system

Abstract

Provide a system. 【Solution means】 Means for automatically acquiring electronic messages, Means for analyzing the acquired electronic messages using natural language processing technology and extracting important information, Means for classifying operations based on the extracted information and setting priorities, Means for displaying operation information on a user device, Means for setting a notification function based on operation information, Means for sharing operation information externally in the form of a daily report, Means for automatically scheduling and notifying in-home work based on the acquired information, 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 method for controlling a persona chatbot, which is performed by at least one processor, and includes 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] In recent years, information transmission by email has become increasingly important in the business field, and many business people are forced to process a large amount of emails. In particular, managers and project managers must quickly check, reply to emails, and prioritize tasks, and there is a risk of overlooking important emails or missing task responses. Under such circumstances, there is a demand for a system that realizes efficient management of emails and visualization of tasks to improve work efficiency.

Means for Solving the Problems

[0005] The present invention comprises means for automatically collecting emails, means for analyzing the collected emails using natural language processing technology and extracting important information, means for classifying tasks and setting priorities based on the extracted information, means for displaying task information on a user terminal, means for setting reminders based on task information, and means for sharing task information externally in a daily report format. This makes it possible to determine the importance of emails and manage tasks quickly and accurately, thereby significantly improving work efficiency.

[0006] "Email" is a means of communication for exchanging messages between users over a computer network.

[0007] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is primarily used to extract meaning from text data.

[0008] "Extraction" refers to the process of selecting and removing necessary parts from data or information, and in this context, it refers to extracting important information from emails.

[0009] A "task" is a unit of activity or work set up to achieve a specific objective.

[0010] "Priority" refers to the ordering or ranking of things based on their importance or urgency, and is a metric particularly used when determining the order in which tasks should be performed.

[0011] A "terminal" is a device that a user uses to access software applications and data, such as a computer or a smartphone.

[0012] A "reminder" is a function that sends notifications or alarms to the user at specific times or under specific conditions, and is intended to support the user's work and schedule.

[0013] A "daily report" is a document that summarizes the status of work and activities for the day, and is usually used for reviewing work and sharing information. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

[0018] 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.

[0019] 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.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system aimed at efficient email management and task visualization, and consists of a server, user terminals, and users. This system not only automatically analyzes received emails, extracts important information, and classifies them as tasks, but also presents priorities to the user, thereby significantly improving work efficiency.

[0036] First, the server accesses the user's email account and collects new emails at regular intervals. This involves a secure authentication process using known security protocols. The collected emails are analyzed using a natural language processing engine to extract important keywords and tasks. Based on this information, the server prioritizes each task and categorizes them by urgency and importance.

[0037] The user's device receives task information and summaries from the server and displays them visually on a dedicated dashboard. The dashboard is designed so that users can quickly see their most important tasks and unanswered emails. This information is also visually organized, allowing users to process tasks according to priority.

[0038] As a concrete example, consider a scenario where the user is a project manager. The server detects an email with the subject "Urgent," and from its analysis, extracts that the project deadline is the next day. The server generates a summary of this critical information and lists "Project Progress Check" as a high-priority task. The terminal displays this information on a dashboard, allowing the user to understand that immediate action is required. Additionally, a reminder function notifies the user of important tasks, preventing them from forgetting to take action.

[0039] Furthermore, the server automatically generates daily reports and shares them with designated team members via email or messaging tools. This allows all team members to stay informed about the status of their work, enabling centralized information sharing and a feedback loop.

[0040] In this way, the present invention provides an effective means for streamlining email management and improving business efficiency.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server accesses the user's email account and automatically collects newly received emails. It uses a secure protocol for user authentication and retrieves email data using IMAP or POP3.

[0044] Step 2:

[0045] The server inputs collected email data into a natural language processing engine, which extracts text from the email body. This text is then analyzed to understand keywords and context, and to identify important information.

[0046] Step 3:

[0047] Based on the analyzed information, the server extracts tasks from the email and assigns a priority and urgency level to each. A machine learning algorithm is used to classify them and assign "high," "medium," and "low" classification tags.

[0048] Step 4:

[0049] The server summarizes the key points of each email and generates a summary. The main points are presented in a clear and concise manner for easy understanding by the user.

[0050] Step 5:

[0051] The server sends the generated summary and task list to the user's terminal.

[0052] Step 6:

[0053] The terminal displays the information it receives on the user interface, providing it visually to the user through a dashboard. The user uses this dashboard to check task priorities and take appropriate action.

[0054] Step 7:

[0055] The device sets reminders based on task information provided by the server. It sends notifications at the specified time to help users avoid missing important tasks.

[0056] Step 8:

[0057] At the end of the day, the server generates a daily report based on aggregated email information and task lists. This report is then sent to designated team members to facilitate information sharing.

[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 today's work environment, users receive a large volume of electronic communications and are required to quickly identify important tasks from among them. However, doing this manually is extremely time-consuming and labor-intensive, so there is a need for efficient management methods. Furthermore, visualizing information and clarifying priorities are important elements for improving work efficiency.

[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 automatically collecting electronic communications, means for analyzing and extracting important information using natural language processing technology, and means for analyzing and classifying information using a generative AI model. This enables the rapid identification of important tasks, visual organization of information, and setting of priorities.

[0063] "Electronic communications" refers to messages and data sent and received via the internet, especially email.

[0064] "Accumulation" refers to the process of centrally collecting and organizing specific data.

[0065] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it is a method for analyzing the meaning and intent of text.

[0066] "Important matters" refer to elements within the information being analyzed that require particularly high-priority processing or action.

[0067] A "generative AI model" is a subfield of machine learning that refers to an artificial intelligence model that learns patterns from large amounts of data and uses that knowledge to make predictions and perform analyses on new data.

[0068] "Classification" refers to the process of grouping data or information based on specific criteria or conditions.

[0069] "Priority setting" refers to determining the order in which to process multiple tasks or work based on their importance and urgency.

[0070] "Visualization" refers to the process of visually representing data and information in the form of graphs, tables, and other visual formats to make them easier to understand.

[0071] This invention is a system for efficiently managing electronic communications and improving the work efficiency of users. The system mainly consists of a server, user terminals, and users.

[0072] The server accesses users' email accounts via the internet and automatically collects electronic communications at regular intervals. Specifically, it uses a standard server computer as hardware, and the software retrieves emails from the communication server using the IMAP protocol. The collected communication data is automatically analyzed using natural language processing technology on the server. Here, a generative AI model is utilized to analyze the text of electronic communications, extract important information, classify the work information according to the analysis results, and set priorities.

[0073] The terminal receives work information provided by the server and displays it on a dedicated dashboard. This dashboard is built with application software that features a user interface, and uses JavaScript® and CSS to enable intuitive operation for the user. Particularly important tasks and unread notifications are color-coded for visual distinction.

[0074] Users can view high-priority tasks through a dashboard displayed on their device and efficiently process tasks according to the list. Furthermore, a notification function allows them to receive reminders when deadlines for particularly important tasks are approaching.

[0075] As a concrete example, consider a case where a generative AI model extracts important information such as "the project deadline is tomorrow" from received messages, and this is displayed on the dashboard with the priority of "urgent action." In this case, the user can immediately understand the priority and take prompt action.

[0076] An example of a prompt message is: "The user can view unread emails regarding project progress in order of priority and identify tasks that require immediate attention. The server extracts tasks from incoming emails through natural language processing, sets their priorities, and reflects them on the dashboard." This system streamlines the management of electronic communications, enabling more effective work execution.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server periodically accesses the user's email account and collects new electronic communications. It receives authentication information and connection protocols as input, and communicates with the mail server using the IMAP protocol. The output is newly received email data. Specifically, the server uses authentication information to securely connect to the communication server and retrieve unread emails.

[0080] Step 2:

[0081] The server analyzes the collected electronic communications using natural language processing technology. It receives email text data as input and passes it to a generative AI model. During data processing, the email text is tokenized, and important keywords and phrases are extracted. The output consists of important information and recommended tasks. Specifically, the generative AI model analyzes the email content and identifies keywords as potential tasks.

[0082] Step 3:

[0083] The server classifies and prioritizes work information based on the extracted critical information. It receives the aforementioned critical information and task information as input and applies criteria to evaluate urgency and importance. Based on the data calculations, it assigns priorities to tasks. The output is a prioritized work list. For example, it might label tasks as "urgent" or "normal" and then sort them.

[0084] Step 4:

[0085] The server sends prioritized task information to the user's terminal. It uses a list of completed tasks as input and the output is data sent to the terminal via the HTTP protocol. Specifically, the server encrypts the data and sends it through a secure channel.

[0086] Step 5:

[0087] The terminal displays work information received from the server on a dashboard. It uses work data received from the server as input, and the output is a visual display in the user interface. Specifically, the terminal uses JavaScript and CSS to color-code important tasks, allowing the user to prioritize and review tasks.

[0088] Step 6:

[0089] Users process tasks through a dashboard displayed on their device. The input is visual information from the dashboard. The output is actions to efficiently complete tasks. Specifically, users address tasks in order of urgency, prioritizing tasks with approaching deadlines based on reminders.

[0090] Step 7:

[0091] The server aggregates the progress of each task, automatically generates a log, and shares it with team members. It receives processed work data and its progress information as input, and outputs a report compiled in log format. Specifically, the server automatically formats the daily report and distributes it via email or messaging tools.

[0092] (Application Example 1)

[0093] 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."

[0094] In modern life, the volume of electronic messages is increasing, and managing them is becoming more complex. Furthermore, there is a need to efficiently manage various household tasks and execute them at the appropriate time. However, existing technologies do not adequately integrate the management of electronic messages and household tasks, and efficient scheduling and automation that would improve the quality of life for families have not been achieved.

[0095] 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.

[0096] In this invention, the server includes means for automatically acquiring electronic messages, means for analyzing the acquired messages using natural language processing technology and extracting important information, and means for automatically scheduling and notifying users of household tasks based on the extracted information. This integrates the management of electronic messages and household tasks, enabling efficient scheduling and automation.

[0097] "Electronic messages" refer to linguistic information, specifically words and information in digital format that are sent and received via the internet.

[0098] "Natural language processing technology" is a field of computer science that enables computers to understand, analyze, and utilize the natural language that humans use in everyday life.

[0099] "Important information" refers to a set of data within an electronic message that is deemed to be of high necessity or urgency based on specific conditions or criteria.

[0100] "Household tasks" refers to the various activities and duties performed within the home as part of daily life.

[0101] A "schedule" refers to a time-based plan or schedule, a plan that shows what actions to take at specific times.

[0102] "Notifications" refer to activities or functions that visually inform users of important information or schedules.

[0103] In implementing this invention, the server first securely and automatically retrieves the user's electronic messages via the internet. The retrieved messages are then analyzed using software employing natural language processing technology. In this process, the server uses an open-source natural language processing library (e.g., spaCy) to identify and extract important information from the messages.

[0104] Next, based on the extracted key information, the server schedules household tasks. This is made possible by using a scheduling library (e.g., schedule), enabling efficient schedule management. The server analyzes the acquired information and automatically plans tasks that may occur in the household (e.g., shopping, cleaning, notifications for important events).

[0105] The user's device receives schedule information and notifications sent from the server. This user device includes smartphones, home displays, or voice assistant devices. A dedicated dashboard is displayed on the device, allowing the user to visually check their schedule, and important information and notifications are communicated to the user via voice and visual notifications.

[0106] For example, even if a user leads a busy life, this system can analyze the contents of an email, such as a "weekend shopping list update," and automatically add the necessary items to their digital calendar. This allows the user to avoid forgetting plans and saves extra time.

[0107] As an example of a prompt to the generating AI model, instructing it to "extract household tasks from the user's emails and schedule them based on their importance" can enable efficient schedule management tailored to the user's needs.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server securely retrieves the user's electronic messages over the internet. During this process, the server accesses the user's email account and authenticates them using security protocols. The input consists of the user's authentication information and the mail server's address, while the output is the data of the received unread emails.

