system

Abstract

Provide a system. 【Solution means】 Means for collecting information from multiple information sources, Means for analyzing the collected information and formatting it into a common format, Means for automatically generating tasks based on the analyzed information, Means for assigning priorities to the generated tasks, Means for tracking the progress of tasks in real time, Means for notifying the user of reminders, Means for analyzing the integrated information and improving public affairs management, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a conventional business environment, it is difficult to integrally manage information from multiple information sources, which often results in overlooking tasks or omissions. Also, task prioritization and progress tracking are often performed manually, which is a factor hindering productivity improvement. The object of this invention is to solve these problems and provide efficient task management to users through automatic collection and analysis of information and task generation.

Means for Solving the Problems

[0005] The present invention comprises means for collecting information from multiple information sources, means for analyzing the collected information and converting it into a common format, and means for automatically generating tasks based on the analyzed information. Furthermore, the system includes means for assigning priorities to the generated tasks, tracking task progress in real time, and notifying the user of reminders. This provides the user with an environment that prevents overlooking tasks and allows for efficient task management.

[0006] A "source of information" is an entity or system used to obtain data or information, including email, chat, and telephone.

[0007] "Means of information gathering" refers to the processes and mechanisms that acquire necessary data from multiple sources and prepare it for subsequent processing within the system.

[0008] "Methods for analyzing information" refer to the process of analyzing collected data and extracting important elements and patterns.

[0009] "Standardization to a common format" is a procedure that converts data in different formats into a unified data structure, enabling systems to process data efficiently.

[0010] "Methods for automatically generating tasks" refer to the process of generating tasks using rules or algorithms based on analyzed data.

[0011] "Methods for assigning priorities" refer to the process of setting priorities for generated tasks according to their importance and urgency.

[0012] "Methods for tracking progress in real time" refers to processes that allow for constant monitoring of task progress and status, enabling immediate understanding of the latest status.

[0013] "Method of notifying reminders" refers to the process of sending notifications to users at a specified date and time to inform them of the due date of a task or event. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a 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.

[0018] 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.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

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

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to an information processing system for achieving efficient task management. The system acquires information from multiple information sources used by the user in their daily work, such as email, chat, and telephone. With the user's permission, the server can utilize the APIs of these platforms to collect new messages and notifications.

[0036] After the information is collected, the server begins analyzing the data. The analysis process extracts task-related keywords and deadline information from email bodies and chat messages. This information is then converted into a common format and stored in a database.

[0037] Based on stored information, a task generation AI automatically generates tasks. This AI analyzes the collected data to identify the actions the user should take. Tasks are also prioritized according to their urgency and importance. To enable users to manage tasks efficiently, task progress is tracked in real time, and notifications are sent to the device as needed. The device displays the task list through the user interface and provides reminder notifications.

[0038] As a concrete example, consider a scenario where a user receives a new email. The server analyzes the email and automatically generates a task such as, "Please send the meeting materials by next Tuesday." The generated task is registered in the database under the title "Document Creation," and its progress is updated continuously on the user's terminal. This allows the user to complete the task without missing the deadline.

[0039] This invention functions as a comprehensive system for users to efficiently manage their work tasks and improve productivity. By utilizing this system, it is expected that tasks will not be overlooked, and a work style that reduces stress will be realized.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server uses APIs to access various information sources (e.g., email servers and chat applications) to retrieve users' pending messages and notifications. The server then stores this data in temporary storage.

[0043] Step 2:

[0044] The server analyzes the acquired information using machine learning algorithms or rule-based analysis engines to extract keywords and deadline information related to the task. Natural language processing techniques are used to accurately extract contextually relevant information.

[0045] Step 3:

[0046] The server converts the analyzed data into a common format and determines the task title, description, due date, sender information, etc. This standardized data is then stored in a database.

[0047] Step 4:

[0048] The generation AI automatically generates tasks based on stored data. The content and priority of the tasks are set based on the user's past behavior history and the importance of the tasks.

[0049] Step 5:

[0050] The server assigns priorities to the generated tasks. The criteria for prioritization include the task's deadline, importance, and the user's workload.

[0051] Step 6:

[0052] The server monitors and updates the task's progress in real time. It sets flags to notify the user based on changes in progress.

[0053] Step 7:

[0054] The device receives notifications from the server and displays them as a task list in the user interface. Here, the tasks are presented in a visually organized format, allowing users to easily check their details and priorities.

[0055] Step 8:

[0056] When a user completes or updates a task, that information is sent to the server via the device. The server updates the task status in the database based on the received information.

[0057] Step 9:

[0058] The server periodically archives completed tasks and generates progress reports as needed. These reports serve as reference material for users to review past work.

[0059] (Example 1)

[0060] 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."

[0061] In today's information environment, users need to manage a wide range of data from various sources. However, manually organizing this information and efficiently converting it into tasks requires considerable effort and time. Therefore, there is a need for systems that automate information collection, analysis, and task creation, enabling efficient and prioritized management.

[0062] 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.

[0063] In this invention, the server includes means for aggregating data from multiple information media, means for analyzing the aggregated data and converting it into a unified format, and means for automatically generating tasks based on the analyzed data. This enables users to streamline information management and perform important tasks without omission.

[0064] "Information media" refers to multiple sources of information that users use for work, such as email, chat messages, and phone records.

[0065] "Data aggregation" refers to the process of automatically collecting information from different information sources and consolidating it in one place.

[0066] "Data analysis" refers to the process of using collected information to extract keywords and deadline information related to a task.

[0067] A "unified format" refers to a format used to convert data from different formats into a consistent format and store it in an easy-to-use manner.

[0068] "Task generation" refers to the process of automatically generating tasks that users should perform based on analyzed information.

[0069] "Prioritizing tasks" refers to a method of determining the order in which each generated task is performed, based on its importance and urgency.

[0070] "Progress tracking" refers to the process of monitoring the progress of ongoing tasks in real time and updating it as needed.

[0071] "Sending notifications" refers to the act of a system promptly informing a user of important tasks and deadline reminders.

[0072] This invention is implemented by an information processing device that performs efficient information management and task generation. The server, with user permission, automatically aggregates data from multiple information sources such as email, chat applications, and telephone. The APIs of each information source are used for data aggregation; for example, a common API is used for email.

[0073] The server analyzes the aggregated data using a natural language processing library (e.g., spaCy or NLTK) to extract important keywords and deadline information. It then converts the extracted information into a unified format and saves it to a database server (e.g., PostgreSQL).

[0074] The generative AI automatically generates tasks using stored information. In this process, the generative AI model (e.g., a GPT-based model) identifies the specific task content according to prompts. The generated tasks are assigned priorities and managed on the server.

[0075] The device displays a task list on the user's screen based on information sent from the server. The user can review the displayed task list and perform the necessary tasks. For urgent tasks, the device sends a notification to the user using a notification API (e.g., Firebase Cloud Messaging).

[0076] As a concrete example, when a user receives a new email, the server analyzes its contents and automatically generates a task such as, "Please submit the project report by next Tuesday." The generated task is registered in the database with the title "Report Creation," and its progress is updated in real time on the user's device. This system ensures that users do not miss important tasks. Another example of a prompt message to the generating AI model is, "Extract meeting material creation tasks from received emails and prioritize them based on their deadlines."

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

[0078] Step 1:

[0079] The server aggregates data from multiple information sources related to the user (email, chat, phone, etc.). The input consists of new messages and notifications provided by these information sources. The server automatically collects this data using the APIs of each platform and stores it as an initial dataset. The output is a collection of unanalyzed messages.

[0080] Step 2:

[0081] The server analyzes the aggregated data. The input is the previously unanalyzed set of messages. Specifically, it uses a natural language processing library (e.g., spaCy or NLTK) to analyze the message content and extract keywords and deadline information related to the task. The server converts these analysis results into a unified format and generates the converted data as output.

[0082] Step 3:

[0083] The generative AI automatically generates tasks based on the transformed data. The input is the transformed data obtained in step 2. The generative AI model (e.g., a GPT-based model) follows the prompts, analyzes the data, and determines the details of specific tasks. The output is a task with its content identified. The generated tasks are assigned priorities based on importance and urgency.

[0084] Step 4:

[0085] The device notifies the user of generated tasks and displays a task list. The input is task information sent from the server. The device uses a notification API (e.g., Firebase Cloud Messaging) to send important task and deadline reminders to the user. The output is the task list and notifications presented to the user.

[0086] Step 5:

[0087] The user checks the task list displayed on the device and performs the necessary actions. The input is the task list displayed on the device. The user works based on this and updates the task progress manually or automatically. The output is a list of completed tasks and a record of their progress.

[0088] (Application Example 1)

[0089] 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."

[0090] In modern urban environments, information overload and inadequate task management are major problems, making it difficult for citizens to select and efficiently utilize the vast amount of information they receive. Therefore, a system is needed to effectively manage information and appropriately break it down into tasks in order to improve citizen services and enhance the quality of life for individuals.

[0091] 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.

[0092] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, and means for improving public affairs management based on the analyzed information. This enables the automation of tasks necessary for citizens' lives and improves services through efficient information utilization.

[0093] "Means of collecting information from multiple sources" refers to system components that aggregate information from different types of communication methods and data sources.

[0094] "Means for analyzing collected information and creating a common format" refers to technologies that analyze acquired information and convert it into a unified format.

[0095] "A means of automatically generating tasks based on analyzed information" refers to a system that automatically creates work items to optimize user behavior based on collected data.

[0096] "Means for assigning priorities to generated tasks" refers to a mechanism that determines the processing order of automatically generated tasks based on their urgency and importance.

[0097] "A means of tracking task progress in real time" refers to a system that allows for immediate confirmation of the status of ongoing work.

[0098] "Means of notifying users of reminders" refers to a function that sends alerts to users at specified times to prompt them to check on their work or pay attention to it.

[0099] "Means for analyzing integrated information and improving public administration" refers to methods that comprehensively analyze multiple pieces of information to enable efficient service provision to citizens.

[0100] To realize this invention, the server first collects data from multiple sources, such as email servers, chat systems, and other digital information providers, using communication means. This includes, for example, the use of APIs and cloud services to establish database connections. The server can securely and efficiently aggregate this data using Google Cloud Platform or Amazon Web Services (AWS).

[0101] Next, the server is responsible for analyzing the collected information and converting it into a common format. In this process, Natural Language Processing (NLP) technology is used, along with the Google Natural Language API and similar text analysis engines, to extract keywords and date information from the data and store it as structured data.

[0102] Next, tasks are automatically generated based on these analyses, and a generation AI model, such as GPT, is used to organize the necessary details and instructions for each task. Tasks are also prioritized according to their importance and urgency. The server aims to highly automate this process and improve the efficiency of urban public services. The generated tasks are managed by a database management system such as AWS DynamoDB.

[0103] The user's device, such as a smartphone application or tablet, tracks progress in real time and sends reminders to the user as needed. This allows users to efficiently receive information about public services and take timely action.

[0104] As a concrete example, consider notifications for library events. For instance, if information about a "children's reading group" event becomes available within a user-specified area, the system analyzes this information and automatically generates a task to attend the event. The generated task then sends a reminder to the user's mobile device before the specified date and time to facilitate preparation for participation.

[0105] An example of a prompt is, "Generate meeting and event attendance tasks based on announcements from the city hall. Ensure the prompt includes specific keywords and deadlines." This helps the AI ​​identify the components of a specific task.

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server collects data from its sources. Specifically, it connects to APIs of mail servers and chat platforms to retrieve new messages and notifications. Inputs include API credentials and the connection URL. Outputs are notifications and messages in raw data format. The server temporarily stores this information in local storage.

[0109] Step 2:

[0110] The server analyzes the collected data and converts it into a common format. Here, Natural Language Processing (NLP) technology is used to extract keywords and deadline information from email bodies and chat messages. The input is the collected raw data, and the output is structured data (e.g., task information, deadlines, priorities, etc.). The server performs the analysis using tools such as the Google Natural Language API and stores the processed data in a database.

[0111] Step 3:

[0112] The server automatically generates tasks using an AI model based on structured data. The input is the structured data obtained in step 2. The AI ​​model analyzes this data and creates specific tasks. The output includes the title, content, and deadline of the automatically generated tasks. The task information is stored in the database as a list that can be prioritized.

