System

Abstract

A system is provided.SOLUTION: The system includes a means having a generative artificial intelligence for processing a plurality of types of information including text information, image information, and voice information, a means for integrating, managing, and sharing task information processed by the generative artificial intelligence into a family-specific schedule table, a means for learning a past task sharing situation and suggesting future task sharing, and a means for notifying each member of the family of task information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In today's dual-income households, managing housework and childcare tasks is a complex and time-consuming challenge amid busy lives. Tasks arise from various information media (paper, apps, calendars, email, verbal communication, etc.), and much time is spent searching for, reviewing, sharing, and discussing the allocation of tasks. This situation can reduce the overall efficiency of the household and the quality of communication between family members. Therefore, there is a need for an improved system to efficiently manage and allocate housework and childcare tasks and make better use of family time. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a family-specific task management system that uses generative artificial intelligence to process multiple forms of information. The system includes the following means:

[0006] 1. A means with generative artificial intelligence that processes multiple forms of information, including text, images, and audio.

[0007] 2. A means for integrating the task information processed by the generating AI into a family-specific schedule and managing and sharing it.

[0008] 3. A means of learning past task allocation situations and suggesting future task allocations.

[0009] 4. A means of notifying each family member of task information.

[0010] This allows all family members to have a centralized view of information, efficiently divide and manage tasks, and improve the efficiency of household life.

[0011] "Text information" refers to information made up of characters or sentences, and includes emails, memos, chat messages, and the like.

[0012] "Image information" is information that is visually represented, such as photographs, screenshots, and scanned documents.

[0013] "Audio information" is information that is communicated through sound, such as voice memos or recorded conversations.

[0014] "Generative AI" is an AI technology that includes machine learning to analyze multiple forms of information and generate and convert the necessary data.

[0015] "Task information" is information that includes specific tasks and schedules to be performed, including the content, deadlines, and persons in charge.

[0016] A "family schedule" is a calendar or list-style information management tool that is shared among family members and used to manage daily tasks such as housework and childcare.

[0017] "Integration" refers to the process of consolidating information in multiple formats and converting it into a form that is easy to manage.

[0018] "Management" refers to properly organizing, storing, and tracking the progress of information and tasks.

[0019] "Sharing" means allowing multiple users to access the same information and to check and edit it.

[0020] "Learning" is a method of accumulating knowledge by analyzing past data and trends and using it to make future decisions and suggestions.

[0021] "Suggestion" refers to suggesting the best course of action or decision based on a current or future situation.

[0022] "Notification" is the act of notifying the user when important information, a task change, or a new task has been added. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0024] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0025] First, the terms used in the following description will be explained.

[0026] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0027] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0028] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0029] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 1, a 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.

[0034] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0036] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0037] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0041] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0043] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0044] The present invention is a task management system for families that facilitates efficient management and allocation of household and childcare tasks. The system utilizes generative artificial intelligence that can process multiple information formats, including text, images, and audio.

[0045] Server initialization and task management

[0046] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[0047] Creating and adding tasks for users

[0048] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, if a mother adds a "shopping" task, the user enters the task information into the system. The server receives the task information and processes it using generative artificial intelligence.

[0049] Task information integration and management

[0050] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[0051] Task notification and allocation

[0052] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Mother," the system automatically sends a notification to "Mother" informing her of the task content and deadline. This allows the user to immediately understand the new task.

[0053] Learning and suggestions

[0054] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the AI ​​model to analyze past task performance and suggest optimal task allocation. For example, if the mother was busy in the past, it will suggest that the next task be assigned to another family member.

[0055] Responding to urgent tasks

[0056] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server will automatically process the emergency task using an AI model and notify the user in charge. This type of system makes it possible to quickly respond to sudden changes in schedules.

[0057] This system unifies task management and information sharing within the family, enabling efficient task allocation. All family members can grasp information in a unified manner, enabling them to carry out tasks efficiently in their daily lives.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also initializes a multimodal generative AI model.

[0061] Step 2:

[0062] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother."

[0063] Step 3:

[0064] A user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, a user creates a "shopping" task.

[0065] Step 4:

[0066] The server receives the task information and sends it to the generating AI through the 'add_task' method. This process begins the integration and management of task information.

[0067] Step 5:

[0068] The device processes various information formats, such as text, images, and audio, using the generative AI's 'process_input' method, which integrates and analyzes information in different formats.

[0069] Step 6:

[0070] The server registers the processed task information in a family-specific schedule that can be accessed by all family members, allowing for centralized task management.

[0071] Step 7:

[0072] The server notifies the assigned user that a new task has been added. For example, if the task "Shopping" is assigned to "Mother," a notification is sent to "Mother."

[0073] Step 8:

[0074] The server executes the "learn_and_suggest" method to learn from past task allocation situations, allowing the AI ​​model to suggest optimal task allocation based on past data.

[0075] Step 9:

[0076] The server assigns new tasks to appropriate family members based on the task sharing suggestions, and handles urgent tasks as well, if necessary.

[0077] Step 10:

[0078] The server sends timely notifications to the assigned users about the assigned tasks, allowing all family members to receive real-time task updates.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] In modern family life, efficient management and fair distribution of household and childcare tasks are important. However, manually managing household tasks is extremely time-consuming and can lead to uneven distribution of the burden among members. Furthermore, while rapid response is required in emergencies, manual task redistribution takes time and is difficult to achieve. Furthermore, the inability to centrally manage and share diverse information formats (text, images, audio) makes information integration difficult. Therefore, a system that solves these issues and enables efficient and fair household task management is needed.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server includes means for equipping a generative model for processing information in multiple formats, including text, image, and audio information, means for integrating, managing, and sharing task information processed by the generative model, means for learning past task execution status and proposing future task allocation, means for notifying each member of the task information, and means for redistributing tasks and notifying them quickly in an emergency. This enables efficient and fair management of household tasks, as well as the integration and sharing of information, enabling rapid response in an emergency.

[0084] "Text information" is information that represents characters or sentences in a digital format.

[0085] "Image information" is information that represents visual data in a digital format.

[0086] "Audio information" is information that represents sound waveforms in digital form.

[0087] A "generative model" is an advanced machine learning algorithm that generates new data or information based on input data.

[0088] "Task information" is digital data that indicates the specific tasks and deadlines for housework, childcare, etc.

[0089] "Integration" is the process of centralizing data of different formats.

[0090] "Management" is the process of planning, executing, and monitoring data and tasks.

[0091] "Sharing" refers to making information accessible to multiple users.

[0092] "Suggestion" refers to the process in which the system suggests the optimal action or allocation of work.

[0093] A "notification" is a message or alert sent to inform a user of specific information.

[0094] An "emergency" is a situation in which a high-priority event occurs that alters normal schedules and plans.

[0095] "Redistribution" refers to the act of rearranging existing tasks or resources.

[0096] A "server" refers to a computer system that provides data and services over a network.

[0097] The following describes in detail an embodiment of the present invention. The present invention is a task management system for home use that facilitates efficient management and allocation of housework and childcare tasks. This system utilizes a generative model that can process multiple information formats, such as text information, image information, and audio information.

[0098] First, the server, which is the central part of the system, instantiates the "FamilyScheduler" class and the generative model. The server uses the Python language to load the AI ​​model using the "TENSORFLOW (registered trademark)" and "pytorch" libraries. This initializes a schedule for managing household tasks and makes available a generative model capable of processing information in various formats.

[0099] Users log in to the system using a smartphone app or web app and enter their information. Users can create new tasks by creating an instance of the "User" class and setting a name. For example, if a mother wants to add a task such as "Buy groceries at the supermarket by the end of the week," the user enters the details of the task into the system. The task information is sent to the server and processed using the generative model.

[0100] The device (smartphone or web browser) processes the task information received from the server using the "process_input" method. At this stage, various types of information, such as text, images, and audio, are integrated and centralized into a home-specific schedule. For example, if a mother inputs a "shopping" task and provides an image of a grocery list and a voice memo, the generative model processes this and integrates the relevant information.

[0101] The server registers the processed task information in the schedule and sends a notification to the responsible user. For example, if a new shopping task is added to "Mother," the system automatically sends a push notification to the mother informing her of the task content and deadline. Notifications can be sent via email or in-app push notifications.

[0102] Furthermore, the server uses the "learn_and_suggest" method to learn from past task execution situations and suggest optimal task allocation. For example, if the mother has been particularly busy in the past, it will suggest that the next shopping task be assigned to the father. This process ensures that the workload of the entire family is evenly distributed.

[0103] In the event of an emergency, the server processes urgent tasks in real time using a generative model and redistributes them. For example, if a mother has an unexpected meeting, the server creates an urgent task based on this information, redistributes it to other users who are available, and notifies them. This enables a rapid response.

[0104] Examples of prompts include:

[0105] "Add a new task. Enter the task content (e.g., shopping), task details (e.g., buy groceries at the supermarket by the end of the week), and due date (e.g., this weekend)."

[0106] This system centralizes task management and information sharing within the home, enabling efficient task allocation and rapid response.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] Server initialization and task management:

[0110] When the system starts up, the server instantiates the "FamilyScheduler" class and the generative model. The input is the server startup instruction and necessary libraries (e.g., tensorflow and pytorch). The server uses these libraries to load the generative model and initialize a schedule for managing household tasks. The output is an initialized task management system and an instance of the generative model. Specifically, the server runs code to load the generative model and verify that the schedule works correctly.

[0111] Step 2:

[0112] User task creation:

[0113] A user logs into the system using a smartphone app or web app and enters their information. Input includes the user's name and login information. The user creates an instance of the "User" class and sets their name. The output is a user profile. Specifically, the mother enters her name into the app's input form and clicks the "Save" button, which sends this information to the server.

[0114] Step 3:

[0115] Add a new task:

[0116] The user creates a new task and enters task information (e.g., task description, due date). The input includes the task description (e.g., "shopping") and due date (e.g., "this weekend"). The server receives this information and processes the task information using a generative model. The output is the processed task information stored in the server. Specifically, the mother enters "Buy groceries at the supermarket by this weekend" into the task addition screen of the app and clicks the "Add" button to send the information.

[0117] Step 4:

[0118] Task information integration and management:

[0119] The device processes the task information received from the server using the "process_input" method. The input is task information in text, image, and audio format. The generative model integrates these different types of data and unifies them into a schedule dedicated to the family. The output is the integrated task information reflected in the schedule. Specifically, the device receives text data and image data from the server and reflects it in the schedule.

[0120] Step 5:

[0121] Task Notifications:

[0122] The server registers the processed task information in the schedule and notifies the responsible user. The input is the integrated task information and the responsible user information. The server uses this to generate a push notification and sends it to the user. The output is a notification displayed on the user's smartphone or device. Specifically, when a new task is added to "Mother," the system automatically sends a push notification to Mother, informing her of the task content and deadline.

[0123] Step 6:

[0124] Task sharing learning and suggestions:

[0125] The server uses the "learn_and_suggest" method to learn about past task execution status and propose future task allocations. The input is past task history data. The generative model analyzes this data and proposes optimal task allocations. The output is that the proposed task allocations are saved on the server and notified to the user. Specifically, if the mother has been busy in the past, a suggestion is made to allocate the next shopping task to the father.

[0126] Step 7:

[0127] Urgent task handling:

[0128] The server redistributes tasks in emergencies and notifies them quickly. The input is information about the emergency and the current task status. The generative model analyzes this and performs appropriate redistribution. The output is that the redistributed task information is notified to the responsible user. Specifically, if the mother has an unexpected meeting, the generative model creates a new task, redistributes it to other users, and notifies them. This information is immediately notified to the relevant users, allowing for a quick response.

[0129] (Application example 1)

[0130] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0131] Currently, task management in business environments is often done manually, resulting in missed or delayed tasks. It is also difficult to share task information and assign tasks to the appropriate personnel, often hindering work efficiency. Furthermore, when an unexpected urgent task arises, existing task management systems make it difficult to respond quickly, potentially causing delays to the entire business. There is a need to address these issues.

[0132] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0133] In this invention, the server

[0134] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[0135] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the business environment;

[0136] A means to learn past task allocation situations and suggest future task allocations;

[0137] means for notifying each member of the work environment of task information;

[0138] A means to automatically process and notify the person in charge when an emergency task occurs;

[0139] A means for agents to add and update task information using their smartphones, tablets, or smart glasses;

[0140] This enables efficient management and allocation of tasks in a work environment, rapid information sharing, and immediate response to urgent tasks.

[0141] "Text information" is information expressed as sentences or character data.

[0142] "Image information" is visual data such as photographs and pictures.

[0143] "Audio information" is acoustic data that includes human voices and other sounds.

[0144] "Generative AI" is an AI technology that processes information in various formats, such as text, images, and audio, and generates appropriate results.

[0145] "Means" are the methods or tools used to achieve a particular goal.

[0146] "Task information" is detailed data related to a particular task or responsibility.

[0147] A "schedule" is a plan showing the timing and person in charge of tasks and plans.

[0148] "Integration" means bringing together multiple pieces of information or data into one.

[0149] "Management" means coordinating and controlling tasks and information in order to operate them efficiently.

[0150] "Sharing" means making the same information available to multiple people or systems.

[0151] "Learning" is the acquisition of knowledge and patterns based on past data and experience.

[0152] A "suggestion" is a recommendation of a particular action or option.

[0153] "Notification" means conveying information or a message to a specific recipient.

[0154] A "system" is a set of devices and programs in which multiple elements function in conjunction with one another.

[0155] An "urgent task" is work that requires immediate action in an unexpected situation.

[0156] A "person in charge" is someone who is in charge of a specific task or job.

[0157] A "smartphone" is a type of mobile information terminal that can use a variety of applications in addition to making calls.

[0158] A "tablet" is a portable computing device that primarily features a touch screen.

[0159] "Smart glasses" are wearable devices that allow the wearer to obtain additional visual information.

[0160] MODE FOR CARRYING OUT THE INVENTION

[0161] The following describes in detail the embodiments of the present invention. The present invention is a system for streamlining task management in a business environment and appropriately allocating task information. The system utilizes a generative AI model that processes various information formats, such as text, images, and audio.

[0162] Server initialization and task management

[0163] The server first instantiates the "TaskMaster" class, which initializes a schedule for managing tasks in the work environment and instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[0164] Creating and adding tasks for users

[0165] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, when an employee adds a task for "inventorying products," the user enters the task information into the system. The server receives this task information and processes it using generative artificial intelligence.

[0166] Task information integration and management

[0167] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates not only text information but also various other information formats such as images and audio, and centralizes it into a schedule dedicated to the work environment. The processed task information is automatically registered in the server's schedule.

[0168] Task notification and allocation

[0169] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Employee A," the system automatically sends a notification to "Employee A" informing him of the task content and deadline. This allows the user to immediately understand the new task.

[0170] Learning and suggestions

[0171] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the generative AI model to analyze past task performance and suggest optimal task allocation. For example, if a specific employee was busy in the past, it will suggest that the next task be assigned to another employee.

[0172] Responding to urgent tasks

[0173] In the case of an emergency, for example, if an employee has a sudden meeting and is temporarily unable to take on another task, the server automatically processes the urgent task using a generative AI model and notifies the responsible user. This type of system makes it possible to quickly respond to sudden schedule changes.

[0174] This system unifies task management and information sharing in the work environment, enabling efficient task allocation. All employees can grasp information in a unified manner, enabling them to carry out tasks efficiently within the workplace.

[0175] Hardware and Software Used

[0176] Hardware:

[0177] Smartphone

[0178] tablet

[0179] Smart Glasses

[0180] software:

[0181] Backend system using Python

[0182] The generative AI model uses, for example, OpenAI's GPT-4 (registered trademark) API.

[0183] Specific usage examples and prompts

[0184] Usage example

[0185] Consider a scenario where an employee adds a new task using a smartphone. For example, an employee adds a task called "Inventory the products."

[0186] Prompt Sentence Examples

[0187] New task information:

[0188] Task: Inventory the goods

[0189] Deadline: 2023-10-15 18:00

[0190] Divide this task appropriately and notify the responsible parties.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] The server initializes the system

[0194] The server instantiates the "TaskMaster" class and initializes a schedule table and generative AI model specific to the work environment, laying the foundation for task management.

[0195] Input: None (at system startup)

[0196] Output: Initialized schedule and generative AI model

[0197] Specific operation: The server creates an instance of the TaskMaster class, initializes the schedule table within it, and loads the generative AI model.

[0198] Step 2:

[0199] A user creates or adds a task

[0200] A user creates an instance of the "User" class, enters task information including a task description and deadline date, and sends it to the server.

[0201] Input: Task information (description, due date)

[0202] Output: Task information sent to the server

[0203] Specific operation: A user uses a device (smartphone, tablet, smart glasses) to enter task information and clicks a button to send it to the server.

[0204] Step 3:

[0205] The server processes task information using a generative AI model

[0206] The server processes the received task information using the "process_input" method of the generation AI model, and analyzes and optimizes the task information.

[0207] Input: Task information

[0208] Output: Task information processed by the generative AI model

[0209] Specific operation: The server passes task information to the generative AI model, which integrates text analysis, image, and audio data to generate optimized task information, including the assignment of personnel.

