system

Abstract

Provide a system. 【Solution means】 Means for collecting data from an information processing device via a communication medium, Means for integrating the data obtained from the information processing device into a central processing unit, Means comprising an artificial intelligence engine for analyzing the data integrated in the central processing unit, Means for determining priorities based on the analysis results and generating a task list, Means for displaying the task list on a user interface, Means for recording the feedback received from the user interface and updating the learning model, Means for analyzing the importance of matters related to e-commerce transactions and generating a reminder, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The amount of information within an enterprise has increased, and it is difficult to manage the information obtained from each information source individually, which may result in overlooking important information and tasks. Also, with conventional methods, it is difficult to efficiently grasp the importance and urgency of information, increasing the burden on users and reducing work efficiency. As a result, information confirmation and task management become inefficient, causing delays and mistakes in business operations.

Means for Solving the Problems

[0005] This invention provides a means for automatically determining the importance and urgency of information by using an artificial intelligence engine that collects data from information processing devices via a communication medium and analyzes the integrated data in a central processing unit. Furthermore, it streamlines task management by generating a list of high-priority tasks based on the analysis results and presenting it to the user through a user interface. It also improves the system's accuracy by collecting user feedback and updating the learning model. In this way, this invention aims to improve operational efficiency by providing centralized information management and efficient task presentation functions.

[0006] "Communication medium" refers to the infrastructure used for sending and receiving data between information processing devices.

[0007] "Information processing device" refers to a hardware or software system used to generate, transmit, receive, or process data.

[0008] "Means for collecting data" refers to methods or mechanisms for obtaining necessary data from information processing equipment.

[0009] A "central processing unit" refers to a core data processing system that integrates collected data and performs analysis.

[0010] "Integrated data" refers to a collection of information gathered from multiple sources and compiled in a unified manner.

[0011] An "artificial intelligence engine" refers to software that uses machine learning and data mining techniques to analyze data, extract meaning from its content, and generate analysis results.

[0012] "Priority" refers to an indicator that shows the degree of importance or urgency of the analyzed information or task.

[0013] A "task list" refers to a list of tasks that need to be performed, generated based on analysis and presented to the user.

[0014] "User interface" refers to the means, such as screens and control panels, that users are provided to interact with and operate a system.

[0015] "Feedback" refers to information, including user operation history and opinions, that users provide to the system and that is used to improve the system's accuracy.

[0016] A "learning model" refers to a mathematical model that uses historical data, including feedback, to improve the analytical capabilities and performance of a system. [Brief explanation of the drawing]

[0017] [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] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] 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.

[0019] First, the language used in the following description will be explained.

[0020] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention relates to a system for efficiently managing the vast amount of information generated within a company and effectively managing user tasks. An embodiment of this system is shown below.

[0039] This system consists of a server, which is an information processing device; terminals used by end users; and users who operate them.

[0040] First, the server collects data from multiple sources, such as email systems, messaging platforms, and calendar systems, via APIs provided by the information processing device. This data includes new emails, messages, and scheduled events. Once the server obtains this data, it converts it into a unified database format and stores it in the database.

[0041] Next, the server analyzes the stored data using an artificial intelligence engine. The AI ​​engine uses machine learning techniques to analyze the data and evaluate the content, origin, recipient, and importance of each piece of data. Text mining techniques are used in this evaluation to extract useful patterns and relationships from the data.

[0042] Based on this analysis, the server determines the priority and generates a task list accordingly. The task list is presented on the user's device through a user interface, allowing the user to quickly see important tasks and information. Reminder notifications are also sent from the device for tasks with approaching deadlines.

[0043] Users can refer to the provided task list, complete tasks, and adjust their priorities individually. This action generates feedback data for the user.

[0044] Ultimately, the server retrains its machine learning model based on the collected feedback data to improve analysis accuracy and utilize this for future task priority determination. In this way, the system of the present invention achieves centralized information management and efficient task management, supporting users in smoothly carrying out their daily tasks.

[0045] As a concrete example, when a user arrives at the office in the morning and logs into their terminal, new emails and meeting schedules are analyzed, and important tasks determined by the server are displayed with priority. This allows users to quickly understand which tasks should be prioritized from the start of their workday.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server establishes API connections with each information processing device based on a pre-configured schedule. The server collects necessary data from sources such as mail servers, communication platforms, and calendar services. It extracts new emails from mail servers, unread messages from messaging services, and new appointments from calendars.

[0049] Step 2:

[0050] The server converts the collected data into a unified format and stores it in a database. This allows data obtained from different sources to be managed centrally. Depending on the type of data, attributes such as sender, recipient, date and time, and content are also stored.

[0051] Step 3:

[0052] The server sends data stored in the database to the artificial intelligence engine. The AI ​​engine analyzes the data using machine learning models and evaluates the relevance, importance, and urgency of the content. It also uses text mining techniques to extract keywords and understand the context.

[0053] Step 4:

[0054] The server generates a task list based on the analysis results of the artificial intelligence engine. Each task is assigned an importance score and listed in order of priority. The task list is stored in a database and prepared to be provided upon user request.

[0055] Step 5:

[0056] The device retrieves the task list from the server when the user logs in and displays it in the user interface. Tasks are sorted according to priority, and high-priority tasks are highlighted with color or icons.

[0057] Step 6:

[0058] Users can view the task list and mark each task as running or completed. They can also manually adjust task priorities and delete unnecessary tasks.

[0059] Step 7:

[0060] The server records user operation history as feedback data. This data is used to retrain machine learning models later, contributing to improved analysis accuracy. Feedback data is accumulated during operation and used periodically to update the models.

[0061] (Example 1)

[0062] 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."

[0063] In today's business environment, a massive amount of information is constantly being generated, and its efficient management is essential. There is a need for a method to effectively integrate and analyze this information and clearly present tasks based on user priorities. However, current systems suffer from the challenge of difficulty in grasping the overall picture due to the dispersed nature of information sources, making it easy to overlook important information. Furthermore, there is a need for systems to continuously learn from user feedback and perform more advanced analysis.

[0064] 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.

[0065] In this invention, the server includes means for collecting electronic information from multiple information sources via a communication medium, means for converting the electronic information into a unified format and storing it on a recording medium, and means for analyzing the electronic information stored on the recording medium using machine learning technology. This makes it possible to effectively integrate and analyze a large amount of distributed information and present necessary tasks based on priority. Furthermore, by reconstructing the machine learning model based on the user's operation results, the system can continuously learn and improve the accuracy of the analysis.

[0066] A "communication medium" is a means of providing a physical or wireless path for sending and receiving data.

[0067] "Electronic information" refers to data that is stored or transmitted in digital format, including documents, messages, and schedule information.

[0068] A "recording medium" is a physical or magnetic means for storing data, and includes databases and storage devices.

[0069] "Machine learning techniques" refer to algorithms and methods that enable computers to learn patterns from data and perform predictions and classifications.

[0070] A "user interaction screen" is a visual interface that allows users to view information and perform actions.

[0071] "Operation results" refer to feedback data obtained based on the actions taken by the user on the dialogue screen.

[0072] "Rebuilding a machine learning model" is the process of updating the algorithm using feedback data to achieve higher analytical accuracy.

[0073] The embodiment of this invention is based on the construction of a system for aggregating and analyzing information. Its configuration and operation are described in detail below.

[0074] The server collects electronic information from multiple sources via communication media. This involves using existing APIs to retrieve data from, for example, email systems, messaging platforms, and scheduling management systems. Specifically, it can utilize APIs within email systems and messaging platforms. The acquired electronic information is then converted into a unified format and stored in a database, which serves as the storage medium. SQL databases are used for this conversion and storage.

[0075] The server analyzes this stored electronic information using machine learning techniques. The algorithms used include various technologies such as natural language processing and text mining, which extract patterns and relationships from the electronic information. Based on this analysis, the priority of the information is evaluated, and a work instruction sheet is created.

[0076] The generated work order sheet is displayed through a user interaction screen on the terminal. Through this screen, the user can check the progress of tasks, set priorities, and perform actions such as reporting completion. The results of these actions are sent to the server as feedback and recorded.

[0077] Finally, the server uses the acquired feedback data to reconstruct the machine learning model. This reconstruction improves the accuracy of the analysis, which is then used to create future work instruction sheets.

[0078] As a concrete example, a user can request the system to update their work order sheet by entering a prompt such as, "Tell me today's important tasks based on my latest emails and meetings." This prompt allows users to quickly grasp their daily priority tasks.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects electronic information from multiple sources via communication media. Inputs include new data from email systems, messaging platforms, and calendar systems. This data is retrieved using APIs. The output is raw electronic data. Specifically, the server sends requests to the APIs at scheduled time intervals and stores the received data in temporary storage.

[0082] Step 2:

[0083] The server converts the collected electronic information into a unified format and stores it on a recording medium. The input is the raw data collected in step 1. This data is converted from JSON or XML format to a table format in an SQL database. The converted data is stored in the database. Specifically, the server uses a data formatting library to check the integrity of the data and remove unnecessary information.

[0084] Step 3:

[0085] The server analyzes electronic information stored on a recording medium using machine learning techniques. The input is data in a unified format held in a database. Here, natural language processing techniques are used to extract important keywords from the text and categorize the data. As a result of the analysis, a prioritized dataset is output. Specifically, the server starts an NLP engine and performs text mining.

[0086] Step 4:

[0087] The server determines priority based on the analysis results and creates a work instruction sheet. The input is the analysis results from step 3. The server scores the priority of each data item and generates a work instruction sheet sorted by priority based on the results. The output is a work instruction sheet that can be presented to the user. Specifically, it uses a scoring algorithm to evaluate importance and organize the list.

[0088] Step 5:

[0089] The terminal displays the work order sheet received from the server on a user interaction screen. The input is the work order sheet generated in step 4. A UI framework is used to render the list displayed on the interaction screen in a user-friendly format. The output is a task list that the user can visually understand. Specifically, the terminal calls a GUI library to format and display the list.

[0090] Step 6:

[0091] Users view tasks through the terminal's interactive screen and adjust priorities or complete tasks as needed. Input consists of the displayed work instruction sheet and user instructions. The results of the operations are recorded as logs and sent to the server as feedback. Specifically, users perform actions such as clicking and dragging and dropping, and these changes are saved immediately.

[0092] Step 7:

[0093] The server uses the collected feedback data to reconstruct the machine learning model. The input is the results of the user's actions obtained in step 6. By analyzing this and updating the model's parameters, the accuracy of subsequent analyses is improved. The output is the updated machine learning model. Specifically, the server adds the feedback to the training data and retrains the model.

[0094] (Application Example 1)

[0095] 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."

[0096] In today's information processing environment, managing vast amounts of data in e-commerce and within companies is extremely important. However, traditional systems have struggled to efficiently integrate and analyze information from multiple sources, preventing users from immediately identifying priority tasks and important matters, leading to delays in operational efficiency. Furthermore, these systems lacked reminder functions based on the priority and importance of these tasks, potentially causing users to overlook urgent matters, especially those with approaching deadlines such as payments.

[0097] 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.

[0098] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data acquired from the information processing device into a central processing device, and means for providing an artificial intelligence engine for analyzing the integrated data in the central processing device. This makes it possible to efficiently analyze data collected from multiple information sources and provide the user with a task list and reminders based on priority and importance.

[0099] A "communication medium" is a means used to send and receive data between information processing devices.

[0100] An "information processing device" is an electronic device that has the function of manipulating, calculating, and analyzing data.

[0101] A "central processing unit" is a central computer system used to integrate and analyze collected data.

[0102] An "artificial intelligence engine" is software equipped with machine learning algorithms that automatically analyze data and support decision-making.

[0103] A "task list" is a list that organizes and displays tasks and errands that a user needs to complete, based on their priority.

[0104] A "user interface" is a means of providing users with screens and operating methods to interact with a digital system.

[0105] "Feedback" refers to information about user actions and reactions, which is used as data for system improvement and learning.

[0106] A "reminder" is a feature that notifies users of tasks with approaching deadlines or important matters.

[0107] This invention is a system for efficiently managing information and prioritizing the processing of important tasks in corporate and e-commerce environments. In one embodiment, a server and a user terminal work together to collect, analyze, and notify data.

[0108] The server receives data from multiple sources via a communication medium. The hardware used is primarily information processing equipment. The received data is integrated into a central processing unit and then analyzed by an artificial intelligence engine. This AI engine uses text mining techniques to evaluate the data and determine its priority. In this analysis process, machine learning algorithms are utilized to extract patterns and relationships from the data.

[0109] The task list generated from the integrated data is displayed through a user interface on the user's device. Here, users can instantly check important tasks and deadlines. User feedback is also sent to the server through the user interface, and the learning model is updated based on this feedback. This improves the accuracy of subsequent analyses and refines task prioritization.

[0110] As a concrete example, in a company operating an e-commerce platform, when a user logs in, an artificial intelligence engine analyzes customer inquiries and payment-related requests, prioritizing and displaying the most important ones. This allows operators to proceed with their work without missing items that require prompt attention. In addition, a reminder function automatically notifies users of unprocessed tasks that are nearing their deadlines.

[0111] One example of how a generative AI model can be used is by inputting a prompt such as, "You are an e-commerce support representative. Please propose a strategy for efficiently handling customer inquiries and outstanding payments." The model will then suggest an appropriate task handling plan.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The server collects data from multiple sources via communication media. In this collection process, an information processing device connects to each source to retrieve emails, messages, and calendar information. The input consists of data from each source, and the output is a collection of integrated raw data.

