System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a login request and registering a user identifier in a database; means for receiving a task input by a user and storing the task in the database; means for retrieving the task from the database and generating an optimal order based on the task by a generative model; and notification means for providing optimal ordered task information to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Improving work efficiency and productivity has become a major challenge in the modern business environment. Many people struggle with prioritizing work and task management, resulting in widespread inefficient work practices. There is a need to solve this problem and provide a way to raise the overall performance of the top 1% of people who are capable of doing their jobs. [Means for solving the problem]

[0005] The present invention provides the following means to solve the above problems.

[0006] First, when a user logs in to the system, a means is provided for receiving a login request and registering the user identifier in a database. Next, a means is provided for receiving tasks entered by the user and saving the tasks in a database. Furthermore, a means is provided for retrieving tasks from the database using a generative model and generating an optimal order based on the tasks. Finally, a notification means is provided for providing the user with optimally ordered task information, thereby providing a system that allows users to efficiently manage tasks.

[0007] "Login Request" means a request submitted by a User to access and authenticate a System.

[0008] "User identifier" means information used to uniquely identify a user within a system.

[0009] A "database" is a system that can store, manage, and search information in an organized manner.

[0010] A "task" is a job or piece of work that a user needs to complete.

[0011] A "generative model" is an algorithm or system that learns from data and analyzes and generates information.

[0012] An "optimal order" is the ideal order for efficiently performing tasks based on certain criteria.

[0013] "Notification mechanism" means a system or method for providing information or messages to a user.

[0014] "Real-time" refers to a situation in which processing or reaction occurs immediately, without delay.

[0015] "Dynamic" refers to the ability to change and respond instantly according to circumstances and conditions.

[0016] "Performance" refers to the ability or results of an individual or system. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a system that enables a user to perform a task effectively. Hereinafter, an embodiment of the system will be described.

[0039] System Overview

[0040] This system allows users to log in, input and manage their own tasks, and then generates an optimal task sequence based on that information and provides notifications. The system is mainly composed of a server, terminals, and users.

[0041] Login process

[0042] First, a user logs into the system using their own terminal. The user accesses the login page and enters their user identifier. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This process makes it possible to identify the user.

[0043] Task Input

[0044] After logging in, a user inputs tasks from their device, such as specific tasks like "writing a report" or "replying to a client's email." The device sends this task information to the server, which receives it and stores the tasks in a database based on the user's identifier.

[0045] Task optimization

[0046] The tasks entered by the user are optimized by the server's generative model. The generative model learns from the movements and performance of individuals who are able to perform the top 1% of tasks. The server retrieves the user's tasks from the database and inputs them into the generative model. The generative model generates the optimal order of the tasks and returns the results to the server.

[0047] Notification of optimization results

[0048] The server sends the generated optimal task order to the user's device. The device receives it and notifies the user. Specifically, the results are displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to immediately understand which tasks should be prioritized and work more efficiently.

[0049] Specific examples

[0050] For example, if a user has the following task:

[0051] 1. Report preparation

[0052] 2. Reply to client emails

[0053] 3. Scheduling team meetings

[0054] The user inputs these tasks into the system, and the generative model takes this and might provide an optimized sequence, for example:

[0055] 1. Reply to client emails

[0056] 2. Scheduling team meetings

[0057] 3. Report preparation

[0058] By notifying the user of these results, the user can efficiently tackle the most important and urgent tasks.

[0059] The above is an embodiment of the present invention. The purpose of this system is to enable users to efficiently manage tasks and improve productivity through the processes of login, task input, optimization, and notification.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[0063] Step 2:

[0064] The terminal sends a login request including the user identifier to the server.

[0065] Step 3:

[0066] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[0067] Step 4:

[0068] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[0069] Step 5:

[0070] The terminal sends a request including the input task information and the user identifier to the server.

[0071] Step 6:

[0072] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[0073] Step 7:

[0074] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[0075] Step 8:

[0076] The terminal sends a task optimization request including the user identifier to the server.

[0077] Step 9:

[0078] The server receives the request and retrieves all tasks corresponding to that user identifier from the database.

[0079] Step 10:

[0080] The server inputs the acquired tasks into a generative model, which then sorts the tasks into an optimal order.

[0081] Step 11:

[0082] The server returns the optimized task order provided by the generative model to the terminal as a response.

[0083] Step 12:

[0084] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[0085] Step 13:

[0086] The user can efficiently proceed with the task based on the optimal order displayed.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] Current task management systems are complex to input and manage tasks, lack the ability to optimize and prioritize tasks, and lack support for users to effectively complete their work. Furthermore, they are slow to respond in real time when new tasks are added, preventing them from contributing to improved user productivity.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by a user and saving the tasks in a database, means for acquiring tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered tasks, and means for analyzing new tasks in real time and dynamically updating the order of tasks. This allows users to easily input and manage tasks and perform them in an optimal order, thereby enabling efficient work.

