stored in the device's storage.

[0245] Step 4:

[0246] The terminal sends the received message to the server. The server passes this to an AI model, which generates an appropriate automated response to the message.

[0247] Step 5:

[0248] The server validates the generated automated response and customizes it as needed, referencing corporate policies and existing response templates. This ensures the consistency and appropriateness of the response.

[0249] Step 6:

[0250] The device receives a customized automated response and replies to the original sender. The sending process is automated via email or chat application.

[0251] Step 7:

[0252] The server analyzes the content of incoming messages and assesses their urgency. Messages deemed highly urgent are immediately notified to the user.

[0253] Step 8:

[0254] The server summarizes and stores all messages received during the holiday period. The summaries are designed to allow users to grasp important information concisely.

[0255] Step 9:

[0256] When a user's vacation ends, the server generates a summary report and sends it to their device. This allows the user to quickly understand their situation.

[0257] (Example 1)

[0258] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0259] In environments where communication continues even while users are on vacation, it is difficult to ensure they get sufficient rest because they are often interrupted regardless of the urgency of the situation. Furthermore, they face the challenge of having to deal with a large volume of unfinished tasks upon returning to work, leading to increased stress.

[0260] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0261] In this invention, the server includes means for collecting and analyzing the user's past communication information, means for training a generative model, and means for automatically generating and transmitting responses to newly received information. This allows users to rest with peace of mind even while on vacation, and after their vacation ends, they can quickly grasp important information and return to work smoothly.

[0262] "User's past communication information" refers to data related to the history of messages such as emails and chats that the user has previously sent and received.

[0263] A "generative model" is an artificial intelligence model that generates documents using natural language processing techniques and is used to automatically create responses based on specific writing styles and patterns.

[0264] "Newly received information" refers to messages such as emails and chats that a user receives while on vacation.

[0265] A "response template" refers to a standard answer format pre-set by a company or organization, and automatically generated responses based on this template may be adjusted.

[0266] "Assessing urgency and immediately notifying important information" refers to the process of identifying information of high importance and priority from received data and notifying users immediately as needed.

[0267] "Summarizing and reporting" refers to analyzing a large amount of received information, extracting the important parts, and presenting them to the user in an easy-to-understand format.

[0268] This invention is a system that allows users to manage important communications even while on vacation, enabling them to enjoy their holidays with peace of mind. This document provides a detailed explanation of how this system is configured and operates.

[0269] First, the server collects the user's past communication information and stores it in a database. This process utilizes various data retrieval APIs, specifically common mail server APIs and chat service APIs. The collected data is analyzed through text processing and converted into an appropriate format.

[0270] The server uses this data to train a generative AI model. The generative AI model used is one that excels at natural language processing, with a typical example being a "natural language generation model." Through this training, the model becomes able to understand the user's unique writing style and patterns.

[0271] When a terminal detects a newly received message, it sends it to the server. The server uses a trained generative AI model to automatically generate a response to the new message. During the response generation process, it refers to the organization's response templates and customizes them as needed.

[0272] The server also has the ability to determine the urgency of received messages and, through AI models and keyword analysis, immediately notifies users of important messages.

[0273] Furthermore, the server summarizes messages received during the holiday and compiles their contents into a single report. This summarization process utilizes an enhanced text summarization algorithm. The summary report is provided to the user at the end of the holiday to help them quickly grasp the information.

[0274] As a concrete example, consider a scenario where a user on vacation inquires about the progress of a project. Based on past data and response templates, the server automatically generates an appropriate response such as, "The user is currently on vacation, but we will address the issue as soon as the person in charge returns."

[0275] An example of a prompt message would be, "User A has received an inquiry about the project's progress. User A is currently on vacation. Generate an appropriate response for this situation." The AI ​​model would then generate a response based on this prompt.

[0276] Thus, in the embodiment of the present invention, users can efficiently manage their communications during vacation, reduce stress, and quickly return to work after their vacation.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The server collects the user's past communication information. This collection is carried out using the email server API and the chat service API. There is past communication history as input, which is saved in the database. Specifically, metadata such as the subject, sender, and body of the email are analyzed and sorted out.

[0280] Step 2:

[0281] The server trains a generated AI model based on the collected communication information. It utilizes the communication data imported as input. The data is serialized and subjected to text processing. As a result, it is in a format suitable for the input of the AI model. The server makes use of natural language processing technology to learn the user's writing style and reply pattern. The output is the trained generation model.

[0282] Step 3:

[0283] The terminal receives a new message. The reception event occurs in real time, and the message content is sent to the server. The input is the newly received message, which contains the sender, subject, etc. As a specific operation, the terminal puts the message into a queue.

[0284] Step 4:

[0285] The server generates a response based on the received message. The inputs are the generated AI model and the newly received message. The server uses the model to form a prompt sentence and generate an automatic response. The output is the generated response message, which may be adjusted based on the organization's template.

[0286] Step 5:

[0287] The terminal replies to the sender with the generated response. The input is the generated response message. The terminal sends the response using the SMTP protocol or the chat API. As a specific operation, it saves the message sending log.

[0288] Step 6:

[0289] The server evaluates the urgency of received messages. The input is the message body, and it uses AI models and keyword extraction techniques. It detects specific keywords and contexts and notifies the user as needed. The output is notifications to the user for messages deemed highly urgent.

[0290] Step 7:

[0291] The server generates a summary report. The input is all messages received during the vacation. The server uses a text summarization algorithm to aggregate the information and create a report that is easy for the user to understand. The output is a summary report that the user can access and review after the vacation.

[0292] (Application Example 1)

[0293] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0294] In recent years, there has been an increasing demand for quick and appropriate responses from users while they are on vacation and away from work. However, providing immediate responses to all inquiries increases the burden on vacationers and makes it difficult to return to work efficiently. To solve this problem, automated responses to messages received during vacation and notifications of organized information are needed. Accurate sentiment analysis and customized responses to individual inquiries are also crucial.

[0295] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0296] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an artificial intelligence model that generates automatic responses based on that communication data, means for automatically generating and transmitting responses to newly received information, means for evaluating urgency and immediately notifying important information, means for summarizing and reporting the received information, means for performing sentiment analysis on response data to improve inquiry responses, and means for saving the automatically generated summaries and making them available for later use. This allows users to rest with peace of mind during their vacation and to return to work efficiently after their vacation.

[0297] "Communication data" refers to records of electronic information exchanges that users have previously engaged in, including messages such as emails and chats.

[0298] An "artificial intelligence model" is a program based on machine learning algorithms designed to perform a specific task, in this case, one that generates automated responses.

[0299] "Newly received information" refers to any new messages or inquiries that the user has not yet responded to.

[0300] A "means for assessing urgency" is a system that determines the importance and urgency of received information and prompts immediate action as needed.

[0301] "Methods for summarizing and reporting" refer to the process of concisely summarizing received information so that users can easily understand its content.

[0302] "Sentiment analysis" is a process that analyzes the emotional tone and reactions of a received message in order to derive an appropriate response.

[0303] An "automatically generated summary" is a short document created by artificial intelligence processing data, which concisely conveys the essence of the information.

[0304] The "means for saving and making available later" is a method for managing the generated information so that it can be referred to by the user when needed.

[0305] In an embodiment of this invention, the system is mainly composed of a server and a terminal. The server first collects the user's past communication data in cloud storage and manages the data using Amazon S3 or the like. Then, based on these data, it utilizes AWS SageMaker to train a generative AI model. The trained artificial intelligence model creates an automatic response that reflects the user's writing style and past response patterns.

[0306] The terminal is equipped with means for sending newly received emails and chat messages to the server, and the AI model on the server generates appropriate responses to these. Also, through sentiment analysis using Amazon Comprehend, the urgency of the received message is evaluated, and important information is immediately notified via Amazon SNS. Messages with a high degree of importance are notified to the user, while others are processed with an automatic response.

[0307] At this time, the server utilizes natural language processing technology such as BERT to generate a summary of the received message and saves the automatically generated summary in storage as needed. After the vacation ends, the user can easily check these summarized reports.

[0308] For example, if the user is a freelance writer and receives inquiry messages from multiple publishers during vacation, the AI model automatically sends responses such as "Currently on vacation. I will respond later" to these inquiries. Also, messages determined to be highly urgent can be sent as push notifications to the user's smartphone. For the generative AI model, a prompt sentence such as "Create an optimal response based on the past communication history" is utilized.

[0309] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0310] Step 1:

[0311] The server collects the user's past communication data from cloud storage. User identification information is required as input. It collects email and chat history data stored in Amazon S3 and prepares it as a dataset for the next processing step. The output is training data for a generative AI model.

[0312] Step 2:

[0313] The server uses AWS SageMaker to train a generative AI model based on the collected communication data. The input is the dataset prepared in Step 1. Using this dataset, the AI ​​model learns the user's writing style and past response patterns. The output is an AI model with user-specific response generation patterns.