[0113] Step 4:

[0114] The server assigns priorities to the generated tasks. The input is the task information generated in step 3, and the output is a prioritized task list. The server compares urgency and importance parameters and sets an appropriate priority for each task. This ensures that the most important tasks appear at the top of the list.

[0115] Step 5:

[0116] The terminal tracks task progress in real time and notifies the user with reminders. Inputs include update information sent from the server and the user's task progress data. Outputs are a task list and notifications displayed to the user. The terminal shows the user progress and the next steps through the application. The reminder function prevents users from missing tasks by issuing alerts just before deadlines.

[0117] Step 6:

[0118] Users manage tasks through their devices and send progress reports to the server. Inputs are the current task status and user input data, while output is updated progress information. Users can report task completion and adjust progress within the app. The server receives this information and updates the task status in the database.

[0119] These processing steps automate tasks necessary for citizens' daily lives and improve public services through efficient information utilization.

[0120] 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.

[0121] This invention combines a task management function with an emotion recognition function to achieve flexible task management that responds to the user's emotional state. The system consists of modules for information gathering, analysis, task generation, and emotion recognition.

[0122] First, the server automatically collects user information from email, chat, and other communication tools. The collected information is analyzed by the server and converted into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0123] The generated tasks are tracked by the server, and reminders are sent to the user's device as needed. Here, the emotion engine is integrated into the entire system and is responsible for recognizing the user's emotional state. The emotion engine collects emotional data (e.g., data from facial recognition and voice analysis) through the device interface and sends it to the server.

[0124] The server uses data from the emotion engine to dynamically change the priority of generated tasks. For example, if a user is feeling stressed, the server can slow down the pace of tasks or adjust the frequency of reminders. Furthermore, based on the emotions identified by the emotion engine, relaxing tasks or new tasks are suggested.

[0125] As a concrete example, if a user experiences stress during their daily work, the emotion engine detects this. The server temporarily lowers the priority of their regular work tasks, suggests a short, relaxing break task, and notifies the user's terminal. In this way, task management that takes the user's emotional state into consideration becomes possible.

[0126] This invention allows users to experience effective task management tailored to their own emotions. It enables them to maintain work efficiency, reduce stress, and improve their work style.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server retrieves new messages and notifications from the mail server and chat application with the user's permission. The retrieved information is temporarily stored in a database.

[0130] Step 2:

[0131] The server uses natural language processing technology to analyze the stored messages and extract task-related information and deadlines. The analysis results are then formatted into a common format and stored in a database.

[0132] Step 3:

[0133] The generation AI automatically generates tasks that the user needs, based on formatted data. The generated tasks include a title, due date, and description.

[0134] Step 4:

[0135] The server assigns priorities to the generated tasks. Priorities are set considering the importance and urgency of each task.

[0136] Step 5:

[0137] The user's device uses an emotion engine to collect emotional data from the user's voice and facial expressions. The collected emotional data is sent to the server in real time.

[0138] Step 6:

[0139] The server analyzes the received emotional data to identify the user's emotional state. Based on the emotional state, task priorities and reminder frequencies are dynamically adjusted.

[0140] Step 7:

[0141] The device displays the current task list and adjusted priorities through the user interface. The user is notified of new tasks and reminders.

[0142] Step 8:

[0143] When a user completes or updates a task, they send that information to the server via their device. The server then reflects the received information in its database and updates the task's progress.

[0144] Step 9:

[0145] The server archives completed tasks and generates progress reports that take into account changes in sentiment. These reports are provided in a format usable on the user's terminal.

[0146] (Example 2)

[0147] 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".

[0148] In modern society, stress management and efficient work performance in the work environment are crucial issues. However, existing task management systems determine task priorities using static methods without considering individual emotional states, and therefore fail to adequately address user stress reduction and the realization of flexible work styles. This leads to problems such as decreased work efficiency and the accumulation of mental fatigue.

[0149] 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.

[0150] In this invention, the server includes means for collecting data from multiple communication means, means for analyzing the collected data and converting it into a unified format, and means for recognizing an individual's emotional state. This enables flexible and efficient task management tailored to an individual's emotional state, thereby reducing work-related stress and improving productivity.

[0151] "Communication methods" refer to the interfaces and protocols used throughout a system for sending and receiving data.

[0152] "Data" refers to information necessary for the operation of the task management system, and includes information obtained in the form of emails, chat content, audio, facial expressions, etc.

[0153] "Analysis" refers to the process of processing collected data according to a specific purpose to understand its meaning and trends.

[0154] A "unified format" refers to a data format that converts data collected in different formats into a form that can be processed consistently.

[0155] "Tasks" refer to tasks or activities generated within this system that users are required to perform.

[0156] "Priority" refers to a ranking of tasks based on their importance and urgency.

[0157] "Emotional state" refers to a specific state that describes a user's psychological and emotional condition and is evaluated using emotion recognition technology.

[0158] "Emotion recognition" refers to technology that estimates a user's emotions and psychological state based on their facial expressions, voice, and text.

[0159] "Continuous tracking" refers to the process of monitoring the progress of a task in real time or periodically, and keeping that status up-to-date.

[0160] "Notification" refers to the act of presenting users with information or reminders about tasks.

[0161] This invention is a system for achieving flexible task management while taking into account the user's emotional state. Its implementation revolves around three key elements: the server, the terminal, and the user.

[0162] The server collects user data from email, chat, and other means of communication. APIs and communication protocols are used for data collection. For example, the IMAP protocol can be used to collect email data.

[0163] The collected data is analyzed on the server using natural language processing. Specifically, the Python NLTK library is used to convert the data into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0164] The device plays a role in collecting emotional data from the user. The OpenCV library is used for facial recognition, analyzing the user's facial expressions via the camera and estimating their emotions. It also uses the microphone and the Google Speech-to-Text API to evaluate emotions from speech. The emotional data collected by the device is sent to a server, which then dynamically adjusts task priorities based on this data.

[0165] For example, when a user experiences stress at work, the emotion engine can detect this. The server takes this high-stress state into account, lowers the priority of normal tasks, suggests relaxing tasks such as "5 minutes of meditation," and sends a notification to the user.

[0166] An example of a prompt message for a generative AI model is: "Please set appropriate task priorities based on the user's perceived stress level. The current stress level is high, so please suggest relaxation tasks."

[0167] This system allows users to enjoy task management tailored to their emotional state, enabling them to improve their work style and reduce stress.

[0168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0169] Step 1:

[0170] The server collects data from communication methods such as email and chat. Input includes email and message data via the IMAP protocol and APIs. This unstructured data is ingested by the server into the system. Since the collected data is not directly usable, data cleaning and format conversion are performed.

[0171] Step 2:

[0172] The server analyzes the collected data using natural language processing (NLTK) techniques. The input is unstructured text data. The NLTK library in Python is used for analysis, including key phrase extraction and sentiment analysis. This results in structured data in a common format. The data is then converted to a unified format and recorded in a digital database.

[0173] Step 3:

[0174] The server automatically generates and prioritizes tasks based on formatted data. The input is structured data. The server assesses the importance and urgency of the tasks and stores this information in a database. The generated tasks are then prioritized by an AI model based on specific criteria.

[0175] Step 4:

[0176] The device collects user emotion data through its camera and microphone. The input is raw user data (facial expressions, voice), which is then analyzed using OpenCV or the Google Speech-to-Text API. The analyzed emotion data is output as the user's emotional state. This data is used to monitor the user's psychological state.

[0177] Step 5:

[0178] The server dynamically adjusts task priorities based on the user's emotional data. The input is data on the user's emotional state. If stress is detected, the server lowers the priority of existing tasks and presents new tasks with a relaxing effect. As a result, information on the adjusted tasks is output and notified to the user.

[0179] Through the above processing steps, users can manage tasks flexibly according to their emotions and reduce stress.

[0180] (Application Example 2)

[0181] 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."

[0182] In recent years, task management systems have become highly sophisticated, but they often prioritize scheduling efficiency without considering the user's emotional state. As a result, users may experience increased stress due to excessive task allocation or inappropriate prioritization that disregards their mental health. To address this problem, there is a need for dynamic task management based on the user's emotional state and flexible task adjustments that take the user's mental health into consideration.

[0183] 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.

[0184] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, means for automatically generating tasks based on the analyzed information and dynamically adjusting their priorities, and means for identifying the user's emotional state and recommending appropriate tasks according to that state. This enables task management that takes the user's emotional state into account, reducing emotional burden while maintaining and improving productivity.

[0185] "Information sources" refer to systems and media, including email, chat, and other communication tools, that provide data about users.

[0186] "Information analysis" is the process of processing collected information and converting it into a data format suitable for a specific purpose.

[0187] "Standardization of data into a common format" refers to unifying data obtained from different sources into a consistent format.

[0188] "Automatically generating tasks" means automatically creating specific work items that are tailored to the user's actions and schedule, based on the analyzed information.

[0189] "Prioritizing tasks" means determining the order and schedule of execution based on the importance and urgency of the tasks that have been generated.

[0190] "Tracking task progress" is the process of monitoring and verifying whether the assigned tasks are progressing according to plan.

[0191] "Sending a reminder" means sending a notification to the user to inform them of the task's completion time and deadline.

[0192] "Identifying emotional states" is the process of detecting emotions from a user's facial expressions and voice to understand their mental state.

[0193] "Dynamic adjustment" means changing the priority and content of tasks in real time in response to changes in circumstances and conditions.

[0194] "Recommending appropriate tasks" means suggesting the most efficient and beneficial activities based on the user's current situation.

[0195] The system for carrying out this invention mainly consists of multiple modules. The server uses an information gathering module to obtain user information from email, chat, and other communication tools. This information is processed by an analysis module and converted into a common format.

[0196] Next, the task generation module automatically generates tasks based on standardized data and assigns them priorities. The progress of the generated tasks is tracked in real time by the progress management module, and reminders are sent to the user's device as needed.

[0197] The emotion recognition module is responsible for identifying the user's emotional state in real time. This module analyzes the user's facial expressions and voice through interfaces such as the device's camera and microphone, and sends the data to the server as emotion data. Based on this data, the server dynamically adjusts task priorities and suggests tasks that promote relaxation according to the user's situation.

[0198] For example, if the server determines that a user is experiencing excessive stress, it automatically adjusts task priorities and notifies the user's device of light tasks for short breaks or refreshment. In this way, users can flexibly manage and execute tasks according to their own emotional state.

[0199] The generative AI model supports task recommendations and adjustments based on the user's emotional state. An example of a prompt would be, "Based on the user's current emotional state, please suggest the most appropriate next task." This enables more comfortable and efficient task management for the user.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server automatically retrieves user information from communication tools such as email and chat using multiple information gathering modules. In this process, the server sends requests from individual data sources and temporarily stores the information received. Input data consists of messages and events from each communication tool, while output data is unformatted text information.

[0203] Step 2:

[0204] The server processes the acquired information using an analysis module and converts it into a common format. This step uses natural language processing techniques to extract meaning from the text and organize it into a format that conforms to the database schema. The input is unformatted text information, and the output is organized data.

[0205] Step 3:

[0206] Based on the organized data, the server automatically generates tasks for the user using a task generation module. In this step, a generation AI model analyzes past task history and user trends to generate new tasks. The input is organized data, and the output is newly generated task information.

[0207] Step 4:

[0208] The server assigns priorities to the generated tasks and incorporates them into the schedule. The input here is task information, and the output is a task list with assigned priorities. In this process, priorities are determined based on the importance and deadlines of the user's work.

[0209] Step 5:

[0210] The device detects the user's emotional state using an emotion recognition module. It analyzes facial expressions and voice tone using the device's camera and microphone. The input for this step is camera video and audio data, and the output is estimated emotion data.

[0211] Step 6:

[0212] The server receives emotional data and dynamically adjusts task priorities. In this step, it re-evaluates the order of tasks based on the emotional state and suggests breaks or lighter tasks as needed. The inputs are emotional data and a task list, and the output is the adjusted task schedule.

