system

Abstract

We provide the system. [Solution] A means for receiving user schedule information and saving it to a storage device, A means of analyzing the user's areas of expertise and fatigue level, A means for optimally assigning tasks based on analysis results, A means of notifying each user of their assigned tasks, A means of analyzing user feedback and optimizing the system, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern shared households, the uneven distribution of housework is a common problem, and in particular, this imbalance is causing stress and dissatisfaction within the family. Also, since an efficient and fair method of sharing housework has not been established, as a result, the harmony within the family may be impaired. Thus, there is a problem that the environment in which all family members cooperate to live comfortably is being hindered.

Means for Solving the Problems

[0005] This invention provides a function that receives and utilizes user schedule information to analyze each member's strengths and fatigue levels. Based on this analysis, tasks are optimally assigned to efficiently and fairly distribute the burden of household chores. Furthermore, by providing a reminder function that responds to task progress and optimizing the system using user feedback, it offers means to promote harmony within the family and reduce stress.

[0006] A "user" is a member of the household who uses the system and provides schedule and task information.

[0007] "Schedule information" refers to information about a user's daily schedule and time, and is data used for assigning tasks.

[0008] "Areas of expertise" refers to information indicating the categories of household chores or tasks that the user is particularly good at.

[0009] "Fatigue level" is a measure that indicates the user's current fatigue state, and this is used to adjust the workload of tasks.

[0010] A "task" refers to household chores or specific daily tasks that are managed, assigned, and tracked by a system.

[0011] "Assignment" is the process of distributing tasks to each user based on the analysis results.

[0012] A "reminder" is a function that notifies users of task deadlines and execution times.

[0013] "Feedback" refers to the user's impressions of using the system and their opinions regarding task performance.

[0014] "Optimization" is the process by which a system improves its performance based on feedback, resulting in more effective task management.

Brief Description of the Drawings

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. <4000082> [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] The system of the present invention operates based on a cloud-based server, terminals used by each member, and information obtained from these devices, in order to efficiently manage the division of household chores within the family.

[0037] The server first receives schedule and task information sent by users and stores it in a database. The database stores each member's daily schedule, past task completion status, and feedback. Based on this information, the server analyzes the user's strengths and fatigue levels. The results of this analysis become the basic data for assigning customized tasks to each user, reflecting their work performance and preferences using an AI algorithm.

[0038] As a concrete example, the server analyzes past activity history to determine that User A is skilled at cooking and User B is good at cleaning quickly. Based on this information, it creates a proposal to assign User A the task of preparing dinner on weekday evenings and assign User B the task of thorough cleaning on weekends.

[0039] Next, the terminal receives task assignment notifications sent from the server and notifies each user. The notifications received on the user's smartphone or PC show the specific task details and deadlines, providing information for completion. Furthermore, the terminal manages the task progress, and when the user reports completion, it sends that data back to the server.

[0040] Users add and update their daily schedules and tasks through their devices. The feedback they provide is used to improve future task assignments. For example, feedback such as "This task was more difficult than expected" is collected, and the server analyzes it to reflect in future assignments and suggestions.

[0041] In this way, the system aims to equalize the burden of household chores throughout each step, supporting efficient household management while maintaining harmony within the family. Furthermore, a reminder function helps users avoid missing task deadlines or completion times.

[0042] This invention provides a model that enables all family members to cooperate in improving their living environment and to achieve sustainable household management.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server receives schedule and task information sent by users and stores it in the database. Detailed data such as date, time, and task content is stored there.

[0046] Step 2:

[0047] The server analyzes past task history and schedules to assess each user's fatigue level. An algorithm is used to quantify the workload each user is carrying.

[0048] Step 3:

[0049] The server performs analysis to determine the user's strengths. Based on past task completion times and feedback, it evaluates which household chores are best suited to that user.

[0050] Step 4:

[0051] The server calculates the optimal task assignment based on the analysis results. It allocates tasks to each member, taking into account their areas of expertise, fatigue levels, and the need for an even distribution of workload.

[0052] Step 5:

[0053] The server sends the calculated task assignments to each user's terminal. A notification message is generated that includes task details and deadlines.

[0054] Step 6:

[0055] The terminal displays notifications from the server to the user. The user is notified of tasks and their deadlines via a smartphone or PC interface.

[0056] Step 7:

[0057] Users complete assigned tasks and report their progress to their terminals. They update the status, such as "Task Complete," and send it to the server.

[0058] Step 8:

[0059] The server records the received progress reports in the database. Completed tasks are marked as complete, and reminders are set for incomplete tasks.

[0060] Step 9:

[0061] Users provide feedback through their devices. Opinions such as the difficulty of the task and their impressions of completing it are recorded.

[0062] Step 10:

[0063] The server optimizes the system based on feedback. It performs new analyses and learns to make future task assignments more accurate.

[0064] (Example 1)

[0065] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] Imbalances and inefficiencies in the division of household chores are a source of disruption and stress in many families. Traditional methods often involve fixed assignments of chores, failing to consider each member's strengths and current fatigue levels. As a result, chores are not distributed fairly, leading to dissatisfaction within the family and undermining harmony. This invention aims to solve these problems by providing a system that efficiently and fairly distributes household chores while considering the user's skills and fatigue level.

[0067] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0068] In this invention, the server includes means for receiving user time planning information and storing it in a storage medium, means for analyzing the user's skills and fatigue level and processing the information using a generative model, and means for optimally distributing activities based on the analysis results and generating personalized suggestions using prompts. This makes it possible to efficiently and fairly assign household chores to each household member, thereby reducing inefficiencies and dissatisfaction with household chores while maintaining harmony within the household.

[0069] The term "user" refers to the primary person who performs tasks within the household and is responsible for providing schedule information and feedback.

[0070] "Time planning information" refers to data that shows a user's schedule and available time, and is used to efficiently allocate household tasks.

[0071] A "storage medium" is a foundation for storing data and has the function of holding received schedule information and analysis results.

[0072] "Skills" refer to the types and areas of work that a user excels at, and are an important factor in the appropriate assignment of household tasks.

[0073] "Fatigue status" refers to the degree of fatigue a user is currently experiencing and is a factor considered when assigning tasks.

[0074] A "generative model" is a machine learning-based algorithm used to analyze user data and generate personalized suggestions.

[0075] "Activities" refer to individual tasks or work performed within the household, and are the objects of efficient management.

[0076] A "prompt" is a set of instructions that uses AI to generate personalized suggestions, contributing to the optimal allocation of household chores.

[0077] To implement this invention, a cloud-based server, a user terminal, and a network environment to connect them are required. The server primarily receives, stores, analyzes, and optimizes task assignments for data. Users use the terminal to input data, receive notifications, and provide feedback.

[0078] The server receives time planning and task information from the user and stores it in a storage medium. A database management system is typically used for this purpose. Next, a generative AI model is used to analyze the user's skills and fatigue level, and based on the results, prompts are used to generate personalized suggestions. This generative AI model can be implemented using machine learning libraries such as TENSORFLOW® or PyTorch.

[0079] Specifically, the system determines a user's strengths based on past data, analyzing characteristics such as, "User A is good at cooking and is busy on weekdays. User B is quick at cleaning but has free time on weekends."

[0080] The device receives task notifications sent from the server. These notifications are transmitted to the user via smartphone or PC, indicating the specific task details and deadlines. Furthermore, the system is structured so that user actions update the progress, and this updated information is sent back to the server.

[0081] Users report their daily activities and provide feedback through their devices. For example, by entering feedback such as "This task was more difficult than expected," the server uses this information to improve task allocation in the future.

[0082] A concrete example of a prompt message would be, "User A has plans to see a movie this weekend. Please adjust household tasks to accommodate the time." By inputting such prompts into a generative model, it is possible to provide a system that achieves efficient household management and harmony within the family.

[0083] Based on this configuration, the present invention maximizes the characteristics of the user and realizes efficient and fair task management within the home.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server receives time planning and task information sent from the user's terminal. Input includes the user's schedule and desired task details. This information is stored in a database, prepared for later analysis. Output is the stored schedule and task information.

[0087] Step 2:

[0088] The server retrieves information stored in the database and uses a generative AI model to analyze the user's skills and fatigue level. For this analysis, information on past task completion times and areas of expertise is used as input. The data calculation process involves building a user profile using machine learning algorithms. The output provides analysis results and suggests optimized activities for each user.

[0089] Step 3:

[0090] The server creates prompts based on the analysis results and determines customized task assignments for each user. The input consists of the analysis results and prompt text obtained in the previous step. Data processing involves integrating this information to generate a specific task assignment schedule. The output is a task assignment schedule tailored to each user.

[0091] Step 4:

[0092] The device receives a task list sent from the server and notifies the user. The input is a task list from the server. Specifically, the device uses a notification function via a smartphone or PC. The output is that the task notification to the user is completed, and the user can understand the task details.

[0093] Step 5:

[0094] Users perform tasks notified to them using a terminal and report their progress. Inputs include the task list displayed on the terminal and the user's work status. Specifically, after completing a task, the user reports completion using a progress input interface. Output is the transmission of progress data to the server, where it is recorded in a database.

[0095] Step 6:

[0096] The server collects user feedback and analyzes the data for future task assignments. Inputs include user feedback and improved prompt statements. Data processing involves analyzing the feedback and performing optimization to reflect it in future tasks. The output is an improved configuration for future task assignments.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] Modern homes and production environments demand efficient distribution and progress management of household chores and work. In homes, the burden of household chores is often unfairly distributed, and in factories and other production sites, the capabilities of individual machine operators are not being fully utilized. To address these challenges, efficient and fair task assignment and management are essential.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for receiving user schedule information and storing it in an information storage device, means for analyzing the user's areas of expertise and fatigue level, means for optimally assigning tasks based on the analysis results, and means for analyzing the robot's operation history and assigning tasks appropriate to the robot's capabilities. This enables efficient division of household chores within the home and task assignment that maximizes the capabilities of each machine operator in a factory.

[0102] "User schedule information" refers to information about activities and schedules that an individual plans to undertake in the future.

[0103] An "information storage device" is a device that stores data over a long period of time and makes it available for reuse as needed.

[0104] "Area of ​​expertise" refers to the range of activities an individual engages in based on their areas of expertise and skills.

[0105] "Fatigue level" refers to information that quantifies or relatively evaluates the current degree of fatigue of an individual.

[0106] "Optimally assigning tasks" refers to efficiently distributing tasks that are best suited to the capabilities and condition of each individual or piece of equipment.

[0107] "Robot operation history" refers to a record of tasks and actions that a robot has performed in the past.

[0108] "Assigning tasks appropriate to capabilities" means selecting and assigning tasks that match the current capabilities of a robot or individual.

[0109] The system that realizes this invention is designed to enable efficient task sharing in homes and factories. The server operates on a cloud-based platform, receives user schedule information, and stores that information in an information storage device on Google Cloud Platform. The server utilizes a generative AI model to analyze the user's areas of expertise, fatigue levels, and the robot's operation history. Based on this analysis, the server assigns the most suitable tasks to the user and the robot.

[0110] The terminal sends task assignment notifications to users and robots, and displays and executes the received information as specific tasks. The notifications include task details, deadlines, and execution methods, allowing for real-time progress monitoring. User feedback is collected via the terminal and sent to the server to help with future task assignments.

[0111] A concrete example is a case where a robot is assigned welding work in an automobile factory and performs it efficiently. In this case, the robot is programmed to optimally execute each step of the work based on the results of an analysis by an AI model, thereby improving productivity. An example of a prompt is: "Design a system that assigns optimal tasks to factory robots based on their past work history. Aim to improve productivity through efficient task allocation and continuous optimization through feedback."

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

[0113] Step 1:

[0114] The server receives input data such as schedule information and operation history from users and robots. This data is stored in an information storage device on Google Cloud Platform. The server generates a dataset containing the schedule information and operation history, which is then used as input data for the next analysis process.

[0115] Step 2:

[0116] The server uses a generative AI model to analyze the user's areas of expertise and fatigue level, as well as the robot's capabilities. Input data is passed to the AI ​​model, and the output includes user and robot characteristics, as well as predictions of past performance. Based on these analysis results, an optimal list of tasks to assign is generated.

[0117] Step 3:

[0118] The server assigns the most suitable tasks to users and robots based on the analysis results. Using the task list as input, it generates specific work instructions for each activity entity and sends them to the terminal. In addition to the work instructions, the server includes deadlines and necessary procedural information in its output.