[0092] A "Login Request" is a user's attempt to access a system and provide information to identify themselves.

[0093] A "user identifier" is information used to uniquely identify a user when logging in to a system.

[0094] "Database" means a system for systematically storing and managing task and user information.

[0095] A "task" is a specific job or piece of work that a user must complete.

[0096] A "generative model" is an AI model that is trained and used to determine the optimal sequence of tasks.

[0097] "Generating an order" is the process of arranging multiple tasks in an optimal order.

[0098] "Notification means" refers to a method or device for providing information to a user.

[0099] "Real-time analysis" means processing and analyzing new information as soon as it is entered.

[0100] "Dynamic updating" means changing or modifying data or settings in a timely manner in response to changes in circumstances or conditions.

[0101] A "prompt sentence" is an input sentence that instructs a generative AI model on how to process something.

[0102] The present invention relates to a system for supporting users to perform their work effectively. Specific embodiments for implementing this system will be described below.

[0103] System configuration

[0104] This system is mainly composed of three entities: a server, a terminal, and a user. The server processes and manages data, while the terminal provides an interface with the user, who inputs and manages business tasks. The server is equipped with a database and generative AI model, and HTTPS is used as the communication protocol.

[0105] Example of login process

[0106] The user logs in to the system using their own terminal. The user accesses the login page and enters their user identifier and password. The terminal sends this information to the server via the HTTPS protocol. The server compares the received information with the database, and if authentication is successful, it generates a session ID and sends it back to the terminal. Authentication is now complete.

[0107] Example of task entry

[0108] After logging in, the user accesses the task input form and inputs specific work tasks such as "create a report" or "reply to a client's email." The device sends this task information and the user identifier to the server. The server stores the received task information in a database and returns a status indicating that the information has been saved to the device.

[0109] Task optimization example

[0110] The server retrieves the user's task information from the database. It then inputs the retrieved task information into the generative AI model. The generative AI model learns from the behavior of individuals with the top 1% performance and determines the optimal order of tasks. The following prompts are used:

[0111] text

[0112] User A has the following tasks:

[0113] 1. Report preparation

[0114] 2. Reply to client emails

[0115] 3. Scheduling team meetings

[0116] Sort them in the order that works best for you.

[0117] The generative AI model generates the optimal sequence of tasks based on these prompts and returns the results to the server.

[0118] Example of notification of optimization results

[0119] The server sends the generated optimal task order to the user's device, which receives the information and displays it to the user via a pop-up notification or dashboard. The user can then check the notification and start working according to the priority tasks.

[0120] Specific example explanation

[0121] For example, if a user has the following tasks:

[0122] 1. Report preparation

[0123] 2. Reply to client emails

[0124] 3. Scheduling team meetings

[0125] The user inputs these tasks into the system, which the generative AI model takes and provides an optimized sequence that looks like this:

[0126] 1. Reply to client emails

[0127] 2. Scheduling team meetings

[0128] 3. Report preparation

[0129] By notifying the user of these results, they can efficiently tackle the most important and urgent tasks first.

[0130] Through these processes, the system aims to improve work productivity by allowing users to easily input and manage tasks and carry out tasks in the optimal order.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] User Login

[0134] A user uses a terminal to access the system's login page and enters a user identifier and password. This input information is sent to the server using the HTTPS protocol. The server receives this login request and checks the user identifier and password in the database. If the check is successful, the server generates a new session ID and sends it back to the terminal. This allows the user to log in to the system.

[0135] Input: User ID, Password

[0136] Output: Session ID

[0137] Step 2:

[0138] Task Input

[0139] After logging in, the user accesses the task input form and inputs a specific work task (e.g., "create a report," "reply to a client's email," etc.). This task information is sent to the server via the terminal. The server stores the received task information in a database together with the user's identifier. A save completion status is returned to the terminal, allowing the user to confirm that the task has been saved correctly.

[0140] Input: Task information, user identifier

[0141] Output: Save completion status

[0142] Step 3:

[0143] Task optimization

[0144] The server retrieves the task information of the user from the database. The retrieved task information is input into the generative AI model. The generative model learns from the movements of individuals with the top 1% performance and calculates the optimal order. The generative model is input with the following prompt:

[0145] text

[0146] User A has the following tasks:

[0147] 1. Report preparation

[0148] 2. Reply to client emails

[0149] 3. Scheduling team meetings

[0150] Sort them in the order that works best for you.