[0210] Step 4:

[0211] Integrate task information into your schedule

[0212] The server integrates the processed task information into a dedicated business schedule and updates the information on tasks and people in charge.

[0213] Input: Task information processed by the generative AI model

[0214] Output: Updated schedule table

[0215] Specific behavior: The server adds a new task entry to the scheduler, sets the assignee and due date.

[0216] Step 5:

[0217] Sending task notifications

[0218] The server notifies the user of the task information, which is sent to the user's device (smartphone, tablet, smart glasses).

[0219] Input: Updated schedule

[0220] Output: Task notification sent to the user's device

[0221] Specific Actions: The server sends a notification message to the appropriate user device, informing the user of the new task and its details.

[0222] Step 6:

[0223] Analyze past task data and perform suggestion functions

[0224] The server analyzes past task allocation situations using a generative AI model and suggests optimal task allocation for the next time.

[0225] Input: Past task data

[0226] Output: Suggested task allocation plan

[0227] Specific operation: The server collects past task data, analyzes it using a generative AI model, and generates a new allocation plan that takes into account the workload of each person in charge, etc.

[0228] Step 7:

[0229] Automated handling of urgent tasks

[0230] When an urgent task arises, the server uses generative AI models to automatically handle the task and notify the appropriate personnel.

[0231] Input: Urgent task information

[0232] Output: Urgent task processing results and notifications

[0233] Specific operation: The server receives an urgent task, determines the optimal response and person in charge using a generative AI model, and immediately notifies the user.

[0234] These steps will improve the efficiency of task management in a business environment and achieve rational task distribution.

[0235] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0236] The present invention provides a task management system for families that facilitates efficient management and sharing of household and childcare tasks, and incorporates an emotion engine that recognizes the user's emotions.

[0237] Server initialization and task management

[0238] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[0239] Creating and adding tasks for users

[0240] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[0241] Task information integration and management

[0242] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[0243] Emotion recognition by emotion engine

[0244] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[0245] Task notification and emotion-based work allocation adjustment

[0246] The server registers the processed task information in a family schedule and adjusts task allocation based on the emotional data output by the emotion engine. For example, if the mother is feeling stressed, the server will allocate tasks to other family members. Notifications are also given at the optimal time and in the most appropriate way based on the mother's emotional state.

[0247] Learning and suggestions

[0248] The server runs the "learn_and_suggest" method to learn from past task allocation and emotional data. This allows the AI ​​model to suggest optimal task allocation based on past data. For example, if the mother has been busy in the past, the next task will be suggested to be assigned to another family member.

[0249] Emergency Task Response and Emotion Recognition

[0250] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[0251] This system unifies task management and information sharing within the family, enabling efficient task allocation, and by utilizing emotion recognition, it enables flexible task adjustment according to the user's emotional state. All family members can grasp information in a unified manner, enabling them to efficiently complete tasks in their daily lives.

[0252] The processing flow will be explained below.

[0253] Step 1:

[0254] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[0255] Step 2:

[0256] A user creates an instance of the "User" class and sets their name. For example, let's create a user named "Mother."

[0257] Step 3:

[0258] A user creates a new task and sends the task information (eg, a "shopping" description and due date) to the server.

[0259] Step 4:

[0260] The server receives the task information and sends it to the AI ​​generator using the "add_task" method, where task information processing begins.

[0261] Step 5:

[0262] The device uses the generative AI's 'process_input' method to process information in various formats, including text, images, and audio, allowing information to be processed in a unified manner regardless of the input format.

[0263] Step 6:

[0264] The server registers the processed task information in a family-specific schedule, which can be accessed by all family members and allows for centralized task integration and management.

[0265] Step 7:

[0266] When a task is added or an important notification is received, the device analyzes the user's voice and facial expressions through the emotion engine, and as a result of this analysis, the device recognizes the user's emotional state.

[0267] Step 8:

[0268] The server adjusts task allocation based on the emotion data obtained from the emotion engine. For example, if a user is feeling stressed, the server will not assign new tasks to that user.

[0269] Step 9:

[0270] When a new task is added, the server notifies the user in charge of the task. The notification is performed at an appropriate time and in an appropriate manner by the emotion engine.

[0271] Step 10:

[0272] The server runs the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[0273] Step 11:

[0274] When assigning new tasks to family members, the server takes emotional data into consideration when deciding on the allocation and notifies the assigned user. Even in the case of urgent tasks, the server uses the emotion engine to handle them appropriately.

[0275] Through these steps, the system centralizes task management and information sharing within the home, realizing efficient task allocation that takes into consideration the user's feelings.

[0276] Example 2

[0277] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0278] In modern households, it is difficult to efficiently manage and share the burden of housework and childcare among all family members. It is also not easy to coordinate tasks based on each member's emotional state or to respond efficiently in emergencies. Furthermore, it is necessary to integrate information in various formats (text, images, audio, etc.) and manage schedules appropriately. Conventional systems do not adequately provide the means to effectively solve these problems.

[0279] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0280] In this invention, the server includes a means with an emotion recognition engine to efficiently manage and easily allocate housework and childcare tasks, a means with a generation AI that processes multiple forms of information including text information, image information, and audio information, and a means for integrating, managing, and sharing the task information processed by the generation AI into a family-specific schedule. This allows all family members to efficiently allocate tasks and flexibly adjust according to their emotional states and emergency situations.

[0281] "Housework and childcare tasks" is a general term for work done at home, such as cleaning, laundry, cooking, and caring for children.

[0282] An "emotion recognition engine" is a system that analyzes a user's voice, facial expressions, etc. to recognize their emotional state.

[0283] "Generative AI" is a system that processes various input formats, such as text, image, and audio information, to generate or infer knowledge.

[0284] A "schedule" is a tabular management tool for centrally managing task information so that each member of the household can check it in real time.

[0285] "Task sharing" means assigning household and childcare tasks to each family member.

[0286] "Suggestion" means that the system suggests appropriate task allocation and actions based on past data and the current situation.

[0287] An "urgent task" is a task that requires immediate action in an emergency.

[0288] "Natural language processing" is a technology for analyzing text information and processing human language.

[0289] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[0290] The present invention is a system that efficiently manages and facilitates the allocation of household chores and childcare tasks within a household. This system combines an emotion recognition engine and a generative AI model to ensure that each family member is able to share tasks fairly and efficiently.

[0291] Server initialization and task management

[0292] The server first creates an instance of the "FamilyScheduler" class. This instance is initialized with a schedule for managing household tasks. At the same time, a multimodal (including text, image, and audio) generative AI model and an emotion recognition engine are also initialized. This establishes the foundation for household task management.

[0293] Creating and adding tasks for users

[0294] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (for example, a description of "Shopping" and a due date of "2023-10-15") to the server. This process registers the user's task information on the server.

[0295] Task information integration and management

[0296] The device processes the task information obtained from the server using a method called "process_input." This method integrates data in various formats, including text, images, and audio, and centralizes it into a schedule for the family. For example, a tablet device can obtain "photos of cleaning" and "voice notes of a shopping list" and integrate this information into the schedule.

[0297] Emotion recognition by emotion engine

[0298] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine analyzes voice and facial images to recognize the user's emotional state. For example, a smartphone can analyze the user's facial expression, detect "fatigue," and send the emotional data to the server.

[0299] Task notification and emotion-based work allocation adjustment

[0300] The server not only registers the processed task information in the schedule, but also adjusts task allocation based on emotional data provided by the emotion engine. For example, if the server detects that the mother is "tired," it will assign the "cooking" task to the father or children. Notifications are made at the optimal time based on this emotional state. A message such as "Mom is tired, please help with cooking" is sent to other family members.

[0301] Learning and suggestions

[0302] The server learns from past task allocation status and emotional data using a method called "learn_and_suggest." For example, if "mother has been busy in the past," the AI ​​model will suggest that the next task be assigned to another family member. This ensures that household tasks are assigned efficiently and fairly.

[0303] Emergency Task Response and Emotion Recognition

[0304] In the case of an emergency, for example, if the mother has to attend a sudden meeting, the server responds quickly using an emotion engine and generative AI model. It detects the emotion "Mother is currently busy" and automatically assigns "childcare" to the father. This information is sent to the father's device as an emergency notification.

[0305] As a concrete example, the prompt sentence for registering the task "shopping" is as follows:

[0306] Prompt Sentence Examples

[0307] "Mom needs to complete the shopping task to buy bread and milk by October 15th."

[0308] This system allows all family members to efficiently share tasks and respond flexibly according to their emotional state and emergency situations.

[0309] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0310] Step 1: Initialize the server

[0311] The server first creates an instance of the "FamilyScheduler" class, which initializes a schedule for managing household tasks. It also initializes the generative AI model and emotion recognition engine.

[0312] Input: None

[0313] Output: Home task schedule, generative AI model, and emotion recognition engine initialization

[0314] Specific operation: The server calls the "FamilyScheduler.initialize()" method to perform initialization.

[0315] Step 2: Creating and adding tasks for users

[0316] A user creates an instance of the "User" class and sets their name. A user named "Mother" creates a new task and adds the task information (e.g., a description of "Shopping" and a due date of "2023-10-15") to the server.

[0317] Input: User name, task description, due date

[0318] Output: Task information is registered on the server

[0319] Specific operation: The user uses the "User.create()" method from the terminal, enters their information, and then uses the "Task.add()" method to send the task information to the server.

[0320] Step 3: Consolidate and manage task information

[0321] The device processes the task information received from the server using the "process_input" method, unifying data such as text, images, and audio, and integrating it into a schedule for the family.

[0322] Input: Task information received from the server (text, image, audio)

[0323] Output: The integrated task information is added to the scheduler

[0324] Specific operation: The terminal calls the "process_input" method, analyzes the received task information, and adds it to the schedule.

[0325] Step 4: Emotion Recognition with the Emotion Engine

[0326] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine performs voice and image analysis to recognize the user's emotional state.

[0327] Input: User's voice data or facial image data

[0328] Output: Parsed emotion data

[0329] Specific operation: The device calls the "EmotionEngine.analyze()" method and analyzes voice and facial images to obtain emotional data.

[0330] Step 5: Task notification and emotion-based allocation adjustment

[0331] The server registers the processed task information in a schedule and adjusts task allocation based on the emotion data from the emotion engine. For example, if the mother feels "tired," the server will assign the "cooking task" to another family member.

[0332] Input: Integrated task information, analyzed emotion data

[0333] Output: Adjusted task allocation, notification message

[0334] Specific operation: The server uses the "TaskSchedule.update()" method to reconstruct task allocation based on emotion data and send a notification.

[0335] Step 6: Learning and Suggestions

[0336] The server uses the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[0337] Input: Past task allocation data, past emotion data

[0338] Output: Suggested task allocation plan

[0339] Specific operation: The server calls the "learn_and_suggest" method, learns from past data, and generates task allocation proposals for the next time and beyond.

[0340] Step 7: Emergency Task Management and Emotion Recognition

[0341] The server uses an emotion engine and generative AI model to quickly respond when an emergency occurs. For example, if a mother has to attend a sudden meeting, the emotion engine will detect that she is "busy" and automatically assign the "childcare" task to another family member.

[0342] Input: Emergency situation, user emotion data

[0343] Output: Urgent task reassignment, notification message

[0344] Specific operation: The server calls the "EmergencyHandler.handle()" method, analyzes the emotion data, and takes appropriate action and notifies the user.

[0345] This allows the whole family to efficiently share tasks and respond flexibly according to emotional states and emergency situations.

[0346] (Application example 2)

[0347] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0348] Improving the efficiency of task management at home and in the workplace and achieving fair task allocation are extremely important. However, conventional task management systems uniformly assign tasks without considering the user's emotional state, which can easily lead to the accumulation of stress and overwork, making efficient task management difficult. As a result, users' health and work efficiency are often adversely affected. The present invention aims to achieve both user health and efficient task allocation by recognizing the user's emotional state and dynamically adjusting tasks based on that information.

[0349] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0350] In this invention, the server includes means for generating artificial intelligence that processes information in multiple formats including text information, image information, and audio information, means for integrating, managing, and sharing the task information processed by the artificial intelligence into a schedule dedicated to family or workplace, means for learning past task allocation status and suggesting future task allocation, means for notifying each member of the family or workplace of the task information, means for recognizing the user's emotional state through audio or image analysis and adjusting task allocation based on the emotional data, and means for optimizing task allocation according to the user's stress level, thereby enabling efficient and healthy task management that takes the user's emotional state into consideration.

[0351] "Text information" is digital data expressed in characters.

[0352] "Image information" is digital data in the form of an image.

[0353] "Audio information" is digital data in audio format.

[0354] "Generative AI" is AI that uses machine learning and deep learning to process information in multiple formats, including text, images, and audio.

[0355] A "family or workplace schedule" is a list of plans and tasks shared among family or workplace members.

[0356] "Means for integration, management, and sharing" refers to methods and systems for centralizing task information and efficiently managing and sharing it.

[0357] The "means for learning past task allocation situations and suggesting future task allocations" refers to a method or system for analyzing past task history and making suggestions regarding future task allocations.

[0358] The "means for notifying each member of task information" refers to a method or system for notifying family members or coworkers of task information.

[0359] "Means for recognizing emotional states through audio or image analysis" refers to a method or system for identifying a user's emotions from audio or image data.

[0360] "Means for adjusting task allocation based on emotional data" refers to a method or system that uses the results of emotional analysis to flexibly change task allocation.

[0361] The "means for optimizing task allocation according to stress state" refers to a method or system for optimizing task allocation taking into account the stress level of the user.

[0362] The following describes in detail an embodiment of the present invention. The present invention is a system for improving the efficiency of task management at home and at work and realizing task allocation based on the user's emotional state. This system recognizes the user's emotional state and adjusts task allocation based on that state, thereby reducing the user's stress and improving task execution efficiency.

[0363] System Configuration

[0364] The server first instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine.

[0365] A user creates an instance of the "User" class and sets their name. In this example, a user named "Staff A" is created. The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[0366] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats, such as text, images, and audio, and centralizes it into a dedicated schedule. The processed task information is automatically registered in the server's schedule.

[0367] Emotion Recognition Engine Details

[0368] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[0369] Adjusting task allocation

[0370] The server adjusts task allocation based on the emotional data output by the emotion engine. For example, if staff member A is feeling stressed, the server will assign cash register duties to another staff member and suggest that staff member A take a break. Notifications are also given at the optimal time and in the most appropriate way based on the emotional state.

[0371] Learning and suggestions

[0372] The server executes the "learn_and_suggest" method to learn from past task allocation status and emotional data. This allows the generative AI model to suggest optimal task allocation based on past data. For example, if staff member A has been busy in the past, it will suggest that the next task be assigned to another staff member.

[0373] Responding to urgent tasks

[0374] In the case of an emergency, for example, when Staff A needs to respond immediately, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[0375] Specific examples

[0376] If Staff A is working at the cash register and is tired, the system will assign the cash register task to Staff B and suggest that Staff A take a break.

[0377] Prompt Sentence Examples

[0378] You will work as part of a staff task management system for a brick-and-mortar store. Your role will be to adjust task allocation based on the following tasks and staff sentiment data:

[0379] Task list: Cashiering, Stocking products

[0380] Emotional Data:

[0381] Staff A: High stress

[0382] Staff B: Normal

[0383] output:

[0384] 1. Suggest a break to Staff A

[0385] 2. Reassign cashier duties to Staff B

[0386] This will improve the efficiency of task management at home and at work, and enable flexible task allocation and adjustment according to the user's emotional state.

[0387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0388] Step 1:

[0389] The server instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine, giving the system task management and emotion recognition capabilities.

[0390] Input: None (initial setting at system startup)

[0391] Output: An instance of the "Scheduler" class

[0392] Step 2:

[0393] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. This registers the task in the system.

[0394] Input: User's name and new task information (e.g. cashier, due date)

[0395] Output: Task information registered on the server

[0396] Step 3:

[0397] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats (text, images, audio) and centralizes it into a dedicated schedule.

[0398] Input: Task information received from the server

[0399] Output: Consolidated task information

[0400] Step 4:

[0401] The device uses an emotion engine to analyze the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[0402] Input: User voice and image data

[0403] Output: Emotional state data

[0404] Step 5:

[0405] The server adjusts task allocation based on the emotional state data output by the emotion engine. For example, if a user is feeling stressed, the server will assign the task to another member.

[0406] Input: Emotional state data

[0407] Output: Adjusted task allocation

[0408] Step 6:

[0409] The server notifies the user of task information according to the user's emotional state. The notification is performed at the most appropriate timing and in the most appropriate manner based on the user's emotional state.

[0410] Input: Adjusted task allocation

[0411] Output: User notification

[0412] Step 7:

[0413] The server runs the "learn_and_suggest" method to learn past task allocation and emotion data, which allows it to suggest future task allocations.

[0414] Input: Past task allocation data, emotion data

[0415] Output: Proposed future task allocation

[0416] Step 8:

[0417] When an emergency task occurs, the server automatically processes it using the generative AI model and emotion engine, notifying the user in charge. The emotion engine analyzes the user's emotional state and adjusts the emergency response method appropriately.