[0119] Step 4:

[0120] The terminal notifies the user and the robot of received work instructions. The notification sequentially displays or instructs the work content, deadline, and execution procedure, preparing the entity responsible for the activity. Specifically, the robot receives a command to start work, and the user receives information on their smartphone as a schedule notification.

[0121] Step 5:

[0122] Users provide feedback on their work progress via their terminal. This feedback consists of completion reports and comments on the work's implementation, and the terminal sends this information to the server. The submitted feedback is then incorporated as points for improvement in future work assignments.

[0123] Step 6:

[0124] The server analyzes the feedback received from the terminals and uses it when assigning tasks to the next group of users. The feedback is added to the dataset, and re-analysis by the AI ​​model improves the accuracy of future task assignments. This leads to continuous task efficiency improvements.

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

[0126] This invention provides an advanced task assignment system that takes into account the user's schedule information and emotional state in order to achieve efficient division of household chores within the home.

[0127] The server first receives schedule information, task information, and user emotion data obtained from the terminal, which are sent by the user, and stores them in a database. The emotion data is analyzed in real time or periodically by the emotion engine, and the user's psychological state is quantified and classified.

[0128] The server optimizes task assignments by cross-analyzing user schedules and emotional data. In doing so, it considers the user's emotional state and adjusts tasks to avoid excessive stress. For example, if a user is feeling fatigued and stressed, the emotional engine will use this information to suggest less demanding tasks or postpone tasks that are premature.

[0129] For example, the server checks user A's schedule and also receives emotional state information indicating "fatigue" from the emotion engine. In this case, the server reduces the amount of household tasks required of user A and, if possible, assigns those tasks to alternative members. Also, if user B is found to be in "relaxed" mode, the server can assign new tasks accordingly, maintaining overall household efficiency.

[0130] The device receives optimized task assignments and notifications sent from the server and displays them to the user. Furthermore, the device utilizes a voice assistant function, enabling the user to report their emotional state interactively and input task progress by voice. Through this two-way communication, the user can easily report their emotions to the system.

[0131] Users perform tasks based on their daily schedules and emotions. Upon completion of a task, they report their progress using their device, allowing the server to update the data and reflect this information in future task assignments. User feedback also takes emotions into account, contributing to system improvements.

[0132] Thus, this embodiment of the present invention realizes task management that takes into account the user's emotions and stress by introducing an emotion engine. This enables all family members to comfortably and efficiently fulfill their roles within the household.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server receives schedule and task information sent by the user and stores it in a database. Furthermore, it records sentiment data acquired in real time from the user's device.

[0136] Step 2:

[0137] The server uses an emotion engine to analyze emotional data. Specifically, it uses technologies such as text analysis and speech recognition to quantify the user's emotional state (e.g., stress, fatigue, relaxation).

[0138] Step 3:

[0139] The server combines schedule information, task importance, user expertise, and emotional state to run an algorithm that optimizes task assignments. If the user is emotionally "fatigued," tasks may be changed to less demanding ones or schedules may be adjusted.

[0140] Step 4:

[0141] The server sends optimized task assignments and notifications to the terminal. The notifications include the task details, priority, and recommended time for completion.

[0142] Step 5:

[0143] The device displays task notifications received from the server to the user. Notifications are provided as on-screen alerts or as voice messages via the voice assistant.

[0144] Step 6:

[0145] Users perform tasks based on notifications. After completing a task, they report their progress and emotional feedback via their device. Emotions are reported again via voice input or other means, and the device sends this information to the server.

[0146] Step 7:

[0147] The server updates the database based on progress reports and new sentiment feedback. This accumulates data that allows for more adaptive suggestions in the next task assignment.

[0148] Step 8:

[0149] Based on the accumulated data, the server optimizes the entire system and makes adjustments to distribute household chores more efficiently and fairly.

[0150] In this way, by incorporating emotional data into task assignment and management, we can reduce the psychological and practical burden on users and support improvements to their home environment.

[0151] (Example 2)

[0152] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0153] Tasks within the household are often assigned uniformly, disregarding individual emotional states and workloads, which can lead to excessive burdens on specific individuals. Furthermore, it is difficult to make flexible adjustments in real time in response to users' emotions and work progress. As a result, overall household efficiency and comfort may be sacrificed.

[0154] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0155] This invention includes a server that receives user schedule information, work information, and emotional information and stores it in a storage device; an emotional processing device that analyzes the emotional information and quantifies and classifies the user's psychological state; and a cross-analysis of the schedule information and emotional state based on the analysis results and optimally assigns tasks to avoid excessive workload. This enables flexible task allocation according to the user's emotions and work progress.

[0156] "Schedule information" refers to information that users record about their daily plans and schedules, and it serves as basic data for the server to appropriately assign tasks by referring to this information.

[0157] "Work information" refers to information about specific activities and tasks required within the household, and tasks are prioritized and assigned based on this information.

[0158] "Emotional information" refers to data that indicates the user's emotional state, and is the data that the server analyzes through its emotion processing unit.

[0159] An "emotion processing device" refers to a device or software that analyzes received emotional information and quantifies and classifies psychological states.

[0160] "Cross-analysis" refers to a method of generating optimal task assignments for a user's situation by simultaneously analyzing and comparing scheduled information and emotional information.

[0161] A "voice response system" refers to a mechanism that enables users to input or receive information from the system via voice, thereby facilitating two-way communication.

[0162] A "generative artificial intelligence model" refers to artificial intelligence technology used to improve systems and optimize tasks based on prompt messages.

[0163] Modes for carrying out the invention

[0164] This invention is a system for efficiently dividing tasks within the home, minimizing burden and considering emotions based on the user's schedule information, task information, and emotional information. In order to implement this system, the following elements must be specifically managed.

[0165] The server receives schedule information, work information, and emotional information sent from the user's terminal in real time and stores it in a database. This requires storage within the server and an interface for network communication. The emotional processing unit analyzes the emotional information, quantifies and categorizes the user's psychological state. Text analysis software and voice analysis software are used in this process. Based on the analysis results, the server cross-analyzes the schedule information and emotional data to derive appropriate work assignments. For example, if the user is experiencing high levels of stress, the server will reorganize tasks to reduce stress.

[0166] The terminal notifies the user of optimized work assignments delivered from the server. This terminal consists of a smartphone or tablet device and has screen display and voice output capabilities. Through a voice response system, the user can report work progress and changes in emotions verbally. This conversational input format allows the user to easily communicate their emotional state to the system.

[0167] Users perform assigned tasks in their daily lives and report their progress to the server via their device. By inputting their emotional state, users can have that data reflected in their next task assignment.

[0168] The generating AI model can receive system improvement suggestions based on prompt messages. A concrete example of a prompt message might be, "Please suggest the optimal task assignment considering the user's schedule and emotions." Through these prompts, further system improvements can be achieved.

[0169] In this way, the present invention realizes a sophisticated division of labor that takes into account the feelings and efficiency of all members of the household.

[0170] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0171] Step 1:

[0172] The server receives schedule information, work information, and sentiment information from the user's device. This information is data entered by the user via smartphone or computer. The server receives this information and stores it in a database. This stored data is used for later analysis and work assignment.

[0173] Step 2:

[0174] The server uses emotion processing software to analyze emotional information and quantify and classify the user's psychological state. The received emotional information is used as input. This process uses text analysis software and speech recognition software to analyze emotional keywords and speech patterns. As output, the user's emotional state is categorized into categories such as "fatigue," "relaxation," and "stress," and stored on the server as numerical data.

[0175] Step 3:

[0176] The server cross-analyzes the schedule information and sentiment data based on the analysis results. The input is the data obtained from Step 1 and Step 2. This analysis uses an optimization algorithm to adjust the workload for each user to minimize it. As output, optimized work assignment data for each user is generated and sent to the terminal.

[0177] Step 4:

[0178] The terminal notifies the user of the optimized work assignment received from the server. The input is the work assignment data generated in step 3. The terminal communicates this information to the user as a screen display or audio alert. Based on this, the user can begin their daily work.

[0179] Step 5:

[0180] Users perform tasks and report their progress and emotional changes to the server via their terminal. Input includes the emotional state and work progress data reported by the user. This data, entered using the terminal's voice response system, is received by the server and used to optimize future work assignments.

[0181] Step 6:

[0182] The server uses a generative artificial intelligence model to receive improvement suggestions based on prompt sentences. The input is the data from steps 1 through 5. The prompt sentence "Please suggest the optimal task assignment considering the user's schedule and emotions." is input to the generative AI model, and improvement suggestions are obtained. The output is a new adjustment proposal for improving the efficiency of task assignments across the entire system.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0185] In factory and other work environments, worker fatigue and emotional state can significantly impact productivity and efficiency. Conventional systems struggle to allocate tasks while considering workers' emotional states, often resulting in stress and fatigue. Furthermore, efficiently managing progress and providing feedback remains a challenge.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes means for receiving user schedule information and storing it in a storage device, means for analyzing the user's areas of expertise and emotional state, and means for optimally assigning tasks based on the analysis results. This makes it possible to take into account the emotional state of the workers and optimally distribute the workload.

[0188] "User" refers to individual people or machines that use a system to perform tasks.

[0189] "Schedule information" refers to data about the user's work schedule and activity time.

[0190] A "storage device" refers to hardware or its functions that can hold data and retrieve it when needed.

[0191] "Areas of expertise" refers to information about tasks or fields in which a user is particularly skilled.

[0192] "Emotional state" refers to data that indicates the user's psychological and emotional health.

[0193] "Analysis" refers to the overall process of extracting and understanding detailed information based on collected data.

[0194] "Task" refers to a specific task or responsibility assigned to a user.

[0195] "Assigning" refers to the process of distributing specific tasks to specific users.

[0196] "Notification" refers to the act or function of communicating information to a user.

[0197] "Feedback" refers to information that shows users' reactions and opinions towards the system.

[0198] "Progress status" refers to information indicating the degree of completion of a task or the extent of its execution to date.

[0199] "Reporting by voice" refers to the act or function of transmitting information using voice.

[0200] This invention provides a system for efficiently assigning tasks to users in work environments such as factories. A server receives user schedule information and stores it in a memory device. An emotion engine is used to analyze information about the user's emotional state and areas of expertise collected via smart glasses or robots. Based on this analysis, the server assigns the user the most suitable task.

[0201] In determining appropriate tasks for each user, the server adjusts the tasks to minimize stress and fatigue based on the user's emotional state. Furthermore, users can report their work progress verbally through two-way voice communication. This allows the server to analyze feedback in real time and incorporate it into future task assignments.

[0202] The hardware and software used include smart glasses and robotic terminals, and an emotion analysis engine performs data analysis. For example, if a worker mutters, "Today is tough," the smart glasses detect the emotion, and the server suggests a less demanding work assignment. In addition, the following prompt statements are used as a generative AI model to analyze and optimize the user's emotion data.

[0203] Example of a prompt:

[0204] "Based on worker sentiment data, please suggest how to assign appropriate tasks."

[0205] This system provides an efficient and stress-free work environment by comprehensively considering the user's emotions and schedule.

[0206] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0207] Step 1:

[0208] The server receives schedule information transmitted from the user's smart glasses or robot terminal and stores it in its storage device. The input is the user's work schedule data, and the output is the stored schedule information. Here, the operations of receiving and recording data take place.

[0209] Step 2:

[0210] The server uses an emotion engine to analyze the user's emotional state and areas of expertise. Inputs are emotional data collected from the user and historical performance data, while output is the analysis of the user's emotional state and areas of expertise. This process includes the use of a generative AI model to quantify the emotional data and convert it into specific states.

[0211] Step 3:

[0212] The server performs calculations to determine the optimal tasks for the user based on the analysis results. The input is analyzed emotional state data and information on the user's areas of expertise, and the output is an optimized task assignment. Task distribution is performed in a way that reduces stress and fatigue, based on the user's psychological state.

[0213] Step 4:

[0214] The server notifies smart glasses and robot terminals of the determined work assignment. The input is optimized work assignment information, and the output is a work instruction to the user terminal. The operation to send the work instruction is performed.

[0215] Step 5:

[0216] The user reports the progress of their work to the server via voice. The input is progress information in voice, and the output is progress data converted to text. This includes the process of converting voice to text using speech recognition technology.