[0115] Step 2:

[0116] The server integrates the collected raw data into a central processing unit and stores it in a database. The input is a collection of raw data, and the output is a database in a unified format. Specifically, it standardizes data in different formats and aggregates it into a single database.

[0117] Step 3:

[0118] The server analyzes the integrated data using an artificial intelligence engine. This analysis utilizes machine learning algorithms to assess data importance and extract relevances. The input is the integrated data from the database, and the output is a prioritized dataset.

[0119] Step 4:

[0120] The server generates a task list based on prioritized data and sends it to the user terminal. The input is a prioritized dataset, and the output is a task list for the user terminal. Specifically, it creates a list that considers the importance of each task to the user.

[0121] Step 5:

[0122] The terminal displays the task list received from the server on the user interface. The input is task list data from the server, and the output is a visualized list display. This allows the user to immediately identify tasks that require attention.

[0123] Step 6:

[0124] The user refers to the displayed task list and provides feedback as needed. Specific actions include updating task completion status and adjusting individual priorities. The input is the user's actions, and the output is feedback data.

[0125] Step 7:

[0126] The server receives feedback data from the user's terminal and retrains the generated AI model. The input is the feedback data, and the output is the updated machine learning model. This improves the accuracy of data analysis in subsequent attempts.

[0127] Step 8:

[0128] The terminal uses a reminder function to notify users of unprocessed tasks that are nearing their due date. Input is a task list and due date information from the server, and output is a notification message to the user. Its specific function is to provide users with timely schedule-related alerts.

[0129] 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.

[0130] This invention provides a system that centrally manages information and enables task management that takes into account the user's emotional state. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects the two.

[0131] First, the server collects data from multiple sources, including email, messaging platforms, and calendar services. During this process, the server retrieves information via APIs and integrates it into a unified database. The data includes basic information such as subject, sender, recipient, and date / time.

[0132] The collected data is passed to an artificial intelligence engine on the server. This engine analyzes the data using text mining techniques to determine the importance and urgency of each piece of information. Furthermore, this invention also includes an emotion engine that recognizes the user's emotional state. The emotion engine detects emotions from the data and operation logs entered by the user and understands the current emotional state.

[0133] Next, the server adjusts the analysis results and generates a prioritized task list based on the emotional state recognized by the emotion engine. If the user is experiencing stress, the task priorities and presentation methods may be changed.

[0134] The generated task list is displayed in the user interface via the device. Users can use this list to efficiently manage their tasks. The interface highlights urgent tasks and presents information in a way that is sensitive to the user's emotions.

[0135] Users can manage tasks while referring to a task list. Furthermore, feedback from the user upon task completion is recorded by the emotion engine, and the server uses this feedback to update its learning model. Through this iterative process, the system flexibly responds to changes in the user's emotions, supporting more appropriate task management.

[0136] For example, when a user decides they want to reduce their workload, the server rearranges the task list to minimize stress, prioritizing tasks that have lowered priority or can be temporarily avoided. In this way, the system of the present invention helps users smoothly perform their daily tasks while also considering the emotional aspects.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server connects to the mail server, messaging service, and calendar API according to a predetermined schedule to retrieve the necessary data. This data includes email subject and content, sender information, message history, and event information registered in the calendar.

[0140] Step 2:

[0141] The server converts the collected data into a unified format and stores it in a database. During storage, each piece of data is stored along with its attribute information (e.g., reception date and time, and related project), and is centrally managed.

[0142] Step 3:

[0143] The server's artificial intelligence engine analyzes stored data and uses text mining techniques to evaluate the content of the information. For example, it can determine project progress and important tasks from email content and quantify the importance and urgency of each piece of information.

[0144] Step 4:

[0145] The server also analyzes user interaction data sent from the terminal using an emotion engine. It estimates the user's emotional state (e.g., stress or fatigue) from things like the rhythm of keystrokes, mouse movements, and entered text.

[0146] Step 5:

[0147] The server integrates the analysis results from the artificial intelligence engine and the judgments of the emotion engine to generate a prioritized task list. If the server determines that the user is in a high-stress state, it adjusts the priority of some tasks and rearranges them in the optimal order to reduce the user's burden.

[0148] Step 6:

[0149] The terminal displays the task list received from the server on the user interface. Tasks are color-coded according to their importance and urgency, and presented in a way that is easy for the user to work on.

[0150] Step 7:

[0151] The user refers to the presented task list and marks each task as performed or completed. Feedback information is sent from the device to the server, enabling task management that also takes into account the user's changing emotional state.

[0152] Step 8:

[0153] The server uses user feedback data to update the learning models of its emotion engine and artificial intelligence engine. This leads to further improvements in the accuracy of task suggestions and emotion estimation in subsequent tasks.

[0154] (Example 2)

[0155] 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".

[0156] Traditional task management systems display tasks uniformly without considering the user's emotional state, leading to user stress and making efficient task management difficult. Furthermore, they fail to fully utilize user feedback, limiting the system's adaptability. Therefore, there is a need for task presentation based on the user's emotional state and a system that can adapt flexibly.

[0157] 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.

[0158] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data into a central processing device, and means for an artificial intelligence engine that analyzes the data using text mining technology. This makes it possible to consider the emotional state of the user and improve the system based on the presentation of prioritized tasks and feedback.

[0159] A "communication medium" is a means of connecting an information processing device and a central processing device to transfer data.

[0160] An "information processing device" is an electronic device used to generate, input, and manipulate data.

[0161] "Data" refers to a series of numbers, strings of characters, or signals that can be recorded and processed.

[0162] A "central processing unit" is a central computer device used to integrate and analyze collected data.

[0163] "Text mining technology" is a technique that uses natural language processing to analyze data and extract important information.

[0164] An "artificial intelligence engine" is software or a program that assists in data analysis and decision-making.

[0165] "Emotional state" refers to the user's psychological state, including emotions such as stress and relief.

[0166] A "task list" is a list that outlines the tasks and appointments that a user needs to work on.

[0167] A "user interface" refers to the display screen and input methods that allow a user to operate a system and receive information.

[0168] "Feedback" refers to information recorded from users' opinions and reactions, used for evaluation or system improvement.

[0169] A "learning model" is an algorithm or program that adapts and evolves based on feedback.

[0170] This invention is a system that collects information and performs task management that takes into account the emotional state of the user. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects them.

[0171] The server collects data from multiple sources, such as email services, messaging platforms, and calendar services, via communication media. Data collection involves obtaining information in real time using APIs and storing it in an integrated database. Specifically, the software uses email APIs and the natural language processing library NLTK to analyze the data and determine task priorities.

[0172] The server's artificial intelligence engine uses text mining technology to analyze data from an integrated database and evaluate the importance and urgency of each task. Furthermore, the server uses an emotion engine to determine the user's emotional state. The emotion engine detects emotions from the user's operation logs and input data, recognizing their mental state, including the presence or absence of stress.

[0173] The generated task list is displayed in the user interface on the device. This interface adjusts how tasks are displayed according to their urgency and emotional state, visually highlighting important tasks. Users can refer to this task list and prioritize tasks accordingly.

[0174] When a user completes a task, feedback is sent from the device to the server. Based on this feedback, the server updates its learning model, allowing it to better adapt to the user's emotions when presenting tasks in the future.

[0175] For example, if the server determines that a user is overwhelmed with work and experiencing stress, it will change the priority of the task list, displaying less urgent tasks first. In this way, users can manage their tasks in a way that is sensitive to their emotions.

[0176] Examples of prompts include, "Show an example of presenting a task when the user is not feeling stressed," and "If the emotion engine detects user anxiety, how will you change the task's priority?"

[0177] This system supports effective task management tailored to the user's emotional state, thereby facilitating the smooth execution of daily tasks.

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The server collects data from various sources via communication media. Specifically, it uses email APIs and messaging APIs to retrieve user email and message information. This input data includes information such as subject, sender, recipient, and date and time. This generates an integrated dataset from diverse sources.

[0181] Step 2:

[0182] The server stores the collected data in an integrated database. The database structure facilitates centralized management of data from different sources. At this stage, newly acquired data is added to the database and integrated while maintaining consistency with existing data. The output includes a unified database.

[0183] Step 3:

[0184] The server's artificial intelligence engine analyzes the collected data. This analysis utilizes text mining techniques to detect particularly important keywords and determine urgency based on context. The input for the analysis is information from an integrated database, and the output provides the importance and classification results of each piece of information.

[0185] Step 4:

[0186] The server's emotion engine determines emotions based on user activity logs and input data. Specifically, it analyzes keyboard speed, mouse movements, and the frequency of inputting specific phrases. Based on this input data, it performs analysis and outputs the user's emotional state.

[0187] Step 5:

[0188] The server integrates results from text mining and a sentiment engine to generate a prioritized task list. The generation process processes the analysis data and prioritizes tasks based on urgency and psychological state. The output is an optimally structured task list.

[0189] Step 6:

[0190] The device displays the generated task list in the user interface. In operation, tasks are listed on the screen and color-coded or highlighted according to their urgency and importance. Users can use this task list to efficiently manage their work.

[0191] Step 7:

[0192] Users provide feedback upon completing a task. The device receives this feedback and sends it to the server. The feedback includes details such as task completion status, time taken, and psychological impressions. Based on this information, the server's learning model is updated as new input. The output is data that is reflected in improvements for the next task list generation.

[0193] (Application Example 2)

[0194] 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 device 14 will be referred to as the "terminal."

[0195] Modern households require flexible task management that accommodates busy daily lives and individual emotional states. However, current task management systems lack the functionality to prioritize and present tasks while taking into account the user's emotional state and stress levels, which can result in unnecessary stress for the user. In light of this situation, the present invention aims to provide a system that recognizes the user's emotional state and performs appropriate task management based on that state.

[0196] 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.

[0197] In this invention, the server includes means for acquiring information from a data collection device via communication means, means for collecting the information obtained from the data collection device in a central processing device, means for providing an intelligent engine for analyzing the information collected in the central processing device, means for incorporating an emotion engine for recognizing emotional states and configuring a list of tasks according to the emotional state of the resident, and means for adjusting the priority of presenting the list of tasks according to the resident's environment and reducing stress. This enables flexible task management that responds to the user's emotional state.

[0198] "Communication means" refers to the intermediary used to obtain information from data collection devices, and plays a role in collecting information through a network.

[0199] A "data aggregation device" is a device that collects and stores information, and provides that information to a server via communication means.

[0200] "Means of acquiring information" refers to devices that have the function of extracting necessary information from data collection equipment and play the first step in information gathering.

[0201] A "central processing unit" is a central device that efficiently processes and analyzes collected information and generates it in a state that can be used by other devices and engines.

[0202] An "intelligent engine" refers to an artificial computing system that analyzes collected information and makes decisions based on the results, particularly influencing the determination of priorities.

[0203] The "emotional engine" is an analytical system that has the function of identifying and sensing changes in the emotional state of residents, and measuring the emotional state of each individual.

[0204] The "task list" is a list of tasks whose priority has been determined based on the results of analysis by an intelligent engine, and it is a means for users to efficiently manage their daily work by referring to it.

[0205] "Means for adjusting the priority of presenting the list of tasks according to the resident's environment" refers to a function that takes into consideration the user's emotional state and environmental circumstances, by changing the order in which the list of tasks is presented, thereby preventing excessive burden on the user.

[0206] The system of this invention is designed to streamline the busy daily lives of users and includes communication means, data collection devices, a central processing unit, an intelligent engine, and an emotion engine.

[0207] The server collects data from various sources using communication methods. This information is gathered at a central processing unit via data aggregation devices, where an intelligent engine analyzes it. This analysis generates a list of tasks that take priority into account. In this process, the intelligent engine uses text mining techniques to analyze the information and determine the optimal order of tasks.

[0208] Furthermore, the server uses an emotion engine to evaluate the user's emotional state in real time and adjust the list of tasks accordingly. This process is designed to minimize the mental burden on the user when performing each task. Software such as TENSORFLOW® and Google® Cloud Natural Language API are used for data analysis and adjustment performed by the intelligent engine and emotion engine.

[0209] As a concrete example, if it's the time of day when the user is relaxing, such as after dinner, the system can re-evaluate task priorities and, if necessary, prioritize suggesting entertainment or relaxation-related activities. In this case, the system would input a prompt message like the following into the AI ​​model to suggest a course of action: "Based on User A's current emotional state, postpone low-priority tasks and prioritize relaxation tasks (e.g., playing music)."

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The server collects information from data aggregation devices via communication methods. Specifically, it retrieves data from mail servers, messaging platforms, calendar services, etc., via APIs. In this process, the input is data from these information sources, and the output is an integrated database-formatted dataset.

[0213] Step 2:

[0214] The server sends the integrated data to a central processing unit for analysis by an intelligent engine. Here, text mining techniques are used to analyze the data and determine the importance and urgency of the tasks. The input is the dataset from the previous step. The output is the priority of each task obtained through the analysis.

[0215] Step 3:

[0216] The server operates an emotion engine to recognize the user's emotional state. Specifically, it inputs and analyzes operation logs and subjective user data to quantify the user's emotions. The input in this step is an emotion index obtained from the user interface, and the output is the user's current emotional state.

[0217] Step 4:

[0218] The server integrates the analysis results from the intelligent engine and the recognition results from the emotion engine to generate a task list. This task list is a task list with adjusted priorities and is organized in a user-friendly format. The output is the adjusted task list.