[0314] Step 3:

[0315] When the device receives a new message, it sends that message to the server. The input is a newly received email or chat message. The information the server receives includes the sender and the content of the message. The output is a notification that the message has been successfully sent to the server.

[0316] Step 4:

[0317] The server analyzes new messages and performs sentiment analysis using AWS Comprehend. The input is the message received in step 3. The server analyzes the emotional tone of the message and assesses its urgency as needed. The output is the urgency assessment result for the message.

[0318] Step 5:

[0319] For messages deemed highly urgent, the server sends a notification to the user via Amazon SNS. The input is the urgency assessment result from step 4. The server generates a push notification and sends it immediately to the user's smartphone. The output is the notification sending completion status.

[0320] Step 6:

[0321] For low-priority messages, the server generates an automated response using a trained AI model. The input is a new message and the AI ​​model. The AI ​​model generates the response using the prompt "Create the optimal response based on past communication history." The output is the generated automated response.

[0322] Step 7:

[0323] The server generates automated responses and summaries, which are then notified to the user or saved for later use. Input is the automated response and message content generated by the AI ​​model. Output is the automated response notification to the user and the status of data storage completion in Amazon S3.

[0324] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0325] This invention combines an emotion engine with a system that automatically responds to emails and chats using a user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. This activity includes analyzing the user's tone of voice and response patterns. The emotion engine then extracts and analyzes emotional data from past communication history to understand the user's emotional tendencies.

[0326] For newly received emails and chat messages, the device receives them in real time and sends them to the server. When the server generates an automated response using an AI model, it incorporates an evaluation of the emotional aspects by an emotion engine and adjusts the tone of the response. In addition, if the emotion engine determines that the content of the received message may cause the user significant stress, it immediately notifies the user of this fact.

[0327] For example, consider a scenario where a user receives an inquiry about a highly debated project while on vacation. The terminal forwards this inquiry to the server, where an AI model generates a response stating, "I am currently on vacation and will address this upon my return." Simultaneously, an emotion engine recognizes signs of tension or anxiety from the communication regarding the project and adjusts the response tone to be more gentle.

[0328] Furthermore, the server summarizes all messages received during the vacation and creates a report that includes emotional feedback analyzed by the sentiment engine, which is then provided to the user upon their return. This allows the user to quickly grasp the situation, including important information and emotional impact.

[0329] In this way, systems that incorporate an emotion engine reduce the psychological burden on users while improving work efficiency and response quality.

[0330] The following describes the processing flow.

[0331] Step 1:

[0332] The server collects users' past email and chat data. This data includes message content, sending date and time, and sender information.

[0333] Step 2:

[0334] The server analyzes the collected data and trains an AI model. In this process, it systematically learns the user's writing style and response patterns.

[0335] Step 3:

[0336] The server uses an emotion engine to extract emotional data from past communication history and analyze it to understand the user's emotional tendencies.

[0337] Step 4:

[0338] The device receives newly arrived emails and chat messages in real time and sends them to the server.

[0339] Step 5:

[0340] The server inputs the received message into an AI model and generates an automated response. The tone of the generated response is then adjusted using the results of the emotion engine's analysis.

[0341] Step 6:

[0342] The server's sentiment engine evaluates whether an incoming message might cause stress to the user, and if so, immediately notifies the user.

[0343] Step 7:

[0344] The terminal receives a pre-arranged automated response sent from the server and automatically replies to the sender.

[0345] Step 8:

[0346] The server compiles messages received during the holiday and creates a summary report that includes changes in emotions.

[0347] Step 9:

[0348] When a user returns from vacation, the device receives a summary report from the server, allowing the user to quickly understand the situation.

[0349] (Example 2)

[0350] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0351] Existing electronic communication systems face challenges such as the cumbersome manual handling of the large number of messages users receive, leading to increased psychological burden. Furthermore, the failure to immediately notify users of urgent messages creates a risk of missing important information. Additionally, responses that disregard the user's emotional state can hinder smooth communication. Therefore, there is a need to automate message handling while ensuring responses that are sensitive to the user's emotions.

[0352] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0353] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an intelligent algorithm that generates automatic responses based on that communication data, and means for understanding the user's emotional tendencies and adjusting the tone of the response using that information. As a result, the user can receive responses that have been automatically adjusted based on past data, enabling efficient, emotionally sensitive, and smooth communication.

[0354] "Communication data" refers to digital information, including messages and associated information, that a user has previously sent or received.

[0355] An "intelligent algorithm" refers to a computational method used to analyze data and generate automated responses, and specifically refers to a program that possesses learning capabilities.

[0356] "Adjusting the tone of responses" refers to the process of changing the tone and style of generated responses according to the user's emotional state.

[0357] "Urgency" is a criterion for evaluating whether a received message requires immediate attention.

[0358] "Summarizing and reporting" is the process of presenting a concise summary of the received message to the user.

[0359] "Organizational regulations" refer to guidelines and policies established by a company or organization, and serve as the basis for decision-making and actions.

[0360] A "response template" is a template that shows a standard response pattern used in specific situations.

[0361] "Emotional tendencies" refer to the patterns and tendencies of emotions that a user has shown in past communications.

[0362] This invention is an automated response system designed to effectively utilize user communication data and reduce the burden on users. This system is primarily operated by a server and terminals.

[0363] The server first collects the user's past communication data. This includes extracting data from email servers. The server processes this data to generate a dataset for the intelligent algorithm to train. This training involves providing data to the intelligent algorithm using the Python programming language. Deep learning frameworks such as TensorFlow and PyTorch are particularly used.

[0364] In parallel, the server utilizes an emotion engine to perform sentiment analysis. This emotion engine employs an API for analyzing emotional tone. This API extracts emotional tone from text within communication data to understand the user's emotional tendencies.

[0365] When a terminal receives a new message, it immediately sends that information to the server. This information is securely transmitted using encryption technology. The server uses this information to input prompts into an AI model, which then generates a response. An example of a prompt sent at this time would be, "Generate an appropriate reply while maintaining the user's tone."

[0366] As a concrete example, consider a scenario where a user receives a work-related message while on vacation. Upon receiving this message, the server automatically sends a response such as, "The user is currently on vacation; we will address this upon their return." This response is generated by an intelligent algorithm and verified by an emotion engine.

[0367] This system configuration allows users to maintain communication automatically and in an emotionally sensitive manner while reducing their psychological burden.

[0368] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0369] Step 1:

[0370] The server collects the user's past communication data from the email server. This collection retrieves email text and metadata associated with a specific user ID via a database connection. The inputs collected in this process include email body, sending and receiving date and time, and sender information. This data is converted into a structured data format for use in subsequent data analysis steps. The output is a dataset in a parseable format.

[0371] Step 2:

[0372] The server trains a generative AI model using the dataset obtained in Step 1. The input data here consists of text data and metadata. The server preprocesses the data, converting the text into an appropriate format such as vector format, and then supplies it to the intelligent algorithm. The intelligent algorithm uses machine learning techniques to train a response generation model. The output is a model that has learned user response patterns.

[0373] Step 3:

[0374] The server analyzes the dataset obtained from Step 1 using an emotion engine. The input data is email text data. The emotion engine extracts emotional tones from the text using, for example, natural language processing techniques to understand the user's emotional tendencies. The output is the user's emotion profile. This profile is used in subsequent response generation.

[0375] Step 4:

[0376] The terminal detects newly received messages and forwards the data to the server. This process uses the content of the new message, sender information, and the date and time of receipt as input. The terminal securely transmits the data to the server using an encryption protocol. The output is the new message information received by the server.

[0377] Step 5:

[0378] The server generates an automated response based on the new message information obtained in step 4. A generation AI model is used for this process. The input consists of the new message information and the trained AI model, and the server provides the model with the prompt "Generate an appropriate response while maintaining the user's tone." Furthermore, the response is adjusted based on a previously analyzed sentiment profile. The output is an automated response with an appropriate emotional tone.

[0379] Step 6:

[0380] The server immediately responds to incoming messages by sending a generated automated response. It also notifies the user if the message is important or stressful, based on the sentiment engine's evaluation. The input here is the generated response message, which the server uses to execute the appropriate message sending procedure. The output is the sent response message and notification.

[0381] (Application Example 2)

[0382] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0383] In today's information environment, the diversification of communication methods has led to an increase in the amount of information users receive, making it more complex to select important messages and manage stress within that information. Furthermore, the impact of psychological stress on users' work efficiency and health cannot be ignored. In this context, there is a need for methods that enable users to efficiently receive and respond to appropriate information without experiencing excessive burden.

[0384] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0385] In this invention, the server includes means for collecting and analyzing the user's past information exchange data, means for evaluating the emotional impact of received messages using an emotion engine, and for detecting and notifying psychological stress based on that evaluation, and means for immediately notifying important messages and providing summary information including the emotion evaluation results. This enables users to efficiently manage messages, reduce psychological burden, and improve their quality of work and life.

[0386] A "user" is an individual or organization that uses the system to exchange information.