[0418] Input: Urgent task information, emotional state data

[0419] Output: Emergency response measures and user notification

[0420] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0421] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0422] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0423] [Second embodiment]

[0424] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0425] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0426] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0428] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0430] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0431] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0432] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0433] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0434] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0435] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0436] The present invention is a task management system for families that facilitates efficient management and allocation of household and childcare tasks. The system utilizes generative artificial intelligence that can process multiple information formats, including text, images, and audio.

[0437] Server initialization and task management

[0438] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[0439] Creating and adding tasks for users

[0440] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, if a mother adds a "shopping" task, the user enters the task information into the system. The server receives the task information and processes it using generative artificial intelligence.

[0441] Task information integration and management

[0442] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[0443] Task notification and allocation

[0444] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Mother," the system automatically sends a notification to "Mother" informing her of the task content and deadline. This allows the user to immediately understand the new task.

[0445] Learning and suggestions

[0446] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the AI ​​model to analyze past task performance and suggest optimal task allocation. For example, if the mother was busy in the past, it will suggest that the next task be assigned to another family member.

[0447] Responding to urgent tasks

[0448] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server will automatically process the emergency task using an AI model and notify the user in charge. This type of system makes it possible to quickly respond to sudden changes in schedules.

[0449] This system unifies task management and information sharing within the family, enabling efficient task allocation. All family members can grasp information in a unified manner, enabling them to carry out tasks efficiently in their daily lives.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also initializes a multimodal generative AI model.

[0453] Step 2:

[0454] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother."

[0455] Step 3:

[0456] A user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, a user creates a "shopping" task.

[0457] Step 4:

[0458] The server receives the task information and sends it to the generating AI through the 'add_task' method. This process begins the integration and management of task information.

[0459] Step 5:

[0460] The device processes various information formats, such as text, images, and audio, using the generative AI's 'process_input' method, which integrates and analyzes information in different formats.

[0461] Step 6:

[0462] The server registers the processed task information in a family-specific schedule that can be accessed by all family members, allowing for centralized task management.

[0463] Step 7:

[0464] The server notifies the assigned user that a new task has been added. For example, if the task "Shopping" is assigned to "Mother," a notification is sent to "Mother."

[0465] Step 8:

[0466] The server executes the "learn_and_suggest" method to learn from past task allocation situations, allowing the AI ​​model to suggest optimal task allocation based on past data.

[0467] Step 9:

[0468] The server assigns new tasks to appropriate family members based on the task sharing suggestions, and handles urgent tasks as well, if necessary.

[0469] Step 10:

[0470] The server sends timely notifications to the assigned users about the assigned tasks, allowing all family members to receive real-time task updates.

[0471] Example 1

[0472] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] In modern family life, efficient management and fair distribution of household and childcare tasks are important. However, manually managing household tasks is extremely time-consuming and can lead to uneven distribution of the burden among members. Furthermore, while rapid response is required in emergencies, manual task redistribution takes time and is difficult to achieve. Furthermore, the inability to centrally manage and share diverse information formats (text, images, audio) makes information integration difficult. Therefore, a system that solves these issues and enables efficient and fair household task management is needed.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0475] In this invention, the server includes means for equipping a generative model for processing information in multiple formats, including text, image, and audio information, means for integrating, managing, and sharing task information processed by the generative model, means for learning past task execution status and proposing future task allocation, means for notifying each member of the task information, and means for redistributing tasks and notifying them quickly in an emergency. This enables efficient and fair management of household tasks, as well as the integration and sharing of information, enabling rapid response in an emergency.

[0476] "Text information" is information that represents characters or sentences in a digital format.

[0477] "Image information" is information that represents visual data in a digital format.

[0478] "Audio information" is information that represents sound waveforms in digital form.

[0479] A "generative model" is an advanced machine learning algorithm that generates new data or information based on input data.

[0480] "Task information" is digital data that indicates the specific tasks and deadlines for housework, childcare, etc.

[0481] "Integration" is the process of centralizing data of different formats.

[0482] "Management" is the process of planning, executing, and monitoring data and tasks.

[0483] "Sharing" refers to making information accessible to multiple users.

[0484] "Suggestion" refers to the process in which the system suggests the optimal action or allocation of work.

[0485] A "notification" is a message or alert sent to inform a user of specific information.

[0486] An "emergency" is a situation in which a high-priority event occurs that alters normal schedules and plans.

[0487] "Redistribution" refers to the act of rearranging existing tasks or resources.

[0488] A "server" refers to a computer system that provides data and services over a network.

[0489] The following describes in detail an embodiment of the present invention. The present invention is a task management system for home use that facilitates efficient management and allocation of housework and childcare tasks. This system utilizes a generative model that can process multiple information formats, such as text information, image information, and audio information.

[0490] First, the central server of the system instantiates the "FamilyScheduler" class and the generative model. The server uses the Python language and loads the AI ​​model using the "tensorflow" and "pytorch" libraries. This initializes a schedule for managing household tasks and makes available the generative model, which is capable of processing information in various formats.

[0491] Users log in to the system using a smartphone app or web app and enter their information. Users can create new tasks by creating an instance of the "User" class and setting a name. For example, if a mother wants to add a task such as "Buy groceries at the supermarket by the end of the week," the user enters the details of the task into the system. The task information is sent to the server and processed using the generative model.

[0492] The device (smartphone or web browser) processes the task information received from the server using the "process_input" method. At this stage, various types of information, such as text, images, and audio, are integrated and centralized into a home-specific schedule. For example, if a mother inputs a "shopping" task and provides an image of a grocery list and a voice memo, the generative model processes this and integrates the relevant information.

[0493] The server registers the processed task information in the schedule and sends a notification to the responsible user. For example, if a new shopping task is added to "Mother," the system automatically sends a push notification to the mother informing her of the task content and deadline. Notifications can be sent via email or in-app push notifications.

[0494] Furthermore, the server uses the "learn_and_suggest" method to learn from past task execution situations and suggest optimal task allocation. For example, if the mother has been particularly busy in the past, it will suggest that the next shopping task be assigned to the father. This process ensures that the workload of the entire family is evenly distributed.

[0495] In the event of an emergency, the server processes urgent tasks in real time using a generative model and redistributes them. For example, if a mother has an unexpected meeting, the server creates an urgent task based on this information, redistributes it to other users who are available, and notifies them. This enables a rapid response.

[0496] Examples of prompts include:

[0497] "Add a new task. Enter the task content (e.g., shopping), task details (e.g., buy groceries at the supermarket by the end of the week), and due date (e.g., this weekend)."

[0498] This system centralizes task management and information sharing within the home, enabling efficient task allocation and rapid response.

[0499] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0500] Step 1:

[0501] Server initialization and task management:

[0502] When the system starts up, the server instantiates the "FamilyScheduler" class and the generative model. The input is the server startup instruction and necessary libraries (e.g., tensorflow and pytorch). The server uses these libraries to load the generative model and initialize a schedule for managing household tasks. The output is an initialized task management system and an instance of the generative model. Specifically, the server runs code to load the generative model and verify that the schedule works correctly.

[0503] Step 2:

[0504] User task creation:

[0505] A user logs into the system using a smartphone app or web app and enters their information. Input includes the user's name and login information. The user creates an instance of the "User" class and sets their name. The output is a user profile. Specifically, the mother enters her name into the app's input form and clicks the "Save" button, which sends this information to the server.

[0506] Step 3:

[0507] Add a new task:

[0508] The user creates a new task and enters task information (e.g., task description, due date). The input includes the task description (e.g., "shopping") and due date (e.g., "this weekend"). The server receives this information and processes the task information using a generative model. The output is the processed task information stored in the server. Specifically, the mother enters "Buy groceries at the supermarket by this weekend" into the task addition screen of the app and clicks the "Add" button to send the information.

[0509] Step 4:

[0510] Task information integration and management:

[0511] The device processes the task information received from the server using the "process_input" method. The input is task information in text, image, and audio format. The generative model integrates these different types of data and unifies them into a schedule dedicated to the family. The output is the integrated task information reflected in the schedule. Specifically, the device receives text data and image data from the server and reflects it in the schedule.

[0512] Step 5:

[0513] Task Notifications:

[0514] The server registers the processed task information in the schedule and notifies the responsible user. The input is the integrated task information and the responsible user information. The server uses this to generate a push notification and sends it to the user. The output is a notification displayed on the user's smartphone or device. Specifically, when a new task is added to "Mother," the system automatically sends a push notification to Mother, informing her of the task content and deadline.

[0515] Step 6:

[0516] Task sharing learning and suggestions:

[0517] The server uses the "learn_and_suggest" method to learn about past task execution status and propose future task allocations. The input is past task history data. The generative model analyzes this data and proposes optimal task allocations. The output is that the proposed task allocations are saved on the server and notified to the user. Specifically, if the mother has been busy in the past, a suggestion is made to allocate the next shopping task to the father.

[0518] Step 7:

[0519] Urgent task handling:

[0520] The server redistributes tasks in emergencies and notifies them quickly. The input is information about the emergency and the current task status. The generative model analyzes this and performs appropriate redistribution. The output is that the redistributed task information is notified to the responsible user. Specifically, if the mother has an unexpected meeting, the generative model creates a new task, redistributes it to other users, and notifies them. This information is immediately notified to the relevant users, allowing for a quick response.

[0521] (Application example 1)

[0522] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0523] Currently, task management in business environments is often done manually, resulting in missed or delayed tasks. It is also difficult to share task information and assign tasks to the appropriate personnel, often hindering work efficiency. Furthermore, when an unexpected urgent task arises, existing task management systems make it difficult to respond quickly, potentially causing delays to the entire business. There is a need to address these issues.

[0524] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0525] In this invention, the server

[0526] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[0527] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the business environment;

[0528] A means to learn past task allocation situations and suggest future task allocations;

[0529] means for notifying each member of the work environment of task information;

[0530] A means to automatically process and notify the person in charge when an emergency task occurs;

[0531] A means for agents to add and update task information using their smartphones, tablets, or smart glasses;

[0532] This enables efficient management and allocation of tasks in a work environment, rapid information sharing, and immediate response to urgent tasks.

[0533] "Text information" is information expressed as sentences or character data.

[0534] "Image information" is visual data such as photographs and pictures.

[0535] "Audio information" is acoustic data that includes human voices and other sounds.

[0536] "Generative AI" is an AI technology that processes information in various formats, such as text, images, and audio, and generates appropriate results.

[0537] "Means" are the methods or tools used to achieve a particular goal.

[0538] "Task information" is detailed data related to a particular task or responsibility.

[0539] A "schedule" is a plan showing the timing and person in charge of tasks and plans.

[0540] "Integration" means bringing together multiple pieces of information or data into one.

[0541] "Management" means coordinating and controlling tasks and information in order to operate them efficiently.

[0542] "Sharing" means making the same information available to multiple people or systems.

[0543] "Learning" is the acquisition of knowledge and patterns based on past data and experience.

[0544] A "suggestion" is a recommendation of a particular action or option.

[0545] "Notification" means conveying information or a message to a specific recipient.

[0546] A "system" is a set of devices and programs in which multiple elements function in conjunction with one another.

[0547] An "urgent task" is work that requires immediate action in an unexpected situation.

[0548] A "person in charge" is someone who is in charge of a specific task or job.

[0549] A "smartphone" is a type of mobile information terminal that can use a variety of applications in addition to making calls.

[0550] A "tablet" is a portable computing device that primarily features a touch screen.

[0551] "Smart glasses" are wearable devices that allow the wearer to obtain additional visual information.

[0552] MODE FOR CARRYING OUT THE INVENTION

[0553] The following describes in detail the embodiments of the present invention. The present invention is a system for streamlining task management in a business environment and appropriately allocating task information. The system utilizes a generative AI model that processes various information formats, such as text, images, and audio.

[0554] Server initialization and task management

[0555] The server first instantiates the "TaskMaster" class, which initializes a schedule for managing tasks in the work environment and instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[0556] Creating and adding tasks for users

[0557] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, when an employee adds a task for "inventorying products," the user enters the task information into the system. The server receives this task information and processes it using generative artificial intelligence.

[0558] Task information integration and management

[0559] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates not only text information but also various other information formats such as images and audio, and centralizes it into a schedule dedicated to the work environment. The processed task information is automatically registered in the server's schedule.

[0560] Task notification and allocation

[0561] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Employee A," the system automatically sends a notification to "Employee A" informing him of the task content and deadline. This allows the user to immediately understand the new task.

[0562] Learning and suggestions

[0563] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the generative AI model to analyze past task performance and suggest optimal task allocation. For example, if a specific employee was busy in the past, it will suggest that the next task be assigned to another employee.

[0564] Responding to urgent tasks

[0565] In the case of an emergency, for example, if an employee has a sudden meeting and is temporarily unable to take on another task, the server automatically processes the urgent task using a generative AI model and notifies the responsible user. This type of system makes it possible to quickly respond to sudden schedule changes.

[0566] This system unifies task management and information sharing in the work environment, enabling efficient task allocation. All employees can grasp information in a unified manner, enabling them to carry out tasks efficiently within the workplace.

[0567] Hardware and Software Used

[0568] Hardware:

[0569] Smartphone

[0570] tablet

[0571] Smart Glasses

[0572] software:

[0573] Backend system using Python

[0574] Generative AI models use, for example, OpenAI's GPT-4 API.

[0575] Specific usage examples and prompts

[0576] Usage example

[0577] Consider a scenario where an employee adds a new task using a smartphone. For example, an employee adds a task called "Inventory the products."

[0578] Prompt Sentence Examples

[0579] New task information:

[0580] Task: Inventory the goods

[0581] Deadline: 2023-10-15 18:00

[0582] Divide this task appropriately and notify the responsible parties.

[0583] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0584] Step 1:

[0585] The server initializes the system

[0586] The server instantiates the "TaskMaster" class and initializes a schedule table and generative AI model specific to the work environment, laying the foundation for task management.

[0587] Input: None (at system startup)

[0588] Output: Initialized schedule and generative AI model

[0589] Specific operation: The server creates an instance of the TaskMaster class, initializes the schedule table within it, and loads the generative AI model.

[0590] Step 2:

[0591] A user creates or adds a task

[0592] A user creates an instance of the "User" class, enters task information including a task description and deadline date, and sends it to the server.

[0593] Input: Task information (description, due date)

[0594] Output: Task information sent to the server

[0595] Specific operation: A user uses a device (smartphone, tablet, smart glasses) to enter task information and clicks a button to send it to the server.

[0596] Step 3:

[0597] The server processes task information using a generative AI model

[0598] The server processes the received task information using the "process_input" method of the generation AI model, and analyzes and optimizes the task information.

[0599] Input: Task information

[0600] Output: Task information processed by the generative AI model

[0601] Specific operation: The server passes task information to the generative AI model, which integrates text analysis, image, and audio data to generate optimized task information, including the assignment of personnel.

[0602] Step 4:

[0603] Integrate task information into your schedule

[0604] The server integrates the processed task information into a dedicated business schedule and updates the information on tasks and people in charge.

[0605] Input: Task information processed by the generative AI model

[0606] Output: Updated schedule table

[0607] Specific behavior: The server adds a new task entry to the scheduler, sets the assignee and due date.

[0608] Step 5:

[0609] Sending task notifications

[0610] The server notifies the user of the task information, which is sent to the user's device (smartphone, tablet, smart glasses).

[0611] Input: Updated schedule

[0612] Output: Task notification sent to the user's device

[0613] Specific Actions: The server sends a notification message to the appropriate user device, informing the user of the new task and its details.

[0614] Step 6:

[0615] Analyze past task data and perform suggestion functions

[0616] The server analyzes past task allocation situations using a generative AI model and suggests optimal task allocation for the next time.

[0617] Input: Past task data

[0618] Output: Suggested task allocation plan

[0619] Specific operation: The server collects past task data, analyzes it using a generative AI model, and generates a new allocation plan that takes into account the workload of each person in charge, etc.

[0620] Step 7:

[0621] Automated handling of urgent tasks

[0622] When an urgent task arises, the server uses generative AI models to automatically handle the task and notify the appropriate personnel.

[0623] Input: Urgent task information

[0624] Output: Urgent task processing results and notifications

[0625] Specific operation: The server receives an urgent task, determines the optimal response and person in charge using a generative AI model, and immediately notifies the user.

[0626] These steps will improve the efficiency of task management in a business environment and achieve rational task distribution.

[0627] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0628] The present invention provides a task management system for families that facilitates efficient management and sharing of household and childcare tasks, and incorporates an emotion engine that recognizes the user's emotions.

[0629] Server initialization and task management

[0630] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[0631] Creating and adding tasks for users

[0632] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[0633] Task information integration and management

[0634] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[0635] Emotion recognition by emotion engine

[0636] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[0637] Task notification and emotion-based work allocation adjustment

[0638] The server registers the processed task information in a family schedule and adjusts task allocation based on the emotional data output by the emotion engine. For example, if the mother is feeling stressed, the server will allocate tasks to other family members. Notifications are also given at the optimal time and in the most appropriate way based on the mother's emotional state.