[0219] Step 5:

[0220] The terminal displays the generated list of tasks on the user's display device. Users can view this list in real time, managing their daily tasks while understanding task priorities and schedules. The output here is a task list presented visually to the user.

[0221] Step 6:

[0222] The user performs tasks based on the displayed list of tasks and provides feedback to the server through the interface. The input is the user's actions and feedback, and this information is used to further improve the learning structure. The output is the updated learning model.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] [Second Embodiment]

[0227] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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".

[0239] This invention relates to a system for efficiently managing the vast amount of information generated within a company and effectively managing user tasks. An embodiment of this system is shown below.

[0240] This system consists of a server, which is an information processing device; terminals used by end users; and users who operate them.

[0241] First, the server collects data from multiple sources, such as email systems, messaging platforms, and calendar systems, via APIs provided by the information processing device. This data includes new emails, messages, and scheduled events. Once the server obtains this data, it converts it into a unified database format and stores it in the database.

[0242] Next, the server analyzes the stored data using an artificial intelligence engine. The AI ​​engine uses machine learning techniques to analyze the data and evaluate the content, origin, recipient, and importance of each piece of data. Text mining techniques are used in this evaluation to extract useful patterns and relationships from the data.

[0243] Based on this analysis, the server determines the priority and generates a task list accordingly. The task list is presented on the user's device through a user interface, allowing the user to quickly see important tasks and information. Reminder notifications are also sent from the device for tasks with approaching deadlines.

[0244] Users can refer to the provided task list, complete tasks, and adjust their priorities individually. This action generates feedback data for the user.

[0245] Ultimately, the server retrains its machine learning model based on the collected feedback data to improve analysis accuracy and utilize this for future task priority determination. In this way, the system of the present invention achieves centralized information management and efficient task management, supporting users in smoothly carrying out their daily tasks.

[0246] As a concrete example, when a user arrives at the office in the morning and logs into their terminal, new emails and meeting schedules are analyzed, and important tasks determined by the server are displayed with priority. This allows users to quickly understand which tasks should be prioritized from the start of their workday.

[0247] The following describes the processing flow.

[0248] Step 1:

[0249] The server establishes API connections with each information processing device based on a pre-configured schedule. The server collects necessary data from sources such as mail servers, communication platforms, and calendar services. It extracts new emails from mail servers, unread messages from messaging services, and new appointments from calendars.

[0250] Step 2:

[0251] The server converts the collected data into a unified format and stores it in a database. This allows data obtained from different sources to be managed centrally. Depending on the type of data, attributes such as sender, recipient, date and time, and content are also stored.

[0252] Step 3:

[0253] The server sends data stored in the database to the artificial intelligence engine. The AI ​​engine analyzes the data using machine learning models and evaluates the relevance, importance, and urgency of the content. It also uses text mining techniques to extract keywords and understand the context.

[0254] Step 4:

[0255] The server generates a task list based on the analysis results of the artificial intelligence engine. Each task is assigned an importance score and listed in order of priority. The task list is stored in a database and prepared to be provided upon user request.

[0256] Step 5:

[0257] The device retrieves the task list from the server when the user logs in and displays it in the user interface. Tasks are sorted according to priority, and high-priority tasks are highlighted with color or icons.

[0258] Step 6:

[0259] Users can view the task list and mark each task as running or completed. They can also manually adjust task priorities and delete unnecessary tasks.

[0260] Step 7:

[0261] The server records user operation history as feedback data. This data is used to retrain machine learning models later, contributing to improved analysis accuracy. Feedback data is accumulated during operation and used periodically to update the models.

[0262] (Example 1)

[0263] 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".

[0264] In today's business environment, a massive amount of information is constantly being generated, and its efficient management is essential. There is a need for a method to effectively integrate and analyze this information and clearly present tasks based on user priorities. However, current systems suffer from the challenge of difficulty in grasping the overall picture due to the dispersed nature of information sources, making it easy to overlook important information. Furthermore, there is a need for systems to continuously learn from user feedback and perform more advanced analysis.

[0265] 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.

[0266] In this invention, the server includes means for collecting electronic information from multiple information sources via a communication medium, means for converting the electronic information into a unified format and storing it on a recording medium, and means for analyzing the electronic information stored on the recording medium using machine learning technology. This makes it possible to effectively integrate and analyze a large amount of distributed information and present necessary tasks based on priority. Furthermore, by reconstructing the machine learning model based on the user's operation results, the system can continuously learn and improve the accuracy of the analysis.

[0267] A "communication medium" is a means of providing a physical or wireless path for sending and receiving data.

[0268] "Electronic information" refers to data that is stored or transmitted in digital format, including documents, messages, and schedule information.

[0269] A "recording medium" is a physical or magnetic means for storing data, and includes databases and storage devices.

[0270] "Machine learning techniques" refer to algorithms and methods that enable computers to learn patterns from data and perform predictions and classifications.

[0271] A "user interaction screen" is a visual interface that allows users to view information and perform actions.

[0272] "Operation results" refer to feedback data obtained based on the actions taken by the user on the dialogue screen.

[0273] "Rebuilding a machine learning model" is the process of updating the algorithm using feedback data to achieve higher analytical accuracy.

[0274] The embodiment of this invention is based on the construction of a system for aggregating and analyzing information. Its configuration and operation are described in detail below.

[0275] The server collects electronic information from multiple sources via communication media. This involves using existing APIs to retrieve data from, for example, email systems, messaging platforms, and scheduling management systems. Specifically, it can utilize APIs within email systems and messaging platforms. The acquired electronic information is then converted into a unified format and stored in a database, which serves as the storage medium. SQL databases are used for this conversion and storage.

[0276] The server analyzes this stored electronic information using machine learning techniques. The algorithms used include various technologies such as natural language processing and text mining, which extract patterns and relationships from the electronic information. Based on this analysis, the priority of the information is evaluated, and a work instruction sheet is created.

[0277] The generated work order sheet is displayed through a user interaction screen on the terminal. Through this screen, the user can check the progress of tasks, set priorities, and perform actions such as reporting completion. The results of these actions are sent to the server as feedback and recorded.

[0278] Finally, the server uses the acquired feedback data to reconstruct the machine learning model. This reconstruction improves the accuracy of the analysis, which is then used to create future work instruction sheets.

[0279] As a concrete example, a user can request the system to update their work order sheet by entering a prompt such as, "Tell me today's important tasks based on my latest emails and meetings." This prompt allows users to quickly grasp their daily priority tasks.

[0280] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0281] Step 1:

[0282] The server collects electronic information from multiple information sources via a communication medium. The inputs are new data from a mail system, a messaging platform, and a calendar system. These data are obtained using an API. As output, electronic information data in raw format is obtained. As a specific operation, the server sends requests to the API at scheduled time intervals and stores the received data in temporary storage.

[0283] Step 2:

[0284] The server converts the collected electronic information into a unified format and stores it in a recording medium. The input is the raw data collected in Step 1. These data are converted from JSON or XML formats into the table format of a SQL database. The converted data is stored in the database. As a specific operation, the server uses a data shaping library to check the data integrity and delete unnecessary information.

[0285] Step 3:

[0286] The server analyzes the electronic information stored in the recording medium using machine learning techniques. The input is the data in unified format stored in the database. Here, natural language processing techniques are used to extract important keywords from the text and categorize the data. As the analysis result, a prioritized dataset is output. Specifically, the server starts an NLP engine and performs text mining.

[0287] Step 4:

[0288] The server determines priorities based on the analysis result and creates a business instruction list. The input is the analysis result of Step 3. The server scores the priority of each data and generates a business instruction list sorted in order of priority based on the result. The output is a business instruction list that can be presented to the user. As a specific operation, a scoring algorithm is used to evaluate the importance and organize the list.

[0289] Step 5:

[0290] The terminal displays the work order sheet received from the server on a user interaction screen. The input is the work order sheet generated in step 4. A UI framework is used to render the list displayed on the interaction screen in a user-friendly format. The output is a task list that the user can visually understand. Specifically, the terminal calls a GUI library to format and display the list.

[0291] Step 6:

[0292] Users view tasks through the terminal's interactive screen and adjust priorities or complete tasks as needed. Input consists of the displayed work instruction sheet and user instructions. The results of the operations are recorded as logs and sent to the server as feedback. Specifically, users perform actions such as clicking and dragging and dropping, and these changes are saved immediately.

[0293] Step 7:

[0294] The server uses the collected feedback data to reconstruct the machine learning model. The input is the results of the user's actions obtained in step 6. By analyzing this and updating the model's parameters, the accuracy of subsequent analyses is improved. The output is the updated machine learning model. Specifically, the server adds the feedback to the training data and retrains the model.

[0295] (Application Example 1)

[0296] 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."

[0297] In today's information processing environment, managing vast amounts of data in e-commerce and within companies is extremely important. However, traditional systems have struggled to efficiently integrate and analyze information from multiple sources, preventing users from immediately identifying priority tasks and important matters, leading to delays in operational efficiency. Furthermore, these systems lacked reminder functions based on the priority and importance of these tasks, potentially causing users to overlook urgent matters, especially those with approaching deadlines such as payments.

[0298] 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.

[0299] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data acquired from the information processing device into a central processing device, and means for providing an artificial intelligence engine for analyzing the integrated data in the central processing device. This makes it possible to efficiently analyze data collected from multiple information sources and provide the user with a task list and reminders based on priority and importance.

[0300] A "communication medium" is a means used to send and receive data between information processing devices.

[0301] An "information processing device" is an electronic device that has the function of manipulating, calculating, and analyzing data.

[0302] A "central processing unit" is a central computer system used to integrate and analyze collected data.

[0303] An "artificial intelligence engine" is software equipped with machine learning algorithms that automatically analyze data and support decision-making.

[0304] A "task list" is a list that organizes and displays tasks and errands that a user needs to complete, based on their priority.

[0305] The "user interface" is a means of providing a screen and operation methods for users to interact with digital systems.

[0306] "Feedback" is information on operation results and reactions obtained from users, and is data used for system improvement and learning.

[0307] A "reminder" is a function for notifying users of tasks and important matters with approaching deadlines.

[0308] This invention is a system for efficiently managing information and preferentially processing important tasks in the environment of enterprises and e-commerce. As an embodiment, a server and user terminals cooperate to collect, analyze, and notify data.

[0309] The server receives data from multiple information sources via a communication medium. The hardware used is mainly an information processing device. The received data is integrated by a central processing unit and then analyzed by an artificial intelligence engine. This artificial intelligence engine evaluates the data using text mining technology and determines priorities. In this analysis process, machine learning algorithms are utilized to extract patterns and correlations from the data.

[0310] The task list generated from the integrated data is displayed through the user interface on the user's terminal. Here, users can immediately check important tasks and upcoming matters. Also, the user's feedback is sent to the server through the user interface, and based on this, the learning model is updated. Thereby, the analysis accuracy for subsequent times is improved, and the determination of task priorities becomes more sophisticated.

[0311] As a concrete example, in a company operating an e-commerce platform, when a user logs in, an artificial intelligence engine analyzes customer inquiries and payment-related requests, prioritizing and displaying the most important ones. This allows operators to proceed with their work without missing items that require prompt attention. In addition, a reminder function automatically notifies users of unprocessed tasks that are nearing their deadlines.

[0312] One example of how a generative AI model can be used is by inputting a prompt such as, "You are an e-commerce support representative. Please propose a strategy for efficiently handling customer inquiries and outstanding payments." The model will then suggest an appropriate task handling plan.

[0313] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0314] Step 1:

[0315] The server collects data from multiple sources via communication media. In this collection process, an information processing device connects to each source to retrieve emails, messages, and calendar information. The input consists of data from each source, and the output is a collection of integrated raw data.

[0316] Step 2:

[0317] The server integrates the collected raw data into a central processing unit and stores it in a database. The input is a collection of raw data, and the output is a database in a unified format. Specifically, it standardizes data in different formats and aggregates it into a single database.

[0318] Step 3:

[0319] The server analyzes the integrated data using an artificial intelligence engine. This analysis utilizes machine learning algorithms to assess data importance and extract relevances. The input is the integrated data from the database, and the output is a prioritized dataset.

[0320] Step 4:

[0321] The server generates a task list based on prioritized data and sends it to the user terminal. The input is a prioritized dataset, and the output is a task list for the user terminal. Specifically, it creates a list that considers the importance of each task to the user.

[0322] Step 5:

[0323] The terminal displays the task list received from the server on the user interface. The input is task list data from the server, and the output is a visualized list display. This allows the user to immediately identify tasks that require attention.

[0324] Step 6:

[0325] The user refers to the displayed task list and provides feedback as needed. Specific actions include updating task completion status and adjusting individual priorities. The input is the user's actions, and the output is feedback data.

[0326] Step 7:

[0327] The server receives feedback data from the user's terminal and retrains the generated AI model. The input is the feedback data, and the output is the updated machine learning model. This improves the accuracy of data analysis in subsequent attempts.

[0328] Step 8:

[0329] The terminal uses a reminder function to notify users of unprocessed tasks that are nearing their due date. Input is a task list and due date information from the server, and output is a notification message to the user. Its specific function is to provide users with timely schedule-related alerts.

[0330] 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.

[0331] This invention provides a system that centrally manages information and enables task management that takes into account the user's emotional state. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects the two.

[0332] First, the server collects data from multiple sources, including email, messaging platforms, and calendar services. During this process, the server retrieves information via APIs and integrates it into a unified database. The data includes basic information such as subject, sender, recipient, and date / time.