[0213] Step 7:

[0214] The device that notifies the user displays a dynamically adjusted task schedule and sends reminders as needed. The input to this process is the adjusted task schedule, and the output is a notification message to the user.

[0215] Step 8:

[0216] The server tracks the progress of all tasks until they are completed. A progress management module updates the status hourly and archives completed tasks. The input is the task progress, and the output is archived tasks and progress reports.

[0217] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search)<url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

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

[0220] [Second Embodiment]

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

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0233] This invention relates to an information processing system for achieving efficient task management. The system acquires information from multiple information sources used by the user in their daily work, such as email, chat, and telephone. With the user's permission, the server can utilize the APIs of these platforms to collect new messages and notifications.

[0234] After the information is collected, the server begins analyzing the data. The analysis process extracts task-related keywords and deadline information from email bodies and chat messages. This information is then converted into a common format and stored in a database.

[0235] Based on stored information, a task generation AI automatically generates tasks. This AI analyzes the collected data to identify the actions the user should take. Tasks are also prioritized according to their urgency and importance. To enable users to manage tasks efficiently, task progress is tracked in real time, and notifications are sent to the device as needed. The device displays the task list through the user interface and provides reminder notifications.

[0236] As a concrete example, consider a scenario where a user receives a new email. The server analyzes the email and automatically generates a task such as, "Please send the meeting materials by next Tuesday." The generated task is registered in the database under the title "Document Creation," and its progress is updated continuously on the user's terminal. This allows the user to complete the task without missing the deadline.

[0237] This invention functions as a comprehensive system for users to efficiently manage their work tasks and improve productivity. By utilizing this system, it is expected that tasks will not be overlooked, and a work style that reduces stress will be realized.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server uses APIs to access various information sources (e.g., email servers and chat applications) to retrieve users' pending messages and notifications. The server then stores this data in temporary storage.

[0241] Step 2:

[0242] The server analyzes the acquired information using machine learning algorithms or rule-based analysis engines to extract keywords and deadline information related to the task. Natural language processing techniques are used to accurately extract contextually relevant information.

[0243] Step 3:

[0244] The server converts the analyzed data into a common format and determines the task title, description, due date, sender information, etc. This standardized data is then stored in a database.

[0245] Step 4:

[0246] The generation AI automatically generates tasks based on stored data. The content and priority of the tasks are set based on the user's past behavior history and the importance of the tasks.

[0247] Step 5:

[0248] The server assigns priorities to the generated tasks. The criteria for prioritization include the task's deadline, importance, and the user's workload.

[0249] Step 6:

[0250] The server monitors and updates the task's progress in real time. It sets flags to notify the user based on changes in progress.

[0251] Step 7:

[0252] The device receives notifications from the server and displays them as a task list in the user interface. Here, the tasks are presented in a visually organized format, allowing users to easily check their details and priorities.

[0253] Step 8:

[0254] When a user completes or updates a task, that information is sent to the server via the device. The server updates the task status in the database based on the received information.

[0255] Step 9:

[0256] The server periodically archives completed tasks and generates progress reports as needed. These reports serve as reference material for users to review past work.

[0257] (Example 1)

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

[0259] In today's information environment, users need to manage a wide range of data from various sources. However, manually organizing this information and efficiently converting it into tasks requires considerable effort and time. Therefore, there is a need for systems that automate information collection, analysis, and task creation, enabling efficient and prioritized management.

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

[0261] In this invention, the server includes means for aggregating data from multiple information media, means for analyzing the aggregated data and converting it into a unified format, and means for automatically generating tasks based on the analyzed data. This enables users to streamline information management and perform important tasks without omission.

[0262] "Information media" refers to multiple sources of information that users utilize in their work, such as email, chat messages, and phone records.

[0263] "Data aggregation" refers to the process of automatically collecting information from different information sources and consolidating it in one place.

[0264] "Data analysis" refers to the process of using collected information to extract keywords and deadline information related to a task.

[0265] A "unified format" refers to a format used to convert data from different formats into a consistent format and store it in an easy-to-use manner.

[0266] "Task generation" refers to the process of automatically generating tasks that users should perform based on analyzed information.

[0267] "Prioritizing tasks" refers to a method of determining the order in which each generated task is performed, based on its importance and urgency.

[0268] "Progress tracking" refers to the process of monitoring the progress of ongoing tasks in real time and updating it as needed.

[0269] "Sending notifications" refers to the act of a system promptly informing a user of important tasks and deadline reminders.

[0270] This invention is implemented by an information processing device that performs efficient information management and task generation. The server, with user permission, automatically aggregates data from multiple information sources such as email, chat applications, and telephone. The APIs of each information source are used for data aggregation; for example, a common API is used for email.

[0271] The server analyzes the aggregated data using a natural language processing library (e.g., spaCy or NLTK) to extract important keywords and deadline information. It then converts the extracted information into a unified format and saves it to a database server (e.g., PostgreSQL).

[0272] The generative AI automatically generates tasks using stored information. In this process, the generative AI model (e.g., a GPT-based model) identifies the specific task content according to prompts. The generated tasks are assigned priorities and managed on the server.

[0273] The device displays a task list on the user's screen based on information sent from the server. The user can review the displayed task list and perform the necessary tasks. For urgent tasks, the device sends a notification to the user using a notification API (e.g., Firebase Cloud Messaging).

[0274] As a concrete example, when a user receives a new email, the server analyzes its contents and automatically generates a task such as, "Please submit the project report by next Tuesday." The generated task is registered in the database with the title "Report Creation," and its progress is updated in real time on the user's device. This system ensures that users do not miss important tasks. Another example of a prompt message to the generating AI model is, "Extract meeting material creation tasks from received emails and prioritize them based on their deadlines."

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The server aggregates data from multiple information sources related to the user (email, chat, phone, etc.). The input consists of new messages and notifications provided by these information sources. The server automatically collects this data using the APIs of each platform and stores it as an initial dataset. The output is a collection of unanalyzed messages.

[0278] Step 2:

[0279] The server analyzes the aggregated data. The input is the previously unanalyzed message group. Specifically, it uses a natural language processing library (e.g., spaCy or NLTK) to analyze the content of the messages and extract keyword and deadline information related to the tasks. The server converts these analysis results into a unified format and generates the converted data as output.

[0280] Step 3:

[0281] The generation AI automatically generates tasks based on the converted data. The input is the converted data obtained in Step 2. The generation AI model (e.g., GPT-based model) analyzes the data according to the prompt text to determine the details of specific tasks. The output is the tasks with specified content. The generated tasks are assigned priorities based on importance and urgency.

[0282] Step 4:

[0283] The terminal notifies the user of the generated tasks and displays a task list. The input is the task information sent from the server. The terminal uses a notification API (e.g., Firebase Cloud Messaging) to send important task and deadline reminders to the user. The output is the task list and notifications presented to the user.

[0284] [[ID=,20]]Step 5:

[0285] The user checks the task list displayed on the terminal and performs the necessary actions. The input is the task list displayed on the terminal. Based on this, the user proceeds with the work and manually or automatically updates the progress of the tasks. The output is a list of completed tasks and a record of their progress.

[0286] (Application Example 1)

[0287] 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."

[0288] In modern urban environments, information overload and inadequate task management are major problems, making it difficult for citizens to select and efficiently utilize the vast amount of information they receive. Therefore, a system is needed to effectively manage information and appropriately break it down into tasks in order to improve citizen services and enhance the quality of life for individuals.

[0289] 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.

[0290] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, and means for improving public affairs management based on the analyzed information. This enables the automation of tasks necessary for citizens' lives and improves services through efficient information utilization.

[0291] "Means of collecting information from multiple sources" refers to system components that aggregate information from different types of communication methods and data sources.

[0292] "Means for analyzing collected information and creating a common format" refers to technologies that analyze acquired information and convert it into a unified format.

[0293] "A means of automatically generating tasks based on analyzed information" refers to a system that automatically creates work items to optimize user behavior based on collected data.

[0294] "Means for assigning priorities to generated tasks" refers to a mechanism that determines the processing order of automatically generated tasks based on their urgency and importance.

[0295] "A means of tracking task progress in real time" refers to a system that allows for immediate confirmation of the status of ongoing work.

[0296] "Means of notifying users of reminders" refers to a function that sends alerts to users at specified times to prompt them to check on their work or pay attention to it.

[0297] "Means for analyzing integrated information and improving public administration" refers to methods that comprehensively analyze multiple pieces of information to enable efficient service provision to citizens.

[0298] To realize this invention, the server first collects data from multiple sources, such as email servers, chat systems, and other digital information providers, using communication means. This includes, for example, the use of APIs and cloud services to establish database connections. The server can use Google Cloud Platform or Amazon Web Services (AWS) to securely and efficiently aggregate this data.

[0299] Next, the server is responsible for analyzing the collected information and converting it into a common format. In this process, Natural Language Processing (NLP) technology is used, along with the Google Natural Language API and similar text analysis engines, to extract keywords and date information from the data and store it as structured data.

[0300] Next, tasks are automatically generated based on these analyses, and a generation AI model, such as GPT, is used to organize the necessary details and instructions for each task. Tasks are also prioritized according to their importance and urgency. The server aims to highly automate this process and improve the efficiency of urban public services. The generated tasks are managed by a database management system such as AWS DynamoDB.

[0301] The user's terminal, such as a smartphone application or a tablet terminal, tracks the progress in real time and sends reminders to the user as needed. This enables the user to efficiently receive information on public services and respond in a timely manner.

[0302] As a specific example, consider the notification of a library event. For instance, when information about an event called "Reading Club for Children" occurs within the area specified by the user, the system analyzes this information and automatically generates a task of event participation. The generated task sends a reminder to the user's mobile device before the specified date and time to facilitate preparation for participation.

[0303] An example of a prompt sentence is "Based on the notice from the city hall, please generate tasks for meetings and event participation. Make sure the prompt contains specific keywords and deadlines required." This assists the AI in identifying the components of specific tasks.

[0304] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0305] Step 1:

[0306] The server collects data from information sources. Specifically, the server connects to the APIs of mail servers and chat platforms to obtain new messages and notifications. The inputs include API credentials and connection destination URLs. The outputs are notifications and messages in raw data format. The server temporarily stores this information in local storage.

[0307] Step 2:

[0308] The server analyzes the collected data and converts it into a common format. Here, Natural Language Processing (NLP) technology is used to extract keywords and deadline information from email bodies and chat messages. The input is the collected raw data, and the output is structured data (e.g., task information, deadlines, priorities, etc.). The server performs the analysis using tools such as the Google Natural Language API and stores the processed data in a database.

[0309] Step 3:

[0310] The server automatically generates tasks using an AI model based on structured data. The input is the structured data obtained in step 2. The AI ​​model analyzes this data and creates specific tasks. The output includes the title, content, and deadline of the automatically generated tasks. The task information is stored in the database as a list that can be prioritized.

[0311] Step 4:

[0312] The server assigns priorities to the generated tasks. The input is the task information generated in step 3, and the output is a prioritized task list. The server compares urgency and importance parameters and sets an appropriate priority for each task. This ensures that the most important tasks appear at the top of the list.

[0313] Step 5:

[0314] The terminal tracks task progress in real time and notifies the user with reminders. Inputs include update information sent from the server and the user's task progress data. Outputs are a task list and notifications displayed to the user. The terminal shows the user progress and the next steps through the application. The reminder function prevents users from missing tasks by issuing alerts just before deadlines.

[0315] Step 6:

[0316] Users manage tasks through their devices and send progress reports to the server. Inputs are the current task status and user input data, while output is updated progress information. Users can report task completion and adjust progress within the app. The server receives this information and updates the task status in the database.

[0317] These processing steps automate tasks necessary for citizens' daily lives and improve public services through efficient information utilization.

[0318] 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.

[0319] This invention combines a task management function with an emotion recognition function to achieve flexible task management that responds to the user's emotional state. The system consists of modules for information gathering, analysis, task generation, and emotion recognition.

[0320] First, the server automatically collects user information from email, chat, and other communication tools. The collected information is analyzed by the server and converted into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0321] The generated tasks are tracked by the server, and reminders are sent to the user's device as needed. Here, the emotion engine is integrated into the entire system and is responsible for recognizing the user's emotional state. The emotion engine collects emotional data (e.g., data from facial recognition and voice analysis) through the device interface and sends it to the server.