[0387] "Information exchange data" refers to the content of communications such as emails and chats that users have previously exchanged.

[0388] An "artificial intelligence model" is an algorithm or system that is trained to generate automated responses based on information exchange data.

[0389] An "emotion engine" is an engine or system that analyzes the emotional impact of a received message and evaluates the results.

[0390] "Psychological stress" refers to the mental burden and tension caused by the content of messages that users encounter.

[0391] "Summary information" is a concise summary of the entire content of a received message, extracting the key points that are important to the user.

[0392] "Instant notification" is a means of communication that quickly informs users of important messages.

[0393] A "template" refers to a standard response format based on organizational regulations.

[0394] "Organizational regulations" refer to a set of rules or guidelines established by a company or organization.

[0395] The system that realizes this invention consists of a server, a terminal, and a user. The server first collects and analyzes the user's past information exchange data. This analysis includes natural language processing to understand the user's language use and response patterns.

[0396] The system processes data using computing resources on the cloud (e.g., AWS EC2). The server uses Python and libraries such as Scikit-learn and Hugging Face Transformers to train an artificial intelligence model based on user communication data. This model analyzes the user's tone of voice and word choice, contributing to the generation of automated responses.

[0397] The terminal operates on smartphones and tablets and is responsible for sending newly received messages to the server. The server analyzes data in real time using TensorFlow Lite and Firebase Realtime Database, and generates automated responses using artificial intelligence models. In this process, the emotion engine evaluates the emotional impact of the received messages, and if psychological burden is detected, it immediately notifies the user and the organization's security team.

[0398] For example, if a user receives work-related messages while on vacation, the server analyzes the stress indicators contained in those messages and generates an appropriate response. At the same time, it provides summary information of the received messages in preparation for when the user returns after their vacation.

[0399] Examples of prompt statements for a generative AI model are as follows:

[0400] "Please enter your email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations."

[0401] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0402] Step 1:

[0403] The server collects past information exchange data from users. Emails and chat logs are provided as input, and this data is stored in a database. This collected data is then used in subsequent training processes.

[0404] Step 2:

[0405] The server uses the collected data to train an artificial intelligence model. It analyzes user response patterns and tone using NLP techniques, employing Python's Scikit-learn and Hugging Face Transformers. The input is information exchange data, and the output is a model related to user response generation.

[0406] Step 3:

[0407] The terminal sends a newly received message to the server. This message is the input, and the server receives it and prepares to generate the next automated response.

[0408] Step 4:

[0409] The server uses an artificial intelligence model to generate an automated response to incoming messages. The input is a new message, and the output is the automated response text. This automated response is enhanced in terms of individuality and relevance because it is based on the user's past data.

[0410] Step 5:

[0411] The server uses an emotion engine to evaluate the emotional impact of incoming messages. The input is the incoming message, the calculation involves sentiment analysis, and the output is a psychological stress index. Based on this evaluation, immediate notification is provided if necessary.

[0412] Step 6:

[0413] The server selects important messages and immediately notifies users. It also generates summary information, including sentiment evaluation results. The input is the sentiment evaluation result and the message content, and the output is summary information. This enables the rapid communication of important information to users.

[0414] Step 7:

[0415] The user inputs information using prompts directed to the generating AI model. The prompt, "Please enter email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations," simplifies the processing of necessary information.

[0416] 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.

[0417] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0418] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0419] [Third Embodiment]

[0420] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0421] 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.

[0422] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0423] 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.

[0424] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0425] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0426] 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.

[0427] 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.

[0428] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0429] The 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.

[0430] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0431] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0432] This invention is a system designed to allow users to relax and enjoy their vacation, automatically responding to emails and chats using the user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. After the trained AI model understands the user's writing style and past reply patterns, it generates responses based on this information.

[0433] The device sends newly received emails and chats to the server, where the server's AI model generates an appropriate response. The response may be adjusted based on the company's policies and templates. Furthermore, the server automatically notifies the user of any particularly urgent messages.

[0434] Furthermore, the server summarizes the content of messages received during vacation and provides a report summarizing this information to the user after their vacation. This allows users to quickly grasp important information upon returning from vacation.

[0435] As a concrete example, consider a scenario where a user receives a project-related inquiry while on vacation. The terminal forwards this inquiry to the server, which, based on similar past data, generates an automated response such as, "The person in charge is currently on vacation, but we will address the issue as soon as they return." This response can also be based on a pre-configured template according to company policy.

[0436] This system allows users to enjoy their vacation without being bothered by communication issues, and upon their return, they can quickly return to work thanks to automatically generated summary reports. In this way, the form of implementation of the invention enables unprecedented improvements in work efficiency and user experience.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] The server collects users' past email and chat data. This includes securely retrieving login information from email accounts and chat applications that users use regularly and storing it in a database.

[0440] Step 2:

[0441] The server analyzes the collected data and uses natural language processing techniques to train an AI model. In this process, it develops the ability to understand the user's writing style and response patterns, and to generate responses to various scenarios.

[0442] Step 3:

[0443] The device receives new emails and chat messages in real time. Received messages are temporarily stored in the device's storage.

[0444] Step 4:

[0445] The terminal sends the received message to the server. The server passes this to an AI model, which generates an appropriate automated response to the message.

[0446] Step 5:

[0447] The server validates the generated automated response and customizes it as needed, referencing corporate policies and existing response templates. This ensures the consistency and appropriateness of the response.

[0448] Step 6:

[0449] The device receives a customized automated response and replies to the original sender. The sending process is automated via email or chat application.

[0450] Step 7:

[0451] The server analyzes the content of incoming messages and assesses their urgency. Messages deemed highly urgent are immediately notified to the user.

[0452] Step 8:

[0453] The server summarizes and stores all messages received during the holiday period. The summaries are designed to allow users to grasp important information concisely.

[0454] Step 9:

[0455] When a user's vacation ends, the server generates a summary report and sends it to their device. This allows the user to quickly understand their situation.

[0456] (Example 1)

[0457] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0458] In environments where communication continues even while users are on vacation, it is difficult to ensure they get sufficient rest because they are often interrupted regardless of the urgency of the situation. Furthermore, they face the challenge of having to deal with a large volume of unfinished tasks upon returning to work, leading to increased stress.

[0459] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0460] In this invention, the server includes means for collecting and analyzing the user's past communication information, means for training a generative model, and means for automatically generating and transmitting responses to newly received information. This allows users to rest with peace of mind even while on vacation, and after their vacation ends, they can quickly grasp important information and return to work smoothly.

[0461] "User's past communication information" refers to data related to the history of messages such as emails and chats that the user has previously sent and received.

[0462] A "generative model" is an artificial intelligence model that generates documents using natural language processing techniques and is used to automatically create responses based on specific writing styles and patterns.

[0463] "Newly received information" refers to messages such as emails and chats that a user receives while on vacation.

[0464] A "response template" refers to a standard answer format pre-set by a company or organization, and automatically generated responses based on this template may be adjusted.

[0465] "Assessing urgency and immediately notifying important information" refers to the process of identifying information of high importance and priority from received data and notifying users immediately as needed.

[0466] "Summarizing and reporting" refers to analyzing a large amount of received information, extracting the important parts, and presenting them to the user in an easy-to-understand format.

[0467] This invention is a system that allows users to manage important communications even while on vacation, enabling them to enjoy their holidays with peace of mind. This document provides a detailed explanation of how this system is configured and operates.

[0468] First, the server collects the user's past communication information and stores it in a database. This process utilizes various data retrieval APIs, specifically common mail server APIs and chat service APIs. The collected data is analyzed through text processing and converted into an appropriate format.

[0469] The server uses this data to train a generative AI model. The generative AI model used is one that excels at natural language processing, with a typical example being a "natural language generation model." Through this training, the model becomes able to understand the user's unique writing style and patterns.

[0470] When a terminal detects a newly received message, it sends it to the server. The server uses a trained generative AI model to automatically generate a response to the new message. During the response generation process, it refers to the organization's response templates and customizes them as needed.

[0471] The server also has the ability to determine the urgency of received messages and, through AI models and keyword analysis, immediately notifies users of important messages.

[0472] Furthermore, the server summarizes messages received during the holiday and compiles their contents into a single report. This summarization process utilizes an enhanced text summarization algorithm. The summary report is provided to the user at the end of the holiday to help them quickly grasp the information.

[0473] As a concrete example, consider a scenario where a user on vacation inquires about the progress of a project. Based on past data and response templates, the server automatically generates an appropriate response such as, "The user is currently on vacation, but we will address the issue as soon as the person in charge returns."

[0474] An example of a prompt message would be, "User A has received an inquiry about the project's progress. User A is currently on vacation. Generate an appropriate response for this situation." The AI ​​model would then generate a response based on this prompt.

[0475] Thus, in the embodiment of the present invention, users can efficiently manage their communications during vacation, reduce stress, and quickly return to work after their vacation.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The server collects the user's past communication information. This collection is done using email server APIs and chat service APIs. Past communication history is taken as input and stored in a database. Specifically, metadata such as email subject, sender, and body is analyzed and organized.