[0639] Learning and suggestions

[0640] The server runs the "learn_and_suggest" method to learn from past task allocation and emotional data. This allows the AI ​​model to suggest optimal task allocation based on past data. For example, if the mother has been busy in the past, the next task will be suggested to be assigned to another family member.

[0641] Emergency Task Response and Emotion Recognition

[0642] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[0643] This system unifies task management and information sharing within the family, enabling efficient task allocation, and by utilizing emotion recognition, it enables flexible task adjustment according to the user's emotional state. All family members can grasp information in a unified manner, enabling them to efficiently complete tasks in their daily lives.

[0644] The processing flow will be explained below.

[0645] Step 1:

[0646] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[0647] Step 2:

[0648] A user creates an instance of the "User" class and sets their name. For example, let's create a user named "Mother."

[0649] Step 3:

[0650] A user creates a new task and sends the task information (eg, a "shopping" description and due date) to the server.

[0651] Step 4:

[0652] The server receives the task information and sends it to the AI ​​generator using the "add_task" method, where task information processing begins.

[0653] Step 5:

[0654] The device uses the generative AI's 'process_input' method to process information in various formats, including text, images, and audio, allowing information to be processed in a unified manner regardless of the input format.

[0655] Step 6:

[0656] The server registers the processed task information in a family-specific schedule, which can be accessed by all family members and allows for centralized task integration and management.

[0657] Step 7:

[0658] When a task is added or an important notification is received, the device analyzes the user's voice and facial expressions through the emotion engine, and as a result of this analysis, the device recognizes the user's emotional state.

[0659] Step 8:

[0660] The server adjusts task allocation based on the emotion data obtained from the emotion engine. For example, if a user is feeling stressed, the server will not assign new tasks to that user.

[0661] Step 9:

[0662] When a new task is added, the server notifies the user in charge of the task. The notification is performed at an appropriate time and in an appropriate manner by the emotion engine.

[0663] Step 10:

[0664] The server runs the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[0665] Step 11:

[0666] When assigning new tasks to family members, the server takes emotional data into consideration when deciding on the allocation and notifies the assigned user. Even in the case of urgent tasks, the server uses the emotion engine to handle them appropriately.

[0667] Through these steps, the system centralizes task management and information sharing within the home, realizing efficient task allocation that takes into consideration the user's feelings.

[0668] Example 2

[0669] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0670] In modern households, it is difficult to efficiently manage and share the burden of housework and childcare among all family members. It is also not easy to coordinate tasks based on each member's emotional state or to respond efficiently in emergencies. Furthermore, it is necessary to integrate information in various formats (text, images, audio, etc.) and manage schedules appropriately. Conventional systems do not adequately provide the means to effectively solve these problems.

[0671] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0672] In this invention, the server includes a means with an emotion recognition engine to efficiently manage and easily allocate housework and childcare tasks, a means with a generation AI that processes multiple forms of information including text information, image information, and audio information, and a means for integrating, managing, and sharing the task information processed by the generation AI into a family-specific schedule. This allows all family members to efficiently allocate tasks and flexibly adjust according to their emotional states and emergency situations.

[0673] "Housework and childcare tasks" is a general term for work done at home, such as cleaning, laundry, cooking, and caring for children.

[0674] An "emotion recognition engine" is a system that analyzes a user's voice, facial expressions, etc. to recognize their emotional state.

[0675] "Generative AI" is a system that processes various input formats, such as text, image, and audio information, to generate or infer knowledge.

[0676] A "schedule" is a tabular management tool for centrally managing task information so that each member of the household can check it in real time.

[0677] "Task sharing" means assigning household and childcare tasks to each family member.

[0678] "Suggestion" means that the system suggests appropriate task allocation and actions based on past data and the current situation.

[0679] An "urgent task" is a task that requires immediate action in an emergency.

[0680] "Natural language processing" is a technology for analyzing text information and processing human language.

[0681] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[0682] The present invention is a system that efficiently manages and facilitates the allocation of household chores and childcare tasks within a household. This system combines an emotion recognition engine and a generative AI model to ensure that each family member is able to share tasks fairly and efficiently.

[0683] Server initialization and task management

[0684] The server first creates an instance of the "FamilyScheduler" class. This instance is initialized with a schedule for managing household tasks. At the same time, a multimodal (including text, image, and audio) generative AI model and an emotion recognition engine are also initialized. This establishes the foundation for household task management.

[0685] Creating and adding tasks for users

[0686] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (for example, a description of "Shopping" and a due date of "2023-10-15") to the server. This process registers the user's task information on the server.

[0687] Task information integration and management

[0688] The device processes the task information obtained from the server using a method called "process_input." This method integrates data in various formats, including text, images, and audio, and centralizes it into a schedule for the family. For example, a tablet device can obtain "photos of cleaning" and "voice notes of a shopping list" and integrate this information into the schedule.

[0689] Emotion recognition by emotion engine

[0690] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine analyzes voice and facial images to recognize the user's emotional state. For example, a smartphone can analyze the user's facial expression, detect "fatigue," and send the emotional data to the server.

[0691] Task notification and emotion-based work allocation adjustment

[0692] The server not only registers the processed task information in the schedule, but also adjusts task allocation based on emotional data provided by the emotion engine. For example, if the server detects that the mother is "tired," it will assign the "cooking" task to the father or children. Notifications are made at the optimal time based on this emotional state. A message such as "Mom is tired, please help with cooking" is sent to other family members.

[0693] Learning and suggestions

[0694] The server learns from past task allocation status and emotional data using a method called "learn_and_suggest." For example, if "mother has been busy in the past," the AI ​​model will suggest that the next task be assigned to another family member. This ensures that household tasks are assigned efficiently and fairly.

[0695] Emergency Task Response and Emotion Recognition

[0696] In the case of an emergency, for example, if the mother has to attend a sudden meeting, the server responds quickly using an emotion engine and generative AI model. It detects the emotion "Mother is currently busy" and automatically assigns "childcare" to the father. This information is sent to the father's device as an emergency notification.

[0697] As a concrete example, the prompt sentence for registering the task "shopping" is as follows:

[0698] Prompt Sentence Examples

[0699] "Mom needs to complete the shopping task to buy bread and milk by October 15th."

[0700] This system allows all family members to efficiently share tasks and respond flexibly according to their emotional state and emergency situations.

[0701] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0702] Step 1: Initialize the server

[0703] The server first creates an instance of the "FamilyScheduler" class, which initializes a schedule for managing household tasks. It also initializes the generative AI model and emotion recognition engine.

[0704] Input: None

[0705] Output: Home task schedule, generative AI model, and emotion recognition engine initialization

[0706] Specific operation: The server calls the "FamilyScheduler.initialize()" method to perform initialization.

[0707] Step 2: Creating and adding tasks for users

[0708] A user creates an instance of the "User" class and sets their name. A user named "Mother" creates a new task and adds the task information (e.g., a description of "Shopping" and a due date of "2023-10-15") to the server.

[0709] Input: User name, task description, due date

[0710] Output: Task information is registered on the server

[0711] Specific operation: The user uses the "User.create()" method from the terminal, enters their information, and then uses the "Task.add()" method to send the task information to the server.

[0712] Step 3: Consolidate and manage task information

[0713] The device processes the task information received from the server using the "process_input" method, unifying data such as text, images, and audio, and integrating it into a schedule for the family.

[0714] Input: Task information received from the server (text, image, audio)

[0715] Output: The integrated task information is added to the scheduler

[0716] Specific operation: The terminal calls the "process_input" method, analyzes the received task information, and adds it to the schedule.

[0717] Step 4: Emotion Recognition with the Emotion Engine

[0718] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine performs voice and image analysis to recognize the user's emotional state.

[0719] Input: User's voice data or facial image data

[0720] Output: Parsed emotion data

[0721] Specific operation: The device calls the "EmotionEngine.analyze()" method and analyzes voice and facial images to obtain emotional data.

[0722] Step 5: Task notification and emotion-based allocation adjustment

[0723] The server registers the processed task information in a schedule and adjusts task allocation based on the emotion data from the emotion engine. For example, if the mother feels "tired," the server will assign the "cooking task" to another family member.

[0724] Input: Integrated task information, analyzed emotion data

[0725] Output: Adjusted task allocation, notification message

[0726] Specific operation: The server uses the "TaskSchedule.update()" method to reconstruct task allocation based on emotion data and send a notification.

[0727] Step 6: Learning and Suggestions

[0728] The server uses the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[0729] Input: Past task allocation data, past emotion data

[0730] Output: Suggested task allocation plan

[0731] Specific operation: The server calls the "learn_and_suggest" method, learns from past data, and generates task allocation proposals for the next time and beyond.

[0732] Step 7: Emergency Task Management and Emotion Recognition

[0733] The server uses an emotion engine and generative AI model to quickly respond when an emergency occurs. For example, if a mother has to attend a sudden meeting, the emotion engine will detect that she is "busy" and automatically assign the "childcare" task to another family member.

[0734] Input: Emergency situation, user emotion data

[0735] Output: Urgent task reassignment, notification message

[0736] Specific operation: The server calls the "EmergencyHandler.handle()" method, analyzes the emotion data, and takes appropriate action and notifies the user.

[0737] This allows the whole family to efficiently share tasks and respond flexibly according to emotional states and emergency situations.

[0738] (Application example 2)

[0739] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0740] Improving the efficiency of task management at home and in the workplace and achieving fair task allocation are extremely important. However, conventional task management systems uniformly assign tasks without considering the user's emotional state, which can easily lead to the accumulation of stress and overwork, making efficient task management difficult. As a result, users' health and work efficiency are often adversely affected. The present invention aims to achieve both user health and efficient task allocation by recognizing the user's emotional state and dynamically adjusting tasks based on that information.

[0741] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0742] In this invention, the server includes means for generating artificial intelligence that processes information in multiple formats including text information, image information, and audio information, means for integrating, managing, and sharing the task information processed by the artificial intelligence into a schedule dedicated to family or workplace, means for learning past task allocation status and suggesting future task allocation, means for notifying each member of the family or workplace of the task information, means for recognizing the user's emotional state through audio or image analysis and adjusting task allocation based on the emotional data, and means for optimizing task allocation according to the user's stress level, thereby enabling efficient and healthy task management that takes the user's emotional state into consideration.

[0743] "Text information" is digital data expressed in characters.

[0744] "Image information" is digital data in the form of an image.

[0745] "Audio information" is digital data in audio format.

[0746] "Generative AI" is AI that uses machine learning and deep learning to process information in multiple formats, including text, images, and audio.

[0747] A "family or workplace schedule" is a list of plans and tasks shared among family or workplace members.

[0748] "Means for integration, management, and sharing" refers to methods and systems for centralizing task information and efficiently managing and sharing it.

[0749] The "means for learning past task allocation situations and suggesting future task allocations" refers to a method or system for analyzing past task history and making suggestions regarding future task allocations.

[0750] The "means for notifying each member of task information" refers to a method or system for notifying family members or coworkers of task information.

[0751] "Means for recognizing emotional states through audio or image analysis" refers to a method or system for identifying a user's emotions from audio or image data.

[0752] "Means for adjusting task allocation based on emotional data" refers to a method or system that uses the results of emotional analysis to flexibly change task allocation.

[0753] The "means for optimizing task allocation according to stress state" refers to a method or system for optimizing task allocation taking into account the stress level of the user.

[0754] The following describes in detail an embodiment of the present invention. The present invention is a system for improving the efficiency of task management at home and at work and realizing task allocation based on the user's emotional state. This system recognizes the user's emotional state and adjusts task allocation based on that state, thereby reducing the user's stress and improving task execution efficiency.

[0755] System Configuration

[0756] The server first instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine.

[0757] A user creates an instance of the "User" class and sets their name. In this example, a user named "Staff A" is created. The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[0758] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats, such as text, images, and audio, and centralizes it into a dedicated schedule. The processed task information is automatically registered in the server's schedule.

[0759] Emotion Recognition Engine Details

[0760] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[0761] Adjusting task allocation

[0762] The server adjusts task allocation based on the emotional data output by the emotion engine. For example, if staff member A is feeling stressed, the server will assign cash register duties to another staff member and suggest that staff member A take a break. Notifications are also given at the optimal time and in the most appropriate way based on the emotional state.

[0763] Learning and suggestions

[0764] The server executes the "learn_and_suggest" method to learn from past task allocation status and emotional data. This allows the generative AI model to suggest optimal task allocation based on past data. For example, if staff member A has been busy in the past, it will suggest that the next task be assigned to another staff member.

[0765] Responding to urgent tasks

[0766] In the case of an emergency, for example, when Staff A needs to respond immediately, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[0767] Specific examples

[0768] If Staff A is working at the cash register and is tired, the system will assign the cash register task to Staff B and suggest that Staff A take a break.

[0769] Prompt Sentence Examples

[0770] You will work as part of a staff task management system for a brick-and-mortar store. Your role will be to adjust task allocation based on the following tasks and staff sentiment data:

[0771] Task list: Cashiering, Stocking products

[0772] Emotional Data:

[0773] Staff A: High stress

[0774] Staff B: Normal

[0775] output:

[0776] 1. Suggest a break to Staff A

[0777] 2. Reassign cashier duties to Staff B

[0778] This will improve the efficiency of task management at home and at work, and enable flexible task allocation and adjustment according to the user's emotional state.

[0779] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0780] Step 1:

[0781] The server instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine, giving the system task management and emotion recognition capabilities.

[0782] Input: None (initial setting at system startup)

[0783] Output: An instance of the "Scheduler" class

[0784] Step 2:

[0785] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. This registers the task in the system.

[0786] Input: User's name and new task information (e.g. cashier, due date)

[0787] Output: Task information registered on the server

[0788] Step 3:

[0789] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats (text, images, audio) and centralizes it into a dedicated schedule.

[0790] Input: Task information received from the server

[0791] Output: Consolidated task information

[0792] Step 4:

[0793] The device uses an emotion engine to analyze the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[0794] Input: User voice and image data

[0795] Output: Emotional state data

[0796] Step 5:

[0797] The server adjusts task allocation based on the emotional state data output by the emotion engine. For example, if a user is feeling stressed, the server will assign the task to another member.

[0798] Input: Emotional state data

[0799] Output: Adjusted task allocation

[0800] Step 6:

[0801] The server notifies the user of task information according to the user's emotional state. The notification is performed at the most appropriate timing and in the most appropriate manner based on the user's emotional state.

[0802] Input: Adjusted task allocation

[0803] Output: User notification

[0804] Step 7:

[0805] The server runs the "learn_and_suggest" method to learn past task allocation and emotion data, which allows it to suggest future task allocations.

[0806] Input: Past task allocation data, emotion data

[0807] Output: Proposed future task allocation

[0808] Step 8:

[0809] When an emergency task occurs, the server automatically processes it using the generative AI model and emotion engine, notifying the user in charge. The emotion engine analyzes the user's emotional state and adjusts the emergency response method appropriately.

[0810] Input: Urgent task information, emotional state data

[0811] Output: Emergency response measures and user notification

[0812] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0813] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0814] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0815] [Third embodiment]

[0816] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0817] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0818] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0819] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0820] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0821] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0822] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0823] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0824] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0825] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0826] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0827] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0828] The present invention is a task management system for families that facilitates efficient management and allocation of household and childcare tasks. The system utilizes generative artificial intelligence that can process multiple information formats, including text, images, and audio.

[0829] Server initialization and task management

[0830] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[0831] Creating and adding tasks for users

[0832] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, if a mother adds a "shopping" task, the user enters the task information into the system. The server receives the task information and processes it using generative artificial intelligence.

[0833] Task information integration and management

[0834] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[0835] Task notification and allocation

[0836] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Mother," the system automatically sends a notification to "Mother" informing her of the task content and deadline. This allows the user to immediately understand the new task.

[0837] Learning and suggestions

[0838] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the AI ​​model to analyze past task performance and suggest optimal task allocation. For example, if the mother was busy in the past, it will suggest that the next task be assigned to another family member.

[0839] Responding to urgent tasks

[0840] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server will automatically process the emergency task using an AI model and notify the user in charge. This type of system makes it possible to quickly respond to sudden changes in schedules.

[0841] This system unifies task management and information sharing within the family, enabling efficient task allocation. All family members can grasp information in a unified manner, enabling them to carry out tasks efficiently in their daily lives.

[0842] The processing flow will be explained below.

[0843] Step 1:

[0844] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also initializes a multimodal generative AI model.

[0845] Step 2:

[0846] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother."

[0847] Step 3:

[0848] A user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, a user creates a "shopping" task.

[0849] Step 4:

[0850] The server receives the task information and sends it to the generating AI through the 'add_task' method. This process begins the integration and management of task information.

[0851] Step 5:

[0852] The device processes various information formats, such as text, images, and audio, using the generative AI's 'process_input' method, which integrates and analyzes information in different formats.

[0853] Step 6:

[0854] The server registers the processed task information in a family-specific schedule that can be accessed by all family members, allowing for centralized task management.