[0322] The server uses data from the emotion engine to dynamically change the priority of generated tasks. For example, if a user is feeling stressed, the server can slow down the pace of tasks or adjust the frequency of reminders. Furthermore, based on the emotions identified by the emotion engine, relaxing tasks or new tasks are suggested.

[0323] As a concrete example, if a user experiences stress during their daily work, the emotion engine detects this. The server temporarily lowers the priority of their regular work tasks, suggests a short, relaxing break task, and notifies the user's terminal. In this way, task management that takes the user's emotional state into consideration becomes possible.

[0324] This invention allows users to experience effective task management tailored to their own emotions. It enables them to maintain work efficiency, reduce stress, and improve their work style.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The server retrieves new messages and notifications from the mail server and chat application with the user's permission. The retrieved information is temporarily stored in a database.

[0328] Step 2:

[0329] The server uses natural language processing technology to analyze the stored messages and extract task-related information and deadlines. The analysis results are then formatted into a common format and stored in a database.

[0330] Step 3:

[0331] The generation AI automatically generates tasks that the user needs, based on formatted data. The generated tasks include a title, due date, and description.

[0332] Step 4:

[0333] The server assigns priorities to the generated tasks. Priorities are set considering the importance and urgency of each task.

[0334] Step 5:

[0335] The user's device uses an emotion engine to collect emotional data from the user's voice and facial expressions. The collected emotional data is sent to the server in real time.

[0336] Step 6:

[0337] The server analyzes the received emotional data to identify the user's emotional state. Based on the emotional state, task priorities and reminder frequencies are dynamically adjusted.

[0338] Step 7:

[0339] The device displays the current task list and adjusted priorities through the user interface. The user is notified of new tasks and reminders.

[0340] Step 8:

[0341] When a user completes or updates a task, they send that information to the server via their device. The server then reflects the received information in its database and updates the task's progress.

[0342] Step 9:

[0343] The server archives completed tasks and generates progress reports that take into account changes in sentiment. These reports are provided in a format usable on the user's terminal.

[0344] (Example 2)

[0345] 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".

[0346] In modern society, stress management and efficient work performance in the work environment are crucial issues. However, existing task management systems determine task priorities using static methods without considering individual emotional states, and therefore fail to adequately address user stress reduction and the realization of flexible work styles. This leads to problems such as decreased work efficiency and the accumulation of mental fatigue.

[0347] 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.

[0348] In this invention, the server includes means for collecting data from multiple communication means, means for analyzing the collected data and converting it into a unified format, and means for recognizing an individual's emotional state. This enables flexible and efficient task management tailored to an individual's emotional state, thereby reducing work-related stress and improving productivity.

[0349] "Communication methods" refer to the interfaces and protocols used throughout a system for sending and receiving data.

[0350] "Data" refers to information necessary for the operation of the task management system, and includes information obtained in the form of emails, chat content, audio, facial expressions, etc.

[0351] "Analysis" refers to the process of processing collected data according to a specific purpose to understand its meaning and trends.

[0352] A "unified format" refers to a data format that converts data collected in different formats into a form that can be processed consistently.

[0353] "Tasks" refer to tasks or activities generated within this system that users are required to perform.

[0354] "Priority" refers to a ranking of tasks based on their importance and urgency.

[0355] "Emotional state" refers to a specific state that describes a user's psychological and emotional condition and is evaluated using emotion recognition technology.

[0356] "Emotion recognition" refers to technology that estimates a user's emotions and psychological state based on their facial expressions, voice, and text.

[0357] "Continuous tracking" refers to the process of monitoring the progress of a task in real time or periodically, and keeping that status up-to-date.

[0358] "Notification" refers to the act of presenting users with information or reminders about tasks.

[0359] This invention is a system for achieving flexible task management while taking into account the user's emotional state. Its implementation revolves around three key elements: the server, the terminal, and the user.

[0360] The server collects user data from email, chat, and other means of communication. APIs and communication protocols are used for data collection. For example, the IMAP protocol can be used to collect email data.

[0361] The collected data is analyzed on the server using natural language processing. Specifically, the Python NLTK library is used to convert the data into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0362] The device plays a role in collecting emotional data from the user. The OpenCV library is used for facial recognition, analyzing the user's facial expressions via the camera and estimating their emotions. It also uses the microphone and the Google Speech-to-Text API to evaluate emotions from speech. The emotional data collected by the device is sent to a server, which then dynamically adjusts task priorities based on this data.

[0363] For example, when a user experiences stress at work, the emotion engine can detect this. The server takes this high-stress state into account, lowers the priority of normal tasks, suggests relaxing tasks such as "5 minutes of meditation," and sends a notification to the user.

[0364] An example of a prompt message for a generative AI model is: "Please set appropriate task priorities based on the user's perceived stress level. The current stress level is high, so please suggest relaxation tasks."

[0365] This system allows users to enjoy task management tailored to their emotional state, enabling them to improve their work style and reduce stress.

[0366] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0367] Step 1:

[0368] The server collects data from communication methods such as email and chat. Input includes email and message data via the IMAP protocol and APIs. This unstructured data is ingested by the server into the system. Since the collected data is not directly usable, data cleaning and format conversion are performed.

[0369] Step 2:

[0370] The server analyzes the collected data using natural language processing (NLTK) techniques. The input is unstructured text data. The NLTK library in Python is used for analysis, including key phrase extraction and sentiment analysis. This results in structured data in a common format. The data is then converted to a unified format and recorded in a digital database.

[0371] Step 3:

[0372] The server automatically generates and prioritizes tasks based on formatted data. The input is structured data. The server assesses the importance and urgency of the tasks and stores this information in a database. The generated tasks are then prioritized by an AI model based on specific criteria.

[0373] Step 4:

[0374] The device collects user emotion data through its camera and microphone. The input is raw user data (facial expressions, voice), which is then analyzed using OpenCV or the Google Speech-to-Text API. The analyzed emotion data is output as the user's emotional state. This data is used to monitor the user's psychological state.

[0375] Step 5:

[0376] The server dynamically adjusts task priorities based on the user's emotional data. The input is data on the user's emotional state. If stress is detected, the server lowers the priority of existing tasks and presents new tasks with a relaxing effect. As a result, information on the adjusted tasks is output and notified to the user.

[0377] Through the above processing steps, users can manage tasks flexibly according to their emotions and reduce stress.

[0378] (Application Example 2)

[0379] 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."

[0380] In recent years, task management systems have become highly sophisticated, but they often prioritize scheduling efficiency without considering the user's emotional state. As a result, users may experience increased stress due to excessive task allocation or inappropriate prioritization that disregards their mental health. To address this problem, there is a need for dynamic task management based on the user's emotional state and flexible task adjustments that take the user's mental health into consideration.

[0381] 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.

[0382] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, means for automatically generating tasks based on the analyzed information and dynamically adjusting their priorities, and means for identifying the user's emotional state and recommending appropriate tasks according to that state. This enables task management that takes the user's emotional state into account, reducing emotional burden while maintaining and improving productivity.

[0383] "Information sources" refer to systems and media, including email, chat, and other communication tools, that provide data about users.

[0384] "Information analysis" is the process of processing collected information and converting it into a data format suitable for a specific purpose.

[0385] "Standardization of data into a common format" refers to unifying data obtained from different sources into a consistent format.

[0386] "Automatically generating tasks" means automatically creating specific work items that are tailored to the user's actions and schedule, based on the analyzed information.

[0387] "Prioritizing tasks" means determining the order and schedule of execution based on the importance and urgency of the tasks that have been generated.

[0388] "Tracking task progress" is the process of monitoring and verifying whether the assigned tasks are progressing according to plan.

[0389] "Sending a reminder" means sending a notification to the user to inform them of the task's completion time and deadline.

[0390] "Identifying emotional states" is the process of detecting emotions from a user's facial expressions and voice to understand their mental state.

[0391] "Dynamic adjustment" means changing the priority and content of tasks in real time in response to changes in circumstances and conditions.

[0392] "Recommending appropriate tasks" means suggesting the most efficient and beneficial activities based on the user's current situation.

[0393] The system for carrying out this invention mainly consists of multiple modules. The server uses an information gathering module to obtain user information from email, chat, and other communication tools. This information is processed by an analysis module and converted into a common format.

[0394] Next, the task generation module automatically generates tasks based on standardized data and assigns them priorities. The progress of the generated tasks is tracked in real time by the progress management module, and reminders are sent to the user's device as needed.

[0395] The emotion recognition module is responsible for identifying the user's emotional state in real time. This module analyzes the user's facial expressions and voice through interfaces such as the device's camera and microphone, and sends the data to the server as emotion data. Based on this data, the server dynamically adjusts task priorities and suggests tasks that promote relaxation according to the user's situation.

[0396] For example, if the server determines that a user is experiencing excessive stress, it automatically adjusts task priorities and notifies the user's device of light tasks for short breaks or refreshment. In this way, users can flexibly manage and execute tasks according to their own emotional state.

[0397] The generative AI model supports task recommendations and adjustments based on the user's emotional state. An example of a prompt would be, "Based on the user's current emotional state, please suggest the most appropriate next task." This enables more comfortable and efficient task management for the user.

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The server automatically retrieves user information from communication tools such as email and chat using multiple information gathering modules. In this process, the server sends requests from individual data sources and temporarily stores the information received. Input data consists of messages and events from each communication tool, while output data is unformatted text information.

[0401] Step 2:

[0402] The server processes the acquired information using an analysis module and converts it into a common format. This step uses natural language processing techniques to extract meaning from the text and organize it into a format that conforms to the database schema. The input is unformatted text information, and the output is organized data.

[0403] Step 3:

[0404] Based on the organized data, the server automatically generates tasks for the user using a task generation module. In this step, a generation AI model analyzes past task history and user trends to generate new tasks. The input is organized data, and the output is newly generated task information.

[0405] Step 4:

[0406] The server assigns priorities to the generated tasks and incorporates them into the schedule. The input here is task information, and the output is a task list with assigned priorities. In this process, priorities are determined based on the importance and deadlines of the user's work.

[0407] Step 5:

[0408] The device detects the user's emotional state using an emotion recognition module. It analyzes facial expressions and voice tone using the device's camera and microphone. The input for this step is camera video and audio data, and the output is estimated emotion data.

[0409] Step 6:

[0410] The server receives emotional data and dynamically adjusts task priorities. In this step, it re-evaluates the order of tasks based on the emotional state and suggests breaks or lighter tasks as needed. The inputs are emotional data and a task list, and the output is the adjusted task schedule.

[0411] Step 7:

[0412] The device that notifies the user displays a dynamically adjusted task schedule and sends reminders as needed. The input to this process is the adjusted task schedule, and the output is a notification message to the user.

[0413] Step 8:

[0414] The server tracks the progress of all tasks until they are completed. A progress management module updates the status hourly and archives completed tasks. The input is the task progress, and the output is archived tasks and progress reports.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] [Third Embodiment]

[0419] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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".

[0431] This invention relates to an information processing system for achieving efficient task management. The system acquires information from multiple information sources used by the user in their daily work, such as email, chat, and telephone. With the user's permission, the server can utilize the APIs of these platforms to collect new messages and notifications.

[0432] After the information is collected, the server begins analyzing the data. The analysis process extracts task-related keywords and deadline information from email bodies and chat messages. This information is then converted into a common format and stored in a database.

[0433] Based on stored information, a task generation AI automatically generates tasks. This AI analyzes the collected data to identify the actions the user should take. Tasks are also prioritized according to their urgency and importance. To enable users to manage tasks efficiently, task progress is tracked in real time, and notifications are sent to the device as needed. The device displays the task list through the user interface and provides reminder notifications.

[0434] As a concrete example, consider a scenario where a user receives a new email. The server analyzes the email and automatically generates a task such as, "Please send the meeting materials by next Tuesday." The generated task is registered in the database under the title "Document Creation," and its progress is updated continuously on the user's terminal. This allows the user to complete the task without missing the deadline.