[0479] Step 2:

[0480] The server trains a generative AI model based on the collected communication information. It utilizes the communication data taken as input. The data is serialized and subjected to text processing, resulting in a format suitable for input to the AI ​​model. The server employs natural language processing techniques to learn the user's writing style and response patterns. The output is the trained generative model.

[0481] Step 3:

[0482] The terminal receives a new message. The reception event occurs in real time, and the message content is sent to the server. The input is the newly received message, which includes the sender, subject, etc. Specifically, the terminal queues the message.

[0483] Step 4:

[0484] The server generates a response based on the received message. The input consists of a generative AI model and the newly received message. The server uses the model to form a prompt and generates an automated response. The output is the generated response message, which may be tailored based on the organization's templates.

[0485] Step 5:

[0486] The terminal sends the generated response back to the sender. The input is the generated response message. The terminal sends the response using the SMTP protocol or chat API. Specifically, it saves a message transmission log.

[0487] Step 6:

[0488] The server evaluates the urgency of received messages. The input is the message body, and it uses AI models and keyword extraction techniques. It detects specific keywords and contexts and notifies the user as needed. The output is notifications to the user for messages deemed highly urgent.

[0489] Step 7:

[0490] The server generates a summary report. The input is all messages received during the vacation. The server uses a text summarization algorithm to aggregate the information and create a report that is easy for the user to understand. The output is a summary report that the user can access and review after the vacation.

[0491] (Application Example 1)

[0492] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0493] In recent years, there has been an increasing demand for quick and appropriate responses from users while they are on vacation and away from work. However, providing immediate responses to all inquiries increases the burden on vacationers and makes it difficult to return to work efficiently. To solve this problem, automated responses to messages received during vacation and notifications of organized information are needed. Accurate sentiment analysis and customized responses to individual inquiries are also crucial.

[0494] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0495] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an artificial intelligence model that generates automatic responses based on that communication data, means for automatically generating and transmitting responses to newly received information, means for evaluating urgency and immediately notifying important information, means for summarizing and reporting the received information, means for performing sentiment analysis on response data to improve inquiry responses, and means for saving the automatically generated summaries and making them available for later use. This allows users to rest with peace of mind during their vacation and to return to work efficiently after their vacation.

[0496] "Communication data" refers to records of electronic information exchanges that users have previously engaged in, including messages such as emails and chats.

[0497] An "artificial intelligence model" is a program based on machine learning algorithms designed to perform a specific task, in this case, one that generates automated responses.

[0498] "Newly received information" refers to any new messages or inquiries that the user has not yet responded to.

[0499] A "means for assessing urgency" is a system that determines the importance and urgency of received information and prompts immediate action as needed.

[0500] "Methods for summarizing and reporting" refer to the process of concisely summarizing received information so that users can easily understand its content.

[0501] "Sentiment analysis" is a process that analyzes the emotional tone and reactions of a received message in order to derive an appropriate response.

[0502] An "automatically generated summary" is a short document created by artificial intelligence processing data, which concisely conveys the essence of the information.

[0503] "Means of saving and making available later" refers to methods for managing generated information and making it accessible to users when needed.

[0504] In this embodiment of the invention, the system is mainly composed of a server and a terminal. The server first collects the user's past communication data into cloud storage and manages the data using Amazon S3 or similar services. Then, it uses AWS SageMaker to train an AI model based on this data. The trained artificial intelligence model creates automated responses that reflect the user's writing style and past response patterns.

[0505] The device has a means to send newly received emails and chat messages to a server, where an AI model generates appropriate responses. Furthermore, sentiment analysis using Amazon Comprehend assesses the urgency of incoming messages, and important information is immediately notified via Amazon SNS. High-priority messages are notified to the user, while others are handled by automated responses.

[0506] At this time, the server uses natural language processing techniques such as BERT to generate summaries of received messages and saves the automatically generated summaries to storage as needed. After the vacation ends, users can easily review these summarized reports.

[0507] For example, if a user is a freelance writer and receives inquiry messages from multiple publishers while on vacation, the AI ​​model will automatically send responses such as "I am currently on vacation. I will respond later." Furthermore, messages deemed urgent can receive push notifications on the user's smartphone. The generating AI model is prompted with phrases like "Create the optimal response based on past communication history."

[0508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0509] Step 1:

[0510] The server collects the user's past communication data from cloud storage. User identification information is required as input. It collects email and chat history data stored in Amazon S3 and prepares it as a dataset for the next processing step. The output is training data for a generative AI model.

[0511] Step 2:

[0512] The server uses AWS SageMaker to train a generative AI model based on the collected communication data. The input is the dataset prepared in Step 1. Using this dataset, the AI ​​model learns the user's writing style and past response patterns. The output is an AI model with user-specific response generation patterns.

[0513] Step 3:

[0514] When the device receives a new message, it sends that message to the server. The input is a newly received email or chat message. The information the server receives includes the sender and the content of the message. The output is a notification that the message has been successfully sent to the server.

[0515] Step 4:

[0516] The server analyzes new messages and performs sentiment analysis using AWS Comprehend. The input is the message received in step 3. The server analyzes the emotional tone of the message and assesses its urgency as needed. The output is the urgency assessment result for the message.

[0517] Step 5:

[0518] For messages deemed highly urgent, the server sends a notification to the user via Amazon SNS. The input is the urgency assessment result from step 4. The server generates a push notification and sends it immediately to the user's smartphone. The output is the notification sending completion status.

[0519] Step 6:

[0520] For low-priority messages, the server generates an automated response using a trained AI model. The input is a new message and the AI ​​model. The AI ​​model generates the response using the prompt "Create the optimal response based on past communication history." The output is the generated automated response.

[0521] Step 7:

[0522] The server generates automated responses and summaries, which are then notified to the user or saved for later use. Input is the automated response and message content generated by the AI ​​model. Output is the automated response notification to the user and the status of data storage completion in Amazon S3.

[0523] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0524] This invention combines an emotion engine with a system that automatically responds to emails and chats using a user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. This activity includes analyzing the user's tone of voice and response patterns. The emotion engine then extracts and analyzes emotional data from past communication history to understand the user's emotional tendencies.

[0525] For newly received emails and chat messages, the device receives them in real time and sends them to the server. When the server generates an automated response using an AI model, it incorporates an evaluation of the emotional aspects by an emotion engine and adjusts the tone of the response. In addition, if the emotion engine determines that the content of the received message may cause the user significant stress, it immediately notifies the user of this fact.

[0526] For example, consider a scenario where a user receives an inquiry about a highly debated project while on vacation. The terminal forwards this inquiry to the server, where an AI model generates a response stating, "I am currently on vacation and will address this upon my return." Simultaneously, an emotion engine recognizes signs of tension or anxiety from the communication regarding the project and adjusts the response tone to be more gentle.

[0527] Furthermore, the server summarizes all messages received during the vacation and creates a report that includes emotional feedback analyzed by the sentiment engine, which is then provided to the user upon their return. This allows the user to quickly grasp the situation, including important information and emotional impact.

[0528] In this way, systems that incorporate an emotion engine reduce the psychological burden on users while improving work efficiency and response quality.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] The server collects users' past email and chat data. This data includes message content, sending date and time, and sender information.

[0532] Step 2:

[0533] The server analyzes the collected data and trains an AI model. In this process, it systematically learns the user's writing style and response patterns.

[0534] Step 3:

[0535] The server uses an emotion engine to extract emotional data from past communication history and analyze it to understand the user's emotional tendencies.

[0536] Step 4:

[0537] The device receives newly arrived emails and chat messages in real time and sends them to the server.

[0538] Step 5:

[0539] The server inputs the received message into an AI model and generates an automated response. The tone of the generated response is then adjusted using the results of the emotion engine's analysis.

[0540] Step 6:

[0541] The server's sentiment engine evaluates whether an incoming message might cause stress to the user, and if so, immediately notifies the user.

[0542] Step 7:

[0543] The terminal receives a pre-arranged automated response sent from the server and automatically replies to the sender.

[0544] Step 8:

[0545] The server compiles messages received during the holiday and creates a summary report that includes changes in emotions.

[0546] Step 9:

[0547] When a user returns from vacation, the device receives a summary report from the server, allowing the user to quickly understand the situation.

[0548] (Example 2)

[0549] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0550] Existing electronic communication systems face challenges such as the cumbersome manual handling of the large number of messages users receive, leading to increased psychological burden. Furthermore, the failure to immediately notify users of urgent messages creates a risk of missing important information. Additionally, responses that disregard the user's emotional state can hinder smooth communication. Therefore, there is a need to automate message handling while ensuring responses that are sensitive to the user's emotions.

[0551] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0552] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an intelligent algorithm that generates automatic responses based on that communication data, and means for understanding the user's emotional tendencies and adjusting the tone of the response using that information. As a result, the user can receive responses that have been automatically adjusted based on past data, enabling efficient, emotionally sensitive, and smooth communication.