[0111] Step 2:

[0112] The server passes the acquired electronic message to a natural language processing engine for analysis. Here, natural language processing technology (e.g., spaCy) is used to extract keywords and important information from the message. The input is the data of the received email, and the output is the extracted important information (e.g., task details and deadlines).

[0113] Step 3:

[0114] The server automatically schedules household tasks based on the extracted key information. Using a scheduling library (e.g., `schedule`), it analyzes the input information and generates a schedule. The input is the extracted information, and the output is a detailed list of planned tasks and their times.

[0115] Step 4:

[0116] The user terminal receives and displays schedule information sent from the server. Here, specific appointments are notified to the user via a dashboard or smart home device. The input is schedule information from the server, and the output is a visual or audio notification to the user.

[0117] Step 5:

[0118] The user reviews the schedule information provided from the terminal and modifies or approves the appointments as needed. The system receives the updated schedule information again based on the user's actions and updates the data. The input is the user's confirmation and modification information, and the output is the updated schedule information.

[0119] 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.

[0120] This invention improves the efficiency of email processing and task management by incorporating an emotion engine that recognizes user emotions into an email management system. The system consists of a server, a user terminal, an emotion engine, and the user. The server is responsible for collecting and analyzing emails, while the emotion engine has the function of estimating the user's emotions from the text within the emails.

[0121] First, the server accesses the user's email account and periodically collects new emails. The collected emails are analyzed using natural language processing techniques to extract important keywords and tasks, while the sentiment engine analyzes the emotions contained in the emails. The sentiment engine sets up multiple emotion categories such as positive, negative, and neutral, and calculates an emotion score based on the content of the emails.

[0122] The server classifies tasks based on the analysis results and sets priorities and urgency levels, but user sentiment information is reflected in the priority setting. For example, if negative sentiment is detected, the priority of related tasks may be set higher. The generated task information and sentiment information are sent to the user's device, which displays them visually on a dashboard. Through this dashboard, the user can easily understand the importance of tasks based on their sentiment.

[0123] As a concrete example, suppose a user receives an email about an important negotiation with a client. If this email contains negative emotions, the server uses an emotion engine to detect the negative emotions and sets a high priority for the "Confirm Negotiation Results" task related to that email. This information is displayed on the terminal, allowing the user to take prompt action and prevent undesirable situations.

[0124] Furthermore, the device adjusts reminder timing based on emotions and task information, providing optimal notifications tailored to the user's emotional state. Additionally, the server automatically generates daily reports, including emotional information, which are distributed to team members, thereby improving team communication and problem-solving capabilities.

[0125] This invention supports efficient and flexible work execution by not only managing emails but also enabling task management that takes into account the user's emotional state.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The server accesses the user's email account and automatically collects newly received emails. It performs security authentication and retrieves email data using the IMAP protocol.

[0129] Step 2:

[0130] The server processes the collected emails using a natural language processing engine to extract keywords and context from the text. A specified model is used to identify meaningful information during this process.

[0131] Step 3:

[0132] The server uses an emotion engine to analyze the user's emotions from the text in the email. It calculates an emotion score and categorizes it as positive, negative, or neutral.

[0133] Step 4:

[0134] Based on the analyzed information, the server extracts tasks related to each email and assigns them importance and urgency. This assignment also takes into account the previously obtained sentiment information. For example, if negative sentiment is detected, the related tasks are classified as having a higher priority.

[0135] Step 5:

[0136] The server sends the generated summary, categorized task list, and sentiment information to the user's device.

[0137] Step 6:

[0138] The dashboard visually displays information received by the device. Tasks are organized by priority, and sentiment information is also displayed, allowing users to intuitively grasp the importance of the information.

[0139] Step 7:

[0140] The device sets reminders based on emotional information and task priorities, and notifies the user at the appropriate time.

[0141] Step 8:

[0142] At the end of the day, the server creates a daily report based on all collected emails and task information, and distributes it to team members via email or other messaging tools, including sentiment information.

[0143] This series of processes allows users to efficiently manage emails and perform task management that takes emotional information into account.

[0144] (Example 2)

[0145] 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".

[0146] One challenge in electronic communication is efficiently managing which tasks should be prioritized, while also considering emotional factors. Especially in busy business environments, quickly and accurately processing the diverse information contained in electronic communications and determining its importance is not easy. Furthermore, there is a growing need to flexibly adjust the urgency and priority of tasks based on emotional information.

[0147] 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.

[0148] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for performing calculations based on the extracted information and estimating an emotional score. This enables task management that takes into account the importance and emotional factors of the electronic communications.

[0149] "Electronic communication" is a general term referring to the exchange of information in the form of documents or messages.

[0150] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate language that humans use on a daily basis.

[0151] An "emotion score" is a numerical representation of the type and degree of emotion contained in a text, and it quantitatively expresses the results of emotion analysis.

[0152] Task management is a methodology for efficiently organizing and executing multiple tasks and work by evaluating their priority and urgency, and processing them systematically.

[0153] This invention improves the efficiency of communication processing and task management in an electronic communication management system by incorporating sentiment analysis functionality. The system consists of a server, a user terminal, a sentiment engine, and the user.

[0154] The server is responsible for automatically collecting electronic communications. Specifically, it accesses users' communication accounts using communication protocols such as IMAP and periodically retrieves new messages. This process can be handled using Python's standard libraries.

[0155] The collected communication data is analyzed using natural language processing (NLTK) techniques. The server uses NLTK and spaCy libraries to extract important keywords and tasks from the communication text. Furthermore, a sentiment engine calculates sentiment scores from the extracted text. This uses generative AI models such as BERT, enabling the analysis of the emotional nuances of the text as numerical data.

[0156] Based on the analysis results, the server sets task priorities. Sentiment scores influence priority determination, and tasks with particularly negative emotions are given a higher priority. This priority setting requires software that implements the algorithm, developed in programming languages ​​such as Python.

[0157] The user's device visually displays task and sentiment information sent from the server on a dashboard. At this stage, the device uses a front-end framework such as React or Vue.js. This allows the user to easily see the importance of tasks based on their sentiment and manage them effectively. The device also adjusts reminder timing based on the sentiment score, providing optimal notifications.

[0158] As a concrete example, consider a scenario where a user receives an important negotiation email from a client. The server uses an emotion engine to detect negative emotions from the email and sets a high priority for the "confirm negotiation results" task associated with that email. This information is immediately displayed on the terminal, allowing the user to respond promptly and prevent unexpected situations from occurring.

[0159] An example of a prompt for a generative AI model is: "Based on the following electronic communication text, use the sentiment engine to identify its sentiment category: 'The client's feedback was somewhat harsh...'"

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] The server accesses the user's communication account via the IMAP protocol and collects new electronic communications. The inputs used are the destination server information and authentication information. The output is unread message data in the inbox, which includes the sender, subject, and body of the email.

[0163] Step 2:

[0164] The server analyzes the collected electronic communication data using natural language processing techniques. Specifically, it uses NLTK and spaCy to analyze and extract words from the input electronic communication data. This process generates important keywords and task candidates as output. At this stage, part-of-speech tagging and semantic analysis are performed on the words.

[0165] Step 3:

[0166] The server uses extracted text data as input and calculates sentiment scores using a generative AI model. This process employs a Transformer-based model (e.g., BERT), and the output includes sentiment categories such as positive, negative, and neutral, along with their respective scores. The model evaluates the nuances of the text and generates numerical sentiment indicators.

[0167] Step 4:

[0168] The server sets task priorities based on the analysis results: keywords and sentiment scores. The inputs are task candidates and sentiment scores. The priority setting algorithm generates a task list and the priority of each task as output. Tasks strongly influenced by negative emotions are assigned a higher priority.

[0169] Step 5:

[0170] The server sends the generated task information to the user's device. The device uses the received task information as input to visually display it on a dashboard using frameworks such as React or Vue.js. As output, the user can view and manage the task list on the screen. The importance of tasks can be intuitively grasped through color coding and icons.

[0171] Step 6:

[0172] The device adjusts reminder timing based on sentiment scores. The task list and its priority are used as input. Reminder settings are configured in conjunction with the calendar API as output. Email and pop-up notifications are provided to the user at appropriate times.

[0173] Step 7:

[0174] The server automatically generates daily reports and provides emotion scores and task information to others in a record format. It uses analysis results as input and generates formatted report data (such as PDF or HTML) as output. This data is then distributed to team members via email or internal communication tools.

[0175] (Application Example 2)

[0176] 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".

[0177] In today's business environment, the increasing influx of information through electronic communications makes it difficult to prioritize important tasks and respond appropriately. Furthermore, there is a growing need to properly evaluate the emotions contained in received communications and recognize them early as business risks or critical issues. This need is particularly urgent for companies that require early warning of security risks such as phishing and malware.

[0178] 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.

[0179] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for analyzing the sentiment of the electronic communications and reflecting it in the task priority. This enables the rapid setting of priorities based on the sentiment conveyed by the received communications, allowing for immediate response to important matters and early warning of security risks.

[0180] "Electronic communications" refers to digital data such as emails and messages sent and received via the internet or local networks.

[0181] "Natural language processing technology" refers to all technologies that enable computers to understand and process human language, and includes information extraction and sentiment analysis.

[0182] "Analyzing emotions" means analyzing the linguistic expressions contained in text data to infer the underlying emotions (positive, negative, etc.).

[0183] "Reflecting this in work priorities" means reassessing the importance and urgency of related tasks based on the emotions and importance of the communication, and enabling them to be addressed in the appropriate order.

[0184] A "server" is a computer resource provided on a network for the purpose of collecting and processing data.

[0185] A description of the embodiment for carrying out the invention will be provided.

[0186] This system combines electronic communication management and sentiment analysis to enable efficient task prioritization. The server operates on the network and automatically collects electronic communications such as emails and messages. The server analyzes the collected communications using advanced natural language processing technologies (e.g., spaCy and NLTK) to extract important information and keywords.

[0187] Based on the content of collected electronic communications, sentiment analysis models are used to calculate sentiment scores such as positive, negative, and neutral. Machine learning frameworks such as TENSORFLOW® and PyTorch are used for sentiment analysis. Based on the sentiment scores, importance and urgency are re-evaluated, and tasks are prioritized.

[0188] The user terminal visually displays this prioritized work information, enabling users to respond quickly. Reminders and notification functions are also provided, improving the user's work efficiency.

[0189] For example, if a user receives an email from a business partner with disturbing content, the server can detect the negative sentiment in the email and set related response tasks with high priority. This result is displayed on the terminal, allowing the user to quickly begin taking action.

[0190] As an example of a prompt, inputting instructions such as "Instruct me how to adjust the priority of tasks based on the emotions detected in this email" into the generating AI model will make task prioritization smoother.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The server accesses the user's email account over the network. It receives user authentication information as input and automatically collects new emails at specified time intervals. The output is the collected email data. Since it retrieves information from the mail server using email protocols (such as IMAP or POP3), communication is secure and reliable.

[0194] Step 2:

[0195] The server analyzes the collected email data using natural language processing (NLP) techniques. The input is email text, and the output extracts important keywords and phrases. NLP libraries (such as spaCy and NLTK) are used to analyze the grammatical structure and extract semantically important information. This makes subsequent analysis more effective.

[0196] Step 3:

[0197] The server calculates an emotion score using an emotion analysis model based on the data obtained from NLP processing. The input is the information extracted in step 2, and the output is a score corresponding to an emotion category (positive, negative, neutral, etc.). Emotion analysis models using TensorFlow or PyTorch are utilized here to quantitatively evaluate emotions from the tone and content of emails.

[0198] Step 4:

[0199] The server categorizes and prioritizes relevant tasks based on sentiment scores and other email information. Inputs are sentiment scores and keywords, and output is a prioritized task list. This prioritization allows for tasks that require immediate attention, particularly communications containing negative emotions.

[0200] Step 5:

[0201] The terminal uses prioritized work information received from the server and displays it visually on the user interface. Input is a work list, and output is a user-friendly dashboard. Here, users can make quick and accurate decisions based on the visualized information.

[0202] Step 6:

[0203] The device sets appropriate reminders and notifications for tasks requiring attention based on the displayed information. Input is priority information within the task list, and output is notifications based on time and conditions. This ensures that users can reliably address important tasks without missing any.