[0435] This invention functions as a comprehensive system for users to efficiently manage their work tasks and improve productivity. By utilizing this system, it is expected that tasks will not be overlooked, and a work style that reduces stress will be realized.

[0436] The following describes the processing flow.

[0437] Step 1:

[0438] The server uses APIs to access various information sources (e.g., email servers and chat applications) to retrieve users' pending messages and notifications. The server then stores this data in temporary storage.

[0439] Step 2:

[0440] The server analyzes the acquired information using machine learning algorithms or rule-based analysis engines to extract keywords and deadline information related to the task. Natural language processing techniques are used to accurately extract contextually relevant information.

[0441] Step 3:

[0442] The server converts the analyzed data into a common format and determines the task title, description, due date, sender information, etc. This standardized data is then stored in a database.

[0443] Step 4:

[0444] The generation AI automatically generates tasks based on stored data. The content and priority of the tasks are set based on the user's past behavior history and the importance of the tasks.

[0445] Step 5:

[0446] The server assigns priorities to the generated tasks. The criteria for prioritization include the task's deadline, importance, and the user's workload.

[0447] Step 6:

[0448] The server monitors and updates the task's progress in real time. It sets flags to notify the user based on changes in progress.

[0449] Step 7:

[0450] The device receives notifications from the server and displays them as a task list in the user interface. Here, the tasks are presented in a visually organized format, allowing users to easily check their details and priorities.

[0451] Step 8:

[0452] When a user completes or updates a task, that information is sent to the server via the device. The server updates the task status in the database based on the received information.

[0453] Step 9:

[0454] The server periodically archives completed tasks and generates progress reports as needed. These reports serve as reference material for users to review past work.

[0455] (Example 1)

[0456] 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."

[0457] In today's information environment, users need to manage a wide range of data from various sources. However, manually organizing this information and efficiently converting it into tasks requires considerable effort and time. Therefore, there is a need for systems that automate information collection, analysis, and task creation, enabling efficient and prioritized management.

[0458] 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.

[0459] In this invention, the server includes means for aggregating data from multiple information media, means for analyzing the aggregated data and converting it into a unified format, and means for automatically generating tasks based on the analyzed data. This enables users to streamline information management and perform important tasks without omission.

[0460] "Information media" refers to multiple sources of information that users utilize in their work, such as email, chat messages, and phone records.

[0461] "Data aggregation" refers to the process of automatically collecting information from different information sources and consolidating it in one place.

[0462] "Data analysis" refers to the process of using collected information to extract keywords and deadline information related to a task.

[0463] A "unified format" refers to a format used to convert data from different formats into a consistent format and store it in an easy-to-use manner.

[0464] "Task generation" refers to the process of automatically generating tasks that users should perform based on analyzed information.

[0465] "Prioritizing tasks" refers to a method of determining the order in which each generated task is performed, based on its importance and urgency.

[0466] "Progress tracking" refers to the process of monitoring the progress of ongoing tasks in real time and updating it as needed.

[0467] "Sending notifications" refers to the act of a system promptly informing a user of important tasks and deadline reminders.

[0468] This invention is implemented by an information processing device that performs efficient information management and task generation. The server, with user permission, automatically aggregates data from multiple information sources such as email, chat applications, and telephone. The APIs of each information source are used for data aggregation; for example, a common API is used for email.

[0469] The server analyzes the aggregated data using a natural language processing library (e.g., spaCy or NLTK) to extract important keywords and deadline information. It then converts the extracted information into a unified format and saves it to a database server (e.g., PostgreSQL).

[0470] The generative AI automatically generates tasks using stored information. In this process, the generative AI model (e.g., a GPT-based model) identifies the specific task content according to prompts. The generated tasks are assigned priorities and managed on the server.

[0471] The device displays a task list on the user's screen based on information sent from the server. The user can review the displayed task list and perform the necessary tasks. For urgent tasks, the device sends a notification to the user using a notification API (e.g., Firebase Cloud Messaging).

[0472] As a concrete example, when a user receives a new email, the server analyzes its contents and automatically generates a task such as, "Please submit the project report by next Tuesday." The generated task is registered in the database with the title "Report Creation," and its progress is updated in real time on the user's device. This system ensures that users do not miss important tasks. Another example of a prompt message to the generating AI model is, "Extract meeting material creation tasks from received emails and prioritize them based on their deadlines."

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The server aggregates data from multiple information sources related to the user (email, chat, phone, etc.). The input consists of new messages and notifications provided by these information sources. The server automatically collects this data using the APIs of each platform and stores it as an initial dataset. The output is a collection of unanalyzed messages.

[0476] Step 2:

[0477] The server analyzes the aggregated data. The input is the previously unanalyzed set of messages. Specifically, it uses a natural language processing library (e.g., spaCy or NLTK) to analyze the message content and extract keywords and deadline information related to the task. The server converts these analysis results into a unified format and generates the converted data as output.

[0478] Step 3:

[0479] The generative AI automatically generates tasks based on the transformed data. The input is the transformed data obtained in step 2. The generative AI model (e.g., a GPT-based model) follows the prompts, analyzes the data, and determines the details of specific tasks. The output is a task with its content identified. The generated tasks are assigned priorities based on importance and urgency.

[0480] Step 4:

[0481] The device notifies the user of generated tasks and displays a task list. The input is task information sent from the server. The device uses a notification API (e.g., Firebase Cloud Messaging) to send important task and deadline reminders to the user. The output is the task list and notifications presented to the user.

[0482] Step 5:

[0483] The user checks the task list displayed on the device and performs the necessary actions. The input is the task list displayed on the device. The user works based on this and updates the task progress manually or automatically. The output is a list of completed tasks and a record of their progress.

[0484] (Application Example 1)

[0485] 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."

[0486] In modern urban environments, information overload and inadequate task management are major problems, making it difficult for citizens to select and efficiently utilize the vast amount of information they receive. Therefore, a system is needed to effectively manage information and appropriately break it down into tasks in order to improve citizen services and enhance the quality of life for individuals.

[0487] 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.

[0488] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, and means for improving public affairs management based on the analyzed information. This enables the automation of tasks necessary for citizens' lives and improves services through efficient information utilization.

[0489] "Means of collecting information from multiple sources" refers to system components that aggregate information from different types of communication methods and data sources.

[0490] "Means for analyzing collected information and creating a common format" refers to technologies that analyze acquired information and convert it into a unified format.

[0491] "A means of automatically generating tasks based on analyzed information" refers to a system that automatically creates work items to optimize user behavior based on collected data.

[0492] "Means for assigning priorities to generated tasks" refers to a mechanism that determines the processing order of automatically generated tasks based on their urgency and importance.

[0493] "A means of tracking task progress in real time" refers to a system that allows for immediate confirmation of the status of ongoing work.

[0494] "Means of notifying users of reminders" refers to a function that sends alerts to users at specified times to prompt them to check on their work or pay attention to it.

[0495] "Means for analyzing integrated information and improving public administration" refers to methods that comprehensively analyze multiple pieces of information to enable efficient service provision to citizens.

[0496] To realize this invention, the server first collects data from multiple sources, such as email servers, chat systems, and other digital information providers, using communication means. This includes, for example, the use of APIs and cloud services to establish database connections. The server can use Google Cloud Platform or Amazon Web Services (AWS) to securely and efficiently aggregate this data.

[0497] Next, the server is responsible for analyzing the collected information and converting it into a common format. In this process, Natural Language Processing (NLP) technology is used, along with the Google Natural Language API and similar text analysis engines, to extract keywords and date information from the data and store it as structured data.

[0498] Next, tasks are automatically generated based on these analyses, and a generation AI model, such as GPT, is used to organize the necessary details and instructions for each task. Tasks are also prioritized according to their importance and urgency. The server aims to highly automate this process and improve the efficiency of urban public services. The generated tasks are managed by a database management system such as AWS DynamoDB.

[0499] The user's device, such as a smartphone application or tablet, tracks progress in real time and sends reminders to the user as needed. This allows users to efficiently receive information about public services and take timely action.

[0500] As a concrete example, consider notifications for library events. For instance, if information about a "children's reading group" event becomes available within a user-specified area, the system analyzes this information and automatically generates a task to attend the event. The generated task then sends a reminder to the user's mobile device before the specified date and time to facilitate preparation for participation.

[0501] An example of a prompt is, "Generate meeting and event attendance tasks based on announcements from the city hall. Ensure the prompt includes specific keywords and deadlines." This helps the AI ​​identify the components of a specific task.

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] The server collects data from its sources. Specifically, it connects to APIs of mail servers and chat platforms to retrieve new messages and notifications. Inputs include API credentials and the connection URL. Outputs are notifications and messages in raw data format. The server temporarily stores this information in local storage.

[0505] Step 2:

[0506] The server analyzes the collected data and converts it into a common format. Here, Natural Language Processing (NLP) technology is used to extract keywords and deadline information from email bodies and chat messages. The input is the collected raw data, and the output is structured data (e.g., task information, deadlines, priorities, etc.). The server performs the analysis using tools such as the Google Natural Language API and stores the processed data in a database.

[0507] Step 3:

[0508] The server automatically generates tasks using an AI model based on structured data. The input is the structured data obtained in step 2. The AI ​​model analyzes this data and creates specific tasks. The output includes the title, content, and deadline of the automatically generated tasks. The task information is stored in the database as a list that can be prioritized.

[0509] Step 4:

[0510] The server assigns priorities to the generated tasks. The input is the task information generated in step 3, and the output is a prioritized task list. The server compares urgency and importance parameters and sets an appropriate priority for each task. This ensures that the most important tasks appear at the top of the list.

[0511] Step 5:

[0512] The terminal tracks task progress in real time and notifies the user with reminders. Inputs include update information sent from the server and the user's task progress data. Outputs are a task list and notifications displayed to the user. The terminal shows the user progress and the next steps through the application. The reminder function prevents users from missing tasks by issuing alerts just before deadlines.

[0513] Step 6:

[0514] Users manage tasks through their devices and send progress reports to the server. Inputs are the current task status and user input data, while output is updated progress information. Users can report task completion and adjust progress within the app. The server receives this information and updates the task status in the database.

[0515] These processing steps automate tasks necessary for citizens' daily lives and improve public services through efficient information utilization.

[0516] 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.

[0517] This invention combines a task management function with an emotion recognition function to achieve flexible task management that responds to the user's emotional state. The system consists of modules for information gathering, analysis, task generation, and emotion recognition.

[0518] First, the server automatically collects user information from email, chat, and other communication tools. The collected information is analyzed by the server and converted into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0519] The generated tasks are tracked by the server, and reminders are sent to the user's device as needed. Here, the emotion engine is integrated into the entire system and is responsible for recognizing the user's emotional state. The emotion engine collects emotional data (e.g., data from facial recognition and voice analysis) through the device interface and sends it to the server.

[0520] The server uses data from the emotion engine to dynamically change the priority of generated tasks. For example, if a user is feeling stressed, the server can slow down the pace of tasks or adjust the frequency of reminders. Furthermore, based on the emotions identified by the emotion engine, relaxing tasks or new tasks are suggested.

[0521] As a concrete example, if a user experiences stress during their daily work, the emotion engine detects this. The server temporarily lowers the priority of their regular work tasks, suggests a short, relaxing break task, and notifies the user's terminal. In this way, task management that takes the user's emotional state into consideration becomes possible.

[0522] This invention allows users to experience effective task management tailored to their own emotions. It enables them to maintain work efficiency, reduce stress, and improve their work style.

[0523] The following describes the processing flow.

[0524] Step 1:

[0525] The server retrieves new messages and notifications from the mail server and chat application with the user's permission. The retrieved information is temporarily stored in a database.

[0526] Step 2:

[0527] The server uses natural language processing technology to analyze the stored messages and extract task-related information and deadlines. The analysis results are then formatted into a common format and stored in a database.

[0528] Step 3:

[0529] The generation AI automatically generates tasks that the user needs, based on formatted data. The generated tasks include a title, due date, and description.

[0530] Step 4:

[0531] The server assigns priorities to the generated tasks. Priorities are set considering the importance and urgency of each task.