[0151] The generative model generates an optimal ordering of tasks based on the prompts, which is returned to the server.

[0152] Input: Task information, prompt

[0153] Output: Optimal task ordering

[0154] Step 4:

[0155] Notification of optimization results

[0156] The server sends the generated optimal task order to the user's device. The device receives this information and displays it to the user via a pop-up notification or dashboard. The user can check the notification content and perform their work efficiently by following the optimized order.

[0157] Input: Optimal task ordering

[0158] Output: Notification (pop-up or dashboard display)

[0159] Step 5:

[0160] Real-time analysis and management of new tasks

[0161] When a user adds a new task, the device immediately sends the task information to the server. The server saves this new task in the database and inputs it back into the generative AI model to reevaluate the current task order. The generative AI model then recalculates the optimal order of all tasks, including the new task, and returns this new order to the server. The optimization result is then notified to the device.

[0162] Input: New task information

[0163] Output: Updated optimal task ordering

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] Conventional task management systems simply manage tasks entered by users as a list, and often lack an efficient method for executing tasks in the optimal order. Furthermore, automated machinery in factories does not properly manage task order or priority, resulting in reduced work efficiency. A particular issue is that real-time task additions and changes are not quickly reflected in the system. This makes it difficult to maintain high productivity, and there is a risk of increased operational costs and production delays.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0168] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered task information, means for transmitting login information, task information, and task optimization results from the user's terminal to the server, and means for distributing the generated optimal task order to automated machines in a factory. This makes it possible to efficiently manage tasks entered by users and execute them in an optimal order, significantly improving the work efficiency of automated machines in a factory. Furthermore, since task additions and changes are reflected in real time, high productivity can be maintained.

[0169] A "Login Request" is a request by a User to submit authentication information necessary to access a System.

[0170] A "user identifier" is identification information for uniquely identifying each user.

[0171] A "database" is a system for storing, managing, and searching data.

[0172] A "task" refers to a specific job or operation, and is the specific content that a user inputs into the system.

[0173] A "generative model" is a system that uses machine learning or other algorithms to generate optimal outputs from input data.

[0174] The "optimal order" is the order in which tasks are rearranged to achieve maximum efficiency.

[0175] A "terminal" refers to a device that a user uses to access the system, such as a PC or smartphone.

[0176] "Notification means" means the method by which the system communicates information to the user, including pop-up notifications and dashboard displays.

[0177] A "server" is a computer system that processes and stores data and fulfills user requests.

[0178] "Factory automation machinery" refers to machinery and equipment used to automatically carry out manufacturing processes.

[0179] The "task optimization result" is a list of tasks whose optimal order has been determined by the generative model.

[0180] "Real time" is a concept that refers to processing being carried out immediately without delay.

[0181] As an embodiment of the present invention, a system is described that aims to improve the work efficiency of automated machines in a factory by utilizing means for processing login requests, task entry, task optimization, notifications, and real-time updates.

[0182] System Overview

[0183] This system consists of a server, terminals, and users. The server generates the optimal work sequence based on the tasks entered by the user and distributes it to the automated machines in the factory.

[0184] Hardware and software used

[0185] Server: A computer system that processes and stores data and handles user requests.

[0186] Terminal: The device (computer, smartphone, etc.) through which a user accesses the system.

[0187] Automation machinery: Machinery and equipment used to carry out manufacturing processes automatically.

[0188] Database: A system for storing, managing, and retrieving data.

[0189] Generative model: A system that uses machine learning algorithms to learn by looking at the behavior of top-performing individuals.

[0190] Notification methods: How information is communicated to users through pop-up notifications and dashboard displays.

[0191] Processing a login request

[0192] A user logs into the system using a terminal. The login request is sent to the server, which registers the user identifier in a database, making it possible to uniquely identify the user within the system.

[0193] Task Input

[0194] After logging in, the user inputs the task from the terminal. For example, this is a specific task such as "transporting parts" or "machine maintenance." The task information is sent to the server and stored in a database based on the user identifier.

[0195] Task optimization

[0196] The server retrieves tasks from the database and generates an optimal task sequence using a generative model. This generative model is trained by referencing the behavior of top-performing individuals. Generating an optimal task sequence is a key step in achieving an efficient workflow.

[0197] Notification and Delivery

[0198] The server sends the generated optimal task sequence to the user's device and simultaneously distributes it to the automated machines in the factory. The user is informed through pop-up notifications and dashboard displays, allowing the user and the automated machines to execute tasks in the optimal sequence.