[0333] The collected data is passed to an artificial intelligence engine on the server. This engine analyzes the data using text mining techniques to determine the importance and urgency of each piece of information. Furthermore, this invention also includes an emotion engine that recognizes the user's emotional state. The emotion engine detects emotions from the data and operation logs entered by the user and understands the current emotional state.

[0334] Next, the server adjusts the analysis results and generates a prioritized task list based on the emotional state recognized by the emotion engine. If the user is experiencing stress, the task priorities and presentation methods may be changed.

[0335] The generated task list is displayed in the user interface via the device. Users can use this list to efficiently manage their tasks. The interface highlights urgent tasks and presents information in a way that is sensitive to the user's emotions.

[0336] Users can manage tasks while referring to a task list. Furthermore, feedback from the user upon task completion is recorded by the emotion engine, and the server uses this feedback to update its learning model. Through this iterative process, the system flexibly responds to changes in the user's emotions, supporting more appropriate task management.

[0337] For example, when a user decides they want to reduce their workload, the server rearranges the task list to minimize stress, prioritizing tasks that have lowered priority or can be temporarily avoided. In this way, the system of the present invention helps users smoothly perform their daily tasks while also considering the emotional aspects.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The server connects to the mail server, messaging service, and calendar API according to a predetermined schedule to retrieve the necessary data. This data includes email subject and content, sender information, message history, and event information registered in the calendar.

[0341] Step 2:

[0342] The server converts the collected data into a unified format and stores it in a database. During storage, each piece of data is stored along with its attribute information (e.g., reception date and time, and related project), and is centrally managed.

[0343] Step 3:

[0344] The server's artificial intelligence engine analyzes stored data and uses text mining techniques to evaluate the content of the information. For example, it can determine project progress and important tasks from email content and quantify the importance and urgency of each piece of information.

[0345] Step 4:

[0346] The server also analyzes user interaction data sent from the terminal using an emotion engine. It estimates the user's emotional state (e.g., stress or fatigue) from things like the rhythm of keystrokes, mouse movements, and entered text.

[0347] Step 5:

[0348] The server integrates the analysis results from the artificial intelligence engine and the judgments of the emotion engine to generate a prioritized task list. If the server determines that the user is in a high-stress state, it adjusts the priority of some tasks and rearranges them in the optimal order to reduce the user's burden.

[0349] Step 6:

[0350] The terminal displays the task list received from the server on the user interface. Tasks are color-coded according to their importance and urgency, and presented in a way that is easy for the user to work on.

[0351] Step 7:

[0352] The user refers to the presented task list and marks each task as performed or completed. Feedback information is sent from the device to the server, enabling task management that also takes into account the user's changing emotional state.

[0353] Step 8:

[0354] The server uses user feedback data to update the learning models of its emotion engine and artificial intelligence engine. This leads to further improvements in the accuracy of task suggestions and emotion estimation in subsequent tasks.

[0355] (Example 2)

[0356] 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".

[0357] Traditional task management systems display tasks uniformly without considering the user's emotional state, leading to user stress and making efficient task management difficult. Furthermore, they fail to fully utilize user feedback, limiting the system's adaptability. Therefore, there is a need for task presentation based on the user's emotional state and a system that can adapt flexibly.

[0358] 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.

[0359] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data into a central processing device, and means for an artificial intelligence engine that analyzes the data using text mining technology. This makes it possible to consider the emotional state of the user and improve the system based on the presentation of prioritized tasks and feedback.

[0360] A "communication medium" is a means of connecting an information processing device and a central processing device to transfer data.

[0361] An "information processing device" is an electronic device used to generate, input, and manipulate data.

[0362] "Data" refers to a series of numbers, strings of characters, or signals that can be recorded and processed.

[0363] A "central processing unit" is a central computer device used to integrate and analyze collected data.

[0364] "Text mining technology" is a technique that uses natural language processing to analyze data and extract important information.

[0365] An "artificial intelligence engine" is software or a program that assists in data analysis and decision-making.

[0366] "Emotional state" refers to the user's psychological state, including emotions such as stress and relief.

[0367] A "task list" is a list that outlines the tasks and appointments that a user needs to work on.

[0368] A "user interface" refers to the display screen and input methods that allow a user to operate a system and receive information.

[0369] "Feedback" refers to information recorded from users' opinions and reactions, used for evaluation or system improvement.

[0370] A "learning model" is an algorithm or program that adapts and evolves based on feedback.

[0371] This invention is a system that collects information and performs task management that takes into account the emotional state of the user. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects them.

[0372] The server collects data from multiple sources, such as email services, messaging platforms, and calendar services, via communication media. Data collection involves obtaining information in real time using APIs and storing it in an integrated database. Specifically, the software uses email APIs and the natural language processing library NLTK to analyze the data and determine task priorities.

[0373] The server's artificial intelligence engine uses text mining technology to analyze data from an integrated database and evaluate the importance and urgency of each task. Furthermore, the server uses an emotion engine to determine the user's emotional state. The emotion engine detects emotions from the user's operation logs and input data, recognizing their mental state, including the presence or absence of stress.

[0374] The generated task list is displayed in the user interface on the device. This interface adjusts how tasks are displayed according to their urgency and emotional state, visually highlighting important tasks. Users can refer to this task list and prioritize tasks accordingly.

[0375] When a user completes a task, feedback is sent from the device to the server. Based on this feedback, the server updates its learning model, allowing it to better adapt to the user's emotions when presenting tasks in the future.

[0376] For example, if the server determines that a user is overwhelmed with work and experiencing stress, it will change the priority of the task list, displaying less urgent tasks first. In this way, users can manage their tasks in a way that is sensitive to their emotions.

[0377] Examples of prompts include, "Show an example of presenting a task when the user is not feeling stressed," and "If the emotion engine detects user anxiety, how will you change the task's priority?"

[0378] This system supports effective task management tailored to the user's emotional state, thereby facilitating the smooth execution of daily tasks.

[0379] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0380] Step 1:

[0381] The server collects data from various sources via communication media. Specifically, it uses email APIs and messaging APIs to retrieve user email and message information. This input data includes information such as subject, sender, recipient, and date and time. This generates an integrated dataset from diverse sources.

[0382] Step 2:

[0383] The server stores the collected data in an integrated database. The database structure facilitates centralized management of data from different sources. At this stage, newly acquired data is added to the database and integrated while maintaining consistency with existing data. The output includes a unified database.

[0384] Step 3:

[0385] The server's artificial intelligence engine analyzes the collected data. This analysis utilizes text mining techniques to detect particularly important keywords and determine urgency based on context. The input for the analysis is information from an integrated database, and the output provides the importance and classification results of each piece of information.

[0386] Step 4:

[0387] The server's emotion engine determines emotions based on user activity logs and input data. Specifically, it analyzes keyboard speed, mouse movements, and the frequency of inputting specific phrases. Based on this input data, it performs analysis and outputs the user's emotional state.

[0388] Step 5:

[0389] The server integrates results from text mining and a sentiment engine to generate a prioritized task list. The generation process processes the analysis data and prioritizes tasks based on urgency and psychological state. The output is an optimally structured task list.

[0390] Step 6:

[0391] The device displays the generated task list in the user interface. In operation, tasks are listed on the screen and color-coded or highlighted according to their urgency and importance. Users can use this task list to efficiently manage their work.

[0392] Step 7:

[0393] Users provide feedback upon completing a task. The device receives this feedback and sends it to the server. The feedback includes details such as task completion status, time taken, and psychological impressions. Based on this information, the server's learning model is updated as new input. The output is data that is reflected in improvements for the next task list generation.

[0394] (Application Example 2)

[0395] 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."

[0396] Modern households require flexible task management that accommodates busy daily lives and individual emotional states. However, current task management systems lack the functionality to prioritize and present tasks while taking into account the user's emotional state and stress levels, which can result in unnecessary stress for the user. In light of this situation, the present invention aims to provide a system that recognizes the user's emotional state and performs appropriate task management based on that state.

[0397] 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.

[0398] In this invention, the server includes means for acquiring information from a data collection device via communication means, means for collecting the information obtained from the data collection device in a central processing device, means for providing an intelligent engine for analyzing the information collected in the central processing device, means for incorporating an emotion engine for recognizing emotional states and configuring a list of tasks according to the emotional state of the resident, and means for adjusting the priority of presenting the list of tasks according to the resident's environment and reducing stress. This enables flexible task management that responds to the user's emotional state.

[0399] "Communication means" refers to the intermediary used to obtain information from data collection devices, and plays a role in collecting information through a network.

[0400] A "data aggregation device" is a device that collects and stores information, and provides that information to a server via communication means.

[0401] "Means of acquiring information" refers to devices that have the function of extracting necessary information from data collection equipment and play the first step in information gathering.

[0402] A "central processing unit" is a central device that efficiently processes and analyzes collected information and generates it in a state that can be used by other devices and engines.

[0403] An "intelligent engine" refers to an artificial computing system that analyzes collected information and makes decisions based on the results, particularly influencing the determination of priorities.

[0404] The "emotional engine" is an analytical system that has the function of identifying and sensing changes in the emotional state of residents, and measuring the emotional state of each individual.

[0405] The "task list" is a list of tasks whose priority has been determined based on the results of analysis by an intelligent engine, and it is a means for users to efficiently manage their daily work by referring to it.

[0406] "Means for adjusting the priority of presenting the list of tasks according to the resident's environment" refers to a function that takes into consideration the user's emotional state and environmental circumstances, by changing the order in which the list of tasks is presented, thereby preventing excessive burden on the user.

[0407] The system of this invention is designed to streamline the busy daily lives of users and includes communication means, data collection devices, a central processing unit, an intelligent engine, and an emotion engine.

[0408] The server collects data from various sources using communication methods. This information is gathered at a central processing unit via data aggregation devices, where an intelligent engine analyzes it. This analysis generates a list of tasks that take priority into account. In this process, the intelligent engine uses text mining techniques to analyze the information and determine the optimal order of tasks.

[0409] Furthermore, the server uses an emotion engine to evaluate the user's emotional state in real time and adjust the list of tasks accordingly. This process is designed to minimize the mental burden on the user when performing each task. Software such as TensorFlow and Google Cloud Natural Language API are used for data analysis and adjustment performed by the intelligent engine and emotion engine.

[0410] As a concrete example, if it's the time of day when the user is relaxing, such as after dinner, the system can re-evaluate task priorities and, if necessary, prioritize suggesting entertainment or relaxation-related activities. In this case, the system would input a prompt message like the following into the AI ​​model to suggest a course of action: "Based on User A's current emotional state, postpone low-priority tasks and prioritize relaxation tasks (e.g., playing music)."

[0411] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0412] Step 1:

[0413] The server collects information from data aggregation devices via communication methods. Specifically, it retrieves data from mail servers, messaging platforms, calendar services, etc., via APIs. In this process, the input is data from these information sources, and the output is an integrated database-formatted dataset.

[0414] Step 2:

[0415] The server sends the integrated data to a central processing unit for analysis by an intelligent engine. Here, text mining techniques are used to analyze the data and determine the importance and urgency of the tasks. The input is the dataset from the previous step. The output is the priority of each task obtained through the analysis.

[0416] Step 3:

[0417] The server operates an emotion engine to recognize the user's emotional state. Specifically, it inputs and analyzes operation logs and subjective user data to quantify the user's emotions. The input in this step is an emotion index obtained from the user interface, and the output is the user's current emotional state.

[0418] Step 4:

[0419] The server integrates the analysis results from the intelligent engine and the recognition results from the emotion engine to generate a task list. This task list is a task list with adjusted priorities and is organized in a user-friendly format. The output is the adjusted task list.

[0420] Step 5:

[0421] The terminal displays the generated list of tasks on the user's display device. Users can view this list in real time, managing their daily tasks while understanding task priorities and schedules. The output here is a task list presented visually to the user.

[0422] Step 6:

[0423] The user performs tasks based on the displayed list of tasks and provides feedback to the server through the interface. The input is the user's actions and feedback, and this information is used to further improve the learning structure. The output is the updated learning model.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] [Third Embodiment]

[0428] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] 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".

[0440] This invention relates to a system for efficiently managing the vast amount of information generated within a company and effectively managing user tasks. An embodiment of this system is shown below.

[0441] This system consists of a server, which is an information processing device; terminals used by end users; and users who operate them.

[0442] First, the server collects data from multiple sources, such as email systems, messaging platforms, and calendar systems, via APIs provided by the information processing device. This data includes new emails, messages, and scheduled events. Once the server obtains this data, it converts it into a unified database format and stores it in the database.

[0443] Next, the server analyzes the stored data using an artificial intelligence engine. The AI ​​engine uses machine learning techniques to analyze the data and evaluate the content, origin, recipient, and importance of each piece of data. Text mining techniques are used in this evaluation to extract useful patterns and relationships from the data.

[0444] Based on this analysis, the server determines the priority and generates a task list accordingly. The task list is presented on the user's device through a user interface, allowing the user to quickly see important tasks and information. Reminder notifications are also sent from the device for tasks with approaching deadlines.

[0445] Users can refer to the provided task list, complete tasks, and adjust their priorities individually. This action generates feedback data for the user.

[0446] Ultimately, the server retrains its machine learning model based on the collected feedback data to improve analysis accuracy and utilize this for future task priority determination. In this way, the system of the present invention achieves centralized information management and efficient task management, supporting users in smoothly carrying out their daily tasks.