[0532] Step 5:

[0533] The user's device uses an emotion engine to collect emotional data from the user's voice and facial expressions. The collected emotional data is sent to the server in real time.

[0534] Step 6:

[0535] The server analyzes the received emotional data to identify the user's emotional state. Based on the emotional state, task priorities and reminder frequencies are dynamically adjusted.

[0536] Step 7:

[0537] The device displays the current task list and adjusted priorities through the user interface. The user is notified of new tasks and reminders.

[0538] Step 8:

[0539] When a user completes or updates a task, they send that information to the server via their device. The server then reflects the received information in its database and updates the task's progress.

[0540] Step 9:

[0541] The server archives completed tasks and generates progress reports that take into account changes in sentiment. These reports are provided in a format usable on the user's terminal.

[0542] (Example 2)

[0543] 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."

[0544] In modern society, stress management and efficient work performance in the work environment are crucial issues. However, existing task management systems determine task priorities using static methods without considering individual emotional states, and therefore fail to adequately address user stress reduction and the realization of flexible work styles. This leads to problems such as decreased work efficiency and the accumulation of mental fatigue.

[0545] 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.

[0546] In this invention, the server includes means for collecting data from multiple communication means, means for analyzing the collected data and converting it into a unified format, and means for recognizing an individual's emotional state. This enables flexible and efficient task management tailored to an individual's emotional state, thereby reducing work-related stress and improving productivity.

[0547] "Communication methods" refer to the interfaces and protocols used throughout a system for sending and receiving data.

[0548] "Data" refers to information necessary for the operation of the task management system, and includes information obtained in the form of emails, chat content, audio, facial expressions, etc.

[0549] "Analysis" refers to the process of processing collected data according to a specific purpose to understand its meaning and trends.

[0550] A "unified format" refers to a data format that converts data collected in different formats into a form that can be processed consistently.

[0551] "Tasks" refer to tasks or activities generated within this system that users are required to perform.

[0552] "Priority" refers to a ranking of tasks based on their importance and urgency.

[0553] "Emotional state" refers to a specific state that describes a user's psychological and emotional condition and is evaluated using emotion recognition technology.

[0554] "Emotion recognition" refers to technology that estimates a user's emotions and psychological state based on their facial expressions, voice, and text.

[0555] "Continuous tracking" refers to the process of monitoring the progress of a task in real time or periodically, and keeping that status up-to-date.

[0556] "Notification" refers to the act of presenting users with information or reminders about tasks.

[0557] This invention is a system for achieving flexible task management while taking into account the user's emotional state. Its implementation revolves around three key elements: the server, the terminal, and the user.

[0558] The server collects user data from email, chat, and other means of communication. APIs and communication protocols are used for data collection. For example, the IMAP protocol can be used to collect email data.

[0559] The collected data is analyzed on the server using natural language processing. Specifically, the Python NLTK library is used to convert the data into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0560] The device plays a role in collecting emotional data from the user. The OpenCV library is used for facial recognition, analyzing the user's facial expressions via the camera and estimating their emotions. It also uses the microphone and the Google Speech-to-Text API to evaluate emotions from speech. The emotional data collected by the device is sent to a server, which then dynamically adjusts task priorities based on this data.

[0561] For example, when a user experiences stress at work, the emotion engine can detect this. The server takes this high-stress state into account, lowers the priority of normal tasks, suggests relaxing tasks such as "5 minutes of meditation," and sends a notification to the user.

[0562] An example of a prompt message for a generative AI model is: "Please set appropriate task priorities based on the user's perceived stress level. The current stress level is high, so please suggest relaxation tasks."

[0563] This system allows users to enjoy task management tailored to their emotional state, enabling them to improve their work style and reduce stress.

[0564] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0565] Step 1:

[0566] The server collects data from communication methods such as email and chat. Input includes email and message data via the IMAP protocol and APIs. This unstructured data is ingested by the server into the system. Since the collected data is not directly usable, data cleaning and format conversion are performed.

[0567] Step 2:

[0568] The server analyzes the collected data using natural language processing (NLTK) techniques. The input is unstructured text data. The NLTK library in Python is used for analysis, including key phrase extraction and sentiment analysis. This results in structured data in a common format. The data is then converted to a unified format and recorded in a digital database.

[0569] Step 3:

[0570] The server automatically generates and prioritizes tasks based on formatted data. The input is structured data. The server assesses the importance and urgency of the tasks and stores this information in a database. The generated tasks are then prioritized by an AI model based on specific criteria.

[0571] Step 4:

[0572] The device collects user emotion data through its camera and microphone. The input is raw user data (facial expressions, voice), which is then analyzed using OpenCV or the Google Speech-to-Text API. The analyzed emotion data is output as the user's emotional state. This data is used to monitor the user's psychological state.

[0573] Step 5:

[0574] The server dynamically adjusts task priorities based on the user's emotional data. The input is data on the user's emotional state. If stress is detected, the server lowers the priority of existing tasks and presents new tasks with a relaxing effect. As a result, information on the adjusted tasks is output and notified to the user.

[0575] Through the above processing steps, users can manage tasks flexibly according to their emotions and reduce stress.

[0576] (Application Example 2)

[0577] 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."

[0578] In recent years, task management systems have become highly sophisticated, but they often prioritize scheduling efficiency without considering the user's emotional state. As a result, users may experience increased stress due to excessive task allocation or inappropriate prioritization that disregards their mental health. To address this problem, there is a need for dynamic task management based on the user's emotional state and flexible task adjustments that take the user's mental health into consideration.

[0579] 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.

[0580] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, means for automatically generating tasks based on the analyzed information and dynamically adjusting their priorities, and means for identifying the user's emotional state and recommending appropriate tasks according to that state. This enables task management that takes the user's emotional state into account, reducing emotional burden while maintaining and improving productivity.

[0581] "Information sources" refer to systems and media, including email, chat, and other communication tools, that provide data about users.

[0582] "Information analysis" is the process of processing collected information and converting it into a data format suitable for a specific purpose.

[0583] "Standardization of data into a common format" refers to unifying data obtained from different sources into a consistent format.

[0584] "Automatically generating tasks" means automatically creating specific work items that are tailored to the user's actions and schedule, based on the analyzed information.

[0585] "Prioritizing tasks" means determining the order and schedule of execution based on the importance and urgency of the tasks that have been generated.

[0586] "Tracking task progress" is the process of monitoring and verifying whether the assigned tasks are progressing according to plan.

[0587] "Sending a reminder" means sending a notification to the user to inform them of the task's completion time and deadline.

[0588] "Identifying emotional states" is the process of detecting emotions from a user's facial expressions and voice to understand their mental state.

[0589] "Dynamic adjustment" means changing the priority and content of tasks in real time in response to changes in circumstances and conditions.

[0590] "Recommending appropriate tasks" means suggesting the most efficient and beneficial activities based on the user's current situation.

[0591] The system for carrying out this invention mainly consists of multiple modules. The server uses an information gathering module to obtain user information from email, chat, and other communication tools. This information is processed by an analysis module and converted into a common format.

[0592] Next, the task generation module automatically generates tasks based on standardized data and assigns them priorities. The progress of the generated tasks is tracked in real time by the progress management module, and reminders are sent to the user's device as needed.

[0593] The emotion recognition module is responsible for identifying the user's emotional state in real time. This module analyzes the user's facial expressions and voice through interfaces such as the device's camera and microphone, and sends the data to the server as emotion data. Based on this data, the server dynamically adjusts task priorities and suggests tasks that promote relaxation according to the user's situation.

[0594] For example, if the server determines that a user is experiencing excessive stress, it automatically adjusts task priorities and notifies the user's device of light tasks for short breaks or refreshment. In this way, users can flexibly manage and execute tasks according to their own emotional state.

[0595] The generative AI model supports task recommendations and adjustments based on the user's emotional state. An example of a prompt would be, "Based on the user's current emotional state, please suggest the most appropriate next task." This enables more comfortable and efficient task management for the user.

[0596] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0597] Step 1:

[0598] The server automatically retrieves user information from communication tools such as email and chat using multiple information gathering modules. In this process, the server sends requests from individual data sources and temporarily stores the information received. Input data consists of messages and events from each communication tool, while output data is unformatted text information.

[0599] Step 2:

[0600] The server processes the acquired information using an analysis module and converts it into a common format. This step uses natural language processing techniques to extract meaning from the text and organize it into a format that conforms to the database schema. The input is unformatted text information, and the output is organized data.

[0601] Step 3:

[0602] Based on the organized data, the server automatically generates tasks for the user using a task generation module. In this step, a generation AI model analyzes past task history and user trends to generate new tasks. The input is organized data, and the output is newly generated task information.

[0603] Step 4:

[0604] The server assigns priorities to the generated tasks and incorporates them into the schedule. The input here is task information, and the output is a task list with assigned priorities. In this process, priorities are determined based on the importance and deadlines of the user's work.

[0605] Step 5:

[0606] The device detects the user's emotional state using an emotion recognition module. It analyzes facial expressions and voice tone using the device's camera and microphone. The input for this step is camera video and audio data, and the output is estimated emotion data.

[0607] Step 6:

[0608] The server receives emotional data and dynamically adjusts task priorities. In this step, it re-evaluates the order of tasks based on the emotional state and suggests breaks or lighter tasks as needed. The inputs are emotional data and a task list, and the output is the adjusted task schedule.

[0609] Step 7:

[0610] The device that notifies the user displays a dynamically adjusted task schedule and sends reminders as needed. The input to this process is the adjusted task schedule, and the output is a notification message to the user.

[0611] Step 8:

[0612] The server tracks the progress of all tasks until they are completed. A progress management module updates the status hourly and archives completed tasks. The input is the task progress, and the output is archived tasks and progress reports.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] [Fourth Embodiment]

[0617] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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).

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] 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".

[0630] This invention relates to an information processing system for achieving efficient task management. The system acquires information from multiple information sources used by the user in their daily work, such as email, chat, and telephone. With the user's permission, the server can utilize the APIs of these platforms to collect new messages and notifications.

[0631] After the information is collected, the server begins analyzing the data. The analysis process extracts task-related keywords and deadline information from email bodies and chat messages. This information is then converted into a common format and stored in a database.

[0632] Based on stored information, a task generation AI automatically generates tasks. This AI analyzes the collected data to identify the actions the user should take. Tasks are also prioritized according to their urgency and importance. To enable users to manage tasks efficiently, task progress is tracked in real time, and notifications are sent to the device as needed. The device displays the task list through the user interface and provides reminder notifications.

[0633] As a concrete example, consider a scenario where a user receives a new email. The server analyzes the email and automatically generates a task such as, "Please send the meeting materials by next Tuesday." The generated task is registered in the database under the title "Document Creation," and its progress is updated continuously on the user's terminal. This allows the user to complete the task without missing the deadline.

[0634] This invention functions as a comprehensive system for users to efficiently manage their work tasks and improve productivity. By utilizing this system, it is expected that tasks will not be overlooked, and a work style that reduces stress will be realized.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] The server uses APIs to access various information sources (e.g., email servers and chat applications) to retrieve users' pending messages and notifications. The server then stores this data in temporary storage.

[0638] Step 2:

[0639] The server analyzes the acquired information using machine learning algorithms or rule-based analysis engines to extract keywords and deadline information related to the task. Natural language processing techniques are used to accurately extract contextually relevant information.

[0640] Step 3:

[0641] The server converts the analyzed data into a common format and determines the task title, description, due date, sender information, etc. This standardized data is then stored in a database.

[0642] Step 4:

[0643] The generation AI automatically generates tasks based on stored data. The content and priority of the tasks are set based on the user's past behavior history and the importance of the tasks.

[0644] Step 5:

[0645] The server assigns priorities to the generated tasks. The criteria for prioritization include the task's deadline, importance, and the user's workload.

[0646] Step 6:

[0647] The server monitors and updates the task's progress in real time. It sets flags to notify the user based on changes in progress.

[0648] Step 7:

[0649] The device receives notifications from the server and displays them as a task list in the user interface. Here, the tasks are presented in a visually organized format, allowing users to easily check their details and priorities.

[0650] Step 8:

[0651] When a user completes or updates a task, that information is sent to the server via the device. The server updates the task status in the database based on the received information.