[0855] Step 7:

[0856] The server notifies the assigned user that a new task has been added. For example, if the task "Shopping" is assigned to "Mother," a notification is sent to "Mother."

[0857] Step 8:

[0858] The server executes the "learn_and_suggest" method to learn from past task allocation situations, allowing the AI ​​model to suggest optimal task allocation based on past data.

[0859] Step 9:

[0860] The server assigns new tasks to appropriate family members based on the task sharing suggestions, and handles urgent tasks as well, if necessary.

[0861] Step 10:

[0862] The server sends timely notifications to the assigned users about the assigned tasks, allowing all family members to receive real-time task updates.

[0863] Example 1

[0864] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0865] In modern family life, efficient management and fair distribution of household and childcare tasks are important. However, manually managing household tasks is extremely time-consuming and can lead to uneven distribution of the burden among members. Furthermore, while rapid response is required in emergencies, manual task redistribution takes time and is difficult to achieve. Furthermore, the inability to centrally manage and share diverse information formats (text, images, audio) makes information integration difficult. Therefore, a system that solves these issues and enables efficient and fair household task management is needed.

[0866] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0867] In this invention, the server includes means for equipping a generative model for processing information in multiple formats, including text, image, and audio information, means for integrating, managing, and sharing task information processed by the generative model, means for learning past task execution status and proposing future task allocation, means for notifying each member of the task information, and means for redistributing tasks and notifying them quickly in an emergency. This enables efficient and fair management of household tasks, as well as the integration and sharing of information, enabling rapid response in an emergency.

[0868] "Text information" is information that represents characters or sentences in a digital format.

[0869] "Image information" is information that represents visual data in a digital format.

[0870] "Audio information" is information that represents sound waveforms in digital form.

[0871] A "generative model" is an advanced machine learning algorithm that generates new data or information based on input data.

[0872] "Task information" is digital data that indicates the specific tasks and deadlines for housework, childcare, etc.

[0873] "Integration" is the process of centralizing data of different formats.

[0874] "Management" is the process of planning, executing, and monitoring data and tasks.

[0875] "Sharing" refers to making information accessible to multiple users.

[0876] "Suggestion" refers to the process in which the system suggests the optimal action or allocation of work.

[0877] A "notification" is a message or alert sent to inform a user of specific information.

[0878] An "emergency" is a situation in which a high-priority event occurs that alters normal schedules and plans.

[0879] "Redistribution" refers to the act of rearranging existing tasks or resources.

[0880] A "server" refers to a computer system that provides data and services over a network.

[0881] The following describes in detail an embodiment of the present invention. The present invention is a task management system for home use that facilitates efficient management and allocation of housework and childcare tasks. This system utilizes a generative model that can process multiple information formats, such as text information, image information, and audio information.

[0882] First, the central server of the system instantiates the "FamilyScheduler" class and the generative model. The server uses the Python language and loads the AI ​​model using the "tensorflow" and "pytorch" libraries. This initializes a schedule for managing household tasks and makes available the generative model, which is capable of processing information in various formats.

[0883] Users log in to the system using a smartphone app or web app and enter their information. Users can create new tasks by creating an instance of the "User" class and setting a name. For example, if a mother wants to add a task such as "Buy groceries at the supermarket by the end of the week," the user enters the details of the task into the system. The task information is sent to the server and processed using the generative model.

[0884] The device (smartphone or web browser) processes the task information received from the server using the "process_input" method. At this stage, various types of information, such as text, images, and audio, are integrated and centralized into a home-specific schedule. For example, if a mother inputs a "shopping" task and provides an image of a grocery list and a voice memo, the generative model processes this and integrates the relevant information.

[0885] The server registers the processed task information in the schedule and sends a notification to the responsible user. For example, if a new shopping task is added to "Mother," the system automatically sends a push notification to the mother informing her of the task content and deadline. Notifications can be sent via email or in-app push notifications.

[0886] Furthermore, the server uses the "learn_and_suggest" method to learn from past task execution situations and suggest optimal task allocation. For example, if the mother has been particularly busy in the past, it will suggest that the next shopping task be assigned to the father. This process ensures that the workload of the entire family is evenly distributed.

[0887] In the event of an emergency, the server processes urgent tasks in real time using a generative model and redistributes them. For example, if a mother has an unexpected meeting, the server creates an urgent task based on this information, redistributes it to other users who are available, and notifies them. This enables a rapid response.

[0888] Examples of prompts include:

[0889] "Add a new task. Enter the task content (e.g., shopping), task details (e.g., buy groceries at the supermarket by the end of the week), and due date (e.g., this weekend)."

[0890] This system centralizes task management and information sharing within the home, enabling efficient task allocation and rapid response.

[0891] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0892] Step 1:

[0893] Server initialization and task management:

[0894] When the system starts up, the server instantiates the "FamilyScheduler" class and the generative model. The input is the server startup instruction and necessary libraries (e.g., tensorflow and pytorch). The server uses these libraries to load the generative model and initialize a schedule for managing household tasks. The output is an initialized task management system and an instance of the generative model. Specifically, the server runs code to load the generative model and verify that the schedule works correctly.

[0895] Step 2:

[0896] User task creation:

[0897] A user logs into the system using a smartphone app or web app and enters their information. Input includes the user's name and login information. The user creates an instance of the "User" class and sets their name. The output is a user profile. Specifically, the mother enters her name into the app's input form and clicks the "Save" button, which sends this information to the server.

[0898] Step 3:

[0899] Add a new task:

[0900] The user creates a new task and enters task information (e.g., task description, due date). The input includes the task description (e.g., "shopping") and due date (e.g., "this weekend"). The server receives this information and processes the task information using a generative model. The output is the processed task information stored in the server. Specifically, the mother enters "Buy groceries at the supermarket by this weekend" into the task addition screen of the app and clicks the "Add" button to send the information.

[0901] Step 4:

[0902] Task information integration and management:

[0903] The device processes the task information received from the server using the "process_input" method. The input is task information in text, image, and audio format. The generative model integrates these different types of data and unifies them into a schedule dedicated to the family. The output is the integrated task information reflected in the schedule. Specifically, the device receives text data and image data from the server and reflects it in the schedule.

[0904] Step 5:

[0905] Task Notifications:

[0906] The server registers the processed task information in the schedule and notifies the responsible user. The input is the integrated task information and the responsible user information. The server uses this to generate a push notification and sends it to the user. The output is a notification displayed on the user's smartphone or device. Specifically, when a new task is added to "Mother," the system automatically sends a push notification to Mother, informing her of the task content and deadline.

[0907] Step 6:

[0908] Task sharing learning and suggestions:

[0909] The server uses the "learn_and_suggest" method to learn about past task execution status and propose future task allocations. The input is past task history data. The generative model analyzes this data and proposes optimal task allocations. The output is that the proposed task allocations are saved on the server and notified to the user. Specifically, if the mother has been busy in the past, a suggestion is made to allocate the next shopping task to the father.

[0910] Step 7:

[0911] Urgent task handling:

[0912] The server redistributes tasks in emergencies and notifies them quickly. The input is information about the emergency and the current task status. The generative model analyzes this and performs appropriate redistribution. The output is that the redistributed task information is notified to the responsible user. Specifically, if the mother has an unexpected meeting, the generative model creates a new task, redistributes it to other users, and notifies them. This information is immediately notified to the relevant users, allowing for a quick response.

[0913] (Application example 1)

[0914] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0915] Currently, task management in business environments is often done manually, resulting in missed or delayed tasks. It is also difficult to share task information and assign tasks to the appropriate personnel, often hindering work efficiency. Furthermore, when an unexpected urgent task arises, existing task management systems make it difficult to respond quickly, potentially causing delays to the entire business. There is a need to address these issues.

[0916] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0917] In this invention, the server

[0918] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[0919] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the business environment;

[0920] A means to learn past task allocation situations and suggest future task allocations;

[0921] means for notifying each member of the work environment of task information;

[0922] A means to automatically process and notify the person in charge when an emergency task occurs;

[0923] A means for agents to add and update task information using their smartphones, tablets, or smart glasses;

[0924] This enables efficient management and allocation of tasks in a work environment, rapid information sharing, and immediate response to urgent tasks.

[0925] "Text information" is information expressed as sentences or character data.

[0926] "Image information" is visual data such as photographs and pictures.

[0927] "Audio information" is acoustic data that includes human voices and other sounds.

[0928] "Generative AI" is an AI technology that processes information in various formats, such as text, images, and audio, and generates appropriate results.

[0929] "Means" are the methods or tools used to achieve a particular goal.

[0930] "Task information" is detailed data related to a particular task or responsibility.

[0931] A "schedule" is a plan showing the timing and person in charge of tasks and plans.

[0932] "Integration" means bringing together multiple pieces of information or data into one.

[0933] "Management" means coordinating and controlling tasks and information in order to operate them efficiently.

[0934] "Sharing" means making the same information available to multiple people or systems.

[0935] "Learning" is the acquisition of knowledge and patterns based on past data and experience.

[0936] A "suggestion" is a recommendation of a particular action or option.

[0937] "Notification" means conveying information or a message to a specific recipient.

[0938] A "system" is a set of devices and programs in which multiple elements function in conjunction with one another.

[0939] An "urgent task" is work that requires immediate action in an unexpected situation.

[0940] A "person in charge" is someone who is in charge of a specific task or job.

[0941] A "smartphone" is a type of mobile information terminal that can use a variety of applications in addition to making calls.

[0942] A "tablet" is a portable computing device that primarily features a touch screen.

[0943] "Smart glasses" are wearable devices that allow the wearer to obtain additional visual information.

[0944] MODE FOR CARRYING OUT THE INVENTION

[0945] The following describes in detail the embodiments of the present invention. The present invention is a system for streamlining task management in a business environment and appropriately allocating task information. The system utilizes a generative AI model that processes various information formats, such as text, images, and audio.

[0946] Server initialization and task management

[0947] The server first instantiates the "TaskMaster" class, which initializes a schedule for managing tasks in the work environment and instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[0948] Creating and adding tasks for users

[0949] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, when an employee adds a task for "inventorying products," the user enters the task information into the system. The server receives this task information and processes it using generative artificial intelligence.

[0950] Task information integration and management

[0951] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates not only text information but also various other information formats such as images and audio, and centralizes it into a schedule dedicated to the work environment. The processed task information is automatically registered in the server's schedule.

[0952] Task notification and allocation

[0953] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Employee A," the system automatically sends a notification to "Employee A" informing him of the task content and deadline. This allows the user to immediately understand the new task.

[0954] Learning and suggestions

[0955] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the generative AI model to analyze past task performance and suggest optimal task allocation. For example, if a specific employee was busy in the past, it will suggest that the next task be assigned to another employee.

[0956] Responding to urgent tasks

[0957] In the case of an emergency, for example, if an employee has a sudden meeting and is temporarily unable to take on another task, the server automatically processes the urgent task using a generative AI model and notifies the responsible user. This type of system makes it possible to quickly respond to sudden schedule changes.

[0958] This system unifies task management and information sharing in the work environment, enabling efficient task allocation. All employees can grasp information in a unified manner, enabling them to carry out tasks efficiently within the workplace.

[0959] Hardware and Software Used

[0960] Hardware:

[0961] Smartphone

[0962] tablet

[0963] Smart Glasses

[0964] software:

[0965] Backend system using Python

[0966] Generative AI models use, for example, OpenAI's GPT-4 API.

[0967] Specific usage examples and prompts

[0968] Usage example

[0969] Consider a scenario where an employee adds a new task using a smartphone. For example, an employee adds a task called "Inventory the products."

[0970] Prompt Sentence Examples

[0971] New task information:

[0972] Task: Inventory the goods

[0973] Deadline: 2023-10-15 18:00

[0974] Divide this task appropriately and notify the responsible parties.

[0975] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0976] Step 1:

[0977] The server initializes the system

[0978] The server instantiates the "TaskMaster" class and initializes a schedule table and generative AI model specific to the work environment, laying the foundation for task management.

[0979] Input: None (at system startup)

[0980] Output: Initialized schedule and generative AI model

[0981] Specific operation: The server creates an instance of the TaskMaster class, initializes the schedule table within it, and loads the generative AI model.

[0982] Step 2:

[0983] A user creates or adds a task

[0984] A user creates an instance of the "User" class, enters task information including a task description and deadline date, and sends it to the server.

[0985] Input: Task information (description, due date)

[0986] Output: Task information sent to the server

[0987] Specific operation: A user uses a device (smartphone, tablet, smart glasses) to enter task information and clicks a button to send it to the server.

[0988] Step 3:

[0989] The server processes task information using a generative AI model

[0990] The server processes the received task information using the "process_input" method of the generation AI model, and analyzes and optimizes the task information.

[0991] Input: Task information

[0992] Output: Task information processed by the generative AI model

[0993] Specific operation: The server passes task information to the generative AI model, which integrates text analysis, image, and audio data to generate optimized task information, including the assignment of personnel.

[0994] Step 4:

[0995] Integrate task information into your schedule

[0996] The server integrates the processed task information into a dedicated business schedule and updates the information on tasks and people in charge.

[0997] Input: Task information processed by the generative AI model

[0998] Output: Updated schedule table

[0999] Specific behavior: The server adds a new task entry to the scheduler, sets the assignee and due date.

[1000] Step 5:

[1001] Sending task notifications

[1002] The server notifies the user of the task information, which is sent to the user's device (smartphone, tablet, smart glasses).

[1003] Input: Updated schedule

[1004] Output: Task notification sent to the user's device

[1005] Specific Actions: The server sends a notification message to the appropriate user device, informing the user of the new task and its details.

[1006] Step 6:

[1007] Analyze past task data and perform suggestion functions

[1008] The server analyzes past task allocation situations using a generative AI model and suggests optimal task allocation for the next time.

[1009] Input: Past task data

[1010] Output: Suggested task allocation plan

[1011] Specific operation: The server collects past task data, analyzes it using a generative AI model, and generates a new allocation plan that takes into account the workload of each person in charge, etc.

[1012] Step 7:

[1013] Automated handling of urgent tasks

[1014] When an urgent task arises, the server uses generative AI models to automatically handle the task and notify the appropriate personnel.

[1015] Input: Urgent task information

[1016] Output: Urgent task processing results and notifications

[1017] Specific operation: The server receives an urgent task, determines the optimal response and person in charge using a generative AI model, and immediately notifies the user.

[1018] These steps will improve the efficiency of task management in a business environment and achieve rational task distribution.

[1019] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1020] The present invention provides a task management system for families that facilitates efficient management and sharing of household and childcare tasks, and incorporates an emotion engine that recognizes the user's emotions.

[1021] Server initialization and task management

[1022] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[1023] Creating and adding tasks for users

[1024] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[1025] Task information integration and management

[1026] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[1027] Emotion recognition by emotion engine

[1028] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[1029] Task notification and emotion-based work allocation adjustment

[1030] The server registers the processed task information in a family schedule and adjusts task allocation based on the emotional data output by the emotion engine. For example, if the mother is feeling stressed, the server will allocate tasks to other family members. Notifications are also given at the optimal time and in the most appropriate way based on the mother's emotional state.

[1031] Learning and suggestions

[1032] The server runs the "learn_and_suggest" method to learn from past task allocation and emotional data. This allows the AI ​​model to suggest optimal task allocation based on past data. For example, if the mother has been busy in the past, the next task will be suggested to be assigned to another family member.

[1033] Emergency Task Response and Emotion Recognition

[1034] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[1035] This system unifies task management and information sharing within the family, enabling efficient task allocation, and by utilizing emotion recognition, it enables flexible task adjustment according to the user's emotional state. All family members can grasp information in a unified manner, enabling them to efficiently complete tasks in their daily lives.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[1039] Step 2:

[1040] A user creates an instance of the "User" class and sets their name. For example, let's create a user named "Mother."

[1041] Step 3:

[1042] A user creates a new task and sends the task information (eg, a "shopping" description and due date) to the server.

[1043] Step 4:

[1044] The server receives the task information and sends it to the AI ​​generator using the "add_task" method, where task information processing begins.

[1045] Step 5:

[1046] The device uses the generative AI's 'process_input' method to process information in various formats, including text, images, and audio, allowing information to be processed in a unified manner regardless of the input format.

[1047] Step 6:

[1048] The server registers the processed task information in a family-specific schedule, which can be accessed by all family members and allows for centralized task integration and management.

[1049] Step 7:

[1050] When a task is added or an important notification is received, the device analyzes the user's voice and facial expressions through the emotion engine, and as a result of this analysis, the device recognizes the user's emotional state.

[1051] Step 8:

[1052] The server adjusts task allocation based on the emotion data obtained from the emotion engine. For example, if a user is feeling stressed, the server will not assign new tasks to that user.

[1053] Step 9:

[1054] When a new task is added, the server notifies the user in charge of the task. The notification is performed at an appropriate time and in an appropriate manner by the emotion engine.

[1055] Step 10:

[1056] The server runs the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[1057] Step 11:

[1058] When assigning new tasks to family members, the server takes emotional data into consideration when deciding on the allocation and notifies the assigned user. Even in the case of urgent tasks, the server uses the emotion engine to handle them appropriately.