[0204] Step 7:

[0205] Users perform tasks and take appropriate actions based on information obtained from their devices. Input is the displayed task information, and output is the specific action to be taken. This streamlines communication and operations within the organization.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention is a system aimed at efficient email management and task visualization, and consists of a server, user terminals, and users. This system not only automatically analyzes received emails, extracts important information, and classifies them as tasks, but also presents priorities to the user, thereby significantly improving work efficiency.

[0223] First, the server accesses the user's email account and collects new emails at regular intervals. This involves a secure authentication process using known security protocols. The collected emails are analyzed using a natural language processing engine to extract important keywords and tasks. Based on this information, the server prioritizes each task and categorizes them by urgency and importance.

[0224] The user's device receives task information and summaries from the server and displays them visually on a dedicated dashboard. The dashboard is designed so that users can quickly see their most important tasks and unanswered emails. This information is also visually organized, allowing users to process tasks according to priority.

[0225] As a concrete example, consider a scenario where the user is a project manager. The server detects an email with the subject "Urgent," and from its analysis, extracts that the project deadline is the next day. The server generates a summary of this critical information and lists "Project Progress Check" as a high-priority task. The terminal displays this information on a dashboard, allowing the user to understand that immediate action is required. Additionally, a reminder function notifies the user of important tasks, preventing them from forgetting to take action.

[0226] Furthermore, the server automatically generates daily reports and shares them with designated team members via email or messaging tools. This allows all team members to stay informed about the status of their work, enabling centralized information sharing and a feedback loop.

[0227] In this way, the present invention provides an effective means for streamlining email management and improving business efficiency.

[0228] The following describes the processing flow.

[0229] Step 1:

[0230] The server accesses the user's email account and automatically collects newly received emails. It uses a secure protocol for user authentication and retrieves email data using IMAP or POP3.

[0231] Step 2:

[0232] The server inputs collected email data into a natural language processing engine, which extracts text from the email body. This text is then analyzed to understand keywords and context, and to identify important information.

[0233] Step 3:

[0234] Based on the analyzed information, the server extracts tasks from the email and assigns a priority and urgency level to each. A machine learning algorithm is used to classify them and assign "high," "medium," and "low" classification tags.

[0235] Step 4:

[0236] The server summarizes the key points of each email and generates a summary. The main points are presented in a clear and concise manner for easy understanding by the user.

[0237] Step 5:

[0238] The server sends the generated summary and task list to the user's terminal.

[0239] Step 6:

[0240] The terminal displays the information it receives on the user interface, providing it visually to the user through a dashboard. The user uses this dashboard to check task priorities and take appropriate action.

[0241] Step 7:

[0242] The device sets reminders based on task information provided by the server. It sends notifications at the specified time to help users avoid missing important tasks.

[0243] Step 8:

[0244] At the end of the day, the server generates a daily report based on aggregated email information and task lists. This report is then sent to designated team members to facilitate information sharing.

[0245] (Example 1)

[0246] 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."

[0247] In today's work environment, users receive a large volume of electronic communications and are required to quickly identify important tasks from among them. However, doing this manually is extremely time-consuming and labor-intensive, so there is a need for efficient management methods. Furthermore, visualizing information and clarifying priorities are important elements for improving work efficiency.

[0248] 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.

[0249] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing and extracting important information using natural language processing technology, and means for analyzing and classifying information using a generative AI model. This enables the rapid identification of important tasks, visual organization of information, and setting of priorities.

[0250] "Electronic communications" refers to messages and data sent and received via the internet, especially email.

[0251] "Accumulation" refers to the process of centrally collecting and organizing specific data.

[0252] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it is a method for analyzing the meaning and intent of text.

[0253] "Important matters" refer to elements within the information being analyzed that require particularly high-priority processing or action.

[0254] A "generative AI model" is a subfield of machine learning that refers to an artificial intelligence model that learns patterns from large amounts of data and uses that knowledge to make predictions and perform analyses on new data.

[0255] "Classification" refers to the process of grouping data or information based on specific criteria or conditions.

[0256] "Priority setting" refers to determining the order in which to process multiple tasks or work based on their importance and urgency.

[0257] "Visualization" refers to the process of visually representing data and information in the form of graphs, tables, and other visual formats to make them easier to understand.

[0258] This invention is a system for efficiently managing electronic communications and improving the work efficiency of users. The system mainly consists of a server, user terminals, and users.

[0259] The server accesses users' email accounts via the internet and automatically collects electronic communications at regular intervals. Specifically, it uses a standard server computer as hardware, and the software retrieves emails from the communication server using the IMAP protocol. The collected communication data is automatically analyzed using natural language processing technology on the server. Here, a generative AI model is utilized to analyze the text of electronic communications, extract important information, classify the work information according to the analysis results, and set priorities.

[0260] The terminal receives work information provided by the server and displays it on a dedicated dashboard. This dashboard is built with application software that has a user interface, and uses JavaScript and CSS to enable intuitive operation for the user. Particularly important tasks and unread notifications are color-coded for visual distinction.

[0261] Users can view high-priority tasks through a dashboard displayed on their device and efficiently process tasks according to the list. Furthermore, a notification function allows them to receive reminders when deadlines for particularly important tasks are approaching.

[0262] As a concrete example, consider a case where a generative AI model extracts important information such as "the project deadline is tomorrow" from received messages, and this is displayed on the dashboard with the priority of "urgent action." In this case, the user can immediately understand the priority and take prompt action.

[0263] An example of a prompt message is: "The user can view unread emails regarding project progress in order of priority and identify tasks that require immediate attention. The server extracts tasks from incoming emails through natural language processing, sets their priorities, and reflects them on the dashboard." This system streamlines the management of electronic communications, enabling more effective work execution.

[0264] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0265] Step 1:

[0266] The server periodically accesses the user's email account and collects new electronic communications. It receives authentication information and connection protocols as input, and communicates with the mail server using the IMAP protocol. The output is newly received email data. Specifically, the server uses authentication information to securely connect to the communication server and retrieve unread emails.

[0267] Step 2:

[0268] The server analyzes the collected electronic communications using natural language processing technology. It receives email text data as input and passes it to a generative AI model. During data processing, the email text is tokenized, and important keywords and phrases are extracted. The output consists of important information and recommended tasks. Specifically, the generative AI model analyzes the email content and identifies keywords as potential tasks.

[0269] Step 3:

[0270] The server classifies and prioritizes work information based on the extracted critical information. It receives the aforementioned critical information and task information as input and applies criteria to evaluate urgency and importance. Based on the data calculations, it assigns priorities to tasks. The output is a prioritized work list. For example, it might label tasks as "urgent" or "normal" and then sort them.

[0271] Step 4:

[0272] The server sends prioritized task information to the user's terminal. It uses a list of completed tasks as input and the output is data sent to the terminal via the HTTP protocol. Specifically, the server encrypts the data and sends it through a secure channel.

[0273] Step 5:

[0274] The terminal displays work information received from the server on a dashboard. It uses work data received from the server as input, and the output is a visual display in the user interface. Specifically, the terminal uses JavaScript and CSS to color-code important tasks, allowing the user to prioritize and review tasks.

[0275] Step 6:

[0276] Users process tasks through a dashboard displayed on their device. The input is visual information from the dashboard. The output is actions to efficiently complete tasks. Specifically, users address tasks in order of urgency, prioritizing tasks with approaching deadlines based on reminders.

[0277] Step 7:

[0278] The server aggregates the progress of each task, automatically generates a log, and shares it with team members. It receives processed work data and its progress information as input, and outputs a report compiled in log format. Specifically, the server automatically formats the daily report and distributes it via email or messaging tools.

[0279] (Application Example 1)

[0280] 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."

[0281] In modern life, the volume of electronic messages is increasing, and managing them is becoming more complex. Furthermore, there is a need to efficiently manage various household tasks and execute them at the appropriate time. However, existing technologies do not adequately integrate the management of electronic messages and household tasks, and efficient scheduling and automation that would improve the quality of life for families have not been achieved.

[0282] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following means.

[0283] In this invention, the server includes means for automatically acquiring an electronic message, means for analyzing the acquired message using natural language processing technology to extract important information, and means for automatically scheduling and notifying household work based on the extracted information. Thereby, the management of electronic messages and household work is integrated, enabling efficient schedule management and automation.

[0284] "Electronic message" refers to language information that is digital-form words and information transmitted and received through the Internet.

[0285] "Natural language processing technology" is a field of computer science for enabling a computer to understand, analyze, and utilize natural language used by humans in daily life.

[0286] "Important information" is a group of data determined to be highly necessary and urgent based on specific conditions and criteria within an electronic message.

[0287] "Household work" refers to various activities and tasks carried out within a household in the course of daily life.

[0288] "Schedule" refers to a plan or schedule based on time, and is a schedule table indicating what actions to take at a specific time.

[0289] "Notification" is an activity or function for notifying a user of important information or a schedule in a visible form.

[0290] In implementing this invention, first, the server automatically and securely acquires the user's electronic message via the Internet. The acquired message is analyzed by software using natural language processing technology. At this time, the server uses an open-source natural language processing library (e.g., spaCy) to identify and extract important information within the message.

[0291] Next, based on the extracted key information, the server schedules household tasks. This is made possible by using a scheduling library (e.g., schedule), enabling efficient schedule management. The server analyzes the acquired information and automatically plans tasks that may occur in the household (e.g., shopping, cleaning, notifications for important events).

[0292] The user's device receives schedule information and notifications sent from the server. This user device includes smartphones, home displays, or voice assistant devices. A dedicated dashboard is displayed on the device, allowing the user to visually check their schedule, and important information and notifications are communicated to the user via voice and visual notifications.

[0293] For example, even if a user leads a busy life, this system can analyze the contents of an email, such as a "weekend shopping list update," and automatically add the necessary items to their digital calendar. This allows the user to avoid forgetting plans and saves extra time.

[0294] As an example of a prompt to the generating AI model, instructing it to "extract household tasks from the user's emails and schedule them based on their importance" can enable efficient schedule management tailored to the user's needs.

[0295] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0296] Step 1:

[0297] The server securely retrieves the user's electronic messages over the internet. During this process, the server accesses the user's email account and authenticates them using security protocols. The input consists of the user's authentication information and the mail server's address, while the output is the data of the received unread emails.

[0298] Step 2:

[0299] The server passes the acquired electronic message to a natural language processing engine for analysis. Here, natural language processing technology (e.g., spaCy) is used to extract keywords and important information from the message. The input is the data of the received email, and the output is the extracted important information (e.g., task details and deadlines).

[0300] Step 3:

[0301] The server automatically schedules household tasks based on the extracted key information. Using a scheduling library (e.g., `schedule`), it analyzes the input information and generates a schedule. The input is the extracted information, and the output is a detailed list of planned tasks and their times.

[0302] Step 4:

[0303] The user terminal receives and displays schedule information sent from the server. Here, specific appointments are notified to the user via a dashboard or smart home device. The input is schedule information from the server, and the output is a visual or audio notification to the user.

[0304] Step 5:

[0305] The user reviews the schedule information provided from the terminal and modifies or approves the appointments as needed. The system receives the updated schedule information again based on the user's actions and updates the data. The input is the user's confirmation and modification information, and the output is the updated schedule information.

[0306] 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.

[0307] The present invention improves the efficiency of email processing and task management by incorporating an emotion engine that recognizes the user's emotions into an email management system. This system consists of a server, the user's terminal, an emotion engine, and the user. The server is responsible for collecting and analyzing emails, and the emotion engine has the function of estimating the user's emotions from the text in the emails.

[0308] First, the server accesses the user's email account and periodically collects new emails. The collected emails are analyzed using natural language processing technology to extract important keywords and tasks, and at the same time, the emotion engine analyzes the emotions contained in the emails. The emotion engine sets multiple emotion categories such as positive, negative, and neutral, and calculates an emotion score based on the content of the emails.