[0553] "Communication data" refers to digital information, including messages and associated information, that a user has previously sent or received.

[0554] An "intelligent algorithm" refers to a computational method used to analyze data and generate automated responses, and specifically refers to a program that possesses learning capabilities.

[0555] "Adjusting the tone of responses" refers to the process of changing the tone and style of generated responses according to the user's emotional state.

[0556] "Urgency" is a criterion for evaluating whether a received message requires immediate attention.

[0557] "Summarizing and reporting" is the process of presenting a concise summary of the received message to the user.

[0558] "Organizational regulations" refer to guidelines and policies established by a company or organization, and serve as the basis for decision-making and actions.

[0559] A "response template" is a template that shows a standard response pattern used in specific situations.

[0560] "Emotional tendencies" refer to the patterns and tendencies of emotions that a user has shown in past communications.

[0561] This invention is an automated response system designed to effectively utilize user communication data and reduce the burden on users. This system is primarily operated by a server and terminals.

[0562] The server first collects the user's past communication data. This includes extracting data from email servers. The server processes this data to generate a dataset for the intelligent algorithm to train. This training involves providing data to the intelligent algorithm using the Python programming language. Deep learning frameworks such as TensorFlow and PyTorch are particularly used.

[0563] In parallel, the server utilizes an emotion engine to perform sentiment analysis. This emotion engine employs an API for analyzing emotional tone. This API extracts emotional tone from text within communication data to understand the user's emotional tendencies.

[0564] When a terminal receives a new message, it immediately sends that information to the server. This information is securely transmitted using encryption technology. The server uses this information to input prompts into an AI model, which then generates a response. An example of a prompt sent at this time would be, "Generate an appropriate reply while maintaining the user's tone."

[0565] As a concrete example, consider a scenario where a user receives a work-related message while on vacation. Upon receiving this message, the server automatically sends a response such as, "The user is currently on vacation; we will address this upon their return." This response is generated by an intelligent algorithm and verified by an emotion engine.

[0566] This system configuration allows users to maintain communication automatically and in an emotionally sensitive manner while reducing their psychological burden.

[0567] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0568] Step 1:

[0569] The server collects the user's past communication data from the email server. This collection retrieves email text and metadata associated with a specific user ID via a database connection. The inputs collected in this process include email body, sending and receiving date and time, and sender information. This data is converted into a structured data format for use in subsequent data analysis steps. The output is a dataset in a parseable format.

[0570] Step 2:

[0571] The server trains a generative AI model using the dataset obtained in Step 1. The input data here consists of text data and metadata. The server preprocesses the data, converting the text into an appropriate format such as vector format, and then supplies it to the intelligent algorithm. The intelligent algorithm uses machine learning techniques to train a response generation model. The output is a model that has learned user response patterns.

[0572] Step 3:

[0573] The server analyzes the dataset obtained from Step 1 using an emotion engine. The input data is email text data. The emotion engine extracts emotional tones from the text using, for example, natural language processing techniques to understand the user's emotional tendencies. The output is the user's emotion profile. This profile is used in subsequent response generation.

[0574] Step 4:

[0575] The terminal detects newly received messages and forwards the data to the server. This process uses the content of the new message, sender information, and the date and time of receipt as input. The terminal securely transmits the data to the server using an encryption protocol. The output is the new message information received by the server.

[0576] Step 5:

[0577] The server generates an automated response based on the new message information obtained in step 4. A generation AI model is used for this process. The input consists of the new message information and the trained AI model, and the server provides the model with the prompt "Generate an appropriate response while maintaining the user's tone." Furthermore, the response is adjusted based on a previously analyzed sentiment profile. The output is an automated response with an appropriate emotional tone.

[0578] Step 6:

[0579] The server immediately responds to incoming messages by sending a generated automated response. It also notifies the user if the message is important or stressful, based on the sentiment engine's evaluation. The input here is the generated response message, which the server uses to execute the appropriate message sending procedure. The output is the sent response message and notification.

[0580] (Application Example 2)

[0581] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0582] In today's information environment, the diversification of communication methods has led to an increase in the amount of information users receive, making it more complex to select important messages and manage stress within that information. Furthermore, the impact of psychological stress on users' work efficiency and health cannot be ignored. In this context, there is a need for methods that enable users to efficiently receive and respond to appropriate information without experiencing excessive burden.

[0583] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0584] In this invention, the server includes means for collecting and analyzing the user's past information exchange data, means for evaluating the emotional impact of received messages using an emotion engine, and for detecting and notifying psychological stress based on that evaluation, and means for immediately notifying important messages and providing summary information including the emotion evaluation results. This enables users to efficiently manage messages, reduce psychological burden, and improve their quality of work and life.

[0585] A "user" is an individual or organization that uses the system to exchange information.

[0586] "Information exchange data" refers to the content of communications such as emails and chats that users have previously exchanged.

[0587] An "artificial intelligence model" is an algorithm or system that is trained to generate automated responses based on information exchange data.

[0588] An "emotion engine" is an engine or system that analyzes the emotional impact of a received message and evaluates the results.

[0589] "Psychological stress" refers to the mental burden and tension caused by the content of messages that users encounter.

[0590] "Summary information" is a concise summary of the entire content of a received message, extracting the key points that are important to the user.

[0591] "Instant notification" is a means of communication that quickly informs users of important messages.

[0592] A "template" refers to a standard response format based on organizational regulations.

[0593] "Organizational regulations" refer to a set of rules or guidelines established by a company or organization.

[0594] The system that realizes this invention consists of a server, a terminal, and a user. The server first collects and analyzes the user's past information exchange data. This analysis includes natural language processing to understand the user's language use and response patterns.

[0595] The system processes data using computing resources on the cloud (e.g., AWS EC2). The server uses Python and libraries such as Scikit-learn and Hugging Face Transformers to train an artificial intelligence model based on user communication data. This model analyzes the user's tone of voice and word choice, contributing to the generation of automated responses.

[0596] The terminal operates on smartphones and tablets and is responsible for sending newly received messages to the server. The server analyzes data in real time using TensorFlow Lite and Firebase Realtime Database, and generates automated responses using artificial intelligence models. In this process, the emotion engine evaluates the emotional impact of the received messages, and if psychological burden is detected, it immediately notifies the user and the organization's security team.

[0597] For example, if a user receives work-related messages while on vacation, the server analyzes the stress indicators contained in those messages and generates an appropriate response. At the same time, it provides summary information of the received messages in preparation for when the user returns after their vacation.

[0598] Examples of prompt statements for a generative AI model are as follows:

[0599] "Please enter your email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations."

[0600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0601] Step 1:

[0602] The server collects past information exchange data from users. Emails and chat logs are provided as input, and this data is stored in a database. This collected data is then used in subsequent training processes.

[0603] Step 2:

[0604] The server uses the collected data to train an artificial intelligence model. It analyzes user response patterns and tone using NLP techniques, employing Python's Scikit-learn and Hugging Face Transformers. The input is information exchange data, and the output is a model related to user response generation.

[0605] Step 3:

[0606] The terminal sends a newly received message to the server. This message is the input, and the server receives it and prepares to generate the next automated response.

[0607] Step 4:

[0608] The server uses an artificial intelligence model to generate an automated response to incoming messages. The input is a new message, and the output is the automated response text. This automated response is enhanced in terms of individuality and relevance because it is based on the user's past data.

[0609] Step 5:

[0610] The server uses an emotion engine to evaluate the emotional impact of incoming messages. The input is the incoming message, the calculation involves sentiment analysis, and the output is a psychological stress index. Based on this evaluation, immediate notification is provided if necessary.

[0611] Step 6:

[0612] The server selects important messages and immediately notifies users. It also generates summary information, including sentiment evaluation results. The input is the sentiment evaluation result and the message content, and the output is summary information. This enables the rapid communication of important information to users.

[0613] Step 7:

[0614] The user inputs information using prompts directed to the generating AI model. The prompt, "Please enter email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations," simplifies the processing of necessary information.

[0615] 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.

[0616] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0617] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0618] [Fourth Embodiment]

[0619] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0620] 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.

[0621] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. 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 (Wide Area Network) and / or a LAN (Local Area Network).

[0622] 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.

[0623] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, 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.

[0624] 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, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0625] 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.

[0626] 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. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0627] 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.

[0628] The specific processing program 56 is an example of a "program" relating 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0629] The 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.

[0630] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0631] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] This invention is a system designed to allow users to relax and enjoy their vacation, automatically responding to emails and chats using the user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. After the trained AI model understands the user's writing style and past reply patterns, it generates responses based on this information.

[0633] The device sends newly received emails and chats to the server, where the server's AI model generates an appropriate response. The response may be adjusted based on the company's policies and templates. Furthermore, the server automatically notifies the user of any particularly urgent messages.