[1059] Through these steps, the system centralizes task management and information sharing within the home, realizing efficient task allocation that takes into consideration the user's feelings.

[1060] Example 2

[1061] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1062] In modern households, it is difficult to efficiently manage and share the burden of housework and childcare among all family members. It is also not easy to coordinate tasks based on each member's emotional state or to respond efficiently in emergencies. Furthermore, it is necessary to integrate information in various formats (text, images, audio, etc.) and manage schedules appropriately. Conventional systems do not adequately provide the means to effectively solve these problems.

[1063] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1064] In this invention, the server includes a means with an emotion recognition engine to efficiently manage and easily allocate housework and childcare tasks, a means with a generation AI that processes multiple forms of information including text information, image information, and audio information, and a means for integrating, managing, and sharing the task information processed by the generation AI into a family-specific schedule. This allows all family members to efficiently allocate tasks and flexibly adjust according to their emotional states and emergency situations.

[1065] "Housework and childcare tasks" is a general term for work done at home, such as cleaning, laundry, cooking, and caring for children.

[1066] An "emotion recognition engine" is a system that analyzes a user's voice, facial expressions, etc. to recognize their emotional state.

[1067] "Generative AI" is a system that processes various input formats, such as text, image, and audio information, to generate or infer knowledge.

[1068] A "schedule" is a tabular management tool for centrally managing task information so that each member of the household can check it in real time.

[1069] "Task sharing" means assigning household and childcare tasks to each family member.

[1070] "Suggestion" means that the system suggests appropriate task allocation and actions based on past data and the current situation.

[1071] An "urgent task" is a task that requires immediate action in an emergency.

[1072] "Natural language processing" is a technology for analyzing text information and processing human language.

[1073] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[1074] The present invention is a system that efficiently manages and facilitates the allocation of household chores and childcare tasks within a household. This system combines an emotion recognition engine and a generative AI model to ensure that each family member is able to share tasks fairly and efficiently.

[1075] Server initialization and task management

[1076] The server first creates an instance of the "FamilyScheduler" class. This instance is initialized with a schedule for managing household tasks. At the same time, a multimodal (including text, image, and audio) generative AI model and an emotion recognition engine are also initialized. This establishes the foundation for household task management.

[1077] Creating and adding tasks for users

[1078] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (for example, a description of "Shopping" and a due date of "2023-10-15") to the server. This process registers the user's task information on the server.

[1079] Task information integration and management

[1080] The device processes the task information obtained from the server using a method called "process_input." This method integrates data in various formats, including text, images, and audio, and centralizes it into a schedule for the family. For example, a tablet device can obtain "photos of cleaning" and "voice notes of a shopping list" and integrate this information into the schedule.

[1081] Emotion recognition by emotion engine

[1082] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine analyzes voice and facial images to recognize the user's emotional state. For example, a smartphone can analyze the user's facial expression, detect "fatigue," and send the emotional data to the server.

[1083] Task notification and emotion-based work allocation adjustment

[1084] The server not only registers the processed task information in the schedule, but also adjusts task allocation based on emotional data provided by the emotion engine. For example, if the server detects that the mother is "tired," it will assign the "cooking" task to the father or children. Notifications are made at the optimal time based on this emotional state. A message such as "Mom is tired, please help with cooking" is sent to other family members.

[1085] Learning and suggestions

[1086] The server learns from past task allocation status and emotional data using a method called "learn_and_suggest." For example, if "mother has been busy in the past," the AI ​​model will suggest that the next task be assigned to another family member. This ensures that household tasks are assigned efficiently and fairly.

[1087] Emergency Task Response and Emotion Recognition

[1088] In the case of an emergency, for example, if the mother has to attend a sudden meeting, the server responds quickly using an emotion engine and generative AI model. It detects the emotion "Mother is currently busy" and automatically assigns "childcare" to the father. This information is sent to the father's device as an emergency notification.

[1089] As a concrete example, the prompt sentence for registering the task "shopping" is as follows:

[1090] Prompt Sentence Examples

[1091] "Mom needs to complete the shopping task to buy bread and milk by October 15th."

[1092] This system allows all family members to efficiently share tasks and respond flexibly according to their emotional state and emergency situations.

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1: Initialize the server

[1095] The server first creates an instance of the "FamilyScheduler" class, which initializes a schedule for managing household tasks. It also initializes the generative AI model and emotion recognition engine.

[1096] Input: None

[1097] Output: Home task schedule, generative AI model, and emotion recognition engine initialization

[1098] Specific operation: The server calls the "FamilyScheduler.initialize()" method to perform initialization.

[1099] Step 2: Creating and adding tasks for users

[1100] A user creates an instance of the "User" class and sets their name. A user named "Mother" creates a new task and adds the task information (e.g., a description of "Shopping" and a due date of "2023-10-15") to the server.

[1101] Input: User name, task description, due date

[1102] Output: Task information is registered on the server

[1103] Specific operation: The user uses the "User.create()" method from the terminal, enters their information, and then uses the "Task.add()" method to send the task information to the server.

[1104] Step 3: Consolidate and manage task information

[1105] The device processes the task information received from the server using the "process_input" method, unifying data such as text, images, and audio, and integrating it into a schedule for the family.

[1106] Input: Task information received from the server (text, image, audio)

[1107] Output: The integrated task information is added to the scheduler

[1108] Specific operation: The terminal calls the "process_input" method, analyzes the received task information, and adds it to the schedule.

[1109] Step 4: Emotion Recognition with the Emotion Engine

[1110] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine performs voice and image analysis to recognize the user's emotional state.

[1111] Input: User's voice data or facial image data

[1112] Output: Parsed emotion data

[1113] Specific operation: The device calls the "EmotionEngine.analyze()" method and analyzes voice and facial images to obtain emotional data.

[1114] Step 5: Task notification and emotion-based allocation adjustment

[1115] The server registers the processed task information in a schedule and adjusts task allocation based on the emotion data from the emotion engine. For example, if the mother feels "tired," the server will assign the "cooking task" to another family member.

[1116] Input: Integrated task information, analyzed emotion data

[1117] Output: Adjusted task allocation, notification message

[1118] Specific operation: The server uses the "TaskSchedule.update()" method to reconstruct task allocation based on emotion data and send a notification.

[1119] Step 6: Learning and Suggestions

[1120] The server uses the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[1121] Input: Past task allocation data, past emotion data

[1122] Output: Suggested task allocation plan

[1123] Specific operation: The server calls the "learn_and_suggest" method, learns from past data, and generates task allocation proposals for the next time and beyond.

[1124] Step 7: Emergency Task Management and Emotion Recognition

[1125] The server uses an emotion engine and generative AI model to quickly respond when an emergency occurs. For example, if a mother has to attend a sudden meeting, the emotion engine will detect that she is "busy" and automatically assign the "childcare" task to another family member.

[1126] Input: Emergency situation, user emotion data

[1127] Output: Urgent task reassignment, notification message

[1128] Specific operation: The server calls the "EmergencyHandler.handle()" method, analyzes the emotion data, and takes appropriate action and notifies the user.

[1129] This allows the whole family to efficiently share tasks and respond flexibly according to emotional states and emergency situations.

[1130] (Application example 2)

[1131] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1132] Improving the efficiency of task management at home and in the workplace and achieving fair task allocation are extremely important. However, conventional task management systems uniformly assign tasks without considering the user's emotional state, which can easily lead to the accumulation of stress and overwork, making efficient task management difficult. As a result, users' health and work efficiency are often adversely affected. The present invention aims to achieve both user health and efficient task allocation by recognizing the user's emotional state and dynamically adjusting tasks based on that information.

[1133] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1134] In this invention, the server includes means for generating artificial intelligence that processes information in multiple formats including text information, image information, and audio information, means for integrating, managing, and sharing the task information processed by the artificial intelligence into a schedule dedicated to family or workplace, means for learning past task allocation status and suggesting future task allocation, means for notifying each member of the family or workplace of the task information, means for recognizing the user's emotional state through audio or image analysis and adjusting task allocation based on the emotional data, and means for optimizing task allocation according to the user's stress level, thereby enabling efficient and healthy task management that takes the user's emotional state into consideration.

[1135] "Text information" is digital data expressed in characters.

[1136] "Image information" is digital data in the form of an image.

[1137] "Audio information" is digital data in audio format.

[1138] "Generative AI" is AI that uses machine learning and deep learning to process information in multiple formats, including text, images, and audio.

[1139] A "family or workplace schedule" is a list of plans and tasks shared among family or workplace members.

[1140] "Means for integration, management, and sharing" refers to methods and systems for centralizing task information and efficiently managing and sharing it.

[1141] The "means for learning past task allocation situations and suggesting future task allocations" refers to a method or system for analyzing past task history and making suggestions regarding future task allocations.

[1142] The "means for notifying each member of task information" refers to a method or system for notifying family members or coworkers of task information.

[1143] "Means for recognizing emotional states through audio or image analysis" refers to a method or system for identifying a user's emotions from audio or image data.

[1144] "Means for adjusting task allocation based on emotional data" refers to a method or system that uses the results of emotional analysis to flexibly change task allocation.

[1145] The "means for optimizing task allocation according to stress state" refers to a method or system for optimizing task allocation taking into account the stress level of the user.

[1146] The following describes in detail an embodiment of the present invention. The present invention is a system for improving the efficiency of task management at home and at work and realizing task allocation based on the user's emotional state. This system recognizes the user's emotional state and adjusts task allocation based on that state, thereby reducing the user's stress and improving task execution efficiency.

[1147] System Configuration

[1148] The server first instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine.

[1149] A user creates an instance of the "User" class and sets their name. In this example, a user named "Staff A" is created. The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[1150] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats, such as text, images, and audio, and centralizes it into a dedicated schedule. The processed task information is automatically registered in the server's schedule.

[1151] Emotion Recognition Engine Details

[1152] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[1153] Adjusting task allocation

[1154] The server adjusts task allocation based on the emotional data output by the emotion engine. For example, if staff member A is feeling stressed, the server will assign cash register duties to another staff member and suggest that staff member A take a break. Notifications are also given at the optimal time and in the most appropriate way based on the emotional state.

[1155] Learning and suggestions

[1156] The server executes the "learn_and_suggest" method to learn from past task allocation status and emotional data. This allows the generative AI model to suggest optimal task allocation based on past data. For example, if staff member A has been busy in the past, it will suggest that the next task be assigned to another staff member.

[1157] Responding to urgent tasks

[1158] In the case of an emergency, for example, when Staff A needs to respond immediately, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[1159] Specific examples

[1160] If Staff A is working at the cash register and is tired, the system will assign the cash register task to Staff B and suggest that Staff A take a break.

[1161] Prompt Sentence Examples

[1162] You will work as part of a staff task management system for a brick-and-mortar store. Your role will be to adjust task allocation based on the following tasks and staff sentiment data:

[1163] Task list: Cashiering, Stocking products

[1164] Emotional Data:

[1165] Staff A: High stress

[1166] Staff B: Normal

[1167] output:

[1168] 1. Suggest a break to Staff A

[1169] 2. Reassign cashier duties to Staff B

[1170] This will improve the efficiency of task management at home and at work, and enable flexible task allocation and adjustment according to the user's emotional state.

[1171] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1172] Step 1:

[1173] The server instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine, giving the system task management and emotion recognition capabilities.

[1174] Input: None (initial setting at system startup)

[1175] Output: An instance of the "Scheduler" class

[1176] Step 2:

[1177] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. This registers the task in the system.

[1178] Input: User's name and new task information (e.g. cashier, due date)

[1179] Output: Task information registered on the server

[1180] Step 3:

[1181] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats (text, images, audio) and centralizes it into a dedicated schedule.

[1182] Input: Task information received from the server

[1183] Output: Consolidated task information

[1184] Step 4:

[1185] The device uses an emotion engine to analyze the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[1186] Input: User voice and image data

[1187] Output: Emotional state data

[1188] Step 5:

[1189] The server adjusts task allocation based on the emotional state data output by the emotion engine. For example, if a user is feeling stressed, the server will assign the task to another member.

[1190] Input: Emotional state data

[1191] Output: Adjusted task allocation

[1192] Step 6:

[1193] The server notifies the user of task information according to the user's emotional state. The notification is performed at the most appropriate timing and in the most appropriate manner based on the user's emotional state.

[1194] Input: Adjusted task allocation

[1195] Output: User notification

[1196] Step 7:

[1197] The server runs the "learn_and_suggest" method to learn past task allocation and emotion data, which allows it to suggest future task allocations.

[1198] Input: Past task allocation data, emotion data

[1199] Output: Proposed future task allocation

[1200] Step 8:

[1201] When an emergency task occurs, the server automatically processes it using the generative AI model and emotion engine, notifying the user in charge. The emotion engine analyzes the user's emotional state and adjusts the emergency response method appropriately.

[1202] Input: Urgent task information, emotional state data

[1203] Output: Emergency response measures and user notification

[1204] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1205] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1206] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1207] [Fourth embodiment]

[1208] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1209] 7, a 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.

[1210] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1211] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1212] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1214] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1215] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1216] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1217] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1218] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1219] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1220] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1221] The present invention is a task management system for families that facilitates efficient management and allocation of household and childcare tasks. The system utilizes generative artificial intelligence that can process multiple information formats, including text, images, and audio.

[1222] Server initialization and task management

[1223] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[1224] Creating and adding tasks for users

[1225] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, if a mother adds a "shopping" task, the user enters the task information into the system. The server receives the task information and processes it using generative artificial intelligence.

[1226] Task information integration and management

[1227] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[1228] Task notification and allocation

[1229] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Mother," the system automatically sends a notification to "Mother" informing her of the task content and deadline. This allows the user to immediately understand the new task.

[1230] Learning and suggestions

[1231] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the AI ​​model to analyze past task performance and suggest optimal task allocation. For example, if the mother was busy in the past, it will suggest that the next task be assigned to another family member.

[1232] Responding to urgent tasks

[1233] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server will automatically process the emergency task using an AI model and notify the user in charge. This type of system makes it possible to quickly respond to sudden changes in schedules.

[1234] This system unifies task management and information sharing within the family, enabling efficient task allocation. All family members can grasp information in a unified manner, enabling them to carry out tasks efficiently in their daily lives.

[1235] The processing flow will be explained below.

[1236] Step 1:

[1237] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks and also initializes a multimodal generative AI model.

[1238] Step 2:

[1239] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother."

[1240] Step 3:

[1241] A user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, a user creates a "shopping" task.

[1242] Step 4:

[1243] The server receives the task information and sends it to the generating AI through the 'add_task' method. This process begins the integration and management of task information.

[1244] Step 5:

[1245] The device processes various information formats, such as text, images, and audio, using the generative AI's 'process_input' method, which integrates and analyzes information in different formats.

[1246] Step 6:

[1247] The server registers the processed task information in a family-specific schedule that can be accessed by all family members, allowing for centralized task management.

[1248] Step 7:

[1249] The server notifies the assigned user that a new task has been added. For example, if the task "Shopping" is assigned to "Mother," a notification is sent to "Mother."

[1250] Step 8:

[1251] The server executes the "learn_and_suggest" method to learn from past task allocation situations, allowing the AI ​​model to suggest optimal task allocation based on past data.

[1252] Step 9:

[1253] The server assigns new tasks to appropriate family members based on the task sharing suggestions, and handles urgent tasks as well, if necessary.

[1254] Step 10:

[1255] The server sends timely notifications to the assigned users about the assigned tasks, allowing all family members to receive real-time task updates.

[1256] Example 1

[1257] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1258] In modern family life, efficient management and fair distribution of household and childcare tasks are important. However, manually managing household tasks is extremely time-consuming and can lead to uneven distribution of the burden among members. Furthermore, while rapid response is required in emergencies, manual task redistribution takes time and is difficult to achieve. Furthermore, the inability to centrally manage and share diverse information formats (text, images, audio) makes information integration difficult. Therefore, a system that solves these issues and enables efficient and fair household task management is needed.

[1259] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1260] In this invention, the server includes means for equipping a generative model for processing information in multiple formats, including text, image, and audio information, means for integrating, managing, and sharing task information processed by the generative model, means for learning past task execution status and proposing future task allocation, means for notifying each member of the task information, and means for redistributing tasks and notifying them quickly in an emergency. This enables efficient and fair management of household tasks, as well as the integration and sharing of information, enabling rapid response in an emergency.

[1261] "Text information" is information that represents characters or sentences in a digital format.

[1262] "Image information" is information that represents visual data in a digital format.

[1263] "Audio information" is information that represents sound waveforms in digital form.

[1264] A "generative model" is an advanced machine learning algorithm that generates new data or information based on input data.

[1265] "Task information" is digital data that indicates the specific tasks and deadlines for housework, childcare, etc.

[1266] "Integration" is the process of centralizing data of different formats.

[1267] "Management" is the process of planning, executing, and monitoring data and tasks.

[1268] "Sharing" refers to making information accessible to multiple users.