[0309] The server classifies tasks based on the analysis results and sets priorities and urgencies, where the user's emotion information is reflected in the setting of priorities. For example, when a negative emotion is detected, it is also considered that the priority of related tasks is set higher. The generated task information and emotion information are sent to the user's terminal, and the terminal visually displays them on the dashboard. Through this dashboard, the user can easily grasp the importance of tasks based on emotions.

[0310] As a specific example, assume that the user receives an email about an important negotiation with a client. If this email contains a negative emotion, the server uses the emotion engine to detect the negative emotion and sets the "confirmation of negotiation results" task related to this email as a high priority. The information is displayed on the terminal, and the user can prevent an undesirable situation by responding promptly.

[0311] Furthermore, the device adjusts reminder timing based on emotions and task information, providing optimal notifications tailored to the user's emotional state. Additionally, the server automatically generates daily reports, including emotional information, which are distributed to team members, thereby improving team communication and problem-solving capabilities.

[0312] This invention supports efficient and flexible work execution by not only managing emails but also enabling task management that takes into account the user's emotional state.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The server accesses the user's email account and automatically collects newly received emails. It performs security authentication and retrieves email data using the IMAP protocol.

[0316] Step 2:

[0317] The server processes the collected emails using a natural language processing engine to extract keywords and context from the text. A specified model is used to identify meaningful information during this process.

[0318] Step 3:

[0319] The server uses an emotion engine to analyze the user's emotions from the text in the email. It calculates an emotion score and categorizes it as positive, negative, or neutral.

[0320] Step 4:

[0321] Based on the analyzed information, the server extracts tasks related to each email and assigns them importance and urgency. This assignment also takes into account the previously obtained sentiment information. For example, if negative sentiment is detected, the related tasks are classified as having a higher priority.

[0322] Step 5:

[0323] The server sends the generated summary, categorized task list, and sentiment information to the user's device.

[0324] Step 6:

[0325] The dashboard visually displays information received by the device. Tasks are organized by priority, and sentiment information is also displayed, allowing users to intuitively grasp the importance of the information.

[0326] Step 7:

[0327] The device sets reminders based on emotional information and task priorities, and notifies the user at the appropriate time.

[0328] Step 8:

[0329] At the end of the day, the server creates a daily report based on all collected emails and task information, and distributes it to team members via email or other messaging tools, including sentiment information.

[0330] This series of processes allows users to efficiently manage emails and perform task management that takes emotional information into account.

[0331] (Example 2)

[0332] 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".

[0333] One challenge in electronic communication is efficiently managing which tasks should be prioritized, while also considering emotional factors. Especially in busy business environments, quickly and accurately processing the diverse information contained in electronic communications and determining its importance is not easy. Furthermore, there is a growing need to flexibly adjust the urgency and priority of tasks based on emotional information.

[0334] 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.

[0335] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for performing calculations based on the extracted information and estimating an emotional score. This enables task management that takes into account the importance and emotional factors of the electronic communications.

[0336] "Electronic communication" is a general term referring to the exchange of information in the form of documents or messages.

[0337] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate language that humans use on a daily basis.

[0338] An "emotion score" is a numerical representation of the type and degree of emotion contained in a text, and it quantitatively expresses the results of emotion analysis.

[0339] Task management is a methodology for efficiently organizing and executing multiple tasks and work by evaluating their priority and urgency, and processing them systematically.

[0340] This invention improves the efficiency of communication processing and task management in an electronic communication management system by incorporating sentiment analysis functionality. The system consists of a server, a user terminal, a sentiment engine, and the user.

[0341] The server is responsible for automatically collecting electronic communications. Specifically, it accesses users' communication accounts using communication protocols such as IMAP and periodically retrieves new messages. This process can be handled using Python's standard libraries.

[0342] The collected communication data is analyzed using natural language processing (NLTK) techniques. The server uses NLTK and spaCy libraries to extract important keywords and tasks from the communication text. Furthermore, a sentiment engine calculates sentiment scores from the extracted text. This uses generative AI models such as BERT, enabling the analysis of the emotional nuances of the text as numerical data.

[0343] Based on the analysis results, the server sets task priorities. Sentiment scores influence priority determination, and tasks with particularly negative emotions are given a higher priority. This priority setting requires software that implements the algorithm, developed in programming languages ​​such as Python.

[0344] The user's device visually displays task and sentiment information sent from the server on a dashboard. At this stage, the device uses a front-end framework such as React or Vue.js. This allows the user to easily see the importance of tasks based on their sentiment and manage them effectively. The device also adjusts reminder timing based on the sentiment score, providing optimal notifications.

[0345] As a concrete example, consider a scenario where a user receives an important negotiation email from a client. The server uses an emotion engine to detect negative emotions from the email and sets a high priority for the "confirm negotiation results" task associated with that email. This information is immediately displayed on the terminal, allowing the user to respond promptly and prevent unexpected situations from occurring.

[0346] An example of a prompt for a generative AI model is: "Based on the following electronic communication text, use the sentiment engine to identify its sentiment category: 'The client's feedback was somewhat harsh...'"

[0347] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0348] Step 1:

[0349] The server accesses the user's communication account via the IMAP protocol and collects new electronic communications. The inputs used are the destination server information and authentication information. The output is unread message data in the inbox, which includes the sender, subject, and body of the email.

[0350] Step 2:

[0351] The server analyzes the collected electronic communication data using natural language processing techniques. Specifically, it uses NLTK and spaCy to analyze and extract words from the input electronic communication data. This process generates important keywords and task candidates as output. At this stage, part-of-speech tagging and semantic analysis are performed on the words.

[0352] Step 3:

[0353] The server uses extracted text data as input and calculates sentiment scores using a generative AI model. This process employs a Transformer-based model (e.g., BERT), and the output includes sentiment categories such as positive, negative, and neutral, along with their respective scores. The model evaluates the nuances of the text and generates numerical sentiment indicators.

[0354] Step 4:

[0355] The server sets task priorities based on the analysis results: keywords and sentiment scores. The inputs are task candidates and sentiment scores. The priority setting algorithm generates a task list and the priority of each task as output. Tasks strongly influenced by negative emotions are assigned a higher priority.

[0356] Step 5:

[0357] The server sends the generated task information to the user's device. The device uses the received task information as input to visually display it on a dashboard using frameworks such as React or Vue.js. As output, the user can view and manage the task list on the screen. The importance of tasks can be intuitively grasped through color coding and icons.

[0358] Step 6:

[0359] The device adjusts reminder timing based on sentiment scores. The task list and its priority are used as input. Reminder settings are configured in conjunction with the calendar API as output. Email and pop-up notifications are provided to the user at appropriate times.

[0360] Step 7:

[0361] The server automatically generates daily reports and provides emotion scores and task information to others in a record format. It uses analysis results as input and generates formatted report data (such as PDF or HTML) as output. This data is then distributed to team members via email or internal communication tools.

[0362] (Application Example 2)

[0363] 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."

[0364] In today's business environment, the increasing influx of information through electronic communications makes it difficult to prioritize important tasks and respond appropriately. Furthermore, there is a growing need to properly evaluate the emotions contained in received communications and recognize them early as business risks or critical issues. This need is particularly urgent for companies that require early warning of security risks such as phishing and malware.

[0365] 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.

[0366] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for analyzing the sentiment of the electronic communications and reflecting it in the task priority. This enables the rapid setting of priorities based on the sentiment conveyed by the received communications, allowing for immediate response to important matters and early warning of security risks.

[0367] "Electronic communications" refers to digital data such as emails and messages sent and received via the internet or local networks.

[0368] "Natural language processing technology" refers to all technologies that enable computers to understand and process human language, and includes information extraction and sentiment analysis.

[0369] "Analyzing emotions" means analyzing the linguistic expressions contained in text data to infer the underlying emotions (positive, negative, etc.).

[0370] "Reflecting this in work priorities" means reassessing the importance and urgency of related tasks based on the emotions and importance of the communication, and enabling them to be addressed in the appropriate order.

[0371] A "server" is a computer resource provided on a network for the purpose of collecting and processing data.

[0372] A description of the embodiment for carrying out the invention will be provided.

[0373] This system combines electronic communication management and sentiment analysis to enable efficient task prioritization. The server operates on the network and automatically collects electronic communications such as emails and messages. The server analyzes the collected communications using advanced natural language processing technologies (e.g., spaCy and NLTK) to extract important information and keywords.

[0374] Based on the content of collected electronic communications, sentiment analysis models are used to calculate sentiment scores such as positive, negative, and neutral. Machine learning frameworks such as TensorFlow and PyTorch are used for sentiment analysis. Based on the sentiment scores, importance and urgency are re-evaluated, and tasks are prioritized.

[0375] The user terminal visually displays this prioritized work information, enabling users to respond quickly. Reminders and notification functions are also provided, improving the user's work efficiency.

[0376] For example, if a user receives an email from a business partner with disturbing content, the server can detect the negative sentiment in the email and set related response tasks with high priority. This result is displayed on the terminal, allowing the user to quickly begin taking action.

[0377] As an example of a prompt, inputting instructions such as "Instruct me how to adjust the priority of tasks based on the emotions detected in this email" into the generating AI model will make task prioritization smoother.

[0378] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0379] Step 1:

[0380] The server accesses the user's email account over the network. It receives user authentication information as input and automatically collects new emails at specified time intervals. The output is the collected email data. Since it retrieves information from the mail server using email protocols (such as IMAP or POP3), communication is secure and reliable.

[0381] Step 2:

[0382] The server analyzes the collected email data using natural language processing (NLP) techniques. The input is email text, and the output extracts important keywords and phrases. NLP libraries (such as spaCy and NLTK) are used to analyze the grammatical structure and extract semantically important information. This makes subsequent analysis more effective.

[0383] Step 3:

[0384] The server calculates an emotion score using an emotion analysis model based on the data obtained from NLP processing. The input is the information extracted in step 2, and the output is a score corresponding to an emotion category (positive, negative, neutral, etc.). Emotion analysis models using TensorFlow or PyTorch are utilized here to quantitatively evaluate emotions from the tone and content of emails.

[0385] Step 4:

[0386] The server categorizes and prioritizes relevant tasks based on sentiment scores and other email information. Inputs are sentiment scores and keywords, and output is a prioritized task list. This prioritization allows for tasks that require immediate attention, particularly communications containing negative emotions.

[0387] Step 5:

[0388] The terminal uses prioritized work information received from the server and displays it visually on the user interface. Input is a work list, and output is a user-friendly dashboard. Here, users can make quick and accurate decisions based on the visualized information.

[0389] Step 6:

[0390] The device sets appropriate reminders and notifications for tasks requiring attention based on the displayed information. Input is priority information within the task list, and output is notifications based on time and conditions. This ensures that users can reliably address important tasks without missing any.

[0391] Step 7:

[0392] Users perform tasks and take appropriate actions based on information obtained from their devices. Input is the displayed task information, and output is the specific action to be taken. This streamlines communication and operations within the organization.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention is a system aimed at efficient email management and task visualization, and consists of a server, user terminals, and users. This system not only automatically analyzes received emails, extracts important information, and classifies them as tasks, but also presents priorities to the user, thereby significantly improving work efficiency.

[0410] First, the server accesses the user's email account and collects new emails at regular intervals. This involves a secure authentication process using known security protocols. The collected emails are analyzed using a natural language processing engine to extract important keywords and tasks. Based on this information, the server prioritizes each task and categorizes them by urgency and importance.

[0411] The user's device receives task information and summaries from the server and displays them visually on a dedicated dashboard. The dashboard is designed so that users can quickly see their most important tasks and unanswered emails. This information is also visually organized, allowing users to process tasks according to priority.

[0412] As a concrete example, consider a scenario where the user is a project manager. The server detects an email with the subject "Urgent," and from its analysis, extracts that the project deadline is the next day. The server generates a summary of this critical information and lists "Project Progress Check" as a high-priority task. The terminal displays this information on a dashboard, allowing the user to understand that immediate action is required. Additionally, a reminder function notifies the user of important tasks, preventing them from forgetting to take action.

[0413] Furthermore, the server automatically generates daily reports and shares them with designated team members via email or messaging tools. This allows all team members to stay informed about the status of their work, enabling centralized information sharing and a feedback loop.