[0217] Step 6:

[0218] The server receives and analyzes user feedback to help with future work assignments. Input is text-based progress and feedback information, while output is improved system settings and adjustments to the learning model. This involves data analysis and system optimization.

[0219] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0220] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0221] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0225] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0226] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0227] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0228] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0229] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0230] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0231] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0232] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0233] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0234] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0235] The system of the present invention operates based on a cloud-based server, terminals used by each member, and information obtained from these devices, in order to efficiently manage the division of household chores within the family.

[0236] The server first receives schedule and task information sent by users and stores it in a database. The database stores each member's daily schedule, past task completion status, and feedback. Based on this information, the server analyzes the user's strengths and fatigue levels. The results of this analysis become the basic data for assigning customized tasks to each user, reflecting their work performance and preferences using an AI algorithm.

[0237] As a concrete example, the server analyzes past activity history to determine that User A is skilled at cooking and User B is good at cleaning quickly. Based on this information, it creates a proposal to assign User A the task of preparing dinner on weekday evenings and assign User B the task of thorough cleaning on weekends.

[0238] Next, the terminal receives task assignment notifications sent from the server and notifies each user. The notifications received on the user's smartphone or PC show the specific task details and deadlines, providing information for completion. Furthermore, the terminal manages the task progress, and when the user reports completion, it sends that data back to the server.

[0239] Users add and update their daily schedules and tasks through their devices. The feedback they provide is used to improve future task assignments. For example, feedback such as "This task was more difficult than expected" is collected, and the server analyzes it to reflect in future assignments and suggestions.

[0240] In this way, the system aims to equalize the burden of household chores throughout each step, supporting efficient household management while maintaining harmony within the family. Furthermore, a reminder function helps users avoid missing task deadlines or completion times.

[0241] This invention provides a model that enables all family members to cooperate in improving their living environment and to achieve sustainable household management.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server receives schedule and task information sent by users and stores it in the database. Detailed data such as date, time, and task content is stored there.

[0245] Step 2:

[0246] The server analyzes past task history and schedules to assess each user's fatigue level. An algorithm is used to quantify the workload each user is carrying.

[0247] Step 3:

[0248] The server performs analysis to determine the user's strengths. Based on past task completion times and feedback, it evaluates which household chores are best suited to that user.

[0249] Step 4:

[0250] The server calculates the optimal task assignment based on the analysis results. It allocates tasks to each member, taking into account their areas of expertise, fatigue levels, and the need for an even distribution of workload.

[0251] Step 5:

[0252] The server sends the calculated task assignments to each user's terminal. A notification message is generated that includes task details and deadlines.

[0253] Step 6:

[0254] The terminal displays notifications from the server to the user. The user is notified of tasks and their deadlines via a smartphone or PC interface.

[0255] Step 7:

[0256] Users complete assigned tasks and report their progress to their terminals. They update the status, such as "Task Complete," and send it to the server.

[0257] Step 8:

[0258] The server records the received progress reports in the database. Completed tasks are marked as complete, and reminders are set for incomplete tasks.

[0259] Step 9:

[0260] Users provide feedback through their devices. Opinions such as the difficulty of the task and their impressions of completing it are recorded.

[0261] Step 10:

[0262] The server optimizes the system based on feedback. It performs new analyses and learns to make future task assignments more accurate.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] Imbalances and inefficiencies in the division of household chores are a source of disruption and stress in many families. Traditional methods often involve fixed assignments of chores, failing to consider each member's strengths and current fatigue levels. As a result, chores are not distributed fairly, leading to dissatisfaction within the family and undermining harmony. This invention aims to solve these problems by providing a system that efficiently and fairly distributes household chores while considering the user's skills and fatigue level.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for receiving user time planning information and storing it in a storage medium, means for analyzing the user's skills and fatigue level and processing the information using a generative model, and means for optimally distributing activities based on the analysis results and generating personalized suggestions using prompts. This makes it possible to efficiently and fairly assign household chores to each household member, thereby reducing inefficiencies and dissatisfaction with household chores while maintaining harmony within the household.

[0268] The term "user" refers to the primary person who performs tasks within the household and is responsible for providing schedule information and feedback.

[0269] "Time planning information" refers to data that shows a user's schedule and available time, and is used to efficiently allocate household tasks.

[0270] A "storage medium" is a foundation for storing data and has the function of holding received schedule information and analysis results.

[0271] "Skills" refer to the types and areas of work that a user excels at, and are an important factor in the appropriate assignment of household tasks.

[0272] "Fatigue status" refers to the degree of fatigue a user is currently experiencing and is a factor considered when assigning tasks.

[0273] A "generative model" is a machine learning-based algorithm used to analyze user data and generate personalized suggestions.

[0274] "Activities" refer to individual tasks or work performed within the household, and are the objects of efficient management.

[0275] A "prompt" is a set of instructions that uses AI to generate personalized suggestions, contributing to the optimal allocation of household chores.

[0276] To implement this invention, a cloud-based server, a user terminal, and a network environment to connect them are required. The server primarily receives, stores, analyzes, and optimizes task assignments for data. Users use the terminal to input data, receive notifications, and provide feedback.

[0277] The server receives time planning and task information from the user and stores it in a storage medium. A database management system is typically used for this purpose. Next, a generative AI model is used to analyze the user's skills and fatigue level, and based on the results, prompts are used to generate personalized suggestions. This generative AI model can be implemented using machine learning libraries such as TensorFlow or PyTorch.

[0278] Specifically, the system determines a user's strengths based on past data, analyzing characteristics such as, "User A is good at cooking and is busy on weekdays. User B is quick at cleaning but has free time on weekends."

[0279] The device receives task notifications sent from the server. These notifications are transmitted to the user via smartphone or PC, indicating the specific task details and deadlines. Furthermore, the system is structured so that user actions update the progress, and this updated information is sent back to the server.

[0280] Users report their daily activities and provide feedback through their devices. For example, by entering feedback such as "This task was more difficult than expected," the server uses this information to improve task allocation in the future.

[0281] As a specific example of the prompt sentence, it is described as "User A plans to watch a movie on the weekend. Please adjust the housework tasks considering the time." By inputting such a prompt into the generation model, a system that can achieve efficient housework management and family harmony can be provided.

[0282] Based on this form, the present invention maximally utilizes the characteristics of the user and realizes efficient and fair task management within the family.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The server receives the time plan information and task information transmitted from the user's terminal. The input includes the user's schedule and the desired task content. These information are stored in the database to prepare for later analysis. As the output, the stored schedule information and task information can be obtained.

[0286] Step 2:

[0287] The server acquires the information stored in the database and analyzes the user's skills and fatigue state using the generation AI model. For this analysis, the completion time of past tasks and information regarding the user's forte are used as input. As the data operation, a process of constructing the user's profile using a machine learning algorithm is performed. As the output, the analysis result is obtained, and proposal data for activities optimized for each user is prepared.

[0288] Step 3:

[0289] The server creates prompts based on the analysis results and determines customized task assignments for each user. The input consists of the analysis results and prompt text obtained in the previous step. Data processing involves integrating this information to generate a specific task assignment schedule. The output is a task assignment schedule tailored to each user.

[0290] Step 4:

[0291] The device receives a task list sent from the server and notifies the user. The input is a task list from the server. Specifically, the device uses a notification function via a smartphone or PC. The output is that the task notification to the user is completed, and the user can understand the task details.

[0292] Step 5:

[0293] Users perform tasks notified to them using a terminal and report their progress. Inputs include the task list displayed on the terminal and the user's work status. Specifically, after completing a task, the user reports completion using a progress input interface. Output is the transmission of progress data to the server, where it is recorded in a database.

[0294] Step 6:

[0295] The server collects user feedback and analyzes the data for future task assignments. Inputs include user feedback and improved prompt statements. Data processing involves analyzing the feedback and performing optimization to reflect it in future tasks. The output is an improved configuration for future task assignments.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] Modern homes and production environments demand efficient distribution and progress management of household chores and work. In homes, the burden of household chores is often unfairly distributed, and in factories and other production sites, the capabilities of individual machine operators are not being fully utilized. To address these challenges, efficient and fair task assignment and management are essential.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes means for receiving user schedule information and storing it in an information storage device, means for analyzing the user's areas of expertise and fatigue level, means for optimally assigning tasks based on the analysis results, and means for analyzing the robot's operation history and assigning tasks appropriate to the robot's capabilities. This enables efficient division of household chores within the home and task assignment that maximizes the capabilities of each machine operator in a factory.

[0301] "User schedule information" refers to information about activities and schedules that an individual plans to undertake in the future.

[0302] An "information storage device" is a device that stores data over a long period of time and makes it available for reuse as needed.

[0303] "Area of ​​expertise" refers to the range of activities an individual engages in based on their areas of expertise and skills.

[0304] "Fatigue level" refers to information that quantifies or relatively evaluates the current degree of fatigue of an individual.

[0305] "Optimally assigning tasks" refers to efficiently distributing tasks that are best suited to the capabilities and condition of each individual or piece of equipment.

[0306] The "operation history of the robot" refers to the record of the work and operations performed by the robot in the past.

[0307] "Assignment of tasks suitable for capabilities" means selecting and instructing tasks that match the current capabilities of the robot or individual.

[0308] The system for realizing this invention is designed to achieve efficient task sharing in homes and factories. The server operates on a cloud-based platform, receives the user's schedule information, and stores the information in an information storage device on the Google Cloud Platform. The server utilizes a generative AI model to analyze the user's area of expertise, fatigue level, and further the operation history of the robot. Based on this analysis information, the server assigns the optimal tasks to the user and the robot.

[0309] The terminal sends task assignment notifications to the user and the robot, and displays and executes the received information as specific tasks. The notification includes the task content, deadline, and execution method, and real-time progress confirmation is possible. The user's feedback is collected via the terminal, sent to the server, and utilized for the next task assignment.

[0310] As a specific example, there is a case where a robot is assigned a welding operation in an automobile factory and performs it efficiently. At this time, based on the results analyzed by the AI model, the robot is programmed to execute each step of the work optimally and improve productivity. An example of a prompt sentence is "Design a system in which a factory robot is assigned an optimal task based on its past work history. Aim to improve productivity through efficient task allocation and continuous optimization based on feedback."

[0311] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0312] Step 1:

[0313] The server receives input data such as schedule information and operation history from users and robots. This data is stored in an information storage device on Google Cloud Platform. The server generates a dataset containing the schedule information and operation history, which is then used as input data for the next analysis process.

[0314] Step 2:

[0315] The server uses a generative AI model to analyze the user's areas of expertise and fatigue level, as well as the robot's capabilities. Input data is passed to the AI ​​model, and the output includes user and robot characteristics, as well as predictions of past performance. Based on these analysis results, an optimal list of tasks to assign is generated.

[0316] Step 3:

[0317] The server assigns the most suitable tasks to users and robots based on the analysis results. Using the task list as input, it generates specific work instructions for each activity entity and sends them to the terminal. In addition to the work instructions, the server includes deadlines and necessary procedural information in its output.

[0318] Step 4:

[0319] The terminal notifies the user and the robot of received work instructions. The notification sequentially displays or instructs the work content, deadline, and execution procedure, preparing the entity responsible for the activity. Specifically, the robot receives a command to start work, and the user receives information on their smartphone as a schedule notification.

[0320] Step 5:

[0321] Users provide feedback on their work progress via their terminal. This feedback consists of completion reports and comments on the work's implementation, and the terminal sends this information to the server. The submitted feedback is then incorporated as points for improvement in future work assignments.

[0322] Step 6:

[0323] The server analyzes the feedback received from the terminals and uses it when assigning tasks to the next group of users. The feedback is added to the dataset, and re-analysis by the AI ​​model improves the accuracy of future task assignments. This leads to continuous task efficiency improvements.

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

[0325] This invention provides an advanced task assignment system that takes into account the user's schedule information and emotional state in order to achieve efficient division of household chores within the home.

[0326] The server first receives schedule information, task information, and user emotion data obtained from the terminal, which are sent by the user, and stores them in a database. The emotion data is analyzed in real time or periodically by the emotion engine, and the user's psychological state is quantified and classified.

[0327] The server optimizes task assignments by cross-analyzing user schedules and emotional data. In doing so, it considers the user's emotional state and adjusts tasks to avoid excessive stress. For example, if a user is feeling fatigued and stressed, the emotional engine will use this information to suggest less demanding tasks or postpone tasks that are premature.