[1269] "Suggestion" refers to the process in which the system suggests the optimal action or allocation of work.

[1270] A "notification" is a message or alert sent to inform a user of specific information.

[1271] An "emergency" is a situation in which a high-priority event occurs that alters normal schedules and plans.

[1272] "Redistribution" refers to the act of rearranging existing tasks or resources.

[1273] A "server" refers to a computer system that provides data and services over a network.

[1274] The following describes in detail an embodiment of the present invention. The present invention is a task management system for home use that facilitates efficient management and allocation of housework and childcare tasks. This system utilizes a generative model that can process multiple information formats, such as text information, image information, and audio information.

[1275] First, the central server of the system instantiates the "FamilyScheduler" class and the generative model. The server uses the Python language and loads the AI ​​model using the "tensorflow" and "pytorch" libraries. This initializes a schedule for managing household tasks and makes available the generative model, which is capable of processing information in various formats.

[1276] Users log in to the system using a smartphone app or web app and enter their information. Users can create new tasks by creating an instance of the "User" class and setting a name. For example, if a mother wants to add a task such as "Buy groceries at the supermarket by the end of the week," the user enters the details of the task into the system. The task information is sent to the server and processed using the generative model.

[1277] The device (smartphone or web browser) processes the task information received from the server using the "process_input" method. At this stage, various types of information, such as text, images, and audio, are integrated and centralized into a home-specific schedule. For example, if a mother inputs a "shopping" task and provides an image of a grocery list and a voice memo, the generative model processes this and integrates the relevant information.

[1278] The server registers the processed task information in the schedule and sends a notification to the responsible user. For example, if a new shopping task is added to "Mother," the system automatically sends a push notification to the mother informing her of the task content and deadline. Notifications can be sent via email or in-app push notifications.

[1279] Furthermore, the server uses the "learn_and_suggest" method to learn from past task execution situations and suggest optimal task allocation. For example, if the mother has been particularly busy in the past, it will suggest that the next shopping task be assigned to the father. This process ensures that the workload of the entire family is evenly distributed.

[1280] In the event of an emergency, the server processes urgent tasks in real time using a generative model and redistributes them. For example, if a mother has an unexpected meeting, the server creates an urgent task based on this information, redistributes it to other users who are available, and notifies them. This enables a rapid response.

[1281] Examples of prompts include:

[1282] "Add a new task. Enter the task content (e.g., shopping), task details (e.g., buy groceries at the supermarket by the end of the week), and due date (e.g., this weekend)."

[1283] This system centralizes task management and information sharing within the home, enabling efficient task allocation and rapid response.

[1284] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1285] Step 1:

[1286] Server initialization and task management:

[1287] When the system starts up, the server instantiates the "FamilyScheduler" class and the generative model. The input is the server startup instruction and necessary libraries (e.g., tensorflow and pytorch). The server uses these libraries to load the generative model and initialize a schedule for managing household tasks. The output is an initialized task management system and an instance of the generative model. Specifically, the server runs code to load the generative model and verify that the schedule works correctly.

[1288] Step 2:

[1289] User task creation:

[1290] A user logs into the system using a smartphone app or web app and enters their information. Input includes the user's name and login information. The user creates an instance of the "User" class and sets their name. The output is a user profile. Specifically, the mother enters her name into the app's input form and clicks the "Save" button, which sends this information to the server.

[1291] Step 3:

[1292] Add a new task:

[1293] The user creates a new task and enters task information (e.g., task description, due date). The input includes the task description (e.g., "shopping") and due date (e.g., "this weekend"). The server receives this information and processes the task information using a generative model. The output is the processed task information stored in the server. Specifically, the mother enters "Buy groceries at the supermarket by this weekend" into the task addition screen of the app and clicks the "Add" button to send the information.

[1294] Step 4:

[1295] Task information integration and management:

[1296] The device processes the task information received from the server using the "process_input" method. The input is task information in text, image, and audio format. The generative model integrates these different types of data and unifies them into a schedule dedicated to the family. The output is the integrated task information reflected in the schedule. Specifically, the device receives text data and image data from the server and reflects it in the schedule.

[1297] Step 5:

[1298] Task Notifications:

[1299] The server registers the processed task information in the schedule and notifies the responsible user. The input is the integrated task information and the responsible user information. The server uses this to generate a push notification and sends it to the user. The output is a notification displayed on the user's smartphone or device. Specifically, when a new task is added to "Mother," the system automatically sends a push notification to Mother, informing her of the task content and deadline.

[1300] Step 6:

[1301] Task sharing learning and suggestions:

[1302] The server uses the "learn_and_suggest" method to learn about past task execution status and propose future task allocations. The input is past task history data. The generative model analyzes this data and proposes optimal task allocations. The output is that the proposed task allocations are saved on the server and notified to the user. Specifically, if the mother has been busy in the past, a suggestion is made to allocate the next shopping task to the father.

[1303] Step 7:

[1304] Urgent task handling:

[1305] The server redistributes tasks in emergencies and notifies them quickly. The input is information about the emergency and the current task status. The generative model analyzes this and performs appropriate redistribution. The output is that the redistributed task information is notified to the responsible user. Specifically, if the mother has an unexpected meeting, the generative model creates a new task, redistributes it to other users, and notifies them. This information is immediately notified to the relevant users, allowing for a quick response.

[1306] (Application example 1)

[1307] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1308] Currently, task management in business environments is often done manually, resulting in missed or delayed tasks. It is also difficult to share task information and assign tasks to the appropriate personnel, often hindering work efficiency. Furthermore, when an unexpected urgent task arises, existing task management systems make it difficult to respond quickly, potentially causing delays to the entire business. There is a need to address these issues.

[1309] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1310] In this invention, the server

[1311] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[1312] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the business environment;

[1313] A means to learn past task allocation situations and suggest future task allocations;

[1314] means for notifying each member of the work environment of task information;

[1315] A means to automatically process and notify the person in charge when an emergency task occurs;

[1316] A means for agents to add and update task information using their smartphones, tablets, or smart glasses;

[1317] This enables efficient management and allocation of tasks in a work environment, rapid information sharing, and immediate response to urgent tasks.

[1318] "Text information" is information expressed as sentences or character data.

[1319] "Image information" is visual data such as photographs and pictures.

[1320] "Audio information" is acoustic data that includes human voices and other sounds.

[1321] "Generative AI" is an AI technology that processes information in various formats, such as text, images, and audio, and generates appropriate results.

[1322] "Means" are the methods or tools used to achieve a particular goal.

[1323] "Task information" is detailed data related to a particular task or responsibility.

[1324] A "schedule" is a plan showing the timing and person in charge of tasks and plans.

[1325] "Integration" means bringing together multiple pieces of information or data into one.

[1326] "Management" means coordinating and controlling tasks and information in order to operate them efficiently.

[1327] "Sharing" means making the same information available to multiple people or systems.

[1328] "Learning" is the acquisition of knowledge and patterns based on past data and experience.

[1329] A "suggestion" is a recommendation of a particular action or option.

[1330] "Notification" means conveying information or a message to a specific recipient.

[1331] A "system" is a set of devices and programs in which multiple elements function in conjunction with one another.

[1332] An "urgent task" is work that requires immediate action in an unexpected situation.

[1333] A "person in charge" is someone who is in charge of a specific task or job.

[1334] A "smartphone" is a type of mobile information terminal that can use a variety of applications in addition to making calls.

[1335] A "tablet" is a portable computing device that primarily features a touch screen.

[1336] "Smart glasses" are wearable devices that allow the wearer to obtain additional visual information.

[1337] MODE FOR CARRYING OUT THE INVENTION

[1338] The following describes in detail the embodiments of the present invention. The present invention is a system for streamlining task management in a business environment and appropriately allocating task information. The system utilizes a generative AI model that processes various information formats, such as text, images, and audio.

[1339] Server initialization and task management

[1340] The server first instantiates the "TaskMaster" class, which initializes a schedule for managing tasks in the work environment and instantiates a multimodal generative AI model capable of processing information in various formats, including text, images, and audio.

[1341] Creating and adding tasks for users

[1342] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. For example, when an employee adds a task for "inventorying products," the user enters the task information into the system. The server receives this task information and processes it using generative artificial intelligence.

[1343] Task information integration and management

[1344] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates not only text information but also various other information formats such as images and audio, and centralizes it into a schedule dedicated to the work environment. The processed task information is automatically registered in the server's schedule.

[1345] Task notification and allocation

[1346] The server registers the processed task information in the schedule and simultaneously sends a notification to the user in charge. For example, if a new task is added to "Employee A," the system automatically sends a notification to "Employee A" informing him of the task content and deadline. This allows the user to immediately understand the new task.

[1347] Learning and suggestions

[1348] The server has a "learn_and_suggest" method for learning past task allocation situations. This method allows the generative AI model to analyze past task performance and suggest optimal task allocation. For example, if a specific employee was busy in the past, it will suggest that the next task be assigned to another employee.

[1349] Responding to urgent tasks

[1350] In the case of an emergency, for example, if an employee has a sudden meeting and is temporarily unable to take on another task, the server automatically processes the urgent task using a generative AI model and notifies the responsible user. This type of system makes it possible to quickly respond to sudden schedule changes.

[1351] This system unifies task management and information sharing in the work environment, enabling efficient task allocation. All employees can grasp information in a unified manner, enabling them to carry out tasks efficiently within the workplace.

[1352] Hardware and Software Used

[1353] Hardware:

[1354] Smartphone

[1355] tablet

[1356] Smart Glasses

[1357] software:

[1358] Backend system using Python

[1359] Generative AI models use, for example, OpenAI's GPT-4 API.

[1360] Specific usage examples and prompts

[1361] Usage example

[1362] Consider a scenario where an employee adds a new task using a smartphone. For example, an employee adds a task called "Inventory the products."

[1363] Prompt Sentence Examples

[1364] New task information:

[1365] Task: Inventory the goods

[1366] Deadline: 2023-10-15 18:00

[1367] Divide this task appropriately and notify the responsible parties.

[1368] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1369] Step 1:

[1370] The server initializes the system

[1371] The server instantiates the "TaskMaster" class and initializes a schedule table and generative AI model specific to the work environment, laying the foundation for task management.

[1372] Input: None (at system startup)

[1373] Output: Initialized schedule and generative AI model

[1374] Specific operation: The server creates an instance of the TaskMaster class, initializes the schedule table within it, and loads the generative AI model.

[1375] Step 2:

[1376] A user creates or adds a task

[1377] A user creates an instance of the "User" class, enters task information including a task description and deadline date, and sends it to the server.

[1378] Input: Task information (description, due date)

[1379] Output: Task information sent to the server

[1380] Specific operation: A user uses a device (smartphone, tablet, smart glasses) to enter task information and clicks a button to send it to the server.

[1381] Step 3:

[1382] The server processes task information using a generative AI model

[1383] The server processes the received task information using the "process_input" method of the generation AI model, and analyzes and optimizes the task information.

[1384] Input: Task information

[1385] Output: Task information processed by the generative AI model

[1386] Specific operation: The server passes task information to the generative AI model, which integrates text analysis, image, and audio data to generate optimized task information, including the assignment of personnel.

[1387] Step 4:

[1388] Integrate task information into your schedule

[1389] The server integrates the processed task information into a dedicated business schedule and updates the information on tasks and people in charge.

[1390] Input: Task information processed by the generative AI model

[1391] Output: Updated schedule table

[1392] Specific behavior: The server adds a new task entry to the scheduler, sets the assignee and due date.

[1393] Step 5:

[1394] Sending task notifications

[1395] The server notifies the user of the task information, which is sent to the user's device (smartphone, tablet, smart glasses).

[1396] Input: Updated schedule

[1397] Output: Task notification sent to the user's device

[1398] Specific Actions: The server sends a notification message to the appropriate user device, informing the user of the new task and its details.

[1399] Step 6:

[1400] Analyze past task data and perform suggestion functions

[1401] The server analyzes past task allocation situations using a generative AI model and suggests optimal task allocation for the next time.

[1402] Input: Past task data

[1403] Output: Suggested task allocation plan

[1404] Specific operation: The server collects past task data, analyzes it using a generative AI model, and generates a new allocation plan that takes into account the workload of each person in charge, etc.

[1405] Step 7:

[1406] Automated handling of urgent tasks

[1407] When an urgent task arises, the server uses generative AI models to automatically handle the task and notify the appropriate personnel.

[1408] Input: Urgent task information

[1409] Output: Urgent task processing results and notifications

[1410] Specific operation: The server receives an urgent task, determines the optimal response and person in charge using a generative AI model, and immediately notifies the user.

[1411] These steps will improve the efficiency of task management in a business environment and achieve rational task distribution.

[1412] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1413] The present invention provides a task management system for families that facilitates efficient management and sharing of household and childcare tasks, and incorporates an emotion engine that recognizes the user's emotions.

[1414] Server initialization and task management

[1415] The server first instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[1416] Creating and adding tasks for users

[1417] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[1418] Task information integration and management

[1419] The device processes the task information received from the server using the "process_input" method of the artificial intelligence generation. This process integrates not only text information but also various other information formats such as images and audio, and unifies them into a single schedule for the family. The processed task information is automatically registered in the server's schedule.

[1420] Emotion recognition by emotion engine

[1421] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[1422] Task notification and emotion-based work allocation adjustment

[1423] The server registers the processed task information in a family schedule and adjusts task allocation based on the emotional data output by the emotion engine. For example, if the mother is feeling stressed, the server will allocate tasks to other family members. Notifications are also given at the optimal time and in the most appropriate way based on the mother's emotional state.

[1424] Learning and suggestions

[1425] The server runs the "learn_and_suggest" method to learn from past task allocation and emotional data. This allows the AI ​​model to suggest optimal task allocation based on past data. For example, if the mother has been busy in the past, the next task will be suggested to be assigned to another family member.

[1426] Emergency Task Response and Emotion Recognition

[1427] In the case of an emergency, for example, if a mother has to attend a sudden meeting and needs to leave her child alone for a certain period of time, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[1428] This system unifies task management and information sharing within the family, enabling efficient task allocation, and by utilizing emotion recognition, it enables flexible task adjustment according to the user's emotional state. All family members can grasp information in a unified manner, enabling them to efficiently complete tasks in their daily lives.

[1429] The processing flow will be explained below.

[1430] Step 1:

[1431] The server instantiates the "FamilyScheduler" class, which initializes a schedule for managing household tasks, as well as a multimodal generative AI model and an emotion engine.

[1432] Step 2:

[1433] A user creates an instance of the "User" class and sets their name. For example, let's create a user named "Mother."

[1434] Step 3:

[1435] A user creates a new task and sends the task information (eg, a "shopping" description and due date) to the server.

[1436] Step 4:

[1437] The server receives the task information and sends it to the AI ​​generator using the "add_task" method, where task information processing begins.

[1438] Step 5:

[1439] The device uses the generative AI's 'process_input' method to process information in various formats, including text, images, and audio, allowing information to be processed in a unified manner regardless of the input format.

[1440] Step 6:

[1441] The server registers the processed task information in a family-specific schedule, which can be accessed by all family members and allows for centralized task integration and management.

[1442] Step 7:

[1443] When a task is added or an important notification is received, the device analyzes the user's voice and facial expressions through the emotion engine, and as a result of this analysis, the device recognizes the user's emotional state.

[1444] Step 8:

[1445] The server adjusts task allocation based on the emotion data obtained from the emotion engine. For example, if a user is feeling stressed, the server will not assign new tasks to that user.

[1446] Step 9:

[1447] When a new task is added, the server notifies the user in charge of the task. The notification is performed at an appropriate time and in an appropriate manner by the emotion engine.

[1448] Step 10:

[1449] The server runs the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[1450] Step 11:

[1451] When assigning new tasks to family members, the server takes emotional data into consideration when deciding on the allocation and notifies the assigned user. Even in the case of urgent tasks, the server uses the emotion engine to handle them appropriately.

[1452] Through these steps, the system centralizes task management and information sharing within the home, realizing efficient task allocation that takes into consideration the user's feelings.

[1453] Example 2

[1454] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1455] In modern households, it is difficult to efficiently manage and share the burden of housework and childcare among all family members. It is also not easy to coordinate tasks based on each member's emotional state or to respond efficiently in emergencies. Furthermore, it is necessary to integrate information in various formats (text, images, audio, etc.) and manage schedules appropriately. Conventional systems do not adequately provide the means to effectively solve these problems.

[1456] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1457] In this invention, the server includes a means with an emotion recognition engine to efficiently manage and easily allocate housework and childcare tasks, a means with a generation AI that processes multiple forms of information including text information, image information, and audio information, and a means for integrating, managing, and sharing the task information processed by the generation AI into a family-specific schedule. This allows all family members to efficiently allocate tasks and flexibly adjust according to their emotional states and emergency situations.

[1458] "Housework and childcare tasks" is a general term for work done at home, such as cleaning, laundry, cooking, and caring for children.

[1459] An "emotion recognition engine" is a system that analyzes a user's voice, facial expressions, etc. to recognize their emotional state.

[1460] "Generative AI" is a system that processes various input formats, such as text, image, and audio information, to generate or infer knowledge.