[0652] Step 9:

[0653] The server periodically archives completed tasks and generates progress reports as needed. These reports serve as reference material for users to review past work.

[0654] (Example 1)

[0655] 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".

[0656] In today's information environment, users need to manage a wide range of data from various sources. However, manually organizing this information and efficiently converting it into tasks requires considerable effort and time. Therefore, there is a need for systems that automate information collection, analysis, and task creation, enabling efficient and prioritized management.

[0657] 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.

[0658] In this invention, the server includes means for aggregating data from multiple information media, means for analyzing the aggregated data and converting it into a unified format, and means for automatically generating tasks based on the analyzed data. This enables users to streamline information management and perform important tasks without omission.

[0659] "Information media" refers to multiple sources of information that users utilize in their work, such as email, chat messages, and phone records.

[0660] "Data aggregation" refers to the process of automatically collecting information from different information sources and consolidating it in one place.

[0661] "Data analysis" refers to the process of using collected information to extract keywords and deadline information related to a task.

[0662] A "unified format" refers to a format used to convert data from different formats into a consistent format and store it in an easy-to-use manner.

[0663] "Task generation" refers to the process of automatically generating tasks that users should perform based on analyzed information.

[0664] "Prioritizing tasks" refers to a method of determining the order in which each generated task is performed, based on its importance and urgency.

[0665] "Progress tracking" refers to the process of monitoring the progress of ongoing tasks in real time and updating it as needed.

[0666] "Sending notifications" refers to the act of a system promptly informing a user of important tasks and deadline reminders.

[0667] This invention is implemented by an information processing device that performs efficient information management and task generation. The server, with user permission, automatically aggregates data from multiple information sources such as email, chat applications, and telephone. The APIs of each information source are used for data aggregation; for example, a common API is used for email.

[0668] The server analyzes the aggregated data using a natural language processing library (e.g., spaCy or NLTK) to extract important keywords and deadline information. It then converts the extracted information into a unified format and saves it to a database server (e.g., PostgreSQL).

[0669] The generative AI automatically generates tasks using stored information. In this process, the generative AI model (e.g., a GPT-based model) identifies the specific task content according to prompts. The generated tasks are assigned priorities and managed on the server.

[0670] The device displays a task list on the user's screen based on information sent from the server. The user can review the displayed task list and perform the necessary tasks. For urgent tasks, the device sends a notification to the user using a notification API (e.g., Firebase Cloud Messaging).

[0671] As a concrete example, when a user receives a new email, the server analyzes its contents and automatically generates a task such as, "Please submit the project report by next Tuesday." The generated task is registered in the database with the title "Report Creation," and its progress is updated in real time on the user's device. This system ensures that users do not miss important tasks. Another example of a prompt message to the generating AI model is, "Extract meeting material creation tasks from received emails and prioritize them based on their deadlines."

[0672] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0673] Step 1:

[0674] The server aggregates data from multiple information sources related to the user (email, chat, phone, etc.). The input consists of new messages and notifications provided by these information sources. The server automatically collects this data using the APIs of each platform and stores it as an initial dataset. The output is a collection of unanalyzed messages.

[0675] Step 2:

[0676] The server analyzes the aggregated data. The input is the previously unanalyzed set of messages. Specifically, it uses a natural language processing library (e.g., spaCy or NLTK) to analyze the message content and extract keywords and deadline information related to the task. The server converts these analysis results into a unified format and generates the converted data as output.

[0677] Step 3:

[0678] The generative AI automatically generates tasks based on the transformed data. The input is the transformed data obtained in step 2. The generative AI model (e.g., a GPT-based model) follows the prompts, analyzes the data, and determines the details of specific tasks. The output is a task with its content identified. The generated tasks are assigned priorities based on importance and urgency.

[0679] Step 4:

[0680] The device notifies the user of generated tasks and displays a task list. The input is task information sent from the server. The device uses a notification API (e.g., Firebase Cloud Messaging) to send important task and deadline reminders to the user. The output is the task list and notifications presented to the user.

[0681] Step 5:

[0682] The user checks the task list displayed on the device and performs the necessary actions. The input is the task list displayed on the device. The user works based on this and updates the task progress manually or automatically. The output is a list of completed tasks and a record of their progress.

[0683] (Application Example 1)

[0684] 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".

[0685] In modern urban environments, information overload and inadequate task management are major problems, making it difficult for citizens to select and efficiently utilize the vast amount of information they receive. Therefore, a system is needed to effectively manage information and appropriately break it down into tasks in order to improve citizen services and enhance the quality of life for individuals.

[0686] 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.

[0687] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, and means for improving public affairs management based on the analyzed information. This enables the automation of tasks necessary for citizens' lives and improves services through efficient information utilization.

[0688] "Means of collecting information from multiple sources" refers to system components that aggregate information from different types of communication methods and data sources.

[0689] "Means for analyzing collected information and creating a common format" refers to technologies that analyze acquired information and convert it into a unified format.

[0690] "A means of automatically generating tasks based on analyzed information" refers to a system that automatically creates work items to optimize user behavior based on collected data.

[0691] "Means for assigning priorities to generated tasks" refers to a mechanism that determines the processing order of automatically generated tasks based on their urgency and importance.

[0692] "A means of tracking task progress in real time" refers to a system that allows for immediate confirmation of the status of ongoing work.

[0693] "Means of notifying users of reminders" refers to a function that sends alerts to users at specified times to prompt them to check on their work or pay attention to it.

[0694] "Means for analyzing integrated information and improving public administration" refers to methods that comprehensively analyze multiple pieces of information to enable efficient service provision to citizens.

[0695] To realize this invention, the server first collects data from multiple sources, such as email servers, chat systems, and other digital information providers, using communication means. This includes, for example, the use of APIs and cloud services to establish database connections. The server can use Google Cloud Platform or Amazon Web Services (AWS) to securely and efficiently aggregate this data.

[0696] Next, the server is responsible for analyzing the collected information and converting it into a common format. In this process, Natural Language Processing (NLP) technology is used, along with the Google Natural Language API and similar text analysis engines, to extract keywords and date information from the data and store it as structured data.

[0697] Next, tasks are automatically generated based on these analyses, and a generation AI model, such as GPT, is used to organize the necessary details and instructions for each task. Tasks are also prioritized according to their importance and urgency. The server aims to highly automate this process and improve the efficiency of urban public services. The generated tasks are managed by a database management system such as AWS DynamoDB.

[0698] The user's device, such as a smartphone application or tablet, tracks progress in real time and sends reminders to the user as needed. This allows users to efficiently receive information about public services and take timely action.

[0699] As a concrete example, consider notifications for library events. For instance, if information about a "children's reading group" event becomes available within a user-specified area, the system analyzes this information and automatically generates a task to attend the event. The generated task then sends a reminder to the user's mobile device before the specified date and time to facilitate preparation for participation.

[0700] An example of a prompt is, "Generate meeting and event attendance tasks based on announcements from the city hall. Ensure the prompt includes specific keywords and deadlines." This helps the AI ​​identify the components of a specific task.

[0701] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0702] Step 1:

[0703] The server collects data from its sources. Specifically, it connects to APIs of mail servers and chat platforms to retrieve new messages and notifications. Inputs include API credentials and the connection URL. Outputs are notifications and messages in raw data format. The server temporarily stores this information in local storage.

[0704] Step 2:

[0705] The server analyzes the collected data and converts it into a common format. Here, Natural Language Processing (NLP) technology is used to extract keywords and deadline information from email bodies and chat messages. The input is the collected raw data, and the output is structured data (e.g., task information, deadlines, priorities, etc.). The server performs the analysis using tools such as the Google Natural Language API and stores the processed data in a database.

[0706] Step 3:

[0707] The server automatically generates tasks using an AI model based on structured data. The input is the structured data obtained in step 2. The AI ​​model analyzes this data and creates specific tasks. The output includes the title, content, and deadline of the automatically generated tasks. The task information is stored in the database as a list that can be prioritized.

[0708] Step 4:

[0709] The server assigns priorities to the generated tasks. The input is the task information generated in step 3, and the output is a prioritized task list. The server compares urgency and importance parameters and sets an appropriate priority for each task. This ensures that the most important tasks appear at the top of the list.

[0710] Step 5:

[0711] The terminal tracks task progress in real time and notifies the user with reminders. Inputs include update information sent from the server and the user's task progress data. Outputs are a task list and notifications displayed to the user. The terminal shows the user progress and the next steps through the application. The reminder function prevents users from missing tasks by issuing alerts just before deadlines.

[0712] Step 6:

[0713] Users manage tasks through their devices and send progress reports to the server. Inputs are the current task status and user input data, while output is updated progress information. Users can report task completion and adjust progress within the app. The server receives this information and updates the task status in the database.

[0714] These processing steps automate tasks necessary for citizens' daily lives and improve public services through efficient information utilization.

[0715] 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.

[0716] This invention combines a task management function with an emotion recognition function to achieve flexible task management that responds to the user's emotional state. The system consists of modules for information gathering, analysis, task generation, and emotion recognition.

[0717] First, the server automatically collects user information from email, chat, and other communication tools. The collected information is analyzed by the server and converted into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0718] The generated tasks are tracked by the server, and reminders are sent to the user's device as needed. Here, the emotion engine is integrated into the entire system and is responsible for recognizing the user's emotional state. The emotion engine collects emotional data (e.g., data from facial recognition and voice analysis) through the device interface and sends it to the server.

[0719] The server uses data from the emotion engine to dynamically change the priority of generated tasks. For example, if a user is feeling stressed, the server can slow down the pace of tasks or adjust the frequency of reminders. Furthermore, based on the emotions identified by the emotion engine, relaxing tasks or new tasks are suggested.

[0720] As a concrete example, if a user experiences stress during their daily work, the emotion engine detects this. The server temporarily lowers the priority of their regular work tasks, suggests a short, relaxing break task, and notifies the user's terminal. In this way, task management that takes the user's emotional state into consideration becomes possible.

[0721] This invention allows users to experience effective task management tailored to their own emotions. It enables them to maintain work efficiency, reduce stress, and improve their work style.

[0722] The following describes the processing flow.

[0723] Step 1:

[0724] The server retrieves new messages and notifications from the mail server and chat application with the user's permission. The retrieved information is temporarily stored in a database.

[0725] Step 2:

[0726] The server uses natural language processing technology to analyze the stored messages and extract task-related information and deadlines. The analysis results are then formatted into a common format and stored in a database.

[0727] Step 3:

[0728] The generation AI automatically generates tasks that the user needs, based on formatted data. The generated tasks include a title, due date, and description.

[0729] Step 4:

[0730] The server assigns priorities to the generated tasks. Priorities are set considering the importance and urgency of each task.

[0731] Step 5:

[0732] The user's device uses an emotion engine to collect emotional data from the user's voice and facial expressions. The collected emotional data is sent to the server in real time.

[0733] Step 6:

[0734] The server analyzes the received emotional data to identify the user's emotional state. Based on the emotional state, task priorities and reminder frequencies are dynamically adjusted.

[0735] Step 7:

[0736] The device displays the current task list and adjusted priorities through the user interface. The user is notified of new tasks and reminders.

[0737] Step 8:

[0738] When a user completes or updates a task, they send that information to the server via their device. The server then reflects the received information in its database and updates the task's progress.

[0739] Step 9:

[0740] The server archives completed tasks and generates progress reports that take into account changes in sentiment. These reports are provided in a format usable on the user's terminal.

[0741] (Example 2)

[0742] 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".

[0743] In modern society, stress management and efficient work performance in the work environment are crucial issues. However, existing task management systems determine task priorities using static methods without considering individual emotional states, and therefore fail to adequately address user stress reduction and the realization of flexible work styles. This leads to problems such as decreased work efficiency and the accumulation of mental fatigue.

[0744] 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.

[0745] In this invention, the server includes means for collecting data from multiple communication means, means for analyzing the collected data and converting it into a unified format, and means for recognizing an individual's emotional state. This enables flexible and efficient task management tailored to an individual's emotional state, thereby reducing work-related stress and improving productivity.

[0746] "Communication methods" refer to the interfaces and protocols used throughout a system for sending and receiving data.