[0414] In this way, the present invention provides an effective means for streamlining email management and improving business efficiency.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] The server accesses the user's email account and automatically collects newly received emails. It uses a secure protocol for user authentication and retrieves email data using IMAP or POP3.

[0418] Step 2:

[0419] The server inputs collected email data into a natural language processing engine, which extracts text from the email body. This text is then analyzed to understand keywords and context, and to identify important information.

[0420] Step 3:

[0421] Based on the analyzed information, the server extracts tasks from the email and assigns a priority and urgency level to each. A machine learning algorithm is used to classify them and assign "high," "medium," and "low" classification tags.

[0422] Step 4:

[0423] The server summarizes the key points of each email and generates a summary. The main points are presented in a clear and concise manner for easy understanding by the user.

[0424] Step 5:

[0425] The server sends the generated summary and task list to the user's terminal.

[0426] Step 6:

[0427] The terminal displays the information it receives on the user interface, providing it visually to the user through a dashboard. The user uses this dashboard to check task priorities and take appropriate action.

[0428] Step 7:

[0429] The device sets reminders based on task information provided by the server. It sends notifications at the specified time to help users avoid missing important tasks.

[0430] Step 8:

[0431] At the end of the day, the server generates a daily report based on aggregated email information and task lists. This report is then sent to designated team members to facilitate information sharing.

[0432] (Example 1)

[0433] 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."

[0434] In today's work environment, users receive a large volume of electronic communications and are required to quickly identify important tasks from among them. However, doing this manually is extremely time-consuming and labor-intensive, so there is a need for efficient management methods. Furthermore, visualizing information and clarifying priorities are important elements for improving work efficiency.

[0435] 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.

[0436] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing and extracting important information using natural language processing technology, and means for analyzing and classifying information using a generative AI model. This enables the rapid identification of important tasks, visual organization of information, and setting of priorities.

[0437] "Electronic communications" refers to messages and data sent and received via the internet, especially email.

[0438] "Accumulation" refers to the process of centrally collecting and organizing specific data.

[0439] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it is a method for analyzing the meaning and intent of text.

[0440] "Important matters" refer to elements within the information being analyzed that require particularly high-priority processing or action.

[0441] A "generative AI model" is a subfield of machine learning that refers to an artificial intelligence model that learns patterns from large amounts of data and uses that knowledge to make predictions and perform analyses on new data.

[0442] "Classification" refers to the process of grouping data or information based on specific criteria or conditions.

[0443] "Priority setting" refers to determining the order in which to process multiple tasks or work based on their importance and urgency.

[0444] "Visualization" refers to the process of visually representing data and information in the form of graphs, tables, and other visual formats to make them easier to understand.

[0445] This invention is a system for efficiently managing electronic communications and improving the work efficiency of users. The system mainly consists of a server, user terminals, and users.

[0446] The server accesses users' email accounts via the internet and automatically collects electronic communications at regular intervals. Specifically, it uses a standard server computer as hardware, and the software retrieves emails from the communication server using the IMAP protocol. The collected communication data is automatically analyzed using natural language processing technology on the server. Here, a generative AI model is utilized to analyze the text of electronic communications, extract important information, classify the work information according to the analysis results, and set priorities.

[0447] The terminal receives work information provided by the server and displays it on a dedicated dashboard. This dashboard is built with application software that has a user interface, and uses JavaScript and CSS to enable intuitive operation for the user. Particularly important tasks and unread notifications are color-coded for visual distinction.

[0448] Users can view high-priority tasks through a dashboard displayed on their device and efficiently process tasks according to the list. Furthermore, a notification function allows them to receive reminders when deadlines for particularly important tasks are approaching.

[0449] As a concrete example, consider a case where a generative AI model extracts important information such as "the project deadline is tomorrow" from received messages, and this is displayed on the dashboard with the priority of "urgent action." In this case, the user can immediately understand the priority and take prompt action.

[0450] An example of a prompt message is: "The user can view unread emails regarding project progress in order of priority and identify tasks that require immediate attention. The server extracts tasks from incoming emails through natural language processing, sets their priorities, and reflects them on the dashboard." This system streamlines the management of electronic communications, enabling more effective work execution.

[0451] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0452] Step 1:

[0453] The server periodically accesses the user's email account and collects new electronic communications. It receives authentication information and connection protocols as input, and communicates with the mail server using the IMAP protocol. The output is newly received email data. Specifically, the server uses authentication information to securely connect to the communication server and retrieve unread emails.

[0454] Step 2:

[0455] The server analyzes the collected electronic communications using natural language processing technology. It receives email text data as input and passes it to a generative AI model. During data processing, the email text is tokenized, and important keywords and phrases are extracted. The output consists of important information and recommended tasks. Specifically, the generative AI model analyzes the email content and identifies keywords as potential tasks.

[0456] Step 3:

[0457] The server classifies and prioritizes work information based on the extracted critical information. It receives the aforementioned critical information and task information as input and applies criteria to evaluate urgency and importance. Based on the data calculations, it assigns priorities to tasks. The output is a prioritized work list. For example, it might label tasks as "urgent" or "normal" and then sort them.

[0458] Step 4:

[0459] The server sends prioritized task information to the user's terminal. It uses a list of completed tasks as input and the output is data sent to the terminal via the HTTP protocol. Specifically, the server encrypts the data and sends it through a secure channel.

[0460] Step 5:

[0461] The terminal displays work information received from the server on a dashboard. It uses work data received from the server as input, and the output is a visual display in the user interface. Specifically, the terminal uses JavaScript and CSS to color-code important tasks, allowing the user to prioritize and review tasks.

[0462] Step 6:

[0463] Users process tasks through a dashboard displayed on their device. The input is visual information from the dashboard. The output is actions to efficiently complete tasks. Specifically, users address tasks in order of urgency, prioritizing tasks with approaching deadlines based on reminders.

[0464] Step 7:

[0465] The server aggregates the progress of each task, automatically generates a log, and shares it with team members. It receives processed work data and its progress information as input, and outputs a report compiled in log format. Specifically, the server automatically formats the daily report and distributes it via email or messaging tools.

[0466] (Application Example 1)

[0467] 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."

[0468] In modern life, the volume of electronic messages is increasing, and managing them is becoming more complex. Furthermore, there is a need to efficiently manage various household tasks and execute them at the appropriate time. However, existing technologies do not adequately integrate the management of electronic messages and household tasks, and efficient scheduling and automation that would improve the quality of life for families have not been achieved.

[0469] 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.

[0470] In this invention, the server includes means for automatically acquiring electronic messages, means for analyzing the acquired messages using natural language processing technology and extracting important information, and means for automatically scheduling and notifying users of household tasks based on the extracted information. This integrates the management of electronic messages and household tasks, enabling efficient scheduling and automation.

[0471] "Electronic messages" refer to linguistic information, specifically words and information in digital format that are sent and received via the internet.

[0472] "Natural language processing technology" is a field of computer science that enables computers to understand, analyze, and utilize the natural language that humans use in everyday life.

[0473] "Important information" refers to a set of data within an electronic message that is deemed to be of high necessity or urgency based on specific conditions or criteria.

[0474] "Household tasks" refers to the various activities and duties performed within the home as part of daily life.

[0475] A "schedule" refers to a time-based plan or schedule, a plan that shows what actions to take at specific times.

[0476] "Notifications" refer to activities or functions that visually inform users of important information or schedules.

[0477] In implementing this invention, the server first securely and automatically retrieves the user's electronic messages via the internet. The retrieved messages are then analyzed using software employing natural language processing technology. In this process, the server uses an open-source natural language processing library (e.g., spaCy) to identify and extract important information from the messages.

[0478] Next, based on the extracted key information, the server schedules household tasks. This is made possible by using a scheduling library (e.g., schedule), enabling efficient schedule management. The server analyzes the acquired information and automatically plans tasks that may occur in the household (e.g., shopping, cleaning, notifications for important events).

[0479] The user's device receives schedule information and notifications sent from the server. This user device includes smartphones, home displays, or voice assistant devices. A dedicated dashboard is displayed on the device, allowing the user to visually check their schedule, and important information and notifications are communicated to the user via voice and visual notifications.

[0480] For example, even if a user leads a busy life, this system can analyze the contents of an email, such as a "weekend shopping list update," and automatically add the necessary items to their digital calendar. This allows the user to avoid forgetting plans and saves extra time.

[0481] As an example of a prompt to the generating AI model, instructing it to "extract household tasks from the user's emails and schedule them based on their importance" can enable efficient schedule management tailored to the user's needs.

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] The server securely retrieves the user's electronic messages over the internet. During this process, the server accesses the user's email account and authenticates them using security protocols. The input consists of the user's authentication information and the mail server's address, while the output is the data of the received unread emails.

[0485] Step 2:

[0486] The server passes the acquired electronic message to a natural language processing engine for analysis. Here, natural language processing technology (e.g., spaCy) is used to extract keywords and important information from the message. The input is the data of the received email, and the output is the extracted important information (e.g., task details and deadlines).

[0487] Step 3:

[0488] The server automatically schedules household tasks based on the extracted key information. Using a scheduling library (e.g., `schedule`), it analyzes the input information and generates a schedule. The input is the extracted information, and the output is a detailed list of planned tasks and their times.

[0489] Step 4:

[0490] The user terminal receives and displays schedule information sent from the server. Here, specific appointments are notified to the user via a dashboard or smart home device. The input is schedule information from the server, and the output is a visual or audio notification to the user.

[0491] Step 5:

[0492] The user reviews the schedule information provided from the terminal and modifies or approves the appointments as needed. The system receives the updated schedule information again based on the user's actions and updates the data. The input is the user's confirmation and modification information, and the output is the updated schedule information.

[0493] 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.

[0494] This invention improves the efficiency of email processing and task management by incorporating an emotion engine that recognizes user emotions into an email management system. The system consists of a server, a user terminal, an emotion engine, and the user. The server is responsible for collecting and analyzing emails, while the emotion engine has the function of estimating the user's emotions from the text within the emails.

[0495] First, the server accesses the user's email account and periodically collects new emails. The collected emails are analyzed using natural language processing techniques to extract important keywords and tasks, while the sentiment engine analyzes the emotions contained in the emails. The sentiment engine sets up multiple emotion categories such as positive, negative, and neutral, and calculates an emotion score based on the content of the emails.

[0496] The server classifies tasks based on the analysis results and sets priorities and urgency levels, but user sentiment information is reflected in the priority setting. For example, if negative sentiment is detected, the priority of related tasks may be set higher. The generated task information and sentiment information are sent to the user's device, which displays them visually on a dashboard. Through this dashboard, the user can easily understand the importance of tasks based on their sentiment.

[0497] As a concrete example, suppose a user receives an email about an important negotiation with a client. If this email contains negative emotions, the server uses an emotion engine to detect the negative emotions and sets a high priority for the "Confirm Negotiation Results" task related to that email. This information is displayed on the terminal, allowing the user to take prompt action and prevent undesirable situations.

[0498] Furthermore, the device adjusts reminder timing based on emotions and task information, providing optimal notifications tailored to the user's emotional state. Additionally, the server automatically generates daily reports, including emotional information, which are distributed to team members, thereby improving team communication and problem-solving capabilities.

[0499] This invention supports efficient and flexible work execution by not only managing emails but also enabling task management that takes into account the user's emotional state.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The server accesses the user's email account and automatically collects newly received emails. It performs security authentication and retrieves email data using the IMAP protocol.

[0503] Step 2:

[0504] The server processes the collected emails using a natural language processing engine to extract keywords and context from the text. A specified model is used to identify meaningful information during this process.

[0505] Step 3:

[0506] The server uses an emotion engine to analyze the user's emotions from the text in the email. It calculates an emotion score and categorizes it as positive, negative, or neutral.

[0507] Step 4:

[0508] Based on the analyzed information, the server extracts tasks related to each email and assigns them importance and urgency. This assignment also takes into account the previously obtained sentiment information. For example, if negative sentiment is detected, the related tasks are classified as having a higher priority.

[0509] Step 5:

[0510] The server sends the generated summary, categorized task list, and sentiment information to the user's device.