[0328] For example, the server checks user A's schedule and also receives emotional state information indicating "fatigue" from the emotion engine. In this case, the server reduces the amount of household tasks required of user A and, if possible, assigns those tasks to alternative members. Also, if user B is found to be in "relaxed" mode, the server can assign new tasks accordingly, maintaining overall household efficiency.

[0329] The device receives optimized task assignments and notifications sent from the server and displays them to the user. Furthermore, the device utilizes a voice assistant function, enabling the user to report their emotional state interactively and input task progress by voice. Through this two-way communication, the user can easily report their emotions to the system.

[0330] Users perform tasks based on their daily schedules and emotions. Upon completion of a task, they report their progress using their device, allowing the server to update the data and reflect this information in future task assignments. User feedback also takes emotions into account, contributing to system improvements.

[0331] Thus, this embodiment of the present invention realizes task management that takes into account the user's emotions and stress by introducing an emotion engine. This enables all family members to comfortably and efficiently fulfill their roles within the household.

[0332] The following describes the processing flow.

[0333] Step 1:

[0334] The server receives schedule and task information sent by the user and stores it in a database. Furthermore, it records sentiment data acquired in real time from the user's device.

[0335] Step 2:

[0336] The server uses an emotion engine to analyze emotional data. Specifically, it uses technologies such as text analysis and speech recognition to quantify the user's emotional state (e.g., stress, fatigue, relaxation).

[0337] Step 3:

[0338] The server combines schedule information, task importance, user expertise, and emotional state to run an algorithm that optimizes task assignments. If the user is emotionally "fatigued," tasks may be changed to less demanding ones or schedules may be adjusted.

[0339] Step 4:

[0340] The server sends optimized task assignments and notifications to the terminal. The notifications include the task details, priority, and recommended time for completion.

[0341] Step 5:

[0342] The device displays task notifications received from the server to the user. Notifications are provided as on-screen alerts or as voice messages via the voice assistant.

[0343] Step 6:

[0344] Users perform tasks based on notifications. After completing a task, they report their progress and emotional feedback via their device. Emotions are reported again via voice input or other means, and the device sends this information to the server.

[0345] Step 7:

[0346] The server updates the database based on progress reports and new sentiment feedback. This accumulates data that allows for more adaptive suggestions in the next task assignment.

[0347] Step 8:

[0348] Based on the accumulated data, the server optimizes the entire system and makes adjustments to distribute household chores more efficiently and fairly.

[0349] In this way, by incorporating emotional data into task assignment and management, we can reduce the psychological and practical burden on users and support improvements to their home environment.

[0350] (Example 2)

[0351] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0352] Tasks within the household are often assigned uniformly, disregarding individual emotional states and workloads, which can lead to excessive burdens on specific individuals. Furthermore, it is difficult to make flexible adjustments in real time in response to users' emotions and work progress. As a result, overall household efficiency and comfort may be sacrificed.

[0353] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0354] This invention includes a server that receives user schedule information, work information, and emotional information and stores it in a storage device; an emotional processing device that analyzes the emotional information and quantifies and classifies the user's psychological state; and a cross-analysis of the schedule information and emotional state based on the analysis results and optimally assigns tasks to avoid excessive workload. This enables flexible task allocation according to the user's emotions and work progress.

[0355] "Schedule information" refers to information that users record about their daily plans and schedules, and it serves as basic data for the server to appropriately assign tasks by referring to this information.

[0356] "Work information" refers to information about specific activities and tasks required within the household, and tasks are prioritized and assigned based on this information.

[0357] "Emotional information" refers to data that indicates the user's emotional state, and is the data that the server analyzes through its emotion processing unit.

[0358] An "emotion processing device" refers to a device or software that analyzes received emotional information and quantifies and classifies psychological states.

[0359] "Cross-analysis" refers to a method of generating optimal task assignments for a user's situation by simultaneously analyzing and comparing scheduled information and emotional information.

[0360] A "voice response system" refers to a mechanism that enables users to input or receive information from the system via voice, thereby facilitating two-way communication.

[0361] A "generative artificial intelligence model" refers to artificial intelligence technology used to improve systems and optimize tasks based on prompt messages.

[0362] Modes for carrying out the invention

[0363] This invention is a system for efficiently dividing tasks within the home, minimizing burden and considering emotions based on the user's schedule information, task information, and emotional information. In order to implement this system, the following elements must be specifically managed.

[0364] The server receives schedule information, work information, and emotional information sent from the user's terminal in real time and stores it in a database. This requires storage within the server and an interface for network communication. The emotional processing unit analyzes the emotional information, quantifies and categorizes the user's psychological state. Text analysis software and voice analysis software are used in this process. Based on the analysis results, the server cross-analyzes the schedule information and emotional data to derive appropriate work assignments. For example, if the user is experiencing high levels of stress, the server will reorganize tasks to reduce stress.

[0365] The terminal notifies the user of optimized work assignments delivered from the server. This terminal consists of a smartphone or tablet device and has screen display and voice output capabilities. Through a voice response system, the user can report work progress and changes in emotions verbally. This conversational input format allows the user to easily communicate their emotional state to the system.

[0366] Users perform assigned tasks in their daily lives and report their progress to the server via their device. By inputting their emotional state, users can have that data reflected in their next task assignment.

[0367] The generating AI model can receive system improvement suggestions based on prompt messages. A concrete example of a prompt message might be, "Please suggest the optimal task assignment considering the user's schedule and emotions." Through these prompts, further system improvements can be achieved.

[0368] In this way, the present invention realizes a sophisticated division of labor that takes into account the feelings and efficiency of all members of the household.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server receives schedule information, work information, and sentiment information from the user's device. This information is data entered by the user via smartphone or computer. The server receives this information and stores it in a database. This stored data is used for later analysis and work assignment.

[0372] Step 2:

[0373] The server uses emotion processing software to analyze emotional information and quantify and classify the user's psychological state. The received emotional information is used as input. This process uses text analysis software and speech recognition software to analyze emotional keywords and speech patterns. As output, the user's emotional state is categorized into categories such as "fatigue," "relaxation," and "stress," and stored on the server as numerical data.

[0374] Step 3:

[0375] The server cross-analyzes the schedule information and sentiment data based on the analysis results. The input is the data obtained from Step 1 and Step 2. This analysis uses an optimization algorithm to adjust the workload for each user to minimize it. As output, optimized work assignment data for each user is generated and sent to the terminal.

[0376] Step 4:

[0377] The terminal notifies the user of the optimized work assignment received from the server. The input is the work assignment data generated in step 3. The terminal communicates this information to the user as a screen display or audio alert. Based on this, the user can begin their daily work.

[0378] Step 5:

[0379] Users perform tasks and report their progress and emotional changes to the server via their terminal. Input includes the emotional state and work progress data reported by the user. This data, entered using the terminal's voice response system, is received by the server and used to optimize future work assignments.

[0380] Step 6:

[0381] The server uses a generative artificial intelligence model to receive improvement suggestions based on prompt sentences. The input is the data from steps 1 through 5. The prompt sentence "Please suggest the optimal task assignment considering the user's schedule and emotions." is input to the generative AI model, and improvement suggestions are obtained. The output is a new adjustment proposal for improving the efficiency of task assignments across the entire system.

[0382] (Application Example 2)

[0383] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0384] In factory and other work environments, worker fatigue and emotional state can significantly impact productivity and efficiency. Conventional systems struggle to allocate tasks while considering workers' emotional states, often resulting in stress and fatigue. Furthermore, efficiently managing progress and providing feedback remains a challenge.

[0385] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0386] In this invention, the server includes means for receiving user schedule information and storing it in a storage device, means for analyzing the user's areas of expertise and emotional state, and means for optimally assigning tasks based on the analysis results. This makes it possible to take into account the emotional state of the workers and optimally distribute the workload.

[0387] "User" refers to individual people or machines that use a system to perform tasks.

[0388] "Schedule information" refers to data about the user's work schedule and activity time.

[0389] A "storage device" refers to hardware or its functions that can hold data and retrieve it when needed.

[0390] "Areas of expertise" refers to information about tasks or fields in which a user is particularly skilled.

[0391] "Emotional state" refers to data that indicates the user's psychological and emotional health.

[0392] "Analysis" refers to the overall process of extracting and understanding detailed information based on collected data.

[0393] "Task" refers to a specific task or responsibility assigned to a user.

[0394] "Assigning" refers to the process of distributing specific tasks to specific users.

[0395] "Notification" refers to the act or function of communicating information to a user.

[0396] "Feedback" refers to information that shows users' reactions and opinions towards the system.

[0397] "Progress status" refers to information indicating the degree of completion of a task or the extent of its execution to date.

[0398] "Reporting by voice" refers to the act or function of transmitting information using voice.

[0399] This invention provides a system for efficiently assigning tasks to users in work environments such as factories. A server receives user schedule information and stores it in a memory device. An emotion engine is used to analyze information about the user's emotional state and areas of expertise collected via smart glasses or robots. Based on this analysis, the server assigns the user the most suitable task.

[0400] In determining appropriate tasks for each user, the server adjusts the tasks to minimize stress and fatigue based on the user's emotional state. Furthermore, users can report their work progress verbally through two-way voice communication. This allows the server to analyze feedback in real time and incorporate it into future task assignments.

[0401] The hardware and software used include smart glasses and robotic terminals, and an emotion analysis engine performs data analysis. For example, if a worker mutters, "Today is tough," the smart glasses detect the emotion, and the server suggests a less demanding work assignment. In addition, the following prompt statements are used as a generative AI model to analyze and optimize the user's emotion data.

[0402] Example of a prompt:

[0403] "Based on worker sentiment data, please suggest how to assign appropriate tasks."

[0404] This system provides an efficient and stress-free work environment by comprehensively considering the user's emotions and schedule.

[0405] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0406] Step 1:

[0407] The server receives schedule information transmitted from the user's smart glasses or robot terminal and stores it in its storage device. The input is the user's work schedule data, and the output is the stored schedule information. Here, the operations of receiving and recording data take place.

[0408] Step 2:

[0409] The server uses an emotion engine to analyze the user's emotional state and areas of expertise. Inputs are emotional data collected from the user and historical performance data, while output is the analysis of the user's emotional state and areas of expertise. This process includes the use of a generative AI model to quantify the emotional data and convert it into specific states.

[0410] Step 3:

[0411] The server performs calculations to determine the optimal tasks for the user based on the analysis results. The input is analyzed emotional state data and information on the user's areas of expertise, and the output is an optimized task assignment. Task distribution is performed in a way that reduces stress and fatigue, based on the user's psychological state.

[0412] Step 4:

[0413] The server notifies smart glasses and robot terminals of the determined work assignment. The input is optimized work assignment information, and the output is a work instruction to the user terminal. The operation to send the work instruction is performed.

[0414] Step 5:

[0415] The user reports the progress of their work to the server via voice. The input is progress information in voice, and the output is progress data converted to text. This includes the process of converting voice to text using speech recognition technology.

[0416] Step 6:

[0417] The server receives and analyzes user feedback to help with future work assignments. Input is text-based progress and feedback information, while output is improved system settings and adjustments to the learning model. This involves data analysis and system optimization.

[0418] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0419] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0420] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0424] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0425] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0426] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0427] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0428] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0429] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0430] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0431] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0432] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0433] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0434] The system of the present invention operates based on a cloud-based server, terminals used by each member, and information obtained from these devices, in order to efficiently manage the division of household chores within the family.

[0435] The server first receives schedule and task information sent by users and stores it in a database. The database stores each member's daily schedule, past task completion status, and feedback. Based on this information, the server analyzes the user's strengths and fatigue levels. The results of this analysis become the basic data for assigning customized tasks to each user, reflecting their work performance and preferences using an AI algorithm.

[0436] As a concrete example, the server analyzes past activity history to determine that User A is skilled at cooking and User B is good at cleaning quickly. Based on this information, it creates a proposal to assign User A the task of preparing dinner on weekday evenings and assign User B the task of thorough cleaning on weekends.

[0437] Next, the terminal receives task assignment notifications sent from the server and notifies each user. The notifications received on the user's smartphone or PC show the specific task details and deadlines, providing information for completion. Furthermore, the terminal manages the task progress, and when the user reports completion, it sends that data back to the server.

[0438] Users add and update their daily schedules and tasks through their devices. The feedback they provide is used to improve future task assignments. For example, feedback such as "This task was more difficult than expected" is collected, and the server analyzes it to reflect in future assignments and suggestions.