[0634] Furthermore, the server summarizes the content of messages received during vacation and provides a report summarizing this information to the user after their vacation. This allows users to quickly grasp important information upon returning from vacation.

[0635] As a concrete example, consider a scenario where a user receives a project-related inquiry while on vacation. The terminal forwards this inquiry to the server, which, based on similar past data, generates an automated response such as, "The person in charge is currently on vacation, but we will address the issue as soon as they return." This response can also be based on a pre-configured template according to company policy.

[0636] This system allows users to enjoy their vacation without being bothered by communication issues, and upon their return, they can quickly return to work thanks to automatically generated summary reports. In this way, the form of implementation of the invention enables unprecedented improvements in work efficiency and user experience.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The server collects users' past email and chat data. This includes securely retrieving login information from email accounts and chat applications that users use regularly and storing it in a database.

[0640] Step 2:

[0641] The server analyzes the collected data and uses natural language processing techniques to train an AI model. In this process, it develops the ability to understand the user's writing style and response patterns, and to generate responses to various scenarios.

[0642] Step 3:

[0643] The device receives new emails and chat messages in real time. Received messages are temporarily stored in the device's storage.

[0644] Step 4:

[0645] The terminal sends the received message to the server. The server passes this to an AI model, which generates an appropriate automated response to the message.

[0646] Step 5:

[0647] The server validates the generated automated response and customizes it as needed, referencing corporate policies and existing response templates. This ensures the consistency and appropriateness of the response.

[0648] Step 6:

[0649] The device receives a customized automated response and replies to the original sender. The sending process is automated via email or chat application.

[0650] Step 7:

[0651] The server analyzes the content of incoming messages and assesses their urgency. Messages deemed highly urgent are immediately notified to the user.

[0652] Step 8:

[0653] The server summarizes and stores all messages received during the holiday period. The summaries are designed to allow users to grasp important information concisely.

[0654] Step 9:

[0655] When a user's vacation ends, the server generates a summary report and sends it to their device. This allows the user to quickly understand their situation.

[0656] (Example 1)

[0657] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] In environments where communication continues even while users are on vacation, it is difficult to ensure they get sufficient rest because they are often interrupted regardless of the urgency of the situation. Furthermore, they face the challenge of having to deal with a large volume of unfinished tasks upon returning to work, leading to increased stress.

[0659] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0660] In this invention, the server includes means for collecting and analyzing the user's past communication information, means for training a generative model, and means for automatically generating and transmitting responses to newly received information. This allows users to rest with peace of mind even while on vacation, and after their vacation ends, they can quickly grasp important information and return to work smoothly.

[0661] "User's past communication information" refers to data related to the history of messages such as emails and chats that the user has previously sent and received.

[0662] A "generative model" is an artificial intelligence model that generates documents using natural language processing techniques and is used to automatically create responses based on specific writing styles and patterns.

[0663] "Newly received information" refers to messages such as emails and chats that a user receives while on vacation.

[0664] A "response template" refers to a standard answer format pre-set by a company or organization, and automatically generated responses based on this template may be adjusted.

[0665] "Assessing urgency and immediately notifying important information" refers to the process of identifying information of high importance and priority from received data and notifying users immediately as needed.

[0666] "Summarizing and reporting" refers to analyzing a large amount of received information, extracting the important parts, and presenting them to the user in an easy-to-understand format.

[0667] This invention is a system that allows users to manage important communications even while on vacation, enabling them to enjoy their holidays with peace of mind. This document provides a detailed explanation of how this system is configured and operates.

[0668] First, the server collects the user's past communication information and stores it in a database. This process utilizes various data retrieval APIs, specifically common mail server APIs and chat service APIs. The collected data is analyzed through text processing and converted into an appropriate format.

[0669] The server uses this data to train a generative AI model. The generative AI model used is one that excels at natural language processing, with a typical example being a "natural language generation model." Through this training, the model becomes able to understand the user's unique writing style and patterns.

[0670] When a terminal detects a newly received message, it sends it to the server. The server uses a trained generative AI model to automatically generate a response to the new message. During the response generation process, it refers to the organization's response templates and customizes them as needed.

[0671] The server also has the ability to determine the urgency of received messages and, through AI models and keyword analysis, immediately notifies users of important messages.

[0672] Furthermore, the server summarizes messages received during the holiday and compiles their contents into a single report. This summarization process utilizes an enhanced text summarization algorithm. The summary report is provided to the user at the end of the holiday to help them quickly grasp the information.

[0673] As a concrete example, consider a scenario where a user on vacation inquires about the progress of a project. Based on past data and response templates, the server automatically generates an appropriate response such as, "The user is currently on vacation, but we will address the issue as soon as the person in charge returns."

[0674] An example of a prompt message would be, "User A has received an inquiry about the project's progress. User A is currently on vacation. Generate an appropriate response for this situation." The AI ​​model would then generate a response based on this prompt.

[0675] Thus, in the embodiment of the present invention, users can efficiently manage their communications during vacation, reduce stress, and quickly return to work after their vacation.

[0676] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0677] Step 1:

[0678] The server collects the user's past communication information. This collection is done using email server APIs and chat service APIs. Past communication history is taken as input and stored in a database. Specifically, metadata such as email subject, sender, and body is analyzed and organized.

[0679] Step 2:

[0680] The server trains a generative AI model based on the collected communication information. It utilizes the communication data taken as input. The data is serialized and subjected to text processing, resulting in a format suitable for input to the AI ​​model. The server employs natural language processing techniques to learn the user's writing style and response patterns. The output is the trained generative model.

[0681] Step 3:

[0682] The terminal receives a new message. The reception event occurs in real time, and the message content is sent to the server. The input is the newly received message, which includes the sender, subject, etc. Specifically, the terminal queues the message.

[0683] Step 4:

[0684] The server generates a response based on the received message. The input consists of a generative AI model and the newly received message. The server uses the model to form a prompt and generates an automated response. The output is the generated response message, which may be tailored based on the organization's templates.

[0685] Step 5:

[0686] The terminal sends the generated response back to the sender. The input is the generated response message. The terminal sends the response using the SMTP protocol or chat API. Specifically, it saves a message transmission log.

[0687] Step 6:

[0688] The server evaluates the urgency of received messages. The input is the message body, and it uses AI models and keyword extraction techniques. It detects specific keywords and contexts and notifies the user as needed. The output is notifications to the user for messages deemed highly urgent.

[0689] Step 7:

[0690] The server generates a summary report. The input is all messages received during the vacation. The server uses a text summarization algorithm to aggregate the information and create a report that is easy for the user to understand. The output is a summary report that the user can access and review after the vacation.

[0691] (Application Example 1)

[0692] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] In recent years, there has been an increasing demand for quick and appropriate responses from users while they are on vacation and away from work. However, providing immediate responses to all inquiries increases the burden on vacationers and makes it difficult to return to work efficiently. To solve this problem, automated responses to messages received during vacation and notifications of organized information are needed. Accurate sentiment analysis and customized responses to individual inquiries are also crucial.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0695] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an artificial intelligence model that generates automatic responses based on that communication data, means for automatically generating and transmitting responses to newly received information, means for evaluating urgency and immediately notifying important information, means for summarizing and reporting the received information, means for performing sentiment analysis on response data to improve inquiry responses, and means for saving the automatically generated summaries and making them available for later use. This allows users to rest with peace of mind during their vacation and to return to work efficiently after their vacation.

[0696] "Communication data" refers to records of electronic information exchanges that users have previously engaged in, including messages such as emails and chats.

[0697] An "artificial intelligence model" is a program based on machine learning algorithms designed to perform a specific task, in this case, one that generates automated responses.

[0698] "Newly received information" refers to any new messages or inquiries that the user has not yet responded to.

[0699] A "means for assessing urgency" is a system that determines the importance and urgency of received information and prompts immediate action as needed.

[0700] "Methods for summarizing and reporting" refer to the process of concisely summarizing received information so that users can easily understand its content.

[0701] "Sentiment analysis" is a process that analyzes the emotional tone and reactions of a received message in order to derive an appropriate response.

[0702] An "automatically generated summary" is a short document created by artificial intelligence processing data, which concisely conveys the essence of the information.

[0703] "Means of saving and making available later" refers to methods for managing generated information and making it accessible to users when needed.

[0704] In this embodiment of the invention, the system is mainly composed of a server and a terminal. The server first collects the user's past communication data into cloud storage and manages the data using Amazon S3 or similar services. Then, it uses AWS SageMaker to train an AI model based on this data. The trained artificial intelligence model creates automated responses that reflect the user's writing style and past response patterns.

[0705] The device has a means to send newly received emails and chat messages to a server, where an AI model generates appropriate responses. Furthermore, sentiment analysis using Amazon Comprehend assesses the urgency of incoming messages, and important information is immediately notified via Amazon SNS. High-priority messages are notified to the user, while others are handled by automated responses.

[0706] At this time, the server uses natural language processing techniques such as BERT to generate summaries of received messages and saves the automatically generated summaries to storage as needed. After the vacation ends, users can easily review these summarized reports.