[0511] Step 6:

[0512] The dashboard visually displays information received by the device. Tasks are organized by priority, and sentiment information is also displayed, allowing users to intuitively grasp the importance of the information.

[0513] Step 7:

[0514] The device sets reminders based on emotional information and task priorities, and notifies the user at the appropriate time.

[0515] Step 8:

[0516] At the end of the day, the server creates a daily report based on all collected emails and task information, and distributes it to team members via email or other messaging tools, including sentiment information.

[0517] This series of processes allows users to efficiently manage emails and perform task management that takes emotional information into account.

[0518] (Example 2)

[0519] 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."

[0520] One challenge in electronic communication is efficiently managing which tasks should be prioritized, while also considering emotional factors. Especially in busy business environments, quickly and accurately processing the diverse information contained in electronic communications and determining its importance is not easy. Furthermore, there is a growing need to flexibly adjust the urgency and priority of tasks based on emotional information.

[0521] 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.

[0522] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for performing calculations based on the extracted information and estimating an emotional score. This enables task management that takes into account the importance and emotional factors of the electronic communications.

[0523] "Electronic communication" is a general term referring to the exchange of information in the form of documents or messages.

[0524] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate language that humans use on a daily basis.

[0525] An "emotion score" is a numerical representation of the type and degree of emotion contained in a text, and it quantitatively expresses the results of emotion analysis.

[0526] Task management is a methodology for efficiently organizing and executing multiple tasks and work by evaluating their priority and urgency, and processing them systematically.

[0527] This invention improves the efficiency of communication processing and task management in an electronic communication management system by incorporating sentiment analysis functionality. The system consists of a server, a user terminal, a sentiment engine, and the user.

[0528] The server is responsible for automatically collecting electronic communications. Specifically, it accesses users' communication accounts using communication protocols such as IMAP and periodically retrieves new messages. This process can be handled using Python's standard libraries.

[0529] The collected communication data is analyzed using natural language processing (NLTK) techniques. The server uses NLTK and spaCy libraries to extract important keywords and tasks from the communication text. Furthermore, a sentiment engine calculates sentiment scores from the extracted text. This uses generative AI models such as BERT, enabling the analysis of the emotional nuances of the text as numerical data.

[0530] Based on the analysis results, the server sets task priorities. Sentiment scores influence priority determination, and tasks with particularly negative emotions are given a higher priority. This priority setting requires software that implements the algorithm, developed in programming languages ​​such as Python.

[0531] The user's device visually displays task and sentiment information sent from the server on a dashboard. At this stage, the device uses a front-end framework such as React or Vue.js. This allows the user to easily see the importance of tasks based on their sentiment and manage them effectively. The device also adjusts reminder timing based on the sentiment score, providing optimal notifications.

[0532] As a concrete example, consider a scenario where a user receives an important negotiation email from a client. The server uses an emotion engine to detect negative emotions from the email and sets a high priority for the "confirm negotiation results" task associated with that email. This information is immediately displayed on the terminal, allowing the user to respond promptly and prevent unexpected situations from occurring.

[0533] An example of a prompt for a generative AI model is: "Based on the following electronic communication text, use the sentiment engine to identify its sentiment category: 'The client's feedback was somewhat harsh...'"

[0534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0535] Step 1:

[0536] The server accesses the user's communication account via the IMAP protocol and collects new electronic communications. The inputs used are the destination server information and authentication information. The output is unread message data in the inbox, which includes the sender, subject, and body of the email.

[0537] Step 2:

[0538] The server analyzes the collected electronic communication data using natural language processing techniques. Specifically, it uses NLTK and spaCy to analyze and extract words from the input electronic communication data. This process generates important keywords and task candidates as output. At this stage, part-of-speech tagging and semantic analysis are performed on the words.

[0539] Step 3:

[0540] The server uses extracted text data as input and calculates sentiment scores using a generative AI model. This process employs a Transformer-based model (e.g., BERT), and the output includes sentiment categories such as positive, negative, and neutral, along with their respective scores. The model evaluates the nuances of the text and generates numerical sentiment indicators.

[0541] Step 4:

[0542] The server sets task priorities based on the analysis results: keywords and sentiment scores. The inputs are task candidates and sentiment scores. The priority setting algorithm generates a task list and the priority of each task as output. Tasks strongly influenced by negative emotions are assigned a higher priority.

[0543] Step 5:

[0544] The server sends the generated task information to the user's device. The device uses the received task information as input to visually display it on a dashboard using frameworks such as React or Vue.js. As output, the user can view and manage the task list on the screen. The importance of tasks can be intuitively grasped through color coding and icons.

[0545] Step 6:

[0546] The device adjusts reminder timing based on sentiment scores. The task list and its priority are used as input. Reminder settings are configured in conjunction with the calendar API as output. Email and pop-up notifications are provided to the user at appropriate times.

[0547] Step 7:

[0548] The server automatically generates daily reports and provides emotion scores and task information to others in a record format. It uses analysis results as input and generates formatted report data (such as PDF or HTML) as output. This data is then distributed to team members via email or internal communication tools.

[0549] (Application Example 2)

[0550] 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."

[0551] In today's business environment, the increasing influx of information through electronic communications makes it difficult to prioritize important tasks and respond appropriately. Furthermore, there is a growing need to properly evaluate the emotions contained in received communications and recognize them early as business risks or critical issues. This need is particularly urgent for companies that require early warning of security risks such as phishing and malware.

[0552] 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.

[0553] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for analyzing the sentiment of the electronic communications and reflecting it in the task priority. This enables the rapid setting of priorities based on the sentiment conveyed by the received communications, allowing for immediate response to important matters and early warning of security risks.

[0554] "Electronic communications" refers to digital data such as emails and messages sent and received via the internet or local networks.

[0555] "Natural language processing technology" refers to all technologies that enable computers to understand and process human language, and includes information extraction and sentiment analysis.

[0556] "Analyzing emotions" means analyzing the linguistic expressions contained in text data to infer the underlying emotions (positive, negative, etc.).

[0557] "Reflecting this in work priorities" means reassessing the importance and urgency of related tasks based on the emotions and importance of the communication, and enabling them to be addressed in the appropriate order.

[0558] A "server" is a computer resource provided on a network for the purpose of collecting and processing data.

[0559] A description of the embodiment for carrying out the invention will be provided.

[0560] This system combines electronic communication management and sentiment analysis to enable efficient task prioritization. The server operates on the network and automatically collects electronic communications such as emails and messages. The server analyzes the collected communications using advanced natural language processing technologies (e.g., spaCy and NLTK) to extract important information and keywords.

[0561] Based on the content of collected electronic communications, sentiment analysis models are used to calculate sentiment scores such as positive, negative, and neutral. Machine learning frameworks such as TensorFlow and PyTorch are used for sentiment analysis. Based on the sentiment scores, importance and urgency are re-evaluated, and tasks are prioritized.

[0562] The user terminal visually displays this prioritized work information, enabling users to respond quickly. Reminders and notification functions are also provided, improving the user's work efficiency.

[0563] For example, if a user receives an email from a business partner with disturbing content, the server can detect the negative sentiment in the email and set related response tasks with high priority. This result is displayed on the terminal, allowing the user to quickly begin taking action.

[0564] As an example of a prompt, inputting instructions such as "Instruct me how to adjust the priority of tasks based on the emotions detected in this email" into the generating AI model will make task prioritization smoother.

[0565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0566] Step 1:

[0567] The server accesses the user's email account over the network. It receives user authentication information as input and automatically collects new emails at specified time intervals. The output is the collected email data. Since it retrieves information from the mail server using email protocols (such as IMAP or POP3), communication is secure and reliable.

[0568] Step 2:

[0569] The server analyzes the collected email data using natural language processing (NLP) techniques. The input is email text, and the output extracts important keywords and phrases. NLP libraries (such as spaCy and NLTK) are used to analyze the grammatical structure and extract semantically important information. This makes subsequent analysis more effective.

[0570] Step 3:

[0571] The server calculates an emotion score using an emotion analysis model based on the data obtained from NLP processing. The input is the information extracted in step 2, and the output is a score corresponding to an emotion category (positive, negative, neutral, etc.). Emotion analysis models using TensorFlow or PyTorch are utilized here to quantitatively evaluate emotions from the tone and content of emails.

[0572] Step 4:

[0573] The server categorizes and prioritizes relevant tasks based on sentiment scores and other email information. Inputs are sentiment scores and keywords, and output is a prioritized task list. This prioritization allows for tasks that require immediate attention, particularly communications containing negative emotions.

[0574] Step 5:

[0575] The terminal uses prioritized work information received from the server and displays it visually on the user interface. Input is a work list, and output is a user-friendly dashboard. Here, users can make quick and accurate decisions based on the visualized information.

[0576] Step 6:

[0577] The device sets appropriate reminders and notifications for tasks requiring attention based on the displayed information. Input is priority information within the task list, and output is notifications based on time and conditions. This ensures that users can reliably address important tasks without missing any.

[0578] Step 7:

[0579] Users perform tasks and take appropriate actions based on information obtained from their devices. Input is the displayed task information, and output is the specific action to be taken. This streamlines communication and operations within the organization.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] [Fourth Embodiment]

[0584] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0585] 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.

[0586] 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).

[0587] 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.

[0588] 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.

[0589] 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).

[0590] 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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".

[0597] This invention is a system aimed at efficient email management and task visualization, and consists of a server, user terminals, and users. This system not only automatically analyzes received emails, extracts important information, and classifies them as tasks, but also presents priorities to the user, thereby significantly improving work efficiency.

[0598] First, the server accesses the user's email account and collects new emails at regular intervals. This involves a secure authentication process using known security protocols. The collected emails are analyzed using a natural language processing engine to extract important keywords and tasks. Based on this information, the server prioritizes each task and categorizes them by urgency and importance.

[0599] The user's device receives task information and summaries from the server and displays them visually on a dedicated dashboard. The dashboard is designed so that users can quickly see their most important tasks and unanswered emails. This information is also visually organized, allowing users to process tasks according to priority.

[0600] As a concrete example, consider a scenario where the user is a project manager. The server detects an email with the subject "Urgent," and from its analysis, extracts that the project deadline is the next day. The server generates a summary of this critical information and lists "Project Progress Check" as a high-priority task. The terminal displays this information on a dashboard, allowing the user to understand that immediate action is required. Additionally, a reminder function notifies the user of important tasks, preventing them from forgetting to take action.

[0601] Furthermore, the server automatically generates daily reports and shares them with designated team members via email or messaging tools. This allows all team members to stay informed about the status of their work, enabling centralized information sharing and a feedback loop.

[0602] In this way, the present invention provides an effective means for streamlining email management and improving business efficiency.

[0603] The following describes the processing flow.

[0604] Step 1:

[0605] The server accesses the user's email account and automatically collects newly received emails. It uses a secure protocol for user authentication and retrieves email data using IMAP or POP3.

[0606] Step 2:

[0607] The server inputs collected email data into a natural language processing engine, which extracts text from the email body. This text is then analyzed to understand keywords and context, and to identify important information.

[0608] Step 3:

[0609] Based on the analyzed information, the server extracts tasks from the email and assigns a priority and urgency level to each. A machine learning algorithm is used to classify them and assign "high," "medium," and "low" classification tags.

[0610] Step 4:

[0611] The server summarizes the key points of each email and generates a summary. The main points are presented in a clear and concise manner for easy understanding by the user.

[0612] Step 5:

[0613] The server sends the generated summary and task list to the user's terminal.

[0614] Step 6:

[0615] The terminal displays the information it receives on the user interface, providing it visually to the user through a dashboard. The user uses this dashboard to check task priorities and take appropriate action.

[0616] Step 7:

[0617] The device sets reminders based on task information provided by the server. It sends notifications at the specified time to help users avoid missing important tasks.

[0618] Step 8:

[0619] At the end of the day, the server generates a daily report based on aggregated email information and task lists. This report is then sent to designated team members to facilitate information sharing.

[0620] (Example 1)

[0621] 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".