[0447] As a concrete example, when a user arrives at the office in the morning and logs into their terminal, new emails and meeting schedules are analyzed, and important tasks determined by the server are displayed with priority. This allows users to quickly understand which tasks should be prioritized from the start of their workday.

[0448] The following describes the processing flow.

[0449] Step 1:

[0450] The server establishes API connections with each information processing device based on a pre-configured schedule. The server collects necessary data from sources such as mail servers, communication platforms, and calendar services. It extracts new emails from mail servers, unread messages from messaging services, and new appointments from calendars.

[0451] Step 2:

[0452] The server converts the collected data into a unified format and stores it in a database. This allows data obtained from different sources to be managed centrally. Depending on the type of data, attributes such as sender, recipient, date and time, and content are also stored.

[0453] Step 3:

[0454] The server sends data stored in the database to the artificial intelligence engine. The AI ​​engine analyzes the data using machine learning models and evaluates the relevance, importance, and urgency of the content. It also uses text mining techniques to extract keywords and understand the context.

[0455] Step 4:

[0456] The server generates a task list based on the analysis results of the artificial intelligence engine. Each task is assigned an importance score and listed in order of priority. The task list is stored in a database and prepared to be provided upon user request.

[0457] Step 5:

[0458] The device retrieves the task list from the server when the user logs in and displays it in the user interface. Tasks are sorted according to priority, and high-priority tasks are highlighted with color or icons.

[0459] Step 6:

[0460] Users can view the task list and mark each task as running or completed. They can also manually adjust task priorities and delete unnecessary tasks.

[0461] Step 7:

[0462] The server records user operation history as feedback data. This data is used to retrain machine learning models later, contributing to improved analysis accuracy. Feedback data is accumulated during operation and used periodically to update the models.

[0463] (Example 1)

[0464] 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."

[0465] In today's business environment, a massive amount of information is constantly being generated, and its efficient management is essential. There is a need for a method to effectively integrate and analyze this information and clearly present tasks based on user priorities. However, current systems suffer from the challenge of difficulty in grasping the overall picture due to the dispersed nature of information sources, making it easy to overlook important information. Furthermore, there is a need for systems to continuously learn from user feedback and perform more advanced analysis.

[0466] 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.

[0467] In this invention, the server includes means for collecting electronic information from multiple information sources via a communication medium, means for converting the electronic information into a unified format and storing it on a recording medium, and means for analyzing the electronic information stored on the recording medium using machine learning technology. This makes it possible to effectively integrate and analyze a large amount of distributed information and present necessary tasks based on priority. Furthermore, by reconstructing the machine learning model based on the user's operation results, the system can continuously learn and improve the accuracy of the analysis.

[0468] A "communication medium" is a means of providing a physical or wireless path for sending and receiving data.

[0469] "Electronic information" refers to data that is stored or transmitted in digital format, including documents, messages, and schedule information.

[0470] A "recording medium" is a physical or magnetic means for storing data, and includes databases and storage devices.

[0471] "Machine learning techniques" refer to algorithms and methods that enable computers to learn patterns from data and perform predictions and classifications.

[0472] A "user interaction screen" is a visual interface that allows users to view information and perform actions.

[0473] "Operation results" refer to feedback data obtained based on the actions taken by the user on the dialogue screen.

[0474] "Rebuilding a machine learning model" is the process of updating the algorithm using feedback data to achieve higher analytical accuracy.

[0475] The embodiment of this invention is based on the construction of a system for aggregating and analyzing information. Its configuration and operation are described in detail below.

[0476] The server collects electronic information from multiple sources via communication media. This involves using existing APIs to retrieve data from, for example, email systems, messaging platforms, and scheduling management systems. Specifically, it can utilize APIs within email systems and messaging platforms. The acquired electronic information is then converted into a unified format and stored in a database, which serves as the storage medium. SQL databases are used for this conversion and storage.

[0477] The server analyzes this stored electronic information using machine learning techniques. The algorithms used include various technologies such as natural language processing and text mining, which extract patterns and relationships from the electronic information. Based on this analysis, the priority of the information is evaluated, and a work instruction sheet is created.

[0478] The generated work order sheet is displayed through a user interaction screen on the terminal. Through this screen, the user can check the progress of tasks, set priorities, and perform actions such as reporting completion. The results of these actions are sent to the server as feedback and recorded.

[0479] Finally, the server uses the acquired feedback data to reconstruct the machine learning model. This reconstruction improves the accuracy of the analysis, which is then used to create future work instruction sheets.

[0480] As a concrete example, a user can request the system to update their work order sheet by entering a prompt such as, "Tell me today's important tasks based on my latest emails and meetings." This prompt allows users to quickly grasp their daily priority tasks.

[0481] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0482] Step 1:

[0483] The server collects electronic information from multiple sources via communication media. Inputs include new data from email systems, messaging platforms, and calendar systems. This data is retrieved using APIs. The output is raw electronic data. Specifically, the server sends requests to the APIs at scheduled time intervals and stores the received data in temporary storage.

[0484] Step 2:

[0485] The server converts the collected electronic information into a unified format and stores it on a recording medium. The input is the raw data collected in step 1. This data is converted from JSON or XML format to a table format in an SQL database. The converted data is stored in the database. Specifically, the server uses a data formatting library to check the integrity of the data and remove unnecessary information.

[0486] Step 3:

[0487] The server analyzes electronic information stored on a recording medium using machine learning techniques. The input is data in a unified format held in a database. Here, natural language processing techniques are used to extract important keywords from the text and categorize the data. As a result of the analysis, a prioritized dataset is output. Specifically, the server starts an NLP engine and performs text mining.

[0488] Step 4:

[0489] The server determines priority based on the analysis results and creates a work instruction sheet. The input is the analysis results from step 3. The server scores the priority of each data item and generates a work instruction sheet sorted by priority based on the results. The output is a work instruction sheet that can be presented to the user. Specifically, it uses a scoring algorithm to evaluate importance and organize the list.

[0490] Step 5:

[0491] The terminal displays the work order sheet received from the server on a user interaction screen. The input is the work order sheet generated in step 4. A UI framework is used to render the list displayed on the interaction screen in a user-friendly format. The output is a task list that the user can visually understand. Specifically, the terminal calls a GUI library to format and display the list.

[0492] Step 6:

[0493] Users view tasks through the terminal's interactive screen and adjust priorities or complete tasks as needed. Input consists of the displayed work instruction sheet and user instructions. The results of the operations are recorded as logs and sent to the server as feedback. Specifically, users perform actions such as clicking and dragging and dropping, and these changes are saved immediately.

[0494] Step 7:

[0495] The server uses the collected feedback data to reconstruct the machine learning model. The input is the results of the user's actions obtained in step 6. By analyzing this and updating the model's parameters, the accuracy of subsequent analyses is improved. The output is the updated machine learning model. Specifically, the server adds the feedback to the training data and retrains the model.

[0496] (Application Example 1)

[0497] 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."

[0498] In today's information processing environment, managing vast amounts of data in e-commerce and within companies is extremely important. However, traditional systems have struggled to efficiently integrate and analyze information from multiple sources, preventing users from immediately identifying priority tasks and important matters, leading to delays in operational efficiency. Furthermore, these systems lacked reminder functions based on the priority and importance of these tasks, potentially causing users to overlook urgent matters, especially those with approaching deadlines such as payments.

[0499] 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.

[0500] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data acquired from the information processing device into a central processing device, and means for providing an artificial intelligence engine for analyzing the integrated data in the central processing device. This makes it possible to efficiently analyze data collected from multiple information sources and provide the user with a task list and reminders based on priority and importance.

[0501] A "communication medium" is a means used to send and receive data between information processing devices.

[0502] An "information processing device" is an electronic device that has the function of manipulating, calculating, and analyzing data.

[0503] A "central processing unit" is a central computer system used to integrate and analyze collected data.

[0504] An "artificial intelligence engine" is software equipped with machine learning algorithms that automatically analyze data and support decision-making.

[0505] A "task list" is a list that organizes and displays tasks and errands that a user needs to complete, based on their priority.

[0506] A "user interface" is a means of providing users with screens and operating methods to interact with a digital system.

[0507] "Feedback" refers to information about user actions and reactions, which is used as data for system improvement and learning.

[0508] A "reminder" is a feature that notifies users of tasks with approaching deadlines or important matters.

[0509] This invention is a system for efficiently managing information and prioritizing the processing of important tasks in corporate and e-commerce environments. In one embodiment, a server and a user terminal work together to collect, analyze, and notify data.

[0510] The server receives data from multiple sources via a communication medium. The hardware used is primarily information processing equipment. The received data is integrated into a central processing unit and then analyzed by an artificial intelligence engine. This AI engine uses text mining techniques to evaluate the data and determine its priority. In this analysis process, machine learning algorithms are utilized to extract patterns and relationships from the data.

[0511] The task list generated from the integrated data is displayed through a user interface on the user's device. Here, users can instantly check important tasks and deadlines. User feedback is also sent to the server through the user interface, and the learning model is updated based on this feedback. This improves the accuracy of subsequent analyses and refines task prioritization.

[0512] As a concrete example, in a company operating an e-commerce platform, when a user logs in, an artificial intelligence engine analyzes customer inquiries and payment-related requests, prioritizing and displaying the most important ones. This allows operators to proceed with their work without missing items that require prompt attention. In addition, a reminder function automatically notifies users of unprocessed tasks that are nearing their deadlines.

[0513] One example of how a generative AI model can be used is by inputting a prompt such as, "You are an e-commerce support representative. Please propose a strategy for efficiently handling customer inquiries and outstanding payments." The model will then suggest an appropriate task handling plan.

[0514] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0515] Step 1:

[0516] The server collects data from multiple sources via communication media. In this collection process, an information processing device connects to each source to retrieve emails, messages, and calendar information. The input consists of data from each source, and the output is a collection of integrated raw data.

[0517] Step 2:

[0518] The server integrates the collected raw data into a central processing unit and stores it in a database. The input is a collection of raw data, and the output is a database in a unified format. Specifically, it standardizes data in different formats and aggregates it into a single database.

[0519] Step 3:

[0520] The server analyzes the integrated data using an artificial intelligence engine. This analysis utilizes machine learning algorithms to assess data importance and extract relevances. The input is the integrated data from the database, and the output is a prioritized dataset.

[0521] Step 4:

[0522] The server generates a task list based on prioritized data and sends it to the user terminal. The input is a prioritized dataset, and the output is a task list for the user terminal. Specifically, it creates a list that considers the importance of each task to the user.

[0523] Step 5:

[0524] The terminal displays the task list received from the server on the user interface. The input is task list data from the server, and the output is a visualized list display. This allows the user to immediately identify tasks that require attention.

[0525] Step 6:

[0526] The user refers to the displayed task list and provides feedback as needed. Specific actions include updating task completion status and adjusting individual priorities. The input is the user's actions, and the output is feedback data.

[0527] Step 7:

[0528] The server receives feedback data from the user's terminal and retrains the generated AI model. The input is the feedback data, and the output is the updated machine learning model. This improves the accuracy of data analysis in subsequent attempts.

[0529] Step 8:

[0530] The terminal uses a reminder function to notify users of unprocessed tasks that are nearing their due date. Input is a task list and due date information from the server, and output is a notification message to the user. Its specific function is to provide users with timely schedule-related alerts.

[0531] 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.

[0532] This invention provides a system that centrally manages information and enables task management that takes into account the user's emotional state. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects the two.

[0533] First, the server collects data from multiple sources, including email, messaging platforms, and calendar services. During this process, the server retrieves information via APIs and integrates it into a unified database. The data includes basic information such as subject, sender, recipient, and date / time.

[0534] The collected data is passed to an artificial intelligence engine on the server. This engine analyzes the data using text mining techniques to determine the importance and urgency of each piece of information. Furthermore, this invention also includes an emotion engine that recognizes the user's emotional state. The emotion engine detects emotions from the data and operation logs entered by the user and understands the current emotional state.

[0535] Next, the server adjusts the analysis results and generates a prioritized task list based on the emotional state recognized by the emotion engine. If the user is experiencing stress, the task priorities and presentation methods may be changed.

[0536] The generated task list is displayed in the user interface via the device. Users can use this list to efficiently manage their tasks. The interface highlights urgent tasks and presents information in a way that is sensitive to the user's emotions.

[0537] Users can manage tasks while referring to a task list. Furthermore, feedback from the user upon task completion is recorded by the emotion engine, and the server uses this feedback to update its learning model. Through this iterative process, the system flexibly responds to changes in the user's emotions, supporting more appropriate task management.

[0538] For example, when a user decides they want to reduce their workload, the server rearranges the task list to minimize stress, prioritizing tasks that have lowered priority or can be temporarily avoided. In this way, the system of the present invention helps users smoothly perform their daily tasks while also considering the emotional aspects.

[0539] The following describes the processing flow.

[0540] Step 1:

[0541] The server connects to the mail server, messaging service, and calendar API according to a predetermined schedule to retrieve the necessary data. This data includes email subject and content, sender information, message history, and event information registered in the calendar.

[0542] Step 2:

[0543] The server converts the collected data into a unified format and stores it in a database. During storage, each piece of data is stored along with its attribute information (e.g., reception date and time, and related project), and is centrally managed.

[0544] Step 3:

[0545] The server's artificial intelligence engine analyzes stored data and uses text mining techniques to evaluate the content of the information. For example, it can determine project progress and important tasks from email content and quantify the importance and urgency of each piece of information.