[0707] For example, if a user is a freelance writer and receives inquiry messages from multiple publishers while on vacation, the AI ​​model will automatically send responses such as "I am currently on vacation. I will respond later." Furthermore, messages deemed urgent can receive push notifications on the user's smartphone. The generating AI model is prompted with phrases like "Create the optimal response based on past communication history."

[0708] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0709] Step 1:

[0710] The server collects the user's past communication data from cloud storage. User identification information is required as input. It collects email and chat history data stored in Amazon S3 and prepares it as a dataset for the next processing step. The output is training data for a generative AI model.

[0711] Step 2:

[0712] The server uses AWS SageMaker to train a generative AI model based on the collected communication data. The input is the dataset prepared in Step 1. Using this dataset, the AI ​​model learns the user's writing style and past response patterns. The output is an AI model with user-specific response generation patterns.

[0713] Step 3:

[0714] When the device receives a new message, it sends that message to the server. The input is a newly received email or chat message. The information the server receives includes the sender and the content of the message. The output is a notification that the message has been successfully sent to the server.

[0715] Step 4:

[0716] The server analyzes new messages and performs sentiment analysis using AWS Comprehend. The input is the message received in step 3. The server analyzes the emotional tone of the message and assesses its urgency as needed. The output is the urgency assessment result for the message.

[0717] Step 5:

[0718] For messages deemed highly urgent, the server sends a notification to the user via Amazon SNS. The input is the urgency assessment result from step 4. The server generates a push notification and sends it immediately to the user's smartphone. The output is the notification sending completion status.

[0719] Step 6:

[0720] For low-priority messages, the server generates an automated response using a trained AI model. The input is a new message and the AI ​​model. The AI ​​model generates the response using the prompt "Create the optimal response based on past communication history." The output is the generated automated response.

[0721] Step 7:

[0722] The server generates automated responses and summaries, which are then notified to the user or saved for later use. Input is the automated response and message content generated by the AI ​​model. Output is the automated response notification to the user and the status of data storage completion in Amazon S3.

[0723] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0724] This invention combines an emotion engine with a system that automatically responds to emails and chats using a user's past communication data. The server first collects the user's past email and chat data and uses it to train an AI model. This activity includes analyzing the user's tone of voice and response patterns. The emotion engine then extracts and analyzes emotional data from past communication history to understand the user's emotional tendencies.

[0725] For newly received emails and chat messages, the device receives them in real time and sends them to the server. When the server generates an automated response using an AI model, it incorporates an evaluation of the emotional aspects by an emotion engine and adjusts the tone of the response. In addition, if the emotion engine determines that the content of the received message may cause the user significant stress, it immediately notifies the user of this fact.

[0726] For example, consider a scenario where a user receives an inquiry about a highly debated project while on vacation. The terminal forwards this inquiry to the server, where an AI model generates a response stating, "I am currently on vacation and will address this upon my return." Simultaneously, an emotion engine recognizes signs of tension or anxiety from the communication regarding the project and adjusts the response tone to be more gentle.

[0727] Furthermore, the server summarizes all messages received during the vacation and creates a report that includes emotional feedback analyzed by the sentiment engine, which is then provided to the user upon their return. This allows the user to quickly grasp the situation, including important information and emotional impact.

[0728] In this way, systems that incorporate an emotion engine reduce the psychological burden on users while improving work efficiency and response quality.

[0729] The following describes the processing flow.

[0730] Step 1:

[0731] The server collects users' past email and chat data. This data includes message content, sending date and time, and sender information.

[0732] Step 2:

[0733] The server analyzes the collected data and trains an AI model. In this process, it systematically learns the user's writing style and response patterns.

[0734] Step 3:

[0735] The server uses an emotion engine to extract emotional data from past communication history and analyze it to understand the user's emotional tendencies.

[0736] Step 4:

[0737] The device receives newly arrived emails and chat messages in real time and sends them to the server.

[0738] Step 5:

[0739] The server inputs the received message into an AI model and generates an automated response. The tone of the generated response is then adjusted using the results of the emotion engine's analysis.

[0740] Step 6:

[0741] The server's sentiment engine evaluates whether an incoming message might cause stress to the user, and if so, immediately notifies the user.

[0742] Step 7:

[0743] The terminal receives a pre-arranged automated response sent from the server and automatically replies to the sender.

[0744] Step 8:

[0745] The server compiles messages received during the holiday and creates a summary report that includes changes in emotions.

[0746] Step 9:

[0747] When a user returns from vacation, the device receives a summary report from the server, allowing the user to quickly understand the situation.

[0748] (Example 2)

[0749] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0750] Existing electronic communication systems face challenges such as the cumbersome manual handling of the large number of messages users receive, leading to increased psychological burden. Furthermore, the failure to immediately notify users of urgent messages creates a risk of missing important information. Additionally, responses that disregard the user's emotional state can hinder smooth communication. Therefore, there is a need to automate message handling while ensuring responses that are sensitive to the user's emotions.

[0751] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0752] In this invention, the server includes means for collecting and analyzing the user's past communication data, means for training an intelligent algorithm that generates automatic responses based on that communication data, and means for understanding the user's emotional tendencies and adjusting the tone of the response using that information. As a result, the user can receive responses that have been automatically adjusted based on past data, enabling efficient, emotionally sensitive, and smooth communication.

[0753] "Communication data" refers to digital information, including messages and associated information, that a user has previously sent or received.

[0754] An "intelligent algorithm" refers to a computational method used to analyze data and generate automated responses, and specifically refers to a program that possesses learning capabilities.

[0755] "Adjusting the tone of responses" refers to the process of changing the tone and style of generated responses according to the user's emotional state.

[0756] "Urgency" is a criterion for evaluating whether a received message requires immediate attention.

[0757] "Summarizing and reporting" is the process of presenting a concise summary of the received message to the user.

[0758] "Organizational regulations" refer to guidelines and policies established by a company or organization, and serve as the basis for decision-making and actions.

[0759] A "response template" is a template that shows a standard response pattern used in specific situations.

[0760] "Emotional tendencies" refer to the patterns and tendencies of emotions that a user has shown in past communications.

[0761] This invention is an automated response system designed to effectively utilize user communication data and reduce the burden on users. This system is primarily operated by a server and terminals.

[0762] The server first collects the user's past communication data. This includes extracting data from email servers. The server processes this data to generate a dataset for the intelligent algorithm to train. This training involves providing data to the intelligent algorithm using the Python programming language. Deep learning frameworks such as TensorFlow and PyTorch are particularly used.

[0763] In parallel, the server utilizes an emotion engine to perform sentiment analysis. This emotion engine employs an API for analyzing emotional tone. This API extracts emotional tone from text within communication data to understand the user's emotional tendencies.

[0764] When a terminal receives a new message, it immediately sends that information to the server. This information is securely transmitted using encryption technology. The server uses this information to input prompts into an AI model, which then generates a response. An example of a prompt sent at this time would be, "Generate an appropriate reply while maintaining the user's tone."

[0765] As a concrete example, consider a scenario where a user receives a work-related message while on vacation. Upon receiving this message, the server automatically sends a response such as, "The user is currently on vacation; we will address this upon their return." This response is generated by an intelligent algorithm and verified by an emotion engine.

[0766] This system configuration allows users to maintain communication automatically and in an emotionally sensitive manner while reducing their psychological burden.

[0767] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0768] Step 1:

[0769] The server collects the user's past communication data from the email server. This collection retrieves email text and metadata associated with a specific user ID via a database connection. The inputs collected in this process include email body, sending and receiving date and time, and sender information. This data is converted into a structured data format for use in subsequent data analysis steps. The output is a dataset in a parseable format.

[0770] Step 2:

[0771] The server trains a generative AI model using the dataset obtained in Step 1. The input data here consists of text data and metadata. The server preprocesses the data, converting the text into an appropriate format such as vector format, and then supplies it to the intelligent algorithm. The intelligent algorithm uses machine learning techniques to train a response generation model. The output is a model that has learned user response patterns.

[0772] Step 3:

[0773] The server analyzes the dataset obtained from Step 1 using an emotion engine. The input data is email text data. The emotion engine extracts emotional tones from the text using, for example, natural language processing techniques to understand the user's emotional tendencies. The output is the user's emotion profile. This profile is used in subsequent response generation.

[0774] Step 4:

[0775] The terminal detects newly received messages and forwards the data to the server. This process uses the content of the new message, sender information, and the date and time of receipt as input. The terminal securely transmits the data to the server using an encryption protocol. The output is the new message information received by the server.

[0776] Step 5:

[0777] The server generates an automated response based on the new message information obtained in step 4. A generation AI model is used for this process. The input consists of the new message information and the trained AI model, and the server provides the model with the prompt "Generate an appropriate response while maintaining the user's tone." Furthermore, the response is adjusted based on a previously analyzed sentiment profile. The output is an automated response with an appropriate emotional tone.