[0199] Real-time updates

[0200] New tasks added by users are analyzed in real time, and the generative model dynamically updates the task order, which is then immediately reflected in the automated machine, ensuring a constantly up-to-date workflow.

[0201] Specific examples

[0202] For example, a factory worker might enter the following task:

[0203] 1. Parts transportation

[0204] 2. Machine maintenance

[0205] 3. Quality check

[0206] The generative model takes these tasks and produces an optimized result in the following order:

[0207] 1. Quality check

[0208] 2. Parts transportation

[0209] 3. Machine maintenance

[0210] The results are communicated to users and automated machines to ensure optimal workflow.

[0211] Example prompt sentence:

[0212] "Generate a new task sequence. Input tasks are: Parts transport, Machine maintenance, and Quality check."

[0213] In this way, the system generates the optimal work sequence based on the tasks entered by the user, realizing an efficient work flow.

[0214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0215] Step 1:

[0216] User login

[0217] A user accesses the system using a terminal and sends a login request. The server receives this request and registers the user identifier in the database. The input information is the user identifier, and the output is the user identifier registered in the database. This process allows the user to be uniquely identified within the system.

[0218] Step 2:

[0219] Task Input

[0220] After logging in, the user inputs specific work tasks from the terminal. For example, task information such as "transport parts" or "machine maintenance" is input. The server receives this task information and stores it in a database along with the user identifier. The input information is the user identifier and task details, and the output is the task information stored in the database.

[0221] Step 3:

[0222] Getting a task

[0223] The server retrieves the task entered by the user from the database, and the retrieved task information is used in the next step. The input information is the user identifier, and the output is the task information retrieved from the database.

[0224] Step 4:

[0225] Task optimization

[0226] The server inputs the acquired task information into a generative model to generate the optimal task order. This generative model learns by referencing the movements of individuals with top performance. The input information is task information, and the output is the optimal task order. Specifically, task information is input into the generative model, and the optimal order is calculated using a machine learning algorithm.

[0227] Step 5:

[0228] Notification of optimization results

[0229] The server sends the generated optimal task sequence to the user's device. The user receives this information on the device through a pop-up notification or dashboard display. At the same time, the optimal task sequence is also distributed to the automated machines in the factory. The input information is the optimal task sequence, and the output is the task sequence sent to the user's device and the automated machines. Specifically, information is transmitted using a notification API or protocol.

[0230] Step 6:

[0231] Real-time updates

[0232] When a user adds a new task, the terminal sends this information to the server. The server analyzes the new task information in real time and dynamically updates the task order. The updated task order is then distributed to the user terminal and the automated machine again. The input information is the new task information, and the output is the updated task order. Specifically, the new task is input into the generative model, integrated with the existing task order, and recalculated.

[0233] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0234] The present invention relates to a system for improving a user's work efficiency. This system has the function of sorting tasks entered by the user into an optimal order and notifying the user, as well as the function of recognizing the user's emotions and reflecting that information in a generative model. The following describes an embodiment of this system.

[0235] System Overview

[0236] The system handles login requests, inputs and saves tasks, optimizes tasks using a generative model, and provides notifications. Furthermore, by incorporating an emotion engine, task management takes into account the user's emotional state.

[0237] Login process

[0238] First, a user accesses the system using their own terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This enables the user to be identified and allows them to start using the system.

[0239] Entering and saving a task

[0240] After logging in, a user inputs tasks from their device, such as writing a report, replying to a client's email, or scheduling a team meeting. The device sends these task information to the server, which then stores the received tasks in a database based on the user's identifier.

[0241] Emotion Engine Functions

[0242] This system incorporates an emotion engine that acquires emotional information from user input and behavior. It then estimates emotions based on the time of day and activity status, and provides the estimation results to the generative model.

[0243] Task optimization

[0244] The server retrieves the user's tasks and emotional information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. The generative model, which learns the movements of top-performing individuals, provides the optimal task sequence that reflects the emotional information, enabling task management that is appropriate for the user's current emotional state.

[0245] Notification of optimization results

[0246] The server sends the generated optimal task order to the device. The device receives it and visually notifies the user. For example, the results can be displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to check which tasks should be prioritized and work more efficiently.

[0247] Specific examples

[0248] For example, if a user has the following tasks:

[0249] 1. Report preparation

[0250] 2. Reply to client emails

[0251] 3. Scheduling team meetings

[0252] Furthermore, suppose the emotion engine recognizes the user's emotion as "stressed and anxious." Based on this information, the generative model might provide the following sequence:

[0253] 1. Responding to client emails (a quick task)

[0254] 2. Scheduling team meetings (tasks that require collaboration)

[0255] 3. Report writing (a task that requires concentration)

[0256] This allows for efficient task management that takes into account the user's emotional state.