[0439] In this way, the system aims to equalize the burden of household chores throughout each step, supporting efficient household management while maintaining harmony within the family. Furthermore, a reminder function helps users avoid missing task deadlines or completion times.

[0440] This invention provides a model that enables all family members to cooperate in improving their living environment and to achieve sustainable household management.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The server receives schedule and task information sent by users and stores it in the database. Detailed data such as date, time, and task content is stored there.

[0444] Step 2:

[0445] The server analyzes past task history and schedules to assess each user's fatigue level. An algorithm is used to quantify the workload each user is carrying.

[0446] Step 3:

[0447] The server performs analysis to determine the user's strengths. Based on past task completion times and feedback, it evaluates which household chores are best suited to that user.

[0448] Step 4:

[0449] The server calculates the optimal task assignment based on the analysis results. It allocates tasks to each member, taking into account their areas of expertise, fatigue levels, and the need for an even distribution of workload.

[0450] Step 5:

[0451] The server sends the calculated task assignments to each user's terminal. A notification message is generated that includes task details and deadlines.

[0452] Step 6:

[0453] The terminal displays notifications from the server to the user. The user is notified of tasks and their deadlines via a smartphone or PC interface.

[0454] Step 7:

[0455] Users complete assigned tasks and report their progress to their terminals. They update the status, such as "Task Complete," and send it to the server.

[0456] Step 8:

[0457] The server records the received progress reports in the database. Completed tasks are marked as complete, and reminders are set for incomplete tasks.

[0458] Step 9:

[0459] Users provide feedback through their devices. Opinions such as the difficulty of the task and their impressions of completing it are recorded.

[0460] Step 10:

[0461] The server optimizes the system based on feedback. It performs new analyses and learns to make future task assignments more accurate.

[0462] (Example 1)

[0463] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0464] Imbalances and inefficiencies in the division of household chores are a source of disruption and stress in many families. Traditional methods often involve fixed assignments of chores, failing to consider each member's strengths and current fatigue levels. As a result, chores are not distributed fairly, leading to dissatisfaction within the family and undermining harmony. This invention aims to solve these problems by providing a system that efficiently and fairly distributes household chores while considering the user's skills and fatigue level.

[0465] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0466] In this invention, the server includes means for receiving user time planning information and storing it in a storage medium, means for analyzing the user's skills and fatigue level and processing the information using a generative model, and means for optimally distributing activities based on the analysis results and generating personalized suggestions using prompts. This makes it possible to efficiently and fairly assign household chores to each household member, thereby reducing inefficiencies and dissatisfaction with household chores while maintaining harmony within the household.

[0467] The term "user" refers to the primary person who performs tasks within the household and is responsible for providing schedule information and feedback.

[0468] "Time planning information" refers to data that shows a user's schedule and available time, and is used to efficiently allocate household tasks.

[0469] A "storage medium" is a foundation for storing data and has the function of holding received schedule information and analysis results.

[0470] "Skills" refer to the types and areas of work that a user excels at, and are an important factor in the appropriate assignment of household tasks.

[0471] "Fatigue status" refers to the degree of fatigue a user is currently experiencing and is a factor considered when assigning tasks.

[0472] A "generative model" is a machine learning-based algorithm used to analyze user data and generate personalized suggestions.

[0473] "Activities" refer to individual tasks or work performed within the household, and are the objects of efficient management.

[0474] A "prompt" is a set of instructions that uses AI to generate personalized suggestions, contributing to the optimal allocation of household chores.

[0475] To implement this invention, a cloud-based server, a user terminal, and a network environment to connect them are required. The server primarily receives, stores, analyzes, and optimizes task assignments for data. Users use the terminal to input data, receive notifications, and provide feedback.

[0476] The server receives time planning and task information from the user and stores it in a storage medium. A database management system is typically used for this purpose. Next, a generative AI model is used to analyze the user's skills and fatigue level, and based on the results, prompts are used to generate personalized suggestions. This generative AI model can be implemented using machine learning libraries such as TensorFlow or PyTorch.

[0477] Specifically, the system determines a user's strengths based on past data, analyzing characteristics such as, "User A is good at cooking and is busy on weekdays. User B is quick at cleaning but has free time on weekends."

[0478] The device receives task notifications sent from the server. These notifications are transmitted to the user via smartphone or PC, indicating the specific task details and deadlines. Furthermore, the system is structured so that user actions update the progress, and this updated information is sent back to the server.

[0479] Users report their daily activities and provide feedback through their devices. For example, by entering feedback such as "This task was more difficult than expected," the server uses this information to improve task allocation in the future.

[0480] A concrete example of a prompt message would be, "User A has plans to see a movie this weekend. Please adjust household tasks to accommodate the time." By inputting such prompts into a generative model, it is possible to provide a system that achieves efficient household management and harmony within the family.

[0481] Based on this configuration, the present invention maximizes the characteristics of the user and realizes efficient and fair task management within the home.

[0482] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0483] Step 1:

[0484] The server receives time planning and task information sent from the user's terminal. Input includes the user's schedule and desired task details. This information is stored in a database, prepared for later analysis. Output is the stored schedule and task information.

[0485] Step 2:

[0486] The server retrieves information stored in the database and uses a generative AI model to analyze the user's skills and fatigue level. For this analysis, information on past task completion times and areas of expertise is used as input. The data calculation process involves building a user profile using machine learning algorithms. The output provides analysis results and suggests optimized activities for each user.

[0487] Step 3:

[0488] The server creates prompts based on the analysis results and determines customized task assignments for each user. The input consists of the analysis results and prompt text obtained in the previous step. Data processing involves integrating this information to generate a specific task assignment schedule. The output is a task assignment schedule tailored to each user.

[0489] Step 4:

[0490] The device receives a task list sent from the server and notifies the user. The input is a task list from the server. Specifically, the device uses a notification function via a smartphone or PC. The output is that the task notification to the user is completed, and the user can understand the task details.

[0491] Step 5:

[0492] Users perform tasks notified to them using a terminal and report their progress. Inputs include the task list displayed on the terminal and the user's work status. Specifically, after completing a task, the user reports completion using a progress input interface. Output is the transmission of progress data to the server, where it is recorded in a database.

[0493] Step 6:

[0494] The server collects user feedback and analyzes the data for future task assignments. Inputs include user feedback and improved prompt statements. Data processing involves analyzing the feedback and performing optimization to reflect it in future tasks. The output is an improved configuration for future task assignments.

[0495] (Application Example 1)

[0496] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0497] Modern homes and production environments demand efficient distribution and progress management of household chores and work. In homes, the burden of household chores is often unfairly distributed, and in factories and other production sites, the capabilities of individual machine operators are not being fully utilized. To address these challenges, efficient and fair task assignment and management are essential.

[0498] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0499] In this invention, the server includes means for receiving user schedule information and storing it in an information storage device, means for analyzing the user's areas of expertise and fatigue level, means for optimally assigning tasks based on the analysis results, and means for analyzing the robot's operation history and assigning tasks appropriate to the robot's capabilities. This enables efficient division of household chores within the home and task assignment that maximizes the capabilities of each machine operator in a factory.

[0500] "User schedule information" refers to information about activities and schedules that an individual plans to undertake in the future.

[0501] An "information storage device" is a device that stores data over a long period of time and makes it available for reuse as needed.

[0502] "Area of ​​expertise" refers to the range of activities an individual engages in based on their areas of expertise and skills.

[0503] "Fatigue level" refers to information that quantifies or relatively evaluates the current degree of fatigue of an individual.

[0504] "Optimally assigning tasks" refers to efficiently distributing tasks that are best suited to the capabilities and condition of each individual or piece of equipment.

[0505] "Robot operation history" refers to a record of tasks and actions that a robot has performed in the past.

[0506] "Assigning tasks appropriate to capabilities" means selecting and assigning tasks that match the current capabilities of a robot or individual.

[0507] The system that realizes this invention is designed to enable efficient task sharing in homes and factories. The server operates on a cloud-based platform, receives user schedule information, and stores that information in an information storage device on Google Cloud Platform. The server utilizes generative AI models to analyze the user's areas of expertise, fatigue levels, and the robot's operation history. Based on this analysis, the server assigns the most suitable tasks to the user and the robot.

[0508] The terminal sends task assignment notifications to users and robots, and displays and executes the received information as specific tasks. The notifications include task details, deadlines, and execution methods, allowing for real-time progress monitoring. User feedback is collected via the terminal and sent to the server to help with future task assignments.

[0509] A concrete example is a case where a robot is assigned welding work in an automobile factory and performs it efficiently. In this case, the robot is programmed to optimally execute each step of the work based on the results of an analysis by an AI model, thereby improving productivity. An example of a prompt is: "Design a system that assigns optimal tasks to factory robots based on their past work history. Aim to improve productivity through efficient task allocation and continuous optimization through feedback."

[0510] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0511] Step 1:

[0512] The server receives input data such as schedule information and operation history from users and robots. This data is stored in an information storage device on Google Cloud Platform. The server generates a dataset containing the schedule information and operation history, which is then used as input data for the next analysis process.

[0513] Step 2:

[0514] The server uses a generative AI model to analyze the user's areas of expertise and fatigue level, as well as the robot's capabilities. Input data is passed to the AI ​​model, and the output includes user and robot characteristics, as well as predictions of past performance. Based on these analysis results, an optimal list of tasks to assign is generated.

[0515] Step 3:

[0516] The server assigns the most suitable tasks to users and robots based on the analysis results. Using the task list as input, it generates specific work instructions for each activity entity and sends them to the terminal. In addition to the work instructions, the server includes deadlines and necessary procedural information in its output.

[0517] Step 4:

[0518] The terminal notifies the user and the robot of received work instructions. The notification sequentially displays or instructs the work content, deadline, and execution procedure, preparing the entity responsible for the activity. Specifically, the robot receives a command to start work, and the user receives information on their smartphone as a schedule notification.

[0519] Step 5:

[0520] Users provide feedback on their work progress via their terminal. This feedback consists of completion reports and comments on the work's implementation, and the terminal sends this information to the server. The submitted feedback is then incorporated as points for improvement in future work assignments.

[0521] Step 6:

[0522] The server analyzes the feedback received from the terminals and uses it when assigning tasks to the next group of users. The feedback is added to the dataset, and re-analysis by the AI ​​model improves the accuracy of future task assignments. This leads to continuous task efficiency improvements.

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

[0524] This invention provides an advanced task assignment system that takes into account the user's schedule information and emotional state in order to achieve efficient division of household chores within the home.

[0525] The server first receives schedule information, task information, and user emotion data obtained from the terminal, which are sent by the user, and stores them in a database. The emotion data is analyzed in real time or periodically by the emotion engine, and the user's psychological state is quantified and classified.

[0526] The server optimizes task assignments by cross-analyzing user schedules and emotional data. In doing so, it considers the user's emotional state and adjusts tasks to avoid excessive stress. For example, if a user is feeling fatigued and stressed, the emotional engine will use this information to suggest less demanding tasks or postpone tasks that are premature.

[0527] For example, the server checks user A's schedule and also receives emotional state information indicating "fatigue" from the emotion engine. In this case, the server reduces the amount of household tasks required of user A and, if possible, assigns those tasks to alternative members. Also, if user B is found to be in "relaxed" mode, the server can assign new tasks accordingly, maintaining overall household efficiency.

[0528] The device receives optimized task assignments and notifications sent from the server and displays them to the user. Furthermore, the device utilizes a voice assistant function, enabling the user to report their emotional state interactively and input task progress by voice. Through this two-way communication, the user can easily report their emotions to the system.

[0529] Users perform tasks based on their daily schedules and emotions. Upon completion of a task, they report their progress using their device, allowing the server to update the data and reflect this information in future task assignments. User feedback also takes emotions into account, contributing to system improvements.

[0530] Thus, this embodiment of the present invention realizes task management that takes into account the user's emotions and stress by introducing an emotion engine. This enables all family members to comfortably and efficiently fulfill their roles within the household.

[0531] The following describes the processing flow.

[0532] Step 1:

[0533] The server receives schedule and task information sent by the user and stores it in a database. Furthermore, it records sentiment data acquired in real time from the user's device.

[0534] Step 2:

[0535] The server uses an emotion engine to analyze emotional data. Specifically, it uses technologies such as text analysis and speech recognition to quantify the user's emotional state (e.g., stress, fatigue, relaxation).