[0622] In today's work environment, users receive a large volume of electronic communications and are required to quickly identify important tasks from among them. However, doing this manually is extremely time-consuming and labor-intensive, so there is a need for efficient management methods. Furthermore, visualizing information and clarifying priorities are important elements for improving work efficiency.

[0623] 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.

[0624] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing and extracting important information using natural language processing technology, and means for analyzing and classifying information using a generative AI model. This enables the rapid identification of important tasks, visual organization of information, and setting of priorities.

[0625] "Electronic communications" refers to messages and data sent and received via the internet, especially email.

[0626] "Accumulation" refers to the process of centrally collecting and organizing specific data.

[0627] "Natural language processing technology" refers to the technology that enables computers to understand and process human language, and in particular, it is a method for analyzing the meaning and intent of text.

[0628] "Important matters" refer to elements within the information being analyzed that require particularly high-priority processing or action.

[0629] A "generative AI model" is a subfield of machine learning that refers to an artificial intelligence model that learns patterns from large amounts of data and uses that knowledge to make predictions and perform analyses on new data.

[0630] "Classification" refers to the process of grouping data or information based on specific criteria or conditions.

[0631] "Priority setting" refers to determining the order in which to process multiple tasks or work based on their importance and urgency.

[0632] "Visualization" refers to the process of visually representing data and information in the form of graphs, tables, and other visual formats to make them easier to understand.

[0633] This invention is a system for efficiently managing electronic communications and improving the work efficiency of users. The system mainly consists of a server, user terminals, and users.

[0634] The server accesses users' email accounts via the internet and automatically collects electronic communications at regular intervals. Specifically, it uses a standard server computer as hardware, and the software retrieves emails from the communication server using the IMAP protocol. The collected communication data is automatically analyzed using natural language processing technology on the server. Here, a generative AI model is utilized to analyze the text of electronic communications, extract important information, classify the work information according to the analysis results, and set priorities.

[0635] The terminal receives work information provided by the server and displays it on a dedicated dashboard. This dashboard is built with application software that has a user interface, and uses JavaScript and CSS to enable intuitive operation for the user. Particularly important tasks and unread notifications are color-coded for visual distinction.

[0636] Users can view high-priority tasks through a dashboard displayed on their device and efficiently process tasks according to the list. Furthermore, a notification function allows them to receive reminders when deadlines for particularly important tasks are approaching.

[0637] As a concrete example, consider a case where a generative AI model extracts important information such as "the project deadline is tomorrow" from received messages, and this is displayed on the dashboard with the priority of "urgent action." In this case, the user can immediately understand the priority and take prompt action.

[0638] An example of a prompt message is: "The user can view unread emails regarding project progress in order of priority and identify tasks that require immediate attention. The server extracts tasks from incoming emails through natural language processing, sets their priorities, and reflects them on the dashboard." This system streamlines the management of electronic communications, enabling more effective work execution.

[0639] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0640] Step 1:

[0641] The server periodically accesses the user's email account and collects new electronic communications. It receives authentication information and connection protocols as input, and communicates with the mail server using the IMAP protocol. The output is newly received email data. Specifically, the server uses authentication information to securely connect to the communication server and retrieve unread emails.

[0642] Step 2:

[0643] The server analyzes the collected electronic communications using natural language processing technology. It receives email text data as input and passes it to a generative AI model. During data processing, the email text is tokenized, and important keywords and phrases are extracted. The output consists of important information and recommended tasks. Specifically, the generative AI model analyzes the email content and identifies keywords as potential tasks.

[0644] Step 3:

[0645] The server classifies and prioritizes work information based on the extracted critical information. It receives the aforementioned critical information and task information as input and applies criteria to evaluate urgency and importance. Based on the data calculations, it assigns priorities to tasks. The output is a prioritized work list. For example, it might label tasks as "urgent" or "normal" and then sort them.

[0646] Step 4:

[0647] The server sends prioritized task information to the user's terminal. It uses a list of completed tasks as input and the output is data sent to the terminal via the HTTP protocol. Specifically, the server encrypts the data and sends it through a secure channel.

[0648] Step 5:

[0649] The terminal displays work information received from the server on a dashboard. It uses work data received from the server as input, and the output is a visual display in the user interface. Specifically, the terminal uses JavaScript and CSS to color-code important tasks, allowing the user to prioritize and review tasks.

[0650] Step 6:

[0651] Users process tasks through a dashboard displayed on their device. The input is visual information from the dashboard. The output is actions to efficiently complete tasks. Specifically, users address tasks in order of urgency, prioritizing tasks with approaching deadlines based on reminders.

[0652] Step 7:

[0653] The server aggregates the progress of each task, automatically generates a log, and shares it with team members. It receives processed work data and its progress information as input, and outputs a report compiled in log format. Specifically, the server automatically formats the daily report and distributes it via email or messaging tools.

[0654] (Application Example 1)

[0655] 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".

[0656] In modern life, the volume of electronic messages is increasing, and managing them is becoming more complex. Furthermore, there is a need to efficiently manage various household tasks and execute them at the appropriate time. However, existing technologies do not adequately integrate the management of electronic messages and household tasks, and efficient scheduling and automation that would improve the quality of life for families have not been achieved.

[0657] 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.

[0658] In this invention, the server includes means for automatically acquiring electronic messages, means for analyzing the acquired messages using natural language processing technology and extracting important information, and means for automatically scheduling and notifying users of household tasks based on the extracted information. This integrates the management of electronic messages and household tasks, enabling efficient scheduling and automation.

[0659] "Electronic messages" refer to linguistic information, specifically words and information in digital format that are sent and received via the internet.

[0660] "Natural language processing technology" is a field of computer science that enables computers to understand, analyze, and utilize the natural language that humans use in everyday life.

[0661] "Important information" refers to a set of data within an electronic message that is deemed to be of high necessity or urgency based on specific conditions or criteria.

[0662] "Household tasks" refers to the various activities and duties performed within the home as part of daily life.

[0663] A "schedule" refers to a time-based plan or schedule, a plan that shows what actions to take at specific times.

[0664] "Notifications" refer to activities or functions that visually inform users of important information or schedules.

[0665] In implementing this invention, the server first securely and automatically retrieves the user's electronic messages via the internet. The retrieved messages are then analyzed using software employing natural language processing technology. In this process, the server uses an open-source natural language processing library (e.g., spaCy) to identify and extract important information from the messages.

[0666] Next, based on the extracted key information, the server schedules household tasks. This is made possible by using a scheduling library (e.g., schedule), enabling efficient schedule management. The server analyzes the acquired information and automatically plans tasks that may occur in the household (e.g., shopping, cleaning, notifications for important events).

[0667] The user's device receives schedule information and notifications sent from the server. This user device includes smartphones, home displays, or voice assistant devices. A dedicated dashboard is displayed on the device, allowing the user to visually check their schedule, and important information and notifications are communicated to the user via voice and visual notifications.

[0668] For example, even if a user leads a busy life, this system can analyze the contents of an email, such as a "weekend shopping list update," and automatically add the necessary items to their digital calendar. This allows the user to avoid forgetting plans and saves extra time.

[0669] As an example of a prompt to the generating AI model, instructing it to "extract household tasks from the user's emails and schedule them based on their importance" can enable efficient schedule management tailored to the user's needs.

[0670] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0671] Step 1:

[0672] The server securely retrieves the user's electronic messages over the internet. During this process, the server accesses the user's email account and authenticates them using security protocols. The input consists of the user's authentication information and the mail server's address, while the output is the data of the received unread emails.

[0673] Step 2:

[0674] The server passes the acquired electronic message to a natural language processing engine for analysis. Here, natural language processing technology (e.g., spaCy) is used to extract keywords and important information from the message. The input is the data of the received email, and the output is the extracted important information (e.g., task details and deadlines).

[0675] Step 3:

[0676] The server automatically schedules household tasks based on the extracted key information. Using a scheduling library (e.g., `schedule`), it analyzes the input information and generates a schedule. The input is the extracted information, and the output is a detailed list of planned tasks and their times.

[0677] Step 4:

[0678] The user terminal receives and displays schedule information sent from the server. Here, specific appointments are notified to the user via a dashboard or smart home device. The input is schedule information from the server, and the output is a visual or audio notification to the user.

[0679] Step 5:

[0680] The user reviews the schedule information provided from the terminal and modifies or approves the appointments as needed. The system receives the updated schedule information again based on the user's actions and updates the data. The input is the user's confirmation and modification information, and the output is the updated schedule information.

[0681] 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.

[0682] This invention improves the efficiency of email processing and task management by incorporating an emotion engine that recognizes user emotions into an email management system. The system consists of a server, a user terminal, an emotion engine, and the user. The server is responsible for collecting and analyzing emails, while the emotion engine has the function of estimating the user's emotions from the text within the emails.

[0683] First, the server accesses the user's email account and periodically collects new emails. The collected emails are analyzed using natural language processing techniques to extract important keywords and tasks, while the sentiment engine analyzes the emotions contained in the emails. The sentiment engine sets up multiple emotion categories such as positive, negative, and neutral, and calculates an emotion score based on the content of the emails.

[0684] The server classifies tasks based on the analysis results and sets priorities and urgency levels, but user sentiment information is reflected in the priority setting. For example, if negative sentiment is detected, the priority of related tasks may be set higher. The generated task information and sentiment information are sent to the user's device, which displays them visually on a dashboard. Through this dashboard, the user can easily understand the importance of tasks based on their sentiment.

[0685] As a concrete example, suppose a user receives an email about an important negotiation with a client. If this email contains negative emotions, the server uses an emotion engine to detect the negative emotions and sets a high priority for the "Confirm Negotiation Results" task related to that email. This information is displayed on the terminal, allowing the user to take prompt action and prevent undesirable situations.

[0686] Furthermore, the device adjusts reminder timing based on emotions and task information, providing optimal notifications tailored to the user's emotional state. Additionally, the server automatically generates daily reports, including emotional information, which are distributed to team members, thereby improving team communication and problem-solving capabilities.

[0687] This invention supports efficient and flexible work execution by not only managing emails but also enabling task management that takes into account the user's emotional state.

[0688] The following describes the processing flow.

[0689] Step 1:

[0690] The server accesses the user's email account and automatically collects newly received emails. It performs security authentication and retrieves email data using the IMAP protocol.

[0691] Step 2:

[0692] The server processes the collected emails using a natural language processing engine to extract keywords and context from the text. A specified model is used to identify meaningful information during this process.

[0693] Step 3:

[0694] The server uses an emotion engine to analyze the user's emotions from the text in the email. It calculates an emotion score and categorizes it as positive, negative, or neutral.

[0695] Step 4:

[0696] Based on the analyzed information, the server extracts tasks related to each email and assigns them importance and urgency. This assignment also takes into account the previously obtained sentiment information. For example, if negative sentiment is detected, the related tasks are classified as having a higher priority.

[0697] Step 5:

[0698] The server sends the generated summary, categorized task list, and sentiment information to the user's device.

[0699] Step 6:

[0700] The dashboard visually displays information received by the device. Tasks are organized by priority, and sentiment information is also displayed, allowing users to intuitively grasp the importance of the information.

[0701] Step 7:

[0702] The device sets reminders based on emotional information and task priorities, and notifies the user at the appropriate time.

[0703] Step 8:

[0704] At the end of the day, the server creates a daily report based on all collected emails and task information, and distributes it to team members via email or other messaging tools, including sentiment information.

[0705] This series of processes allows users to efficiently manage emails and perform task management that takes emotional information into account.

[0706] (Example 2)

[0707] 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".

[0708] One challenge in electronic communication is efficiently managing which tasks should be prioritized, while also considering emotional factors. Especially in busy business environments, quickly and accurately processing the diverse information contained in electronic communications and determining its importance is not easy. Furthermore, there is a growing need to flexibly adjust the urgency and priority of tasks based on emotional information.

[0709] 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.

[0710] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for performing calculations based on the extracted information and estimating an emotional score. This enables task management that takes into account the importance and emotional factors of the electronic communications.

[0711] "Electronic communication" is a general term referring to the exchange of information in the form of documents or messages.

[0712] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate language that humans use on a daily basis.