[0257] The above is an embodiment of the present invention. The purpose of this system is to improve the work efficiency and satisfaction of users through the processes of login, task input, emotion recognition, task optimization, and notification.

[0258] The processing flow will be explained below.

[0259] Step 1:

[0260] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[0261] Step 2:

[0262] The terminal sends a login request including the user identifier to the server.

[0263] Step 3:

[0264] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[0265] Step 4:

[0266] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[0267] Step 5:

[0268] The terminal sends a request including the input task information and the user identifier to the server.

[0269] Step 6:

[0270] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[0271] Step 7:

[0272] Users can input their emotions using the terminal, or the emotion engine can automatically obtain emotion information from the user's actions and inputs.

[0273] Step 8:

[0274] The device sends emotion information to the server, including when the user manually inputs an emotion.

[0275] Step 9:

[0276] The server receives the user's emotion information and stores it in a database. The emotion engine can also provide emotion information in real time.

[0277] Step 10:

[0278] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[0279] Step 11:

[0280] The terminal sends a task optimization request including the user identifier to the server.

[0281] Step 12:

[0282] The server receives the request and retrieves all task information and emotion information corresponding to the user identifier from the database.

[0283] Step 13:

[0284] The server inputs the acquired task information and emotion information into the generative model, which then generates the optimal task order based on this information. Because the generative model learns from the movements of individuals with top performance, it generates an order that reflects the user's situation and emotions.

[0285] Step 14:

[0286] The server returns the optimized task order provided by the generative model to the terminal as a response.

[0287] Step 15:

[0288] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[0289] Step 16:

[0290] The user can efficiently proceed with the task based on the optimal order displayed.

[0291] As a concrete example, if a user inputs the tasks "Write a report," "Reply to client email," and "Schedule a team meeting," and the emotion engine detects "Stress," the generative model might provide the following optimization sequence:

[0292] 1. Responding to client emails (a quick task)

[0293] 2. Scheduling team meetings (tasks that require collaboration)

[0294] 3. Report writing (a task that requires concentration)

[0295] This allows users to manage tasks efficiently while taking into account their emotional state.

[0296] Example 2

[0297] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0298] Conventional task management systems have the problem that they determine task order without considering the user's emotional state, making it difficult to maximize the user's work efficiency. Furthermore, they are unable to dynamically update task order in real time, making it difficult to adapt to changing work environments. Therefore, there is a need for a system that can reflect the user's emotional state and enable efficient task management.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0300] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for acquiring emotional information from the user's input and actions and estimating the emotional state with an emotion engine, means for acquiring tasks and emotional information from the database and generating an optimal order based on that information with a generative model, and means for notifying the user of the optimally ordered task information using a terminal or notification device. This enables efficient task management that takes into account the user's emotional state in real time and adapts to changing work environments.

[0301] A "login request" is an operation in which a user accesses a system and attempts to log in to the system by submitting authentication information.

[0302] A "user identifier" is information for uniquely identifying a user, and typically includes an ID and password.

[0303] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved efficiently.

[0304] A "task" is an item of work or activity that a user inputs into the system.

[0305] "Emotion information" is data that indicates the user's emotional state, and is estimated based on the tone of the text, behavioral patterns, and the like.

[0306] An "emotion engine" is an algorithm or system for inferring a user's emotional state from their input and behavior.

[0307] A "generative model" is an algorithm or artificial intelligence (AI) model that generates optimal task sequences based on acquired data.

[0308] The "optimal order" is the order of task execution determined by the generative model in order to maximize the user's work efficiency.

[0309] The "notification means" refers to a method for notifying the user of the generated task sequence visually or in another form, and includes terminal display, push notification, and the like.

[0310] MODE FOR CARRYING OUT THE INVENTION

[0311] System Configuration

[0312] This invention relates to a system for improving user work efficiency. This system has the functions of sorting tasks entered by the user into an optimal order and notifying the user, as well as recognizing the user's emotions and incorporating that information into a generative model.

[0313] Hardware and Software Configuration

[0314] The system includes the following major components:

[0315] 1. Device (PC, smartphone, etc.):

[0316] It provides a user interface and accepts user operations.

[0317] A screen for entering a user identifier and task information is displayed.

[0318] 2. Server:

[0319] A login request is received and the user identifier is registered in the database.

[0320] Receives task information entered by the user and stores it in a database.

[0321] It incorporates an emotion engine that obtains emotional information from user input and actions.

[0322] Task and emotion information is obtained from the database and input into the generative model.

[0323] Generate optimal task sequences using a generative model.

[0324] The generated optimal task order is notified to the terminal.