[0536] Step 3:

[0537] The server combines schedule information, task importance, user expertise, and emotional state to run an algorithm that optimizes task assignments. If the user is emotionally "fatigued," tasks may be changed to less demanding ones or schedules may be adjusted.

[0538] Step 4:

[0539] The server sends optimized task assignments and notifications to the terminal. The notifications include the task details, priority, and recommended time for completion.

[0540] Step 5:

[0541] The device displays task notifications received from the server to the user. Notifications are provided as on-screen alerts or as voice messages via the voice assistant.

[0542] Step 6:

[0543] Users perform tasks based on notifications. After completing a task, they report their progress and emotional feedback via their device. Emotions are reported again via voice input or other means, and the device sends this information to the server.

[0544] Step 7:

[0545] The server updates the database based on progress reports and new sentiment feedback. This accumulates data that allows for more adaptive suggestions in the next task assignment.

[0546] Step 8:

[0547] Based on the accumulated data, the server optimizes the entire system and makes adjustments to distribute household chores more efficiently and fairly.

[0548] In this way, by incorporating emotional data into task assignment and management, we can reduce the psychological and practical burden on users and support improvements to their home environment.

[0549] (Example 2)

[0550] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] Tasks within the household are often assigned uniformly, disregarding individual emotional states and workloads, which can lead to excessive burdens on specific individuals. Furthermore, it is difficult to make flexible adjustments in real time in response to users' emotions and work progress. As a result, overall household efficiency and comfort may be sacrificed.

[0552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0553] This invention includes a server that receives user schedule information, work information, and emotional information and stores it in a storage device; an emotional processing device that analyzes the emotional information and quantifies and classifies the user's psychological state; and a cross-analysis of the schedule information and emotional state based on the analysis results and optimally assigns tasks to avoid excessive workload. This enables flexible task allocation according to the user's emotions and work progress.

[0554] "Schedule information" refers to information that users record about their daily plans and schedules, and it serves as basic data for the server to appropriately assign tasks by referring to this information.

[0555] "Work information" refers to information about specific activities and tasks required within the household, and tasks are prioritized and assigned based on this information.

[0556] "Emotional information" refers to data that indicates the user's emotional state, and is the data that the server analyzes through its emotion processing unit.

[0557] An "emotion processing device" refers to a device or software that analyzes received emotional information and quantifies and classifies psychological states.

[0558] "Cross-analysis" refers to a method of generating optimal task assignments for a user's situation by simultaneously analyzing and comparing scheduled information and emotional information.

[0559] A "voice response system" refers to a mechanism that enables users to input or receive information from the system via voice, thereby facilitating two-way communication.

[0560] A "generative artificial intelligence model" refers to artificial intelligence technology used to improve systems and optimize tasks based on prompt messages.

[0561] Modes for carrying out the invention

[0562] This invention is a system for efficiently dividing tasks within the home, minimizing burden and considering emotions based on the user's schedule information, task information, and emotional information. In order to implement this system, the following elements must be specifically managed.

[0563] The server receives schedule information, work information, and emotional information sent from the user's terminal in real time and stores it in a database. This requires storage within the server and an interface for network communication. The emotional processing unit analyzes the emotional information, quantifies and categorizes the user's psychological state. Text analysis software and voice analysis software are used in this process. Based on the analysis results, the server cross-analyzes the schedule information and emotional data to derive appropriate work assignments. For example, if the user is experiencing high levels of stress, the server will reorganize tasks to reduce stress.

[0564] The terminal notifies the user of optimized work assignments delivered from the server. This terminal consists of a smartphone or tablet device and has screen display and voice output capabilities. Through a voice response system, the user can report work progress and changes in emotions verbally. This conversational input format allows the user to easily communicate their emotional state to the system.

[0565] Users perform assigned tasks in their daily lives and report their progress to the server via their device. By inputting their emotional state, users can have that data reflected in their next task assignment.

[0566] The generating AI model can receive system improvement suggestions based on prompt messages. A concrete example of a prompt message might be, "Please suggest the optimal task assignment considering the user's schedule and emotions." Through these prompts, further system improvements can be achieved.

[0567] In this way, the present invention realizes a sophisticated division of labor that takes into account the feelings and efficiency of all members of the household.

[0568] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0569] Step 1:

[0570] The server receives schedule information, work information, and sentiment information from the user's device. This information is data entered by the user via smartphone or computer. The server receives this information and stores it in a database. This stored data is used for later analysis and work assignment.

[0571] Step 2:

[0572] The server uses emotion processing software to analyze emotional information and quantify and classify the user's psychological state. The received emotional information is used as input. This process uses text analysis software and speech recognition software to analyze emotional keywords and speech patterns. As output, the user's emotional state is categorized into categories such as "fatigue," "relaxation," and "stress," and stored on the server as numerical data.

[0573] Step 3:

[0574] The server cross-analyzes the schedule information and sentiment data based on the analysis results. The input is the data obtained from Step 1 and Step 2. This analysis uses an optimization algorithm to adjust the workload for each user to minimize it. As output, optimized work assignment data for each user is generated and sent to the terminal.

[0575] Step 4:

[0576] The terminal notifies the user of the optimized work assignment received from the server. The input is the work assignment data generated in step 3. The terminal communicates this information to the user as a screen display or audio alert. Based on this, the user can begin their daily work.

[0577] Step 5:

[0578] Users perform tasks and report their progress and emotional changes to the server via their terminal. Input includes the emotional state and work progress data reported by the user. This data, entered using the terminal's voice response system, is received by the server and used to optimize future work assignments.

[0579] Step 6:

[0580] The server uses a generative artificial intelligence model to receive improvement suggestions based on prompt sentences. The input is the data from steps 1 through 5. The prompt sentence "Please suggest the optimal task assignment considering the user's schedule and emotions." is input to the generative AI model, and improvement suggestions are obtained. The output is a new adjustment proposal for improving the efficiency of task assignments across the entire system.

[0581] (Application Example 2)

[0582] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0583] In factory and other work environments, worker fatigue and emotional state can significantly impact productivity and efficiency. Conventional systems struggle to allocate tasks while considering workers' emotional states, often resulting in stress and fatigue. Furthermore, efficiently managing progress and providing feedback remains a challenge.

[0584] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0585] In this invention, the server includes means for receiving user schedule information and storing it in a storage device, means for analyzing the user's areas of expertise and emotional state, and means for optimally assigning tasks based on the analysis results. This makes it possible to take into account the emotional state of the workers and optimally distribute the workload.

[0586] "User" refers to individual people or machines that use a system to perform tasks.

[0587] "Schedule information" refers to data about the user's work schedule and activity time.

[0588] A "storage device" refers to hardware or its functions that can hold data and retrieve it when needed.

[0589] "Areas of expertise" refers to information about tasks or fields in which a user is particularly skilled.

[0590] "Emotional state" refers to data that indicates the user's psychological and emotional health.

[0591] "Analysis" refers to the overall process of extracting and understanding detailed information based on collected data.

[0592] "Task" refers to a specific task or responsibility assigned to a user.

[0593] "Assigning" refers to the process of distributing specific tasks to specific users.

[0594] "Notification" refers to the act or function of communicating information to a user.

[0595] "Feedback" refers to information that shows users' reactions and opinions towards the system.

[0596] "Progress status" refers to information indicating the degree of completion of a task or the extent of its execution to date.

[0597] "Reporting by voice" refers to the act or function of transmitting information using voice.

[0598] This invention provides a system for efficiently assigning tasks to users in work environments such as factories. A server receives user schedule information and stores it in a memory device. An emotion engine is used to analyze information about the user's emotional state and areas of expertise collected via smart glasses or robots. Based on this analysis, the server assigns the user the most suitable task.

[0599] In determining appropriate tasks for each user, the server adjusts the tasks to minimize stress and fatigue based on the user's emotional state. Furthermore, users can report their work progress verbally through two-way voice communication. This allows the server to analyze feedback in real time and incorporate it into future task assignments.

[0600] The hardware and software used include smart glasses and robotic terminals, and an emotion analysis engine performs data analysis. For example, if a worker mutters, "Today is tough," the smart glasses detect the emotion, and the server suggests a less demanding work assignment. In addition, the following prompt statements are used as a generative AI model to analyze and optimize the user's emotion data.

[0601] Example of a prompt:

[0602] "Based on worker sentiment data, please suggest how to assign appropriate tasks."

[0603] This system provides an efficient and stress-free work environment by comprehensively considering the user's emotions and schedule.

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The server receives schedule information transmitted from the user's smart glasses or robot terminal and stores it in its storage device. The input is the user's work schedule data, and the output is the stored schedule information. Here, the operations of receiving and recording data take place.

[0607] Step 2:

[0608] The server uses an emotion engine to analyze the user's emotional state and areas of expertise. Inputs are emotional data collected from the user and historical performance data, while output is the analysis of the user's emotional state and areas of expertise. This process includes the use of a generative AI model to quantify the emotional data and convert it into specific states.

[0609] Step 3:

[0610] The server performs calculations to determine the optimal tasks for the user based on the analysis results. The input is analyzed emotional state data and information on the user's areas of expertise, and the output is an optimized task assignment. Task distribution is performed in a way that reduces stress and fatigue, based on the user's psychological state.

[0611] Step 4:

[0612] The server notifies smart glasses and robot terminals of the determined work assignment. The input is optimized work assignment information, and the output is a work instruction to the user terminal. The operation to send the work instruction is performed.

[0613] Step 5:

[0614] The user reports the progress of their work to the server via voice. The input is progress information in voice, and the output is progress data converted to text. This includes the process of converting voice to text using speech recognition technology.

[0615] Step 6:

[0616] The server receives and analyzes user feedback to help with future work assignments. Input is text-based progress and feedback information, while output is improved system settings and adjustments to the learning model. This involves data analysis and system optimization.

[0617] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0618] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0623] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0625] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0627] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0628] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0629] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0630] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0631] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0632] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0633] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] The system of the present invention operates based on a cloud-based server, terminals used by each member, and information obtained from these devices, in order to efficiently manage the division of household chores within the family.

[0635] The server first receives schedule and task information sent by users and stores it in a database. The database stores each member's daily schedule, past task completion status, and feedback. Based on this information, the server analyzes the user's strengths and fatigue levels. The results of this analysis become the basic data for assigning customized tasks to each user, reflecting their work performance and preferences using an AI algorithm.

[0636] As a concrete example, the server analyzes past activity history to determine that User A is skilled at cooking and User B is good at cleaning quickly. Based on this information, it creates a proposal to assign User A the task of preparing dinner on weekday evenings and assign User B the task of thorough cleaning on weekends.

[0637] Next, the terminal receives task assignment notifications sent from the server and notifies each user. The notifications received on the user's smartphone or PC show the specific task details and deadlines, providing information for completion. Furthermore, the terminal manages the task progress, and when the user reports completion, it sends that data back to the server.

[0638] Users add and update their daily schedules and tasks through their devices. The feedback they provide is used to improve future task assignments. For example, feedback such as "This task was more difficult than expected" is collected, and the server analyzes it to reflect in future assignments and suggestions.

[0639] In this way, the system aims to equalize the burden of household chores throughout each step, supporting efficient household management while maintaining harmony within the family. Furthermore, a reminder function helps users avoid missing task deadlines or completion times.

[0640] This invention provides a model that enables all family members to cooperate in improving their living environment and to achieve sustainable household management.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The server receives schedule and task information sent by users and stores it in the database. Detailed data such as date, time, and task content is stored there.

[0644] Step 2:

[0645] The server analyzes past task history and schedules to assess each user's fatigue level. An algorithm is used to quantify the workload each user is carrying.

[0646] Step 3:

[0647] The server performs analysis to determine the user's strengths. Based on past task completion times and feedback, it evaluates which household chores are best suited to that user.

[0648] Step 4:

[0649] The server calculates the optimal task assignment based on the analysis results. It allocates tasks to each member, taking into account their areas of expertise, fatigue levels, and the need for an even distribution of workload.

[0650] Step 5:

[0651] The server sends the calculated task assignments to each user's terminal. A notification message is generated that includes task details and deadlines.

[0652] Step 6:

[0653] The terminal displays notifications from the server to the user. The user is notified of tasks and their deadlines via a smartphone or PC interface.

[0654] Step 7:

[0655] Users complete assigned tasks and report their progress to their terminals. They update the status, such as "Task Complete," and send it to the server.