[0546] Step 4:

[0547] The server also analyzes user interaction data sent from the terminal using an emotion engine. It estimates the user's emotional state (e.g., stress or fatigue) from things like the rhythm of keystrokes, mouse movements, and entered text.

[0548] Step 5:

[0549] The server integrates the analysis results from the artificial intelligence engine and the judgments of the emotion engine to generate a prioritized task list. If the server determines that the user is in a high-stress state, it adjusts the priority of some tasks and rearranges them in the optimal order to reduce the user's burden.

[0550] Step 6:

[0551] The terminal displays the task list received from the server on the user interface. Tasks are color-coded according to their importance and urgency, and presented in a way that is easy for the user to work on.

[0552] Step 7:

[0553] The user refers to the presented task list and marks each task as performed or completed. Feedback information is sent from the device to the server, enabling task management that also takes into account the user's changing emotional state.

[0554] Step 8:

[0555] The server uses user feedback data to update the learning models of its emotion engine and artificial intelligence engine. This leads to further improvements in the accuracy of task suggestions and emotion estimation in subsequent tasks.

[0556] (Example 2)

[0557] 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."

[0558] Traditional task management systems display tasks uniformly without considering the user's emotional state, leading to user stress and making efficient task management difficult. Furthermore, they fail to fully utilize user feedback, limiting the system's adaptability. Therefore, there is a need for task presentation based on the user's emotional state and a system that can adapt flexibly.

[0559] 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.

[0560] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data into a central processing device, and means for an artificial intelligence engine that analyzes the data using text mining technology. This makes it possible to consider the emotional state of the user and improve the system based on the presentation of prioritized tasks and feedback.

[0561] A "communication medium" is a means of connecting an information processing device and a central processing device to transfer data.

[0562] An "information processing device" is an electronic device used to generate, input, and manipulate data.

[0563] "Data" refers to a series of numbers, strings of characters, or signals that can be recorded and processed.

[0564] A "central processing unit" is a central computer device used to integrate and analyze collected data.

[0565] "Text mining technology" is a technique that uses natural language processing to analyze data and extract important information.

[0566] An "artificial intelligence engine" is software or a program that assists in data analysis and decision-making.

[0567] "Emotional state" refers to the user's psychological state, including emotions such as stress and relief.

[0568] A "task list" is a list that outlines the tasks and appointments that a user needs to work on.

[0569] A "user interface" refers to the display screen and input methods that allow a user to operate a system and receive information.

[0570] "Feedback" refers to information recorded from users' opinions and reactions, used for evaluation or system improvement.

[0571] A "learning model" is an algorithm or program that adapts and evolves based on feedback.

[0572] This invention is a system that collects information and performs task management that takes into account the emotional state of the user. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects them.

[0573] The server collects data from multiple sources, such as email services, messaging platforms, and calendar services, via communication media. Data collection involves obtaining information in real time using APIs and storing it in an integrated database. Specifically, the software uses email APIs and the natural language processing library NLTK to analyze the data and determine task priorities.

[0574] The server's artificial intelligence engine uses text mining technology to analyze data from an integrated database and evaluate the importance and urgency of each task. Furthermore, the server uses an emotion engine to determine the user's emotional state. The emotion engine detects emotions from the user's operation logs and input data, recognizing their mental state, including the presence or absence of stress.

[0575] The generated task list is displayed in the user interface on the device. This interface adjusts how tasks are displayed according to their urgency and emotional state, visually highlighting important tasks. Users can refer to this task list and prioritize tasks accordingly.

[0576] When a user completes a task, feedback is sent from the device to the server. Based on this feedback, the server updates its learning model, allowing it to better adapt to the user's emotions when presenting tasks in the future.

[0577] For example, if the server determines that a user is overwhelmed with work and experiencing stress, it will change the priority of the task list, displaying less urgent tasks first. In this way, users can manage their tasks in a way that is sensitive to their emotions.

[0578] Examples of prompts include, "Show an example of presenting a task when the user is not feeling stressed," and "If the emotion engine detects user anxiety, how will you change the task's priority?"

[0579] This system supports effective task management tailored to the user's emotional state, thereby facilitating the smooth execution of daily tasks.

[0580] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0581] Step 1:

[0582] The server collects data from various sources via communication media. Specifically, it uses email APIs and messaging APIs to retrieve user email and message information. This input data includes information such as subject, sender, recipient, and date and time. This generates an integrated dataset from diverse sources.

[0583] Step 2:

[0584] The server stores the collected data in an integrated database. The database structure facilitates centralized management of data from different sources. At this stage, newly acquired data is added to the database and integrated while maintaining consistency with existing data. The output includes a unified database.

[0585] Step 3:

[0586] The server's artificial intelligence engine analyzes the collected data. This analysis utilizes text mining techniques to detect particularly important keywords and determine urgency based on context. The input for the analysis is information from an integrated database, and the output provides the importance and classification results of each piece of information.

[0587] Step 4:

[0588] The server's emotion engine determines emotions based on user activity logs and input data. Specifically, it analyzes keyboard speed, mouse movements, and the frequency of inputting specific phrases. Based on this input data, it performs analysis and outputs the user's emotional state.

[0589] Step 5:

[0590] The server integrates results from text mining and a sentiment engine to generate a prioritized task list. The generation process processes the analysis data and prioritizes tasks based on urgency and psychological state. The output is an optimally structured task list.

[0591] Step 6:

[0592] The device displays the generated task list in the user interface. In operation, tasks are listed on the screen and color-coded or highlighted according to their urgency and importance. Users can use this task list to efficiently manage their work.

[0593] Step 7:

[0594] Users provide feedback upon completing a task. The device receives this feedback and sends it to the server. The feedback includes details such as task completion status, time taken, and psychological impressions. Based on this information, the server's learning model is updated as new input. The output is data that is reflected in improvements for the next task list generation.

[0595] (Application Example 2)

[0596] 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."

[0597] Modern households require flexible task management that accommodates busy daily lives and individual emotional states. However, current task management systems lack the functionality to prioritize and present tasks while taking into account the user's emotional state and stress levels, which can result in unnecessary stress for the user. In light of this situation, the present invention aims to provide a system that recognizes the user's emotional state and performs appropriate task management based on that state.

[0598] 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.

[0599] In this invention, the server includes means for acquiring information from a data collection device via communication means, means for collecting the information obtained from the data collection device in a central processing device, means for providing an intelligent engine for analyzing the information collected in the central processing device, means for incorporating an emotion engine for recognizing emotional states and configuring a list of tasks according to the emotional state of the resident, and means for adjusting the priority of presenting the list of tasks according to the resident's environment and reducing stress. This enables flexible task management that responds to the user's emotional state.

[0600] "Communication means" refers to the intermediary used to obtain information from data collection devices, and plays a role in collecting information through a network.

[0601] A "data aggregation device" is a device that collects and stores information, and provides that information to a server via communication means.

[0602] "Means of acquiring information" refers to devices that have the function of extracting necessary information from data collection equipment and play the first step in information gathering.

[0603] A "central processing unit" is a central device that efficiently processes and analyzes collected information and generates it in a state that can be used by other devices and engines.

[0604] An "intelligent engine" refers to an artificial computing system that analyzes collected information and makes decisions based on the results, particularly influencing the determination of priorities.

[0605] The "emotional engine" is an analytical system that has the function of identifying and sensing changes in the emotional state of residents, and measuring the emotional state of each individual.

[0606] The "task list" is a list of tasks whose priority has been determined based on the results of analysis by an intelligent engine, and it is a means for users to efficiently manage their daily work by referring to it.

[0607] "Means for adjusting the priority of presenting the list of tasks according to the resident's environment" refers to a function that takes into consideration the user's emotional state and environmental circumstances, by changing the order in which the list of tasks is presented, thereby preventing excessive burden on the user.

[0608] The system of this invention is designed to streamline the busy daily lives of users and includes communication means, data collection devices, a central processing unit, an intelligent engine, and an emotion engine.

[0609] The server collects data from various sources using communication methods. This information is gathered at a central processing unit via data aggregation devices, where an intelligent engine analyzes it. This analysis generates a list of tasks that take priority into account. In this process, the intelligent engine uses text mining techniques to analyze the information and determine the optimal order of tasks.

[0610] Furthermore, the server uses an emotion engine to evaluate the user's emotional state in real time and adjust the list of tasks accordingly. This process is designed to minimize the mental burden on the user when performing each task. Software such as TensorFlow and Google Cloud Natural Language API are used for data analysis and adjustment performed by the intelligent engine and emotion engine.

[0611] As a concrete example, if it's the time of day when the user is relaxing, such as after dinner, the system can re-evaluate task priorities and, if necessary, prioritize suggesting entertainment or relaxation-related activities. In this case, the system would input a prompt message like the following into the AI ​​model to suggest a course of action: "Based on User A's current emotional state, postpone low-priority tasks and prioritize relaxation tasks (e.g., playing music)."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server collects information from data aggregation devices via communication methods. Specifically, it retrieves data from mail servers, messaging platforms, calendar services, etc., via APIs. In this process, the input is data from these information sources, and the output is an integrated database-formatted dataset.

[0615] Step 2:

[0616] The server sends the integrated data to a central processing unit for analysis by an intelligent engine. Here, text mining techniques are used to analyze the data and determine the importance and urgency of the tasks. The input is the dataset from the previous step. The output is the priority of each task obtained through the analysis.

[0617] Step 3:

[0618] The server operates an emotion engine to recognize the user's emotional state. Specifically, it inputs and analyzes operation logs and subjective user data to quantify the user's emotions. The input in this step is an emotion index obtained from the user interface, and the output is the user's current emotional state.

[0619] Step 4:

[0620] The server integrates the analysis results from the intelligent engine and the recognition results from the emotion engine to generate a task list. This task list is a task list with adjusted priorities and is organized in a user-friendly format. The output is the adjusted task list.

[0621] Step 5:

[0622] The terminal displays the generated list of tasks on the user's display device. Users can view this list in real time, managing their daily tasks while understanding task priorities and schedules. The output here is a task list presented visually to the user.

[0623] Step 6:

[0624] The user performs tasks based on the displayed list of tasks and provides feedback to the server through the interface. The input is the user's actions and feedback, and this information is used to further improve the learning structure. The output is the updated learning model.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] [Fourth Embodiment]

[0629] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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).

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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".

[0642] This invention relates to a system for efficiently managing the vast amount of information generated within a company and effectively managing user tasks. An embodiment of this system is shown below.

[0643] This system consists of a server, which is an information processing device; terminals used by end users; and users who operate them.

[0644] First, the server collects data from multiple sources, such as email systems, messaging platforms, and calendar systems, via APIs provided by the information processing device. This data includes new emails, messages, and scheduled events. Once the server obtains this data, it converts it into a unified database format and stores it in the database.

[0645] Next, the server analyzes the stored data using an artificial intelligence engine. The AI ​​engine uses machine learning techniques to analyze the data and evaluate the content, origin, recipient, and importance of each piece of data. Text mining techniques are used in this evaluation to extract useful patterns and relationships from the data.

[0646] Based on this analysis, the server determines the priority and generates a task list accordingly. The task list is presented on the user's device through a user interface, allowing the user to quickly see important tasks and information. Reminder notifications are also sent from the device for tasks with approaching deadlines.

[0647] Users can refer to the provided task list, complete tasks, and adjust their priorities individually. This action generates feedback data for the user.

[0648] Ultimately, the server retrains its machine learning model based on the collected feedback data to improve analysis accuracy and utilize this for future task priority determination. In this way, the system of the present invention achieves centralized information management and efficient task management, supporting users in smoothly carrying out their daily tasks.

[0649] As a concrete example, when a user arrives at the office in the morning and logs into their terminal, new emails and meeting schedules are analyzed, and important tasks determined by the server are displayed with priority. This allows users to quickly understand which tasks should be prioritized from the start of their workday.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] The server establishes API connections with each information processing device based on a pre-configured schedule. The server collects necessary data from sources such as mail servers, communication platforms, and calendar services. It extracts new emails from mail servers, unread messages from messaging services, and new appointments from calendars.

[0653] Step 2:

[0654] The server converts the collected data into a unified format and stores it in a database. This allows data obtained from different sources to be managed centrally. Depending on the type of data, attributes such as sender, recipient, date and time, and content are also stored.

[0655] Step 3:

[0656] The server sends data stored in the database to the artificial intelligence engine. The AI ​​engine analyzes the data using machine learning models and evaluates the relevance, importance, and urgency of the content. It also uses text mining techniques to extract keywords and understand the context.

[0657] Step 4:

[0658] The server generates a task list based on the analysis results of the artificial intelligence engine. Each task is assigned an importance score and listed in order of priority. The task list is stored in a database and prepared to be provided upon user request.

[0659] Step 5:

[0660] The device retrieves the task list from the server when the user logs in and displays it in the user interface. Tasks are sorted according to priority, and high-priority tasks are highlighted with color or icons.

[0661] Step 6:

[0662] Users can view the task list and mark each task as running or completed. They can also manually adjust task priorities and delete unnecessary tasks.

[0663] Step 7:

[0664] The server records user operation history as feedback data. This data is used to retrain machine learning models later, contributing to improved analysis accuracy. Feedback data is accumulated during operation and used periodically to update the models.

[0665] (Example 1)

[0666] 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".

[0667] In today's business environment, a massive amount of information is constantly being generated, and its efficient management is essential. There is a need for a method to effectively integrate and analyze this information and clearly present tasks based on user priorities. However, current systems suffer from the challenge of difficulty in grasping the overall picture due to the dispersed nature of information sources, making it easy to overlook important information. Furthermore, there is a need for systems to continuously learn from user feedback and perform more advanced analysis.