[0747] "Data" refers to information necessary for the operation of the task management system, and includes information obtained in the form of emails, chat content, audio, facial expressions, etc.

[0748] "Analysis" refers to the process of processing collected data according to a specific purpose to understand its meaning and trends.

[0749] A "unified format" refers to a data format that converts data collected in different formats into a form that can be processed consistently.

[0750] "Tasks" refer to tasks or activities generated within this system that users are required to perform.

[0751] "Priority" refers to a ranking of tasks based on their importance and urgency.

[0752] "Emotional state" refers to a specific state that describes a user's psychological and emotional condition and is evaluated using emotion recognition technology.

[0753] "Emotion recognition" refers to technology that estimates a user's emotions and psychological state based on their facial expressions, voice, and text.

[0754] "Continuous tracking" refers to the process of monitoring the progress of a task in real time or periodically, and keeping that status up-to-date.

[0755] "Notification" refers to the act of presenting users with information or reminders about tasks.

[0756] This invention is a system for achieving flexible task management while taking into account the user's emotional state. Its implementation revolves around three key elements: the server, the terminal, and the user.

[0757] The server collects user data from email, chat, and other means of communication. APIs and communication protocols are used for data collection. For example, the IMAP protocol can be used to collect email data.

[0758] The collected data is analyzed on the server using natural language processing. Specifically, the Python NLTK library is used to convert the data into a common format. Based on this formatted data, the server automatically generates tasks and sets priorities.

[0759] The device plays a role in collecting emotional data from the user. The OpenCV library is used for facial recognition, analyzing the user's facial expressions via the camera and estimating their emotions. It also uses the microphone and the Google Speech-to-Text API to evaluate emotions from speech. The emotional data collected by the device is sent to a server, which then dynamically adjusts task priorities based on this data.

[0760] For example, when a user experiences stress at work, the emotion engine can detect this. The server takes this high-stress state into account, lowers the priority of normal tasks, suggests relaxing tasks such as "5 minutes of meditation," and sends a notification to the user.

[0761] An example of a prompt message for a generative AI model is: "Please set appropriate task priorities based on the user's perceived stress level. The current stress level is high, so please suggest relaxation tasks."

[0762] This system allows users to enjoy task management tailored to their emotional state, enabling them to improve their work style and reduce stress.

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1:

[0765] The server collects data from communication methods such as email and chat. Input includes email and message data via the IMAP protocol and APIs. This unstructured data is ingested by the server into the system. Since the collected data is not directly usable, data cleaning and format conversion are performed.

[0766] Step 2:

[0767] The server analyzes the collected data using natural language processing (NLTK) techniques. The input is unstructured text data. The NLTK library in Python is used for analysis, including key phrase extraction and sentiment analysis. This results in structured data in a common format. The data is then converted to a unified format and recorded in a digital database.

[0768] Step 3:

[0769] The server automatically generates and prioritizes tasks based on formatted data. The input is structured data. The server assesses the importance and urgency of the tasks and stores this information in a database. The generated tasks are then prioritized by an AI model based on specific criteria.

[0770] Step 4:

[0771] The device collects user emotion data through its camera and microphone. The input is raw user data (facial expressions, voice), which is then analyzed using OpenCV or the Google Speech-to-Text API. The analyzed emotion data is output as the user's emotional state. This data is used to monitor the user's psychological state.

[0772] Step 5:

[0773] The server dynamically adjusts task priorities based on the user's emotional data. The input is data on the user's emotional state. If stress is detected, the server lowers the priority of existing tasks and presents new tasks with a relaxing effect. As a result, information on the adjusted tasks is output and notified to the user.

[0774] Through the above processing steps, users can manage tasks flexibly according to their emotions and reduce stress.

[0775] (Application Example 2)

[0776] 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".

[0777] In recent years, task management systems have become highly sophisticated, but they often prioritize scheduling efficiency without considering the user's emotional state. As a result, users may experience increased stress due to excessive task allocation or inappropriate prioritization that disregards their mental health. To address this problem, there is a need for dynamic task management based on the user's emotional state and flexible task adjustments that take the user's mental health into consideration.

[0778] 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.

[0779] In this invention, the server includes means for collecting information from multiple information sources, means for analyzing the collected information and formatting it into a common format, means for automatically generating tasks based on the analyzed information and dynamically adjusting their priorities, and means for identifying the user's emotional state and recommending appropriate tasks according to that state. This enables task management that takes the user's emotional state into account, reducing emotional burden while maintaining and improving productivity.

[0780] "Information sources" refer to systems and media, including email, chat, and other communication tools, that provide data about users.

[0781] "Information analysis" is the process of processing collected information and converting it into a data format suitable for a specific purpose.

[0782] "Standardization of data into a common format" refers to unifying data obtained from different sources into a consistent format.

[0783] "Automatically generating tasks" means automatically creating specific work items that are tailored to the user's actions and schedule, based on the analyzed information.

[0784] "Prioritizing tasks" means determining the order and schedule of execution based on the importance and urgency of the tasks that have been generated.

[0785] "Tracking task progress" is the process of monitoring and verifying whether the assigned tasks are progressing according to plan.

[0786] "Sending a reminder" means sending a notification to the user to inform them of the task's completion time and deadline.

[0787] "Identifying emotional states" is the process of detecting emotions from a user's facial expressions and voice to understand their mental state.

[0788] "Dynamic adjustment" means changing the priority and content of tasks in real time in response to changes in circumstances and conditions.

[0789] "Recommending appropriate tasks" means suggesting the most efficient and beneficial activities based on the user's current situation.

[0790] The system for carrying out this invention mainly consists of multiple modules. The server uses an information gathering module to obtain user information from email, chat, and other communication tools. This information is processed by an analysis module and converted into a common format.

[0791] Next, the task generation module automatically generates tasks based on standardized data and assigns them priorities. The progress of the generated tasks is tracked in real time by the progress management module, and reminders are sent to the user's device as needed.

[0792] The emotion recognition module is responsible for identifying the user's emotional state in real time. This module analyzes the user's facial expressions and voice through interfaces such as the device's camera and microphone, and sends the data to the server as emotion data. Based on this data, the server dynamically adjusts task priorities and suggests tasks that promote relaxation according to the user's situation.

[0793] For example, if the server determines that a user is experiencing excessive stress, it automatically adjusts task priorities and notifies the user's device of light tasks for short breaks or refreshment. In this way, users can flexibly manage and execute tasks according to their own emotional state.

[0794] The generative AI model supports task recommendations and adjustments based on the user's emotional state. An example of a prompt would be, "Based on the user's current emotional state, please suggest the most appropriate next task." This enables more comfortable and efficient task management for the user.

[0795] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0796] Step 1:

[0797] The server automatically retrieves user information from communication tools such as email and chat using multiple information gathering modules. In this process, the server sends requests from individual data sources and temporarily stores the information received. Input data consists of messages and events from each communication tool, while output data is unformatted text information.

[0798] Step 2:

[0799] The server processes the acquired information using an analysis module and converts it into a common format. This step uses natural language processing techniques to extract meaning from the text and organize it into a format that conforms to the database schema. The input is unformatted text information, and the output is organized data.

[0800] Step 3:

[0801] Based on the organized data, the server automatically generates tasks for the user using a task generation module. In this step, a generation AI model analyzes past task history and user trends to generate new tasks. The input is organized data, and the output is newly generated task information.

[0802] Step 4:

[0803] The server assigns priorities to the generated tasks and incorporates them into the schedule. The input here is task information, and the output is a task list with assigned priorities. In this process, priorities are determined based on the importance and deadlines of the user's work.

[0804] Step 5:

[0805] The device detects the user's emotional state using an emotion recognition module. It analyzes facial expressions and voice tone using the device's camera and microphone. The input for this step is camera video and audio data, and the output is estimated emotion data.

[0806] Step 6:

[0807] The server receives emotional data and dynamically adjusts task priorities. In this step, it re-evaluates the order of tasks based on the emotional state and suggests breaks or lighter tasks as needed. The inputs are emotional data and a task list, and the output is the adjusted task schedule.

[0808] Step 7:

[0809] The device that notifies the user displays a dynamically adjusted task schedule and sends reminders as needed. The input to this process is the adjusted task schedule, and the output is a notification message to the user.

[0810] Step 8:

[0811] The server tracks the progress of all tasks until they are completed. A progress management module updates the status hourly and archives completed tasks. The input is the task progress, and the output is archived tasks and progress reports.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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."

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] The following is further disclosed regarding the embodiments described above.

[0834] (Claim 1)

[0835] Means of gathering information from multiple sources,

[0836] A means of analyzing the collected information and converting it into a common format,

[0837] A means of automatically generating tasks based on the analyzed information,

[0838] A means of assigning priorities to the generated tasks,

[0839] A means of tracking task progress in real time,

[0840] A means of notifying users of reminders,

[0841] A system that includes this.

[0842] (Claim 2)

[0843] The system according to claim 1, further comprising means for predicting the deadline of generated tasks.

[0844] (Claim 3)

[0845] The system according to claim 1, further comprising means for archiving completed tasks and generating reports.

[0846] "Example 1"

[0847] (Claim 1)

[0848] A means of aggregating data from multiple information sources,

[0849] A means of analyzing aggregated data and converting it into a unified format,

[0850] A means of automatically generating tasks based on the analyzed data,

[0851] A means of setting priorities for the generated tasks,

[0852] A means to track the progress of the work in real time,

[0853] A means of sending notifications to users,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1 for estimating the deadline for generated work.

[0857] (Claim 3)

[0858] The system according to claim 1, which saves completed work and creates a record.

[0859] "Application Example 1"

[0860] (Claim 1)

[0861] Means of gathering information from multiple sources,

[0862] A means of analyzing the collected information and converting it into a common format,

[0863] A means of automatically generating tasks based on the analyzed information,

[0864] A means of assigning priorities to the generated tasks,

[0865] A means of tracking task progress in real time,

[0866] A means of notifying users of reminders,

[0867] A means of analyzing integrated information and improving public administration,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, further comprising means for predicting the deadline of generated tasks.

[0871] (Claim 3)

[0872] The system according to claim 1, further comprising means for archiving completed tasks and generating reports.

[0873] "Example 2 of combining an emotion engine"

[0874] (Claim 1)

[0875] A means of collecting data from multiple communication methods,

[0876] A means of analyzing the collected data and converting it into a unified format,

[0877] A means of automatically generating tasks based on the analyzed data,

[0878] A means of assigning priority to the generated tasks,

[0879] Means of recognizing an individual's emotional state,

[0880] A means of dynamically adjusting the priority of tasks based on recognized emotional states,

[0881] A means of tracking the progress of the work step by step,

[0882] Means of sending notifications to individuals,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, further comprising means for estimating the deadline for the generated work.

[0886] (Claim 3)

[0887] The system according to claim 1, further comprising means for storing completed work and generating reports.

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

[0889] (Claim 1)

[0890] Means of gathering information from multiple sources,

[0891] A means of analyzing the collected information and converting it into a common format,

[0892] A means of automatically generating tasks based on the analyzed information,

[0893] A means of assigning priorities to the generated tasks,

[0894] A means of tracking task progress in real time,

[0895] A means of notifying users of reminders,

[0896] A means for identifying the user's emotional state and dynamically adjusting task priorities based on that state,

[0897] A means of recommending appropriate tasks according to the user's emotional state,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, further comprising means for predicting the deadline of generated tasks and adjusting the pace of task progress based on the user's changing emotional state.

[0901] (Claim 3)

[0902] The system according to claim 1, further comprising means for archiving completed tasks and generating reports, and recording a history of task execution based on user sentiment. [Explanation of Symbols]

[0903] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of gathering information from multiple sources, A means of analyzing the collected information and converting it into a common format, A means of automatically generating tasks based on the analyzed information, A means of assigning priorities to the generated tasks, A means of tracking task progress in real time, A means of notifying users of reminders, A means of analyzing integrated information and improving public administration, A system that includes this.

2. The system according to claim 1, further comprising means for predicting the deadline of generated tasks.

3. The system according to claim 1, further comprising means for archiving completed tasks and generating reports.

Images