[0325] 3. Database (e.g. MySQL, MongoDB):

[0326] Stores user identifier and task information.

[0327] 4. Generative models (e.g. GPT-4):

[0328] The optimal task sequence is generated based on the user's task information and emotional information.

[0329] 5. Emotion Engine:

[0330] Analyze and estimate emotional information from user input and behavior.

[0331] How it works

[0332] Login Procedure

[0333] A user accesses the system using a terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in a database.

[0334] Entering and saving a task

[0335] After the user logs in, the device provides a task input screen through a user interface. The user inputs tasks such as writing a report, replying to a client's email, scheduling a team meeting, etc. The device sends this task information to the server, which then stores the task information in a database.

[0336] emotion recognition

[0337] The server uses an emotion engine to obtain emotional information from the user's input and actions, for example, by using the context of the user's messages or a facial recognition camera to estimate the user's emotional state. This emotional information is then used for subsequent task generation.

[0338] Task optimization

[0339] The server retrieves the user's tasks and emotional information from the database and inputs this into a generative model. The generative model (e.g., GPT-4) generates the optimal task sequence based on this information. This generative model learns the behavior of top-performing individuals and incorporates emotional information to maximize the user's work efficiency.

[0340] Specific examples

[0341] For example, if a user has the following tasks:

[0342] 1. Report preparation

[0343] 2. Reply to client emails

[0344] 3. Scheduling team meetings

[0345] Furthermore, suppose the emotion engine recognizes the user's emotion as "stress and anxiety." Based on this information, the generative model might provide the following sequence:

[0346] 1. Responding to client emails (a quick task)

[0347] 2. Scheduling team meetings (tasks that require collaboration)

[0348] 3. Report writing (a task that requires concentration)

[0349] This allows for efficient task management that takes into account the user's emotional state.

[0350] Prompt Sentence Examples

[0351] "A user has the following tasks: write a report, reply to a client email, schedule a team meeting. And the user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[0352] The above is a specific embodiment for carrying out the present invention. The present system takes into account the user's emotional state in real time, enabling efficient and flexible task management.

[0353] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0354] Specific processing steps of the program

[0355] Step 1: Submit a login request

[0356] The user accesses the login page using their own device and enters the user identifier (ID and password). The device receives this and sends it to the server.

[0357] Input: User ID (ID and password)

[0358] Output: Login request sent to the server

[0359] Specific actions: Enter your ID and password in the text boxes and click the login button.

[0360] Step 2: User identity authentication and registration

[0361] The server receives the login request, authenticates the user by checking the user's identifier against a database, and if authentication is successful, records the user as authenticated in the database.

[0362] Input: User identifier sent to the server

[0363] Output: Authentication results registered in the database

[0364] Specific operation: The server performs an authentication query on the database, receives the result, and if successful, sends a login success message to the terminal.

[0365] Step 3: Entering the task

[0366] Users use their devices to access a task entry screen, specifically to enter tasks such as writing a report, replying to a client email, or scheduling a team meeting.

[0367] Input: Task information entered by the user

[0368] Output: Task information sent from the device to the server

[0369] Specific actions: Enter the task details in the text box and click the Save button.

[0370] Step 4: Save task information

[0371] The server receives the task information sent from the terminal and stores it in a database together with the user identifier.

[0372] Input: Task information and user identifier sent from the device

[0373] Output: Task information stored in the database

[0374] Specific operation: The server executes the stored query against the database and receives the stored results.

[0375] Step 5: Acquiring emotional information

[0376] The emotion engine on the server obtains the user's emotional information from the behavioral data and input data when the user enters a task. For example, emotions are estimated from the context of the text and the speed of input.

[0377] Input: User behavior and input data

[0378] Output: Estimated emotion information

[0379] Specific operation: The server analyzes the input data and applies the emotion estimation algorithm to obtain the result.

[0380] Step 6: Storing Emotional Information

[0381] The server stores the estimated emotion information in a database.

[0382] Input: Estimated emotion information

[0383] Output: Emotion information stored in a database

[0384] Specific operation: The server executes a query to the database to store emotion information.

[0385] Step 7: Acquiring task and emotional information

[0386] The server obtains the user's task information and emotion information from the database.

[0387] Input: Task information and emotion information stored in a database

[0388] Output: Obtained task information and emotion information

[0389] Specific operation: The server executes a query to the database to obtain task and emotion information.

[0390] Step 8: Optimize task order

[0391] The server inputs the acquired task information and emotion information into a generative model to generate the optimal task order. The generative model (e.g., GPT-4) analyzes the input data and calculates the optimal task execution order.