[0668] 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.

[0669] In this invention, the server includes means for collecting electronic information from multiple information sources via a communication medium, means for converting the electronic information into a unified format and storing it on a recording medium, and means for analyzing the electronic information stored on the recording medium using machine learning technology. This makes it possible to effectively integrate and analyze a large amount of distributed information and present necessary tasks based on priority. Furthermore, by reconstructing the machine learning model based on the user's operation results, the system can continuously learn and improve the accuracy of the analysis.

[0670] A "communication medium" is a means of providing a physical or wireless path for sending and receiving data.

[0671] "Electronic information" refers to data that is stored or transmitted in digital format, including documents, messages, and schedule information.

[0672] A "recording medium" is a physical or magnetic means for storing data, and includes databases and storage devices.

[0673] "Machine learning techniques" refer to algorithms and methods that enable computers to learn patterns from data and perform predictions and classifications.

[0674] A "user interaction screen" is a visual interface that allows users to view information and perform actions.

[0675] "Operation results" refer to feedback data obtained based on the actions taken by the user on the dialogue screen.

[0676] "Rebuilding a machine learning model" is the process of updating the algorithm using feedback data to achieve higher analytical accuracy.

[0677] The embodiment of this invention is based on the construction of a system for aggregating and analyzing information. Its configuration and operation are described in detail below.

[0678] The server collects electronic information from multiple sources via communication media. This involves using existing APIs to retrieve data from, for example, email systems, messaging platforms, and scheduling management systems. Specifically, it can utilize APIs within email systems and messaging platforms. The acquired electronic information is then converted into a unified format and stored in a database, which serves as the storage medium. SQL databases are used for this conversion and storage.

[0679] The server analyzes this stored electronic information using machine learning techniques. The algorithms used include various technologies such as natural language processing and text mining, which extract patterns and relationships from the electronic information. Based on this analysis, the priority of the information is evaluated, and a work instruction sheet is created.

[0680] The generated work order sheet is displayed through a user interaction screen on the terminal. Through this screen, the user can check the progress of tasks, set priorities, and perform actions such as reporting completion. The results of these actions are sent to the server as feedback and recorded.

[0681] Finally, the server uses the acquired feedback data to reconstruct the machine learning model. This reconstruction improves the accuracy of the analysis, which is then used to create future work instruction sheets.

[0682] As a concrete example, a user can request the system to update their work order sheet by entering a prompt such as, "Tell me today's important tasks based on my latest emails and meetings." This prompt allows users to quickly grasp their daily priority tasks.

[0683] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0684] Step 1:

[0685] The server collects electronic information from multiple sources via communication media. Inputs include new data from email systems, messaging platforms, and calendar systems. This data is retrieved using APIs. The output is raw electronic data. Specifically, the server sends requests to the APIs at scheduled time intervals and stores the received data in temporary storage.

[0686] Step 2:

[0687] The server converts the collected electronic information into a unified format and stores it on a recording medium. The input is the raw data collected in step 1. This data is converted from JSON or XML format to a table format in an SQL database. The converted data is stored in the database. Specifically, the server uses a data formatting library to check the integrity of the data and remove unnecessary information.

[0688] Step 3:

[0689] The server analyzes electronic information stored on a recording medium using machine learning techniques. The input is data in a unified format held in a database. Here, natural language processing techniques are used to extract important keywords from the text and categorize the data. As a result of the analysis, a prioritized dataset is output. Specifically, the server starts an NLP engine and performs text mining.

[0690] Step 4:

[0691] The server determines priority based on the analysis results and creates a work instruction sheet. The input is the analysis results from step 3. The server scores the priority of each data item and generates a work instruction sheet sorted by priority based on the results. The output is a work instruction sheet that can be presented to the user. Specifically, it uses a scoring algorithm to evaluate importance and organize the list.

[0692] Step 5:

[0693] The terminal displays the work order sheet received from the server on a user interaction screen. The input is the work order sheet generated in step 4. A UI framework is used to render the list displayed on the interaction screen in a user-friendly format. The output is a task list that the user can visually understand. Specifically, the terminal calls a GUI library to format and display the list.

[0694] Step 6:

[0695] Users view tasks through the terminal's interactive screen and adjust priorities or complete tasks as needed. Input consists of the displayed work instruction sheet and user instructions. The results of the operations are recorded as logs and sent to the server as feedback. Specifically, users perform actions such as clicking and dragging and dropping, and these changes are saved immediately.

[0696] Step 7:

[0697] The server uses the collected feedback data to reconstruct the machine learning model. The input is the results of the user's actions obtained in step 6. By analyzing this and updating the model's parameters, the accuracy of subsequent analyses is improved. The output is the updated machine learning model. Specifically, the server adds the feedback to the training data and retrains the model.

[0698] (Application Example 1)

[0699] 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".

[0700] In today's information processing environment, managing vast amounts of data in e-commerce and within companies is extremely important. However, traditional systems have struggled to efficiently integrate and analyze information from multiple sources, preventing users from immediately identifying priority tasks and important matters, leading to delays in operational efficiency. Furthermore, these systems lacked reminder functions based on the priority and importance of these tasks, potentially causing users to overlook urgent matters, especially those with approaching deadlines such as payments.

[0701] 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.

[0702] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data acquired from the information processing device into a central processing device, and means for providing an artificial intelligence engine for analyzing the integrated data in the central processing device. This makes it possible to efficiently analyze data collected from multiple information sources and provide the user with a task list and reminders based on priority and importance.

[0703] A "communication medium" is a means used to send and receive data between information processing devices.

[0704] An "information processing device" is an electronic device that has the function of manipulating, calculating, and analyzing data.

[0705] A "central processing unit" is a central computer system used to integrate and analyze collected data.

[0706] An "artificial intelligence engine" is software equipped with machine learning algorithms that automatically analyze data and support decision-making.

[0707] A "task list" is a list that organizes and displays tasks and errands that a user needs to complete, based on their priority.

[0708] A "user interface" is a means of providing users with screens and operating methods to interact with a digital system.

[0709] "Feedback" refers to information about user actions and reactions, which is used as data for system improvement and learning.

[0710] A "reminder" is a feature that notifies users of tasks with approaching deadlines or important matters.

[0711] This invention is a system for efficiently managing information and prioritizing the processing of important tasks in corporate and e-commerce environments. In one embodiment, a server and a user terminal work together to collect, analyze, and notify data.

[0712] The server receives data from multiple sources via a communication medium. The hardware used is primarily information processing equipment. The received data is integrated into a central processing unit and then analyzed by an artificial intelligence engine. This AI engine uses text mining techniques to evaluate the data and determine its priority. In this analysis process, machine learning algorithms are utilized to extract patterns and relationships from the data.

[0713] The task list generated from the integrated data is displayed through a user interface on the user's device. Here, users can instantly check important tasks and deadlines. User feedback is also sent to the server through the user interface, and the learning model is updated based on this feedback. This improves the accuracy of subsequent analyses and refines task prioritization.

[0714] As a concrete example, in a company operating an e-commerce platform, when a user logs in, an artificial intelligence engine analyzes customer inquiries and payment-related requests, prioritizing and displaying the most important ones. This allows operators to proceed with their work without missing items that require prompt attention. In addition, a reminder function automatically notifies users of unprocessed tasks that are nearing their deadlines.

[0715] One example of how a generative AI model can be used is by inputting a prompt such as, "You are an e-commerce support representative. Please propose a strategy for efficiently handling customer inquiries and outstanding payments." The model will then suggest an appropriate task handling plan.

[0716] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0717] Step 1:

[0718] The server collects data from multiple sources via communication media. In this collection process, an information processing device connects to each source to retrieve emails, messages, and calendar information. The input consists of data from each source, and the output is a collection of integrated raw data.

[0719] Step 2:

[0720] The server integrates the collected raw data into a central processing unit and stores it in a database. The input is a collection of raw data, and the output is a database in a unified format. Specifically, it standardizes data in different formats and aggregates it into a single database.

[0721] Step 3:

[0722] The server analyzes the integrated data using an artificial intelligence engine. This analysis utilizes machine learning algorithms to assess data importance and extract relevances. The input is the integrated data from the database, and the output is a prioritized dataset.

[0723] Step 4:

[0724] The server generates a task list based on prioritized data and sends it to the user terminal. The input is a prioritized dataset, and the output is a task list for the user terminal. Specifically, it creates a list that considers the importance of each task to the user.

[0725] Step 5:

[0726] The terminal displays the task list received from the server on the user interface. The input is task list data from the server, and the output is a visualized list display. This allows the user to immediately identify tasks that require attention.

[0727] Step 6:

[0728] The user refers to the displayed task list and provides feedback as needed. Specific actions include updating task completion status and adjusting individual priorities. The input is the user's actions, and the output is feedback data.

[0729] Step 7:

[0730] The server receives feedback data from the user's terminal and retrains the generated AI model. The input is the feedback data, and the output is the updated machine learning model. This improves the accuracy of data analysis in subsequent attempts.

[0731] Step 8:

[0732] The terminal uses a reminder function to notify users of unprocessed tasks that are nearing their due date. Input is a task list and due date information from the server, and output is a notification message to the user. Its specific function is to provide users with timely schedule-related alerts.

[0733] 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.

[0734] This invention provides a system that centrally manages information and enables task management that takes into account the user's emotional state. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects the two.

[0735] First, the server collects data from multiple sources, including email, messaging platforms, and calendar services. During this process, the server retrieves information via APIs and integrates it into a unified database. The data includes basic information such as subject, sender, recipient, and date / time.

[0736] The collected data is passed to an artificial intelligence engine on the server. This engine analyzes the data using text mining techniques to determine the importance and urgency of each piece of information. Furthermore, this invention also includes an emotion engine that recognizes the user's emotional state. The emotion engine detects emotions from the data and operation logs entered by the user and understands the current emotional state.

[0737] Next, the server adjusts the analysis results and generates a prioritized task list based on the emotional state recognized by the emotion engine. If the user is experiencing stress, the task priorities and presentation methods may be changed.

[0738] The generated task list is displayed in the user interface via the device. Users can use this list to efficiently manage their tasks. The interface highlights urgent tasks and presents information in a way that is sensitive to the user's emotions.

[0739] Users can manage tasks while referring to a task list. Furthermore, feedback from the user upon task completion is recorded by the emotion engine, and the server uses this feedback to update its learning model. Through this iterative process, the system flexibly responds to changes in the user's emotions, supporting more appropriate task management.

[0740] For example, when a user decides they want to reduce their workload, the server rearranges the task list to minimize stress, prioritizing tasks that have lowered priority or can be temporarily avoided. In this way, the system of the present invention helps users smoothly perform their daily tasks while also considering the emotional aspects.

[0741] The following describes the processing flow.

[0742] Step 1:

[0743] The server connects to the mail server, messaging service, and calendar API according to a predetermined schedule to retrieve the necessary data. This data includes email subject and content, sender information, message history, and event information registered in the calendar.

[0744] Step 2:

[0745] The server converts the collected data into a unified format and stores it in a database. During storage, each piece of data is stored along with its attribute information (e.g., reception date and time, and related project), and is centrally managed.

[0746] Step 3:

[0747] The server's artificial intelligence engine analyzes stored data and uses text mining techniques to evaluate the content of the information. For example, it can determine project progress and important tasks from email content and quantify the importance and urgency of each piece of information.

[0748] Step 4:

[0749] The server also analyzes user interaction data sent from the terminal using an emotion engine. It estimates the user's emotional state (e.g., stress or fatigue) from things like the rhythm of keystrokes, mouse movements, and entered text.

[0750] Step 5:

[0751] The server integrates the analysis results from the artificial intelligence engine and the judgments of the emotion engine to generate a prioritized task list. If the server determines that the user is in a high-stress state, it adjusts the priority of some tasks and rearranges them in the optimal order to reduce the user's burden.

[0752] Step 6:

[0753] The terminal displays the task list received from the server on the user interface. Tasks are color-coded according to their importance and urgency, and presented in a way that is easy for the user to work on.

[0754] Step 7:

[0755] The user refers to the presented task list and marks each task as performed or completed. Feedback information is sent from the device to the server, enabling task management that also takes into account the user's changing emotional state.

[0756] Step 8:

[0757] The server uses user feedback data to update the learning models of its emotion engine and artificial intelligence engine. This leads to further improvements in the accuracy of task suggestions and emotion estimation in subsequent tasks.

[0758] (Example 2)

[0759] 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".

[0760] Traditional task management systems display tasks uniformly without considering the user's emotional state, leading to user stress and making efficient task management difficult. Furthermore, they fail to fully utilize user feedback, limiting the system's adaptability. Therefore, there is a need for task presentation based on the user's emotional state and a system that can adapt flexibly.

[0761] 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.

[0762] In this invention, the server includes means for collecting data from an information processing device via a communication medium, means for integrating the data into a central processing device, and means for an artificial intelligence engine that analyzes the data using text mining technology. This makes it possible to consider the emotional state of the user and improve the system based on the presentation of prioritized tasks and feedback.

[0763] A "communication medium" is a means of connecting an information processing device and a central processing device to transfer data.

[0764] An "information processing device" is an electronic device used to generate, input, and manipulate data.

[0765] "Data" refers to a series of numbers, strings of characters, or signals that can be recorded and processed.