[1461] A "schedule" is a tabular management tool for centrally managing task information so that each member of the household can check it in real time.

[1462] "Task sharing" means assigning household and childcare tasks to each family member.

[1463] "Suggestion" means that the system suggests appropriate task allocation and actions based on past data and the current situation.

[1464] An "urgent task" is a task that requires immediate action in an emergency.

[1465] "Natural language processing" is a technology for analyzing text information and processing human language.

[1466] A "personal digital assistant" is a portable computing device such as a smartphone or tablet.

[1467] The present invention is a system that efficiently manages and facilitates the allocation of household chores and childcare tasks within a household. This system combines an emotion recognition engine and a generative AI model to ensure that each family member is able to share tasks fairly and efficiently.

[1468] Server initialization and task management

[1469] The server first creates an instance of the "FamilyScheduler" class. This instance is initialized with a schedule for managing household tasks. At the same time, a multimodal (including text, image, and audio) generative AI model and an emotion recognition engine are also initialized. This establishes the foundation for household task management.

[1470] Creating and adding tasks for users

[1471] A user creates an instance of the "User" class and sets their name. In this example, we create a user named "Mother." The user creates a new task and adds the task information (for example, a description of "Shopping" and a due date of "2023-10-15") to the server. This process registers the user's task information on the server.

[1472] Task information integration and management

[1473] The device processes the task information obtained from the server using a method called "process_input." This method integrates data in various formats, including text, images, and audio, and centralizes it into a schedule for the family. For example, a tablet device can obtain "photos of cleaning" and "voice notes of a shopping list" and integrate this information into the schedule.

[1474] Emotion recognition by emotion engine

[1475] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine analyzes voice and facial images to recognize the user's emotional state. For example, a smartphone can analyze the user's facial expression, detect "fatigue," and send the emotional data to the server.

[1476] Task notification and emotion-based work allocation adjustment

[1477] The server not only registers the processed task information in the schedule, but also adjusts task allocation based on emotional data provided by the emotion engine. For example, if the server detects that the mother is "tired," it will assign the "cooking" task to the father or children. Notifications are made at the optimal time based on this emotional state. A message such as "Mom is tired, please help with cooking" is sent to other family members.

[1478] Learning and suggestions

[1479] The server learns from past task allocation status and emotional data using a method called "learn_and_suggest." For example, if "mother has been busy in the past," the AI ​​model will suggest that the next task be assigned to another family member. This ensures that household tasks are assigned efficiently and fairly.

[1480] Emergency Task Response and Emotion Recognition

[1481] In the case of an emergency, for example, if the mother has to attend a sudden meeting, the server responds quickly using an emotion engine and generative AI model. It detects the emotion "Mother is currently busy" and automatically assigns "childcare" to the father. This information is sent to the father's device as an emergency notification.

[1482] As a concrete example, the prompt sentence for registering the task "shopping" is as follows:

[1483] Prompt Sentence Examples

[1484] "Mom needs to complete the shopping task to buy bread and milk by October 15th."

[1485] This system allows all family members to efficiently share tasks and respond flexibly according to their emotional state and emergency situations.

[1486] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1487] Step 1: Initialize the server

[1488] The server first creates an instance of the "FamilyScheduler" class, which initializes a schedule for managing household tasks. It also initializes the generative AI model and emotion recognition engine.

[1489] Input: None

[1490] Output: Home task schedule, generative AI model, and emotion recognition engine initialization

[1491] Specific operation: The server calls the "FamilyScheduler.initialize()" method to perform initialization.

[1492] Step 2: Creating and adding tasks for users

[1493] A user creates an instance of the "User" class and sets their name. A user named "Mother" creates a new task and adds the task information (e.g., a description of "Shopping" and a due date of "2023-10-15") to the server.

[1494] Input: User name, task description, due date

[1495] Output: Task information is registered on the server

[1496] Specific operation: The user uses the "User.create()" method from the terminal, enters their information, and then uses the "Task.add()" method to send the task information to the server.

[1497] Step 3: Consolidate and manage task information

[1498] The device processes the task information received from the server using the "process_input" method, unifying data such as text, images, and audio, and integrating it into a schedule for the family.

[1499] Input: Task information received from the server (text, image, audio)

[1500] Output: The integrated task information is added to the scheduler

[1501] Specific operation: The terminal calls the "process_input" method, analyzes the received task information, and adds it to the schedule.

[1502] Step 4: Emotion Recognition with the Emotion Engine

[1503] The device uses the emotion engine when the user inputs task information or receives notifications. The emotion engine performs voice and image analysis to recognize the user's emotional state.

[1504] Input: User's voice data or facial image data

[1505] Output: Parsed emotion data

[1506] Specific operation: The device calls the "EmotionEngine.analyze()" method and analyzes voice and facial images to obtain emotional data.

[1507] Step 5: Task notification and emotion-based allocation adjustment

[1508] The server registers the processed task information in a schedule and adjusts task allocation based on the emotion data from the emotion engine. For example, if the mother feels "tired," the server will assign the "cooking task" to another family member.

[1509] Input: Integrated task information, analyzed emotion data

[1510] Output: Adjusted task allocation, notification message

[1511] Specific operation: The server uses the "TaskSchedule.update()" method to reconstruct task allocation based on emotion data and send a notification.

[1512] Step 6: Learning and Suggestions

[1513] The server uses the "learn_and_suggest" method to learn from past task allocation and emotion data, allowing the AI ​​model to suggest optimal task allocation.

[1514] Input: Past task allocation data, past emotion data

[1515] Output: Suggested task allocation plan

[1516] Specific operation: The server calls the "learn_and_suggest" method, learns from past data, and generates task allocation proposals for the next time and beyond.

[1517] Step 7: Emergency Task Management and Emotion Recognition

[1518] The server uses an emotion engine and generative AI model to quickly respond when an emergency occurs. For example, if a mother has to attend a sudden meeting, the emotion engine will detect that she is "busy" and automatically assign the "childcare" task to another family member.

[1519] Input: Emergency situation, user emotion data

[1520] Output: Urgent task reassignment, notification message

[1521] Specific operation: The server calls the "EmergencyHandler.handle()" method, analyzes the emotion data, and takes appropriate action and notifies the user.

[1522] This allows the whole family to efficiently share tasks and respond flexibly according to emotional states and emergency situations.

[1523] (Application example 2)

[1524] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1525] Improving the efficiency of task management at home and in the workplace and achieving fair task allocation are extremely important. However, conventional task management systems uniformly assign tasks without considering the user's emotional state, which can easily lead to the accumulation of stress and overwork, making efficient task management difficult. As a result, users' health and work efficiency are often adversely affected. The present invention aims to achieve both user health and efficient task allocation by recognizing the user's emotional state and dynamically adjusting tasks based on that information.

[1526] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1527] In this invention, the server includes means for generating artificial intelligence that processes information in multiple formats including text information, image information, and audio information, means for integrating, managing, and sharing the task information processed by the artificial intelligence into a schedule dedicated to family or workplace, means for learning past task allocation status and suggesting future task allocation, means for notifying each member of the family or workplace of the task information, means for recognizing the user's emotional state through audio or image analysis and adjusting task allocation based on the emotional data, and means for optimizing task allocation according to the user's stress level, thereby enabling efficient and healthy task management that takes the user's emotional state into consideration.

[1528] "Text information" is digital data expressed in characters.

[1529] "Image information" is digital data in the form of an image.

[1530] "Audio information" is digital data in audio format.

[1531] "Generative AI" is AI that uses machine learning and deep learning to process information in multiple formats, including text, images, and audio.

[1532] A "family or workplace schedule" is a list of plans and tasks shared among family or workplace members.

[1533] "Means for integration, management, and sharing" refers to methods and systems for centralizing task information and efficiently managing and sharing it.

[1534] The "means for learning past task allocation situations and suggesting future task allocations" refers to a method or system for analyzing past task history and making suggestions regarding future task allocations.

[1535] The "means for notifying each member of task information" refers to a method or system for notifying family members or coworkers of task information.

[1536] "Means for recognizing emotional states through audio or image analysis" refers to a method or system for identifying a user's emotions from audio or image data.

[1537] "Means for adjusting task allocation based on emotional data" refers to a method or system that uses the results of emotional analysis to flexibly change task allocation.

[1538] The "means for optimizing task allocation according to stress state" refers to a method or system for optimizing task allocation taking into account the stress level of the user.

[1539] The following describes in detail an embodiment of the present invention. The present invention is a system for improving the efficiency of task management at home and at work and realizing task allocation based on the user's emotional state. This system recognizes the user's emotional state and adjusts task allocation based on that state, thereby reducing the user's stress and improving task execution efficiency.

[1540] System Configuration

[1541] The server first instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine.

[1542] A user creates an instance of the "User" class and sets their name. In this example, a user named "Staff A" is created. The user creates a new task and adds the task information (task description, due date, etc.) to the server.

[1543] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats, such as text, images, and audio, and centralizes it into a dedicated schedule. The processed task information is automatically registered in the server's schedule.

[1544] Emotion Recognition Engine Details

[1545] The device is equipped with an emotion engine that analyzes the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[1546] Adjusting task allocation

[1547] The server adjusts task allocation based on the emotional data output by the emotion engine. For example, if staff member A is feeling stressed, the server will assign cash register duties to another staff member and suggest that staff member A take a break. Notifications are also given at the optimal time and in the most appropriate way based on the emotional state.

[1548] Learning and suggestions

[1549] The server executes the "learn_and_suggest" method to learn from past task allocation status and emotional data. This allows the generative AI model to suggest optimal task allocation based on past data. For example, if staff member A has been busy in the past, it will suggest that the next task be assigned to another staff member.

[1550] Responding to urgent tasks

[1551] In the case of an emergency, for example, when Staff A needs to respond immediately, the server automatically processes the emergency task using the AI ​​model and emotion engine, and notifies the user in charge. In this case, the emotion engine also analyzes the user's emotional state and adjusts the emergency response method.

[1552] Specific examples

[1553] If Staff A is working at the cash register and is tired, the system will assign the cash register task to Staff B and suggest that Staff A take a break.

[1554] Prompt Sentence Examples

[1555] You will work as part of a staff task management system for a brick-and-mortar store. Your role will be to adjust task allocation based on the following tasks and staff sentiment data:

[1556] Task list: Cashiering, Stocking products

[1557] Emotional Data:

[1558] Staff A: High stress

[1559] Staff B: Normal

[1560] output:

[1561] 1. Suggest a break to Staff A

[1562] 2. Reassign cashier duties to Staff B

[1563] This will improve the efficiency of task management at home and at work, and enable flexible task allocation and adjustment according to the user's emotional state.

[1564] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1565] Step 1:

[1566] The server instantiates a "Scheduler" class, which initializes a schedule for managing tasks, as well as a generative AI model and an emotion engine, giving the system task management and emotion recognition capabilities.

[1567] Input: None (initial setting at system startup)

[1568] Output: An instance of the "Scheduler" class

[1569] Step 2:

[1570] A user creates an instance of the "User" class and sets their name. The user creates a new task and adds the task information (task description, due date, etc.) to the server. This registers the task in the system.

[1571] Input: User's name and new task information (e.g. cashier, due date)

[1572] Output: Task information registered on the server

[1573] Step 3:

[1574] The device processes the task information received from the server using the "process_input" method of the generative AI model. This process integrates information in multiple formats (text, images, audio) and centralizes it into a dedicated schedule.

[1575] Input: Task information received from the server

[1576] Output: Consolidated task information

[1577] Step 4:

[1578] The device uses an emotion engine to analyze the user's voice and facial expressions. When the user inputs task information or receives an important notification, the emotion engine uses voice or image analysis to recognize the user's emotional state.

[1579] Input: User voice and image data

[1580] Output: Emotional state data

[1581] Step 5:

[1582] The server adjusts task allocation based on the emotional state data output by the emotion engine. For example, if a user is feeling stressed, the server will assign the task to another member.

[1583] Input: Emotional state data

[1584] Output: Adjusted task allocation

[1585] Step 6:

[1586] The server notifies the user of task information according to the user's emotional state. The notification is performed at the most appropriate timing and in the most appropriate manner based on the user's emotional state.

[1587] Input: Adjusted task allocation

[1588] Output: User notification

[1589] Step 7:

[1590] The server runs the "learn_and_suggest" method to learn past task allocation and emotion data, which allows it to suggest future task allocations.

[1591] Input: Past task allocation data, emotion data

[1592] Output: Proposed future task allocation

[1593] Step 8:

[1594] When an emergency task occurs, the server automatically processes it using the generative AI model and emotion engine, notifying the user in charge. The emotion engine analyzes the user's emotional state and adjusts the emergency response method appropriately.

[1595] Input: Urgent task information, emotional state data

[1596] Output: Emergency response measures and user notification

[1597] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1598] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1599] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1600] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1601] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1602] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1603] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1604] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1605] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1606] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1607] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1608] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1609] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1610] 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.

[1611] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1612] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1613] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1614] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1615] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1616] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1617] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1618] The following is further disclosed regarding the above embodiment.

[1619] (Claim 1)

[1620] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[1621] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the family;

[1622] A means to learn past task allocation situations and suggest future task allocations;

[1623] The system includes means for notifying each member of the family of task information.

[1624] (Claim 2)

[1625] 10. The system of claim 1, wherein the generative artificial intelligence processes images taken with a smartphone, screenshots from apps, and voice memos.

[1626] (Claim 3)

[1627] The system according to claim 1, wherein the generating artificial intelligence analyzes text information using natural language processing and generates task information.

[1628] "Example 1"

[1629] (Claim 1)

[1630] means for generating a generative model for processing multiple forms of information, including text, image, and audio information;

[1631] A means for integrating, managing, and sharing task information processed by the generative model;

[1632] A means for learning past task execution status and proposing future task allocation;

[1633] means for notifying each member of task information;

[1634] A means of redistributing tasks and providing prompt notification in the event of an emergency;

[1635] A system including:

[1636] (Claim 2)

[1637] 10. The system of claim 1, wherein the generative model processes images captured on a smart device, screenshots from an application, and audio data.

[1638] (Claim 3)

[1639] 2. The system according to claim 1, wherein the generative model analyzes text information using natural language processing to generate task information.

[1640] "Application Example 1"

[1641] (Claim 1)

[1642] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[1643] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the business environment;

[1644] A means to learn past task allocation situations and suggest future task allocations;

[1645] means for notifying each member of the work environment of task information;

[1646] A means to automatically process and notify the person in charge when an emergency task occurs;

[1647] A system that includes a means for agents to add and update task information using smartphones, tablets, or smart glasses.

[1648] (Claim 2)

[1649] 10. The system of claim 1, wherein the generative artificial intelligence processes images taken with a mobile device, screenshots from an application, and voice memos.

[1650] (Claim 3)

[1651] The system according to claim 1, wherein the generating artificial intelligence analyzes text information using natural language processing and generates task information.

[1652] "Example 2: Combining Emotion Engines"

[1653] (Claim 1)

[1654] A means with an emotion recognition engine to help efficiently manage and share household and childcare tasks;

[1655] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[1656] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the family;

[1657] means for the emotion recognition engine to analyze the user's emotional state and adjust task allocation;

[1658] A means of learning past task allocation status and emotion data to suggest future task allocation;

[1659] means for notifying each member of the family of task information;

[1660] A system that includes a means to automatically process and notify urgent tasks using an emotion engine and generative artificial intelligence.

[1661] (Claim 2)

[1662] 10. The system of claim 1, wherein the generative artificial intelligence processes images taken with a personal digital assistant, screenshots from an application, and voice memos.

[1663] (Claim 3)

[1664] The system according to claim 1, wherein the generating artificial intelligence analyzes text information using natural language processing and generates task information.

[1665] "Application example 2 when combining emotion engines"

[1666] (Claim 1)

[1667] means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information;

[1668] A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to family or workplace;

[1669] A means to learn past task allocation situations and suggest future task allocations;

[1670] A means for notifying each member of the family or workplace of task information;

[1671] a means for recognizing the emotional state of a user through voice analysis or image analysis and adjusting task allocation based on the emotional data;

[1672] A means for optimizing task allocation according to the stress level of a user;

[1673] A system including:

[1674] (Claim 2)

[1675] The system of claim 1 , wherein the generative artificial intelligence processes images captured by a smartphone or smart glasses, screenshots from apps, and voice memos.

[1676] (Claim 3)

[1677] The system according to claim 1, wherein the generating artificial intelligence analyzes text information using natural language processing and generates task information. [Explanation of symbols]

[1678] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for generating artificial intelligence to process information in multiple formats, including text, image, and audio information; A means for integrating, managing, and sharing the task information processed by the generating artificial intelligence into a schedule dedicated to the family; A means to learn past task allocation situations and suggest future task allocations; The system includes means for notifying each member of the family of task information.

2. The system of claim 1 , wherein the generative artificial intelligence processes images taken with a smartphone, screenshots from an app, and voice memos.

3. The system according to claim 1 , wherein the generating artificial intelligence analyzes text information using natural language processing and generates task information.

Images