[0656] Step 8:

[0657] The server records the received progress reports in the database. Completed tasks are marked as complete, and reminders are set for incomplete tasks.

[0658] Step 9:

[0659] Users provide feedback through their devices. Opinions such as the difficulty of the task and their impressions of completing it are recorded.

[0660] Step 10:

[0661] The server optimizes the system based on feedback. It performs new analyses and learns to make future task assignments more accurate.

[0662] (Example 1)

[0663] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0664] Imbalances and inefficiencies in the division of household chores are a source of disruption and stress in many families. Traditional methods often involve fixed assignments of chores, failing to consider each member's strengths and current fatigue levels. As a result, chores are not distributed fairly, leading to dissatisfaction within the family and undermining harmony. This invention aims to solve these problems by providing a system that efficiently and fairly distributes household chores while considering the user's skills and fatigue level.

[0665] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0666] In this invention, the server includes means for receiving user time planning information and storing it in a storage medium, means for analyzing the user's skills and fatigue level and processing the information using a generative model, and means for optimally distributing activities based on the analysis results and generating personalized suggestions using prompts. This makes it possible to efficiently and fairly assign household chores to each household member, thereby reducing inefficiencies and dissatisfaction with household chores while maintaining harmony within the household.

[0667] The term "user" refers to the primary person who performs tasks within the household and is responsible for providing schedule information and feedback.

[0668] "Time planning information" refers to data that shows a user's schedule and available time, and is used to efficiently allocate household tasks.

[0669] A "storage medium" is a foundation for storing data and has the function of holding received schedule information and analysis results.

[0670] "Skills" refer to the types and areas of work that a user excels at, and are an important factor in the appropriate assignment of household tasks.

[0671] "Fatigue status" refers to the degree of fatigue a user is currently experiencing and is a factor considered when assigning tasks.

[0672] A "generative model" is a machine learning-based algorithm used to analyze user data and generate personalized suggestions.

[0673] "Activities" refer to individual tasks or work performed within the household, and are the objects of efficient management.

[0674] A "prompt" is a set of instructions that uses AI to generate personalized suggestions, contributing to the optimal allocation of household chores.

[0675] To implement this invention, a cloud-based server, a user terminal, and a network environment to connect them are required. The server primarily receives, stores, analyzes, and optimizes task assignments for data. Users use the terminal to input data, receive notifications, and provide feedback.

[0676] The server receives time planning and task information from the user and stores it in a storage medium. A database management system is typically used for this purpose. Next, a generative AI model is used to analyze the user's skills and fatigue level, and based on the results, prompts are used to generate personalized suggestions. This generative AI model can be implemented using machine learning libraries such as TensorFlow or PyTorch.

[0677] Specifically, the system uses past data to determine the user's strengths and analyzes characteristics such as, "User A is good at cooking and is busy on weekdays. User B is quick at cleaning but has free time on weekends."

[0678] The device receives task notifications sent from the server. These notifications are transmitted to the user via smartphone or PC, indicating the specific task details and deadlines. Furthermore, the system is structured so that user actions update the progress, and this updated information is sent back to the server.

[0679] Users report their daily activities and provide feedback through their devices. For example, by entering feedback such as "This task was more difficult than expected," the server uses this information to improve task allocation in the future.

[0680] A concrete example of a prompt message would be, "User A has plans to see a movie this weekend. Please adjust household tasks to accommodate the time." By inputting such prompts into a generative model, it is possible to provide a system that achieves efficient household management and harmony within the family.

[0681] Based on this configuration, the present invention maximizes the characteristics of the user and realizes efficient and fair task management within the home.

[0682] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0683] Step 1:

[0684] The server receives time planning and task information sent from the user's terminal. Input includes the user's schedule and desired task details. This information is stored in a database, prepared for later analysis. Output is the stored schedule and task information.

[0685] Step 2:

[0686] The server retrieves information stored in the database and uses a generative AI model to analyze the user's skills and fatigue level. For this analysis, information on past task completion times and areas of expertise is used as input. The data calculation process involves building a user profile using machine learning algorithms. The output provides analysis results and suggests optimized activities for each user.

[0687] Step 3:

[0688] The server creates prompts based on the analysis results and determines customized task assignments for each user. The input consists of the analysis results and prompt text obtained in the previous step. Data processing involves integrating this information to generate a specific task assignment schedule. The output is a task assignment schedule tailored to each user.

[0689] Step 4:

[0690] The device receives a task list sent from the server and notifies the user. The input is a task list from the server. Specifically, the device uses a notification function via a smartphone or PC. The output is that the task notification to the user is completed, and the user can understand the task details.

[0691] Step 5:

[0692] Users perform tasks notified to them using a terminal and report their progress. Inputs include the task list displayed on the terminal and the user's work status. Specifically, after completing a task, the user reports completion using a progress input interface. Output is the transmission of progress data to the server, where it is recorded in a database.

[0693] Step 6:

[0694] The server collects user feedback and analyzes the data for future task assignments. Inputs include user feedback and improved prompt statements. Data processing involves analyzing the feedback and performing optimization to reflect it in future tasks. The output is an improved configuration for future task assignments.

[0695] (Application Example 1)

[0696] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] Modern homes and production environments demand efficient distribution and progress management of household chores and work. In homes, the burden of household chores is often unfairly distributed, and in factories and other production sites, the capabilities of individual machine operators are not being fully utilized. To address these challenges, efficient and fair task assignment and management are essential.

[0698] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0699] In this invention, the server includes means for receiving user schedule information and storing it in an information storage device, means for analyzing the user's areas of expertise and fatigue level, means for optimally assigning tasks based on the analysis results, and means for analyzing the robot's operation history and assigning tasks appropriate to the robot's capabilities. This enables efficient division of household chores within the home and task assignment that maximizes the capabilities of each machine operator in a factory.

[0700] "User schedule information" refers to information about activities and schedules that an individual plans to undertake in the future.

[0701] An "information storage device" is a device that stores data over a long period of time and makes it available for reuse as needed.

[0702] "Area of ​​expertise" refers to the range of activities an individual engages in based on their areas of expertise and skills.

[0703] "Fatigue level" refers to information that quantifies or relatively evaluates the current degree of fatigue of an individual.

[0704] "Optimally assigning tasks" refers to efficiently distributing tasks that are best suited to the capabilities and condition of each individual or piece of equipment.

[0705] "Robot operation history" refers to a record of tasks and actions that a robot has performed in the past.

[0706] "Assigning tasks appropriate to capabilities" means selecting and assigning tasks that match the current capabilities of a robot or individual.

[0707] The system that realizes this invention is designed to enable efficient task sharing in homes and factories. The server operates on a cloud-based platform, receives user schedule information, and stores that information in an information storage device on Google Cloud Platform. The server utilizes generative AI models to analyze the user's areas of expertise, fatigue levels, and the robot's operation history. Based on this analysis, the server assigns the most suitable tasks to the user and the robot.

[0708] The terminal sends task assignment notifications to users and robots, and displays and executes the received information as specific tasks. The notifications include task details, deadlines, and execution methods, allowing for real-time progress monitoring. User feedback is collected via the terminal and sent to the server to help with future task assignments.

[0709] A concrete example is a case where a robot is assigned welding work in an automobile factory and performs it efficiently. In this case, the robot is programmed to optimally execute each step of the work based on the results of an analysis by an AI model, thereby improving productivity. An example of a prompt is: "Design a system that assigns optimal tasks to factory robots based on their past work history. Aim to improve productivity through efficient task allocation and continuous optimization through feedback."

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The server receives input data such as schedule information and operation history from users and robots. This data is stored in an information storage device on Google Cloud Platform. The server generates a dataset containing the schedule information and operation history, which is then used as input data for the next analysis process.

[0713] Step 2:

[0714] The server uses a generative AI model to analyze the user's areas of expertise and fatigue level, as well as the robot's capabilities. Input data is passed to the AI ​​model, and the output includes user and robot characteristics, as well as predictions of past performance. Based on these analysis results, an optimal list of tasks to assign is generated.

[0715] Step 3:

[0716] The server assigns the most suitable tasks to users and robots based on the analysis results. Using the task list as input, it generates specific work instructions for each activity entity and sends them to the terminal. In addition to the work instructions, the server includes deadlines and necessary procedural information in its output.

[0717] Step 4:

[0718] The terminal notifies the user and the robot of received work instructions. The notification sequentially displays or instructs the work content, deadline, and execution procedure, preparing the entity responsible for the activity. Specifically, the robot receives a command to start work, and the user receives information on their smartphone as a schedule notification.

[0719] Step 5:

[0720] Users provide feedback on their work progress via their terminal. This feedback consists of completion reports and comments on the work's implementation, and the terminal sends this information to the server. The submitted feedback is then incorporated as points for improvement in future work assignments.

[0721] Step 6:

[0722] The server analyzes the feedback received from the terminals and uses it when assigning tasks to the next group of people. The feedback is added to the dataset, and re-analysis by the AI ​​model improves the accuracy of future task assignments. This leads to continuous task efficiency improvements.

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

[0724] This invention provides an advanced task assignment system that takes into account the user's schedule information and emotional state in order to achieve efficient division of household chores within the family.

[0725] The server first receives schedule information, task information, and user emotion data obtained from the terminal, which are sent by the user, and stores them in a database. The emotion data is analyzed in real time or periodically by the emotion engine, and the user's psychological state is quantified and classified.

[0726] The server optimizes task assignments by cross-analyzing user schedules and emotional data. In doing so, it considers the user's emotional state and adjusts tasks to avoid excessive stress. For example, if a user is feeling fatigued and stressed, the emotional engine will use this information to suggest less demanding tasks or postpone tasks that are premature.

[0727] For example, the server checks user A's schedule and also receives emotional state information indicating "fatigue" from the emotion engine. In this case, the server reduces the amount of household tasks required of user A and, if possible, assigns those tasks to alternative members. Also, if user B is found to be in "relaxed" mode, the server can assign new tasks accordingly, maintaining overall household efficiency.

[0728] The device receives optimized task assignments and notifications sent from the server and displays them to the user. Furthermore, the device utilizes a voice assistant function, enabling the user to report their emotional state interactively and input task progress by voice. Through this two-way communication, the user can easily report their emotions to the system.

[0729] Users perform tasks based on their daily schedules and emotions. Upon completion of a task, they report their progress using their device, allowing the server to update the data and reflect this information in future task assignments. User feedback also takes emotions into account, contributing to system improvements.

[0730] Thus, this embodiment of the present invention realizes task management that takes into account the user's emotions and stress by introducing an emotion engine. This enables all family members to comfortably and efficiently fulfill their roles within the household.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] The server receives schedule and task information sent by the user and stores it in a database. Furthermore, it records sentiment data acquired in real time from the user's device.

[0734] Step 2:

[0735] The server uses an emotion engine to analyze emotional data. Specifically, it uses technologies such as text analysis and speech recognition to quantify the user's emotional state (e.g., stress, fatigue, relaxation).

[0736] Step 3:

[0737] The server combines schedule information, task importance, user expertise, and emotional state to run an algorithm that optimizes task assignments. If the user is emotionally "fatigued," tasks may be changed to less demanding ones or schedules may be adjusted.

[0738] Step 4:

[0739] The server sends optimized task assignments and notifications to the terminal. The notifications include the task details, priority, and recommended time for completion.

[0740] Step 5:

[0741] The device displays task notifications received from the server to the user. Notifications are provided as on-screen alerts or as voice messages via the voice assistant.

[0742] Step 6:

[0743] Users perform tasks based on notifications. After completing a task, they report their progress and emotional feedback via their device. Emotions are reported again via voice input or other means, and the device sends this information to the server.

[0744] Step 7:

[0745] The server updates the database based on progress reports and new sentiment feedback. This accumulates data that allows for more adaptive suggestions in the next task assignment.

[0746] Step 8:

[0747] Based on the accumulated data, the server optimizes the entire system and makes adjustments to distribute household chores more efficiently and fairly.

[0748] In this way, by incorporating emotional data into task assignment and management, we can reduce the psychological and practical burden on users and support improvements to their home environment.

[0749] (Example 2)

[0750] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0751] Tasks within the household are often assigned uniformly, disregarding individual emotional states and workloads, which can lead to excessive burdens on specific individuals. Furthermore, it is difficult to make flexible adjustments in real time in response to users' emotions and work progress. As a result, overall household efficiency and comfort may be sacrificed.