[0778] Step 6:

[0779] The server immediately responds to incoming messages by sending a generated automated response. It also notifies the user if the message is important or stressful, based on the sentiment engine's evaluation. The input here is the generated response message, which the server uses to execute the appropriate message sending procedure. The output is the sent response message and notification.

[0780] (Application Example 2)

[0781] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0782] In today's information environment, the diversification of communication methods has led to an increase in the amount of information users receive, making it more complex to select important messages and manage stress within that information. Furthermore, the impact of psychological stress on users' work efficiency and health cannot be ignored. In this context, there is a need for methods that enable users to efficiently receive and respond to appropriate information without experiencing excessive burden.

[0783] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0784] In this invention, the server includes means for collecting and analyzing the user's past information exchange data, means for evaluating the emotional impact of received messages using an emotion engine, and for detecting and notifying psychological stress based on that evaluation, and means for immediately notifying important messages and providing summary information including the emotion evaluation results. This enables users to efficiently manage messages, reduce psychological burden, and improve their quality of work and life.

[0785] A "user" is an individual or organization that uses the system to exchange information.

[0786] "Information exchange data" refers to the content of communications such as emails and chats that users have previously exchanged.

[0787] An "artificial intelligence model" is an algorithm or system that is trained to generate automated responses based on information exchange data.

[0788] An "emotion engine" is an engine or system that analyzes the emotional impact of a received message and evaluates the results.

[0789] "Psychological stress" refers to the mental burden and tension caused by the content of messages that users encounter.

[0790] "Summary information" is a concise summary of the entire content of a received message, extracting the key points that are important to the user.

[0791] "Instant notification" is a means of communication that quickly informs users of important messages.

[0792] A "template" refers to a standard response format based on organizational regulations.

[0793] "Organizational regulations" refer to a set of rules or guidelines established by a company or organization.

[0794] The system that realizes this invention consists of a server, a terminal, and a user. The server first collects and analyzes the user's past information exchange data. This analysis includes natural language processing to understand the user's language use and response patterns.

[0795] The system processes data using computing resources on the cloud (e.g., AWS EC2). The server uses Python and libraries such as Scikit-learn and Hugging Face Transformers to train an artificial intelligence model based on user communication data. This model analyzes the user's tone of voice and word choice, contributing to the generation of automated responses.

[0796] The terminal operates on smartphones and tablets and is responsible for sending newly received messages to the server. The server analyzes data in real time using TensorFlow Lite and Firebase Realtime Database, and generates automated responses using artificial intelligence models. In this process, the emotion engine evaluates the emotional impact of the received messages, and if psychological burden is detected, it immediately notifies the user and the organization's security team.

[0797] For example, if a user receives work-related messages while on vacation, the server analyzes the stress indicators contained in those messages and generates an appropriate response. At the same time, it provides summary information of the received messages in preparation for when the user returns after their vacation.

[0798] Examples of prompt statements for a generative AI model are as follows:

[0799] "Please enter your email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations."

[0800] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0801] Step 1:

[0802] The server collects past information exchange data from users. Emails and chat logs are provided as input, and this data is stored in a database. This collected data is then used in subsequent training processes.

[0803] Step 2:

[0804] The server uses the collected data to train an artificial intelligence model. It analyzes user response patterns and tone using NLP techniques, employing Python's Scikit-learn and Hugging Face Transformers. The input is information exchange data, and the output is a model related to user response generation.

[0805] Step 3:

[0806] The terminal sends a newly received message to the server. This message is the input, and the server receives it and prepares to generate the next automated response.

[0807] Step 4:

[0808] The server uses an artificial intelligence model to generate an automated response to incoming messages. The input is a new message, and the output is the automated response text. This automated response is enhanced in terms of individuality and relevance because it is based on the user's past data.

[0809] Step 5:

[0810] The server uses an emotion engine to evaluate the emotional impact of incoming messages. The input is the incoming message, the calculation involves sentiment analysis, and the output is a psychological stress index. Based on this evaluation, immediate notification is provided if necessary.

[0811] Step 6:

[0812] The server selects important messages and immediately notifies users. It also generates summary information, including sentiment evaluation results. The input is the sentiment evaluation result and the message content, and the output is summary information. This enables the rapid communication of important information to users.

[0813] Step 7:

[0814] The user inputs information using prompts directed to the generating AI model. The prompt, "Please enter email text. We will provide an automated response and sentiment assessment. We will offer sentiment-based stress indicators and response recommendations," simplifies the processing of necessary information.

[0815] 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.

[0816] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. 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. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0817] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0818] 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.

[0819] Figure 9 shows an 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.

[0820] 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.

[0821] 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.

[0822] 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, motorcycles, etc., 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, for example, based 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.

[0823] 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."

[0824] 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.

[0825] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0826] 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 of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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 the like 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.

[0835] 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.

[0836] The following is further disclosed regarding the embodiments described above.

[0837] (Claim 1)

[0838] Means for collecting and analyzing users' past communication data,

[0839] A means for training an AI model that generates an automated response based on that communication data,

[0840] A means for automatically generating and sending a response to a newly received message,

[0841] A means of assessing urgency and immediately notifying important messages,

[0842] A means of summarizing and reporting received messages,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, comprising means for customizing responses to newly received messages based on corporate policies or response templates.

[0846] (Claim 3)

[0847] The system according to claim 1, comprising means for sending a summary report to the user at the end of their vacation so that the user can rest comfortably while on vacation.

[0848] "Example 1"

[0849] (Claim 1)

[0850] A means of collecting and analyzing a user's past communication information,

[0851] A means for training a generative model that generates an automatic response based on that communication information,

[0852] A means for automatically generating and sending a response to newly received information,

[0853] A means of assessing urgency and immediately notifying important information,

[0854] A means of summarizing and reporting the received information,

[0855] A means of analyzing the content of information received during a user's vacation according to specific criteria and creating a new response template,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, comprising means for customizing responses to newly received information based on organizational policies or response templates.

[0859] (Claim 3)

[0860] The system according to claim 1, comprising means for sending a summary report to the user at the end of their vacation so that the user can rest comfortably while on vacation.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] Means for collecting and analyzing users' past communication data,

[0864] A means for training an artificial intelligence model that generates an automated response based on that communication data,

[0865] A means for automatically generating and sending a response to newly received information,

[0866] A means of assessing urgency and immediately notifying important information,

[0867] A means of summarizing and reporting the received information,

[0868] A means to improve inquiry responses by performing sentiment analysis on response data,

[0869] A means of saving automatically generated summaries and making them available later,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising means for customizing responses to newly received information based on organizational policies and response templates.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising means for sending a summary report to the user at the end of their vacation so that the user can rest comfortably while on vacation.

[0875] "Example 2 of combining an emotion engine"

[0876] (Claim 1)

[0877] Means for collecting and analyzing users' past communication data,

[0878] A means for training an intelligent algorithm that generates an automatic response based on that communication data,

[0879] A means for automatically generating and sending a response to a newly received message,

[0880] A means of understanding the user's emotional tendencies and using that information to adjust the tone of the response,

[0881] A means of assessing urgency and immediately notifying important messages,

[0882] A means of summarizing and reporting received messages,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, comprising means for customizing responses to newly received messages based on organizational regulations or response templates.

[0886] (Claim 3)

[0887] The system according to claim 1, comprising means for sending a summary report to the user at the end of their vacation so that the user can rest comfortably while on vacation.

[0888] "Application example 2 when combining with an emotional engine"

[0889] (Claim 1)

[0890] A means of collecting and analyzing users' past information exchange data,

[0891] A means for training an artificial intelligence model that generates automated responses based on the information exchange data,

[0892] A means of automatically generating and providing a response to a newly received message,

[0893] A means of using an emotion engine to evaluate the emotional impact of received messages, and based on that evaluation to detect and notify of psychological stress,

[0894] A means of providing immediate notification of important messages and summary information including sentiment evaluation results,

[0895] A system that includes this.

[0896] (Claim 2)

[0897] The system according to claim 1, further comprising means for adjusting responses to newly received messages based on organizational regulations or response templates.

[0898] (Claim 3)

[0899] The system according to claim 1, which provides summary information to users at the end of their vacation so that they can relax comfortably during their vacation, and also includes means to reduce psychological burden by utilizing emotional evaluation. [Explanation of symbols]

[0900] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting and analyzing users' past communication data, A means for training an artificial intelligence model that generates an automated response based on that communication data, A means for automatically generating and sending a response to newly received information, A means of assessing urgency and immediately notifying important information, A means of summarizing and reporting the received information, A means to improve inquiry responses by performing sentiment analysis on response data, A means of saving automatically generated summaries and making them available later, A system that includes this.

2. The system according to claim 1, comprising means for customizing responses to newly received information based on organizational policies and response templates.

3. The system according to claim 1, comprising means for sending a summary report to the user at the end of their vacation so that the user can rest comfortably while on vacation.

Images