[0392] Input: Task information and emotion information

[0393] Output: The generated optimal task order

[0394] Specific operation: The server sends data to the generative model and receives a response from the model.

[0395] Step 9: Notification of optimization results

[0396] The server notifies the device of the optimal task order, which the device receives and visually notifies the user (e.g., pop-up notification or dashboard display).

[0397] Input: The generated optimal task order

[0398] Output: The optimal task order reported to the device.

[0399] Specific operation: The server sends notification data to the device, and the device displays the notification.

[0400] Specific examples

[0401] Example prompt: "A user has the following tasks: write a report, respond to a client email, and schedule a team meeting. The user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[0402] (Application example 2)

[0403] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0404] In modern factories and production lines, maximizing work efficiency is essential, but the emotional state and fatigue level of workers are often not taken into consideration. As a result, worker stress and fatigue can lead to reduced work efficiency, resulting in reduced productivity. Furthermore, the lack of effective coordination between worker and machine task management has led to numerous problems. Therefore, an optimal task management system that takes into account the emotional state of workers is needed.

[0405] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0406] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving the tasks from the database and generating an optimal order based on the tasks using a generative model, notification means for providing the user with optimally ordered task information, an emotion engine for recognizing the user's emotional state and reflecting that information in the generative model, and means for determining and notifying the user of the optimal task order based on the emotion information. This enables efficient task management that takes into account the emotional state of the worker, reducing worker stress and fatigue and improving productivity.

[0407] "Login Request" means a request by a User to submit authentication information necessary to access the System.

[0408] "User identifier" means unique information that identifies a specific user. This typically includes a user ID or email address.

[0409] "Database" means a data structure that enables information to be managed in an organized manner and quickly searched and updated.

[0410] A "task" is a specific task or activity that a user must perform. Examples include writing a report or replying to an email.

[0411] A "generative model" refers to an algorithm or system that generates new data or procedures based on input information.

[0412] "Optimal order" refers to the order in which tasks are executed that is most effective for a particular purpose.

[0413] "Notification Method" means any method for conveying information to a user. Examples include pop-up notifications and email notifications.

[0414] "Emotional state" refers to the user's current emotional and psychological state, including stress and fatigue levels.

[0415] "Emotion engine" refers to a system that recognizes and analyzes the user's emotional state and generates information based on that.

[0416] "Means for determining optimal task order" refers to a process or device for optimizing the order in which tasks are executed based on the user's emotional state and other information.

[0417] The present invention relates to a system that rearranges the optimal order of tasks for work robots and workers in a factory, thereby supporting efficient work. The system includes the following elements:

[0418] Login process

[0419] First, a login request is received from the work robot and worker to log in to the system individually. The server registers the user identifier in a database and identifies the worker and robot. This process uses a common login authentication method. For example, workers log in using individual ID cards or biometric authentication.

[0420] Entering and saving a task

[0421] After logging in, workers and managers input work tasks into their terminals. This information includes a wide variety of tasks, such as assembling parts or performing maintenance work. The terminals then send this task information to the server, which then stores the tasks in a database.

[0422] Emotion Engine Functions

[0423] The system incorporates an emotion engine that recognizes the user's emotional state. The emotion engine infers emotions based on the user's inputs and actions, as well as the time of day and activity status. This emotion information is provided to a generative model, which then reflects it in generating the optimal task sequence.

[0424] Task optimization

[0425] The server retrieves task and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. In this process, the generative model learns by referencing the movements of individuals with top performance, enabling effective task management.

[0426] Notification of optimization results

[0427] The server sends the generated optimal task order to the terminal, which receives this information and notifies the worker or robot visually or audibly, such as through a pop-up notification, an alarm, or a display on a dashboard.

[0428] Specific examples

[0429] For example, if you have a task like this:

[0430] Assembling the parts (Time required: 60 minutes)

[0431] Quality inspection (time required: 30 minutes)

[0432] Line maintenance (time required: 15 minutes)

[0433] Furthermore, let's say the emotion engine recognizes the worker's emotional state as "Stress 5, Fatigue 7." Based on this prompt, the generative AI model will provide the optimal task sequence as follows:

[0434] 1. Line maintenance

[0435] 2. Quality Inspection

[0436] 3. Assembling the parts

[0437] This optimization result allows for efficient task management that takes into account the emotional state of the worker.

[0438] Example prompt sentence:

[0439] Emotional state: {'Stress': 5, 'Fatigue': 7}

[0440] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[0441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0442] Step 1:

[0443] The server receives login requests from the work robot and worker, and registers the user identifier in the database. At this time, information such as the worker's ID card or biometric authentication is entered. The server verifies the authentication information and saves the user identifier in the database. This completes the identification of the worker and robot, and the system can begin to be used.