[0752] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0753] This invention includes a server that receives user schedule information, work information, and emotional information and stores it in a storage device; an emotional processing device that analyzes the emotional information and quantifies and classifies the user's psychological state; and a cross-analysis of the schedule information and emotional state based on the analysis results and optimally assigns tasks to avoid excessive workload. This enables flexible task allocation according to the user's emotions and work progress.

[0754] "Schedule information" refers to information that users record about their daily plans and schedules, and it serves as basic data for the server to appropriately assign tasks by referring to this information.

[0755] "Work information" refers to information about specific activities and tasks required within the household, and tasks are prioritized and assigned based on this information.

[0756] "Emotional information" refers to data that indicates the user's emotional state, and is the data that the server analyzes through its emotion processing unit.

[0757] An "emotion processing device" refers to a device or software that analyzes received emotional information and quantifies and classifies psychological states.

[0758] "Cross-analysis" refers to a method of generating optimal task assignments for a user's situation by simultaneously analyzing and comparing scheduled information and emotional information.

[0759] A "voice response system" refers to a mechanism that enables users to input or receive information from the system via voice, thereby facilitating two-way communication.

[0760] A "generative artificial intelligence model" refers to artificial intelligence technology used to improve systems and optimize tasks based on prompt messages.

[0761] Modes for carrying out the invention

[0762] This invention is a system for efficiently dividing tasks within the home, minimizing burden and considering emotions based on the user's schedule information, task information, and emotional information. In order to implement this system, the following elements must be specifically managed.

[0763] The server receives schedule information, work information, and emotional information sent from the user's terminal in real time and stores it in a database. This requires storage within the server and an interface for network communication. The emotional processing unit analyzes the emotional information, quantifies and categorizes the user's psychological state. Text analysis software and voice analysis software are used in this process. Based on the analysis results, the server cross-analyzes the schedule information and emotional data to derive appropriate work assignments. For example, if the user is experiencing high levels of stress, the server will reorganize tasks to reduce stress.

[0764] The terminal notifies the user of optimized work assignments delivered from the server. This terminal consists of a smartphone or tablet device and has screen display and voice output capabilities. Through a voice response system, the user can report work progress and changes in emotions verbally. This conversational input format allows the user to easily communicate their emotional state to the system.

[0765] Users perform assigned tasks in their daily lives and report their progress to the server via their device. By inputting their emotional state, users can have that data reflected in their next task assignment.

[0766] The generating AI model can receive system improvement suggestions based on prompt messages. A concrete example of a prompt message might be, "Please suggest the optimal task assignment considering the user's schedule and emotions." Through these prompts, further system improvements can be achieved.

[0767] In this way, the present invention realizes a sophisticated division of labor that takes into account the feelings and efficiency of all members of the household.

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] The server receives schedule information, work information, and sentiment information from the user's device. This information is data entered by the user via smartphone or computer. The server receives this information and stores it in a database. This stored data is used for later analysis and work assignment.

[0771] Step 2:

[0772] The server uses emotion processing software to analyze emotional information and quantify and classify the user's psychological state. The received emotional information is used as input. This process uses text analysis software and speech recognition software to analyze emotional keywords and speech patterns. As output, the user's emotional state is categorized into categories such as "fatigue," "relaxation," and "stress," and stored on the server as numerical data.

[0773] Step 3:

[0774] The server cross-analyzes the schedule information and sentiment data based on the analysis results. The input is the data obtained from Step 1 and Step 2. This analysis uses an optimization algorithm to adjust the workload for each user to minimize it. As output, optimized work assignment data for each user is generated and sent to the terminal.

[0775] Step 4:

[0776] The terminal notifies the user of the optimized work assignment received from the server. The input is the work assignment data generated in step 3. The terminal communicates this information to the user as a screen display or audio alert. Based on this, the user can begin their daily work.

[0777] Step 5:

[0778] Users perform tasks and report their progress and emotional changes to the server via their terminal. Input includes the emotional state and work progress data reported by the user. This data, entered using the terminal's voice response system, is received by the server and used to optimize future work assignments.

[0779] Step 6:

[0780] The server uses a generative artificial intelligence model to receive improvement suggestions based on prompt sentences. The input is the data from steps 1 through 5. The prompt sentence "Please suggest the optimal task assignment considering the user's schedule and emotions." is input to the generative AI model, and improvement suggestions are obtained. The output is a new adjustment proposal for improving the efficiency of task assignments across the entire system.

[0781] (Application Example 2)

[0782] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0783] In factory and other work environments, worker fatigue and emotional state can significantly impact productivity and efficiency. Conventional systems struggle to allocate tasks while considering workers' emotional states, often resulting in stress and fatigue. Furthermore, efficiently managing progress and providing feedback remains a challenge.

[0784] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0785] In this invention, the server includes means for receiving user schedule information and storing it in a storage device, means for analyzing the user's areas of expertise and emotional state, and means for optimally assigning tasks based on the analysis results. This makes it possible to take into account the emotional state of the workers and optimally distribute the workload.

[0786] "User" refers to individual people or machines that use a system to perform tasks.

[0787] "Schedule information" refers to data about the user's work schedule and activity time.

[0788] A "storage device" refers to hardware or its functions that can hold data and retrieve it when needed.

[0789] "Areas of expertise" refers to information about tasks or fields in which a user is particularly skilled.

[0790] "Emotional state" refers to data that indicates the user's psychological and emotional health.

[0791] "Analysis" refers to the overall process of extracting and understanding detailed information based on collected data.

[0792] "Task" refers to a specific task or responsibility assigned to a user.

[0793] "Assigning" refers to the process of distributing specific tasks to specific users.

[0794] "Notification" refers to the act or function of communicating information to a user.

[0795] "Feedback" refers to information that shows users' reactions and opinions towards the system.

[0796] "Progress status" refers to information indicating the degree of completion of a task or the extent of its execution to date.

[0797] "Reporting by voice" refers to the act or function of transmitting information using voice.

[0798] This invention provides a system for efficiently assigning tasks to users in work environments such as factories. A server receives user schedule information and stores it in a memory device. An emotion engine is used to analyze information about the user's emotional state and areas of expertise collected via smart glasses or robots. Based on this analysis, the server assigns the user the most suitable task.

[0799] In determining appropriate tasks for each user, the server adjusts the tasks to minimize stress and fatigue based on the user's emotional state. Furthermore, users can report their work progress verbally through two-way voice communication. This allows the server to analyze feedback in real time and incorporate it into future task assignments.

[0800] The hardware and software used include smart glasses and robotic terminals, and an emotion analysis engine performs data analysis. For example, if a worker mutters, "Today is tough," the smart glasses detect the emotion, and the server suggests a less demanding work assignment. In addition, the following prompt statements are used as a generative AI model to analyze and optimize the user's emotion data.

[0801] Example of a prompt:

[0802] "Based on worker sentiment data, please suggest how to assign appropriate tasks."

[0803] This system provides an efficient and stress-free work environment by comprehensively considering the user's emotions and schedule.

[0804] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0805] Step 1:

[0806] The server receives schedule information transmitted from the user's smart glasses or robot terminal and stores it in its storage device. The input is the user's work schedule data, and the output is the stored schedule information. Here, the operations of receiving and recording data take place.

[0807] Step 2:

[0808] The server uses an emotion engine to analyze the user's emotional state and areas of expertise. Inputs are emotional data collected from the user and historical performance data, while output is the analysis of the user's emotional state and areas of expertise. This process includes the use of a generative AI model to quantify the emotional data and convert it into specific states.

[0809] Step 3:

[0810] The server performs calculations to determine the optimal tasks for the user based on the analysis results. The input is analyzed emotional state data and information on the user's areas of expertise, and the output is an optimized task assignment. Task distribution is performed in a way that reduces stress and fatigue, based on the user's psychological state.

[0811] Step 4:

[0812] The server notifies smart glasses and robot terminals of the determined work assignment. The input is optimized work assignment information, and the output is a work instruction to the user terminal. The operation to send the work instruction is performed.

[0813] Step 5:

[0814] The user reports the progress of their work to the server via voice. The input is progress information in voice, and the output is progress data converted to text. This includes the process of converting voice to text using speech recognition technology.

[0815] Step 6:

[0816] The server receives and analyzes user feedback to help with future work assignments. Input is text-based progress and feedback information, while output is improved system settings and adjustments to the learning model. This involves data analysis and system optimization.

[0817] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0818] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0819] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0820] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0821] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0822] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0823] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0824] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0825] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0826] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0827] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0828] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0829] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0830] 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.

[0831] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0832] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0833] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0834] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0835] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0836] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0837] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0838] The following is further disclosed regarding the embodiments described above.

[0839] (Claim 1)

[0840] A means for receiving user schedule information and saving it to a storage device,

[0841] A means of analyzing the user's areas of expertise and fatigue level,

[0842] A means for optimally assigning tasks based on analysis results,

[0843] A means of notifying each user of their assigned tasks,

[0844] A means of analyzing user feedback and optimizing the system,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, further comprising means for monitoring the progress of a task and setting reminders according to the progress.

[0848] (Claim 3)

[0849] The system according to claim 1, further comprising means for enabling the addition of tasks and progress reporting using a voice assistant.

[0850] "Example 1"

[0851] (Claim 1)

[0852] A means for receiving user time planning information and storing it on a storage medium,

[0853] A means for analyzing the user's skills and fatigue state, and processing that information using a generative model,

[0854] A means for optimally distributing activities based on analysis results and generating personalized suggestions using prompts,

[0855] A means of communicating the distributed activities to each user and providing details via an information terminal,

[0856] A means of collecting user feedback and adapting the system to improve the allocation of activities in the future,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, further comprising means for monitoring the progress of an activity and setting up notifications based on the progress.

[0860] (Claim 3)

[0861] The system according to claim 1, further comprising means for enabling the addition and progress reporting of activities using a voice support device.

[0862] "Application Example 1"

[0863] (Claim 1)

[0864] A means for receiving user schedule information and storing it in an information storage device,

[0865] A means for analyzing the user's areas of expertise and fatigue level,

[0866] A means for optimally assigning tasks based on analysis results,

[0867] A means of notifying each user of their assigned tasks,

[0868] A means of analyzing user feedback and improving the system,

[0869] A means for analyzing the robot's operation history and assigning tasks appropriate to the robot's capabilities,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, further comprising means for monitoring the progress of work and setting up alerts according to the progress.

[0873] (Claim 3)

[0874] The system according to claim 1, further comprising means for enabling the addition and progress reporting of tasks using voice support technology.

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

[0876] (Claim 1)

[0877] A means for receiving user schedule information, work information, and emotional information and storing it in a storage device,

[0878] A means of analyzing emotional information using an emotion processing device and quantifying and classifying the user's psychological state,

[0879] Based on the analysis results, a method is developed to optimally allocate tasks by cross-analyzing scheduled information and emotional states to avoid excessive workload,

[0880] A means of notifying each user of their assigned tasks,

[0881] A two-way communication means that allows users to input emotional reports and work progress using a voice response system,

[0882] A means of analyzing user feedback and improving the system,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, further comprising means for monitoring the progress of work and setting up notifications according to the progress.

[0886] (Claim 3)

[0887] The system according to claim 1, further comprising means for enabling improvement suggestions based on prompt sentences using a generative artificial intelligence model.

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

[0889] (Claim 1)

[0890] A means for receiving user schedule information and saving it to a storage device,

[0891] A means of analyzing the user's areas of expertise and emotional state,

[0892] A means for optimally assigning tasks based on analysis results,

[0893] A means of assigning tasks to other workers when there is an excessive workload,

[0894] A means of notifying each user of their assigned tasks,

[0895] A means of analyzing user feedback and optimizing the system,

[0896] A means to enable reporting of work progress via voice,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, further comprising means for monitoring the progress of work and setting reminders according to the progress.

[0900] (Claim 3)

[0901] The system according to claim 1, further comprising means for enabling the addition of tasks and progress reporting using interactive instructions. [Explanation of Symbols]

[0902] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving user schedule information and saving it to a storage device, A means of analyzing the user's areas of expertise and fatigue level, A means for optimally assigning tasks based on analysis results, A means of notifying each user of their assigned tasks, A means of analyzing user feedback and optimizing the system, A system that includes this.

2. The system according to claim 1, further comprising means for monitoring the progress of a task and setting reminders according to the progress.

3. The system according to claim 1, further comprising means for enabling the addition of tasks and progress reporting using a voice assistant.

Images