[0766] A "central processing unit" is a central computer device used to integrate and analyze collected data.

[0767] "Text mining technology" is a technique that uses natural language processing to analyze data and extract important information.

[0768] An "artificial intelligence engine" is software or a program that assists in data analysis and decision-making.

[0769] "Emotional state" refers to the user's psychological state, including emotions such as stress and relief.

[0770] A "task list" is a list that outlines the tasks and appointments that a user needs to work on.

[0771] A "user interface" refers to the display screen and input methods that allow a user to operate a system and receive information.

[0772] "Feedback" refers to information recorded from users' opinions and reactions, used for evaluation or system improvement.

[0773] A "learning model" is an algorithm or program that adapts and evolves based on feedback.

[0774] This invention is a system that collects information and performs task management that takes into account the emotional state of the user. The system is implemented using a server, which is an information processing device, a terminal operated by the user, and a communication medium that connects them.

[0775] The server collects data from multiple sources, such as email services, messaging platforms, and calendar services, via communication media. Data collection involves obtaining information in real time using APIs and storing it in an integrated database. Specifically, the software uses email APIs and the natural language processing library NLTK to analyze the data and determine task priorities.

[0776] The server's artificial intelligence engine uses text mining technology to analyze data from an integrated database and evaluate the importance and urgency of each task. Furthermore, the server uses an emotion engine to determine the user's emotional state. The emotion engine detects emotions from the user's operation logs and input data, recognizing their mental state, including the presence or absence of stress.

[0777] The generated task list is displayed in the user interface on the device. This interface adjusts how tasks are displayed according to their urgency and emotional state, visually highlighting important tasks. Users can refer to this task list and prioritize tasks accordingly.

[0778] When a user completes a task, feedback is sent from the device to the server. Based on this feedback, the server updates its learning model, allowing it to better adapt to the user's emotions when presenting tasks in the future.

[0779] For example, if the server determines that a user is overwhelmed with work and experiencing stress, it will change the priority of the task list, displaying less urgent tasks first. In this way, users can manage their tasks in a way that is sensitive to their emotions.

[0780] Examples of prompts include, "Show an example of presenting a task when the user is not feeling stressed," and "If the emotion engine detects user anxiety, how will you change the task's priority?"

[0781] This system supports effective task management tailored to the user's emotional state, thereby facilitating the smooth execution of daily tasks.

[0782] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0783] Step 1:

[0784] The server collects data from various sources via communication media. Specifically, it uses email APIs and messaging APIs to retrieve user email and message information. This input data includes information such as subject, sender, recipient, and date and time. This generates an integrated dataset from diverse sources.

[0785] Step 2:

[0786] The server stores the collected data in an integrated database. The database structure facilitates centralized management of data from different sources. At this stage, newly acquired data is added to the database and integrated while maintaining consistency with existing data. The output includes a unified database.

[0787] Step 3:

[0788] The server's artificial intelligence engine analyzes the collected data. This analysis utilizes text mining techniques to detect particularly important keywords and determine urgency based on context. The input for the analysis is information from an integrated database, and the output provides the importance and classification results of each piece of information.

[0789] Step 4:

[0790] The server's emotion engine determines emotions based on user activity logs and input data. Specifically, it analyzes keyboard speed, mouse movements, and the frequency of inputting specific phrases. Based on this input data, it performs analysis and outputs the user's emotional state.

[0791] Step 5:

[0792] The server integrates results from text mining and a sentiment engine to generate a prioritized task list. The generation process processes the analysis data and prioritizes tasks based on urgency and psychological state. The output is an optimally structured task list.

[0793] Step 6:

[0794] The device displays the generated task list in the user interface. In operation, tasks are listed on the screen and color-coded or highlighted according to their urgency and importance. Users can use this task list to efficiently manage their work.

[0795] Step 7:

[0796] Users provide feedback upon completing a task. The device receives this feedback and sends it to the server. The feedback includes details such as task completion status, time taken, and psychological impressions. Based on this information, the server's learning model is updated as new input. The output is data that is reflected in improvements for the next task list generation.

[0797] (Application Example 2)

[0798] 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".

[0799] Modern households require flexible task management that accommodates busy daily lives and individual emotional states. However, current task management systems lack the functionality to prioritize and present tasks while taking into account the user's emotional state and stress levels, which can result in unnecessary stress for the user. In light of this situation, the present invention aims to provide a system that recognizes the user's emotional state and performs appropriate task management based on that state.

[0800] 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.

[0801] In this invention, the server includes means for acquiring information from a data collection device via communication means, means for collecting the information obtained from the data collection device in a central processing device, means for providing an intelligent engine for analyzing the information collected in the central processing device, means for incorporating an emotion engine for recognizing emotional states and configuring a list of tasks according to the emotional state of the resident, and means for adjusting the priority of presenting the list of tasks according to the resident's environment and reducing stress. This enables flexible task management that responds to the user's emotional state.

[0802] "Communication means" refers to the intermediary used to obtain information from data collection devices, and plays a role in collecting information through a network.

[0803] A "data aggregation device" is a device that collects and stores information, and provides that information to a server via communication means.

[0804] "Means of acquiring information" refers to devices that have the function of extracting necessary information from data collection equipment and play the first step in information gathering.

[0805] A "central processing unit" is a central device that efficiently processes and analyzes collected information and generates it in a state that can be used by other devices and engines.

[0806] An "intelligent engine" refers to an artificial computing system that analyzes collected information and makes decisions based on the results, particularly influencing the determination of priorities.

[0807] The "emotional engine" is an analytical system that has the function of identifying and sensing changes in the emotional state of residents, and measuring the emotional state of each individual.

[0808] The "task list" is a list of tasks whose priority has been determined based on the results of analysis by an intelligent engine, and it is a means for users to efficiently manage their daily work by referring to it.

[0809] "Means for adjusting the priority of presenting the list of tasks according to the resident's environment" refers to a function that takes into consideration the user's emotional state and environmental circumstances, by changing the order in which the list of tasks is presented, thereby preventing excessive burden on the user.

[0810] The system of this invention is designed to streamline the busy daily lives of users and includes communication means, data collection devices, a central processing unit, an intelligent engine, and an emotion engine.

[0811] The server collects data from various sources using communication methods. This information is gathered at a central processing unit via data aggregation devices, where an intelligent engine analyzes it. This analysis generates a list of tasks that take priority into account. In this process, the intelligent engine uses text mining techniques to analyze the information and determine the optimal order of tasks.

[0812] Furthermore, the server uses an emotion engine to evaluate the user's emotional state in real time and adjust the list of tasks accordingly. This process is designed to minimize the mental burden on the user when performing each task. Software such as TensorFlow and Google Cloud Natural Language API are used for data analysis and adjustment performed by the intelligent engine and emotion engine.

[0813] As a concrete example, if it's the time of day when the user is relaxing, such as after dinner, the system can re-evaluate task priorities and, if necessary, prioritize suggesting entertainment or relaxation-related activities. In this case, the system would input a prompt message like the following into the AI ​​model to suggest a course of action: "Based on User A's current emotional state, postpone low-priority tasks and prioritize relaxation tasks (e.g., playing music)."

[0814] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0815] Step 1:

[0816] The server collects information from data aggregation devices via communication methods. Specifically, it retrieves data from mail servers, messaging platforms, calendar services, etc., via APIs. In this process, the input is data from these information sources, and the output is an integrated database-formatted dataset.

[0817] Step 2:

[0818] The server sends the integrated data to a central processing unit for analysis by an intelligent engine. Here, text mining techniques are used to analyze the data and determine the importance and urgency of the tasks. The input is the dataset from the previous step. The output is the priority of each task obtained through the analysis.

[0819] Step 3:

[0820] The server operates an emotion engine to recognize the user's emotional state. Specifically, it inputs and analyzes operation logs and subjective user data to quantify the user's emotions. The input in this step is an emotion index obtained from the user interface, and the output is the user's current emotional state.

[0821] Step 4:

[0822] The server integrates the analysis results from the intelligent engine and the recognition results from the emotion engine to generate a task list. This task list is a task list with adjusted priorities and is organized in a user-friendly format. The output is the adjusted task list.

[0823] Step 5:

[0824] The terminal displays the generated list of tasks on the user's display device. Users can view this list in real time, managing their daily tasks while understanding task priorities and schedules. The output here is a task list presented visually to the user.

[0825] Step 6:

[0826] The user performs tasks based on the displayed list of tasks and provides feedback to the server through the interface. The input is the user's actions and feedback, and this information is used to further improve the learning structure. The output is the updated learning model.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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."

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] The following is further disclosed regarding the embodiments described above.

[0849] (Claim 1)

[0850] A means of collecting data from an information processing device via a communication medium,

[0851] Means for integrating data acquired from the aforementioned information processing device into a central processing device,

[0852] The means comprising an artificial intelligence engine for analyzing the integrated data in the central processing unit,

[0853] A means for determining priority based on analysis results and generating a task list,

[0854] Means for displaying the aforementioned task list on the user interface,

[0855] A means for recording feedback received from the user interface and updating the learning model,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the means for collecting data via the communication medium is means for extracting data from an information processing device based on a scheduled task.

[0859] (Claim 3)

[0860] The system according to claim 1, wherein the means for generating the task list includes means for analyzing the integrated data using text mining techniques.

[0861] "Example 1"

[0862] (Claim 1)

[0863] A means of collecting electronic information from multiple sources via a communication medium,

[0864] Means for converting the aforementioned electronic information into a unified format and storing it on a recording medium,

[0865] A means for analyzing electronic information stored on the recording medium using machine learning technology,

[0866] A means of determining priorities based on the analysis results and creating a work instruction sheet,

[0867] A means for displaying the aforementioned work instruction sheet on a user interaction screen,

[0868] A means for recording the user's operation results received from the aforementioned dialogue screen and for reconstructing a machine learning model,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, wherein the means for collecting data via the communication medium is means for selecting data from information sources based on scheduled tasks.

[0872] (Claim 3)

[0873] The system according to claim 1, wherein the means for creating the aforementioned work instruction sheet includes means for analyzing unified electronic information using natural language processing technology.

[0874] "Application Example 1"

[0875] (Claim 1)

[0876] A means of collecting data from an information processing device via a communication medium,

[0877] Means for integrating data acquired from the aforementioned information processing device into a central processing device,

[0878] The means comprising an artificial intelligence engine for analyzing the integrated data in the central processing unit,

[0879] A means for determining priority based on analysis results and generating a task list,

[0880] Means for displaying the aforementioned task list on the user interface,

[0881] A means for recording feedback received from the user interface and updating the learning model,

[0882] A means for analyzing the importance of requirements related to e-commerce and generating reminders,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, wherein the means for collecting data via the communication medium is means for extracting data from an information processing device based on a scheduled task.

[0886] (Claim 3)

[0887] The system according to claim 1, wherein the means for generating the task list includes means for analyzing the integrated data using text mining techniques.

[0888] "Example 2 of combining an emotion engine"

[0889] (Claim 1)

[0890] A means of collecting data from an information processing device via a communication medium,

[0891] Means for integrating data acquired from the aforementioned information processing device into a central processing device,

[0892] The means includes an artificial intelligence engine for analyzing the data integrated in the central processing unit using text mining technology,

[0893] A means to determine priorities and generate a task list while considering the user's emotional state based on the analysis results,

[0894] A means for displaying the aforementioned task list on the user interface and providing information according to the emotional state,

[0895] A means for recording feedback received from the user interface and updating the learning model of the central processing unit,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, wherein the means for collecting data via the communication medium is a means for extracting data from an information processing device based on a predetermined schedule.

[0899] (Claim 3)

[0900] The system according to claim 1, wherein the means for generating the task list includes means for recognizing the user's emotional state and adjusting the method of presenting tasks.

[0901] "Application example 2 when combining with an emotional engine"

[0902] (Claim 1)

[0903] A means of acquiring information from a data collection device via a communication means,

[0904] A means for collecting information obtained from the aforementioned data collection device into a central processing device,

[0905] A means comprising an intelligent engine for analyzing information collected by the aforementioned central processing device,

[0906] A means of determining priorities based on the analysis results and creating a list of tasks,

[0907] A means for displaying the aforementioned list of tasks on the user's display device,

[0908] A means for recording the response received from the user's display device and improving the learning structure,

[0909] A means of constructing a list of tasks according to the emotional state of the resident, equipped with an emotion engine for recognizing emotional states,

[0910] Presenting a list of tasks tailored to the resident's environment, adjusting the priority, and using this as a means to reduce stress,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, wherein the means for acquiring information via the aforementioned communication means is a means for selecting data from an information processing device based on a scheduled task.

[0914] (Claim 3)

[0915] The system according to claim 1, wherein the means for generating the aforementioned list of tasks includes means for analyzing the collected information using text mining technology. [Explanation of Symbols]

[0916] 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 collecting data from an information processing device via a communication medium, Means for integrating data acquired from the aforementioned information processing device into a central processing device, The means comprising an artificial intelligence engine for analyzing the integrated data in the central processing unit, A means for determining priority based on analysis results and generating a task list, Means for displaying the aforementioned task list on the user interface, A means for recording feedback received from the user interface and updating the learning model, A means for analyzing the importance of requirements related to e-commerce and generating reminders, A system that includes this.

2. The system according to claim 1, wherein the means for collecting data via the communication medium is means for extracting data from an information processing device based on a scheduled task.

3. The system according to claim 1, wherein the means for generating the task list includes means for analyzing the integrated data using text mining techniques.

Images