[0713] An "emotion score" is a numerical representation of the type and degree of emotion contained in a text, and it quantitatively expresses the results of emotion analysis.

[0714] Task management is a methodology for efficiently organizing and executing multiple tasks and work by evaluating their priority and urgency, and processing them systematically.

[0715] This invention improves the efficiency of communication processing and task management in an electronic communication management system by incorporating sentiment analysis functionality. The system consists of a server, a user terminal, a sentiment engine, and the user.

[0716] The server is responsible for automatically collecting electronic communications. Specifically, it accesses users' communication accounts using communication protocols such as IMAP and periodically retrieves new messages. This process can be handled using Python's standard libraries.

[0717] The collected communication data is analyzed using natural language processing (NLTK) techniques. The server uses NLTK and spaCy libraries to extract important keywords and tasks from the communication text. Furthermore, a sentiment engine calculates sentiment scores from the extracted text. This uses generative AI models such as BERT, enabling the analysis of the emotional nuances of the text as numerical data.

[0718] Based on the analysis results, the server sets task priorities. Sentiment scores influence priority determination, and tasks with particularly negative emotions are given a higher priority. This priority setting requires software that implements the algorithm, developed in programming languages ​​such as Python.

[0719] The user's device visually displays task and sentiment information sent from the server on a dashboard. At this stage, the device uses a front-end framework such as React or Vue.js. This allows the user to easily see the importance of tasks based on their sentiment and manage them effectively. The device also adjusts reminder timing based on the sentiment score, providing optimal notifications.

[0720] As a concrete example, consider a scenario where a user receives an important negotiation email from a client. The server uses an emotion engine to detect negative emotions from the email and sets a high priority for the "confirm negotiation results" task associated with that email. This information is immediately displayed on the terminal, allowing the user to respond promptly and prevent unexpected situations from occurring.

[0721] An example of a prompt for a generative AI model is: "Based on the following electronic communication text, use the sentiment engine to identify its sentiment category: 'The client's feedback was somewhat harsh...'"

[0722] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0723] Step 1:

[0724] The server accesses the user's communication account via the IMAP protocol and collects new electronic communications. The inputs used are the destination server information and authentication information. The output is unread message data in the inbox, which includes the sender, subject, and body of the email.

[0725] Step 2:

[0726] The server analyzes the collected electronic communication data using natural language processing techniques. Specifically, it uses NLTK and spaCy to analyze and extract words from the input electronic communication data. This process generates important keywords and task candidates as output. At this stage, part-of-speech tagging and semantic analysis are performed on the words.

[0727] Step 3:

[0728] The server uses extracted text data as input and calculates sentiment scores using a generative AI model. This process employs a Transformer-based model (e.g., BERT), and the output includes sentiment categories such as positive, negative, and neutral, along with their respective scores. The model evaluates the nuances of the text and generates numerical sentiment indicators.

[0729] Step 4:

[0730] The server sets task priorities based on the analysis results: keywords and sentiment scores. The inputs are task candidates and sentiment scores. The priority setting algorithm generates a task list and the priority of each task as output. Tasks strongly influenced by negative emotions are assigned a higher priority.

[0731] Step 5:

[0732] The server sends the generated task information to the user's device. The device uses the received task information as input to visually display it on a dashboard using frameworks such as React or Vue.js. As output, the user can view and manage the task list on the screen. The importance of tasks can be intuitively grasped through color coding and icons.

[0733] Step 6:

[0734] The device adjusts reminder timing based on sentiment scores. The task list and its priority are used as input. Reminder settings are configured in conjunction with the calendar API as output. Email and pop-up notifications are provided to the user at appropriate times.

[0735] Step 7:

[0736] The server automatically generates daily reports and provides emotion scores and task information to others in a record format. It uses analysis results as input and generates formatted report data (such as PDF or HTML) as output. This data is then distributed to team members via email or internal communication tools.

[0737] (Application Example 2)

[0738] 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".

[0739] In today's business environment, the increasing influx of information through electronic communications makes it difficult to prioritize important tasks and respond appropriately. Furthermore, there is a growing need to properly evaluate the emotions contained in received communications and recognize them early as business risks or critical issues. This need is particularly urgent for companies that require early warning of security risks such as phishing and malware.

[0740] 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.

[0741] In this invention, the server includes means for automatically collecting electronic communications, means for analyzing the collected electronic communications using natural language processing technology and extracting important information, and means for analyzing the sentiment of the electronic communications and reflecting it in the task priority. This enables the rapid setting of priorities based on the sentiment conveyed by the received communications, allowing for immediate response to important matters and early warning of security risks.

[0742] "Electronic communications" refers to digital data such as emails and messages sent and received via the internet or local networks.

[0743] "Natural language processing technology" refers to all technologies that enable computers to understand and process human language, and includes information extraction and sentiment analysis.

[0744] "Analyzing emotions" means analyzing the linguistic expressions contained in text data to infer the underlying emotions (positive, negative, etc.).

[0745] "Reflecting this in work priorities" means reassessing the importance and urgency of related tasks based on the emotions and importance of the communication, and enabling them to be addressed in the appropriate order.

[0746] A "server" is a computer resource provided on a network for the purpose of collecting and processing data.

[0747] A description of the embodiment for carrying out the invention will be provided.

[0748] This system combines electronic communication management and sentiment analysis to enable efficient task prioritization. The server operates on the network and automatically collects electronic communications such as emails and messages. The server analyzes the collected communications using advanced natural language processing technologies (e.g., spaCy and NLTK) to extract important information and keywords.

[0749] Based on the content of collected electronic communications, sentiment analysis models are used to calculate sentiment scores such as positive, negative, and neutral. Machine learning frameworks such as TensorFlow and PyTorch are used for sentiment analysis. Based on the sentiment scores, importance and urgency are re-evaluated, and tasks are prioritized.

[0750] The user terminal visually displays this prioritized work information, enabling users to respond quickly. Reminders and notification functions are also provided, improving the user's work efficiency.

[0751] For example, if a user receives an email from a business partner with disturbing content, the server can detect the negative sentiment in the email and set related response tasks with high priority. This result is displayed on the terminal, allowing the user to quickly begin taking action.

[0752] As an example of a prompt, inputting instructions such as "Instruct me how to adjust the priority of tasks based on the emotions detected in this email" into the generating AI model will make task prioritization smoother.

[0753] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0754] Step 1:

[0755] The server accesses the user's email account over the network. It receives user authentication information as input and automatically collects new emails at specified time intervals. The output is the collected email data. Since it retrieves information from the mail server using email protocols (such as IMAP or POP3), communication is secure and reliable.

[0756] Step 2:

[0757] The server analyzes the collected email data using natural language processing (NLP) techniques. The input is email text, and the output extracts important keywords and phrases. NLP libraries (such as spaCy and NLTK) are used to analyze the grammatical structure and extract semantically important information. This makes subsequent analysis more effective.

[0758] Step 3:

[0759] The server calculates an emotion score using an emotion analysis model based on the data obtained from NLP processing. The input is the information extracted in step 2, and the output is a score corresponding to an emotion category (positive, negative, neutral, etc.). Emotion analysis models using TensorFlow or PyTorch are utilized here to quantitatively evaluate emotions from the tone and content of emails.

[0760] Step 4:

[0761] The server categorizes and prioritizes relevant tasks based on sentiment scores and other email information. Inputs are sentiment scores and keywords, and output is a prioritized task list. This prioritization allows for tasks that require immediate attention, particularly communications containing negative emotions.

[0762] Step 5:

[0763] The terminal uses prioritized work information received from the server and displays it visually on the user interface. Input is a work list, and output is a user-friendly dashboard. Here, users can make quick and accurate decisions based on the visualized information.

[0764] Step 6:

[0765] The device sets appropriate reminders and notifications for tasks requiring attention based on the displayed information. Input is priority information within the task list, and output is notifications based on time and conditions. This ensures that users can reliably address important tasks without missing any.

[0766] Step 7:

[0767] Users perform tasks and take appropriate actions based on information obtained from their devices. Input is the displayed task information, and output is the specific action to be taken. This streamlines communication and operations within the organization.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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."

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] The following is further disclosed regarding the embodiments described above.

[0790] (Claim 1)

[0791] A means of automatically collecting emails,

[0792] A means of analyzing collected emails using natural language processing technology and extracting important information,

[0793] A means of classifying tasks and setting priorities based on extracted information,

[0794] A means of displaying task information on the user terminal,

[0795] A means of setting reminders based on task information,

[0796] A means of sharing task information externally in the form of a daily report,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, further comprising means for classifying tasks contained in emails based on their urgency.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising means for summarizing information extracted from emails and generating a summary.

[0802] "Example 1"

[0803] (Claim 1)

[0804] A means of automatically accumulating electronic communications,

[0805] A means of analyzing accumulated electronic communications using natural language processing technology and extracting important information,

[0806] A means of classifying and prioritizing tasks based on the extracted items,

[0807] A means of displaying work information on the user's terminal,

[0808] A means of setting up notifications based on work information,

[0809] A method for sending work information to an external party in log format,

[0810] A means for analyzing and classifying information using a generative AI model,

[0811] Means for visualizing based on analysis results,

[0812] A system that includes this.

[0813] (Claim 2)

[0814] The system according to claim 1, further comprising means for classifying tasks included in electronic communications based on their urgency.

[0815] (Claim 3)

[0816] The system according to claim 1, further comprising means for summarizing information extracted from electronic communications and generating an overview.

[0817] "Application Example 1"

[0818] (Claim 1)

[0819] A means of automatically acquiring electronic messages,

[0820] A means of analyzing acquired electronic messages using natural language processing technology and extracting important information,

[0821] A means of classifying tasks and setting priorities based on extracted information,

[0822] Means for displaying business information on a user device,

[0823] A means of setting up a notification function based on business information,

[0824] A means of sharing business information externally in the form of a daily report,

[0825] A means of automatically scheduling and notifying household tasks based on acquired information,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, further comprising means for classifying tasks contained in acquired electronic messages based on their urgency.

[0829] (Claim 3)

[0830] The system according to claim 1, further comprising means for summarizing information extracted from an electronic message and generating a concise display format.

[0831] "Example 2 of combining an emotion engine"

[0832] (Claim 1)

[0833] A means of automatically collecting electronic communications,

[0834] A means of analyzing collected electronic communications using natural language processing technology and extracting important information,

[0835] A means for performing calculations based on extracted information to estimate an emotional score,

[0836] A means of setting task priorities based on sentiment scores,

[0837] A means for displaying task information on the user's device,

[0838] A means of adjusting reminders according to the user's emotional state,

[0839] A means of providing task information to others in a recorded format,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, which sets tasks included in electronic communications based on priority and sentiment scores.

[0843] (Claim 3)

[0844] The system according to claim 1, further comprising means for summarizing information extracted from electronic communications and generating a report.

[0845] "Application example 2 when combining with an emotional engine"

[0846] (Claim 1)

[0847] A means of automatically collecting electronic communications,

[0848] A means of analyzing collected electronic communications using natural language processing technology and extracting important information,

[0849] A means of classifying and prioritizing tasks based on extracted information,

[0850] A means of displaying work information on the user terminal,

[0851] A means of setting up warnings based on work information,

[0852] A means of sharing work information externally in report format,

[0853] A means of analyzing the emotions in electronic communications and reflecting them in work priorities,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, further comprising means for classifying tasks included in electronic communications based on their urgency.

[0857] (Claim 3)

[0858] The system according to claim 1, further comprising means for summarizing information extracted from electronic communications and generating an overview. [Explanation of Symbols]

[0859] 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. A means of automatically acquiring electronic messages, A means of analyzing acquired electronic messages using natural language processing technology and extracting important information, A means of classifying tasks and setting priorities based on extracted information, Means for displaying business information on a user device, A means of setting up a notification function based on business information, A means of sharing business information externally in the form of a daily report, A means of automatically scheduling and notifying household tasks based on acquired information, A system that includes this.

2. The system according to claim 1, further comprising means for classifying tasks contained in acquired electronic messages based on their urgency.

3. The system according to claim 1, further comprising means for summarizing information extracted from an electronic message and generating a concise display format.

Images