[0444] Input: Worker authentication information (ID card, biometrics, etc.)

[0445] Output: User ID registered in the database

[0446] Step 2:

[0447] The terminal sends work tasks entered by workers or managers to the server. Tasks include information such as parts assembly and maintenance work. The server receives this task information and stores it in a database. This allows for centralized management of task information.

[0448] Input: Work task information (task name, required time, etc.)

[0449] Output: Task information stored in the database

[0450] Step 3:

[0451] The device provides the user's input and actions to the emotion engine, which recognizes and analyzes the user's emotional state. The emotion engine infers emotional information based on the time of day and activity status. The inferred emotional information is provided to a generative model, which generates the optimal task sequence based on this information.

[0452] Input: User input information, behavioral data, time period, activity status

[0453] Output: Emotional information (stress, fatigue, etc.)

[0454] Step 4:

[0455] The server retrieves task information and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task order based on the emotion information. During this process, the model learns by referencing the behavior of individuals with top performance, enabling effective task management.

[0456] Input: Task information and emotion information from the database

[0457] Output: Optimal task ordering

[0458] Step 5:

[0459] The server sends the generated optimal task order to the terminal, which then receives it and notifies the worker or robot visually or audibly, such as by pop-up notification, alarm, or display on the dashboard.

[0460] Input: Optimal task ordering

[0461] Output: Notifications to workers and robots (pop-up notifications, alarms, etc.)

[0462] Step 6:

[0463] The server collects the tasks performed and the feedback of the workers and stores it in a database, which allows for continuous evaluation of task management performance and helps improve the generative model.

[0464] Input: Task information, worker feedback

[0465] Output: Task execution information and feedback stored in a database

[0466] Example prompt

[0467] Here is an example of a real input prompt:

[0468] Emotional state: {'Stress': 5, 'Fatigue': 7}

[0469] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[0470] Based on this prompt, the generative model can generate the optimal task sequence as follows:

[0471] 1. Line maintenance

[0472] 2. Quality Inspection

[0473] 3. Assembling the parts

[0474] This order is determined taking into account the emotional state of the worker.

[0475] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0476] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0477] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0478] [Second embodiment]

[0479] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0480] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0481] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0482] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0483] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0484] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0485] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0486] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0489] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0490] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0491] The present invention relates to a system that enables a user to perform a task effectively. Hereinafter, an embodiment of the system will be described.

[0492] System Overview

[0493] This system allows users to log in, input and manage their own tasks, and then generates an optimal task sequence based on that information and provides notifications. The system is mainly composed of a server, terminals, and users.

[0494] Login process

[0495] First, a user logs into the system using their own terminal. The user accesses the login page and enters their user identifier. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This process makes it possible to identify the user.

[0496] Task Input

[0497] After logging in, a user inputs tasks from their device, such as specific tasks like "writing a report" or "replying to a client's email." The device sends this task information to the server, which receives it and stores the tasks in a database based on the user's identifier.

[0498] Task optimization

[0499] The tasks entered by the user are optimized by the server's generative model. The generative model learns from the movements and performance of individuals who are able to perform the top 1% of tasks. The server retrieves the user's tasks from the database and inputs them into the generative model. The generative model generates the optimal order of the tasks and returns the results to the server.

[0500] Notification of optimization results

[0501] The server sends the generated optimal task order to the user's device. The device receives it and notifies the user. Specifically, the results are displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to immediately understand which tasks should be prioritized and work more efficiently.

[0502] Specific examples

[0503] For example, if a user has the following task:

[0504] 1. Report preparation

[0505] 2. Reply to client emails

[0506] 3. Scheduling team meetings

[0507] The user inputs these tasks into the system, and the generative model takes this and might provide an optimized sequence, for example:

[0508] 1. Reply to client emails

[0509] 2. Scheduling team meetings

[0510] 3. Report preparation

[0511] By notifying the user of these results, the user can efficiently tackle the most important and urgent tasks.

[0512] The above is an embodiment of the present invention. The purpose of this system is to enable users to efficiently manage tasks and improve productivity through the processes of login, task input, optimization, and notification.

[0513] The processing flow will be explained below.

[0514] Step 1:

[0515] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[0516] Step 2:

[0517] The terminal sends a login request including the user identifier to the server.

[0518] Step 3:

[0519] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[0520] Step 4:

[0521] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[0522] Step 5:

[0523] The terminal sends a request including the input task information and the user identifier to the server.

[0524] Step 6:

[0525] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[0526] Step 7:

[0527] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[0528] Step 8:

[0529] The terminal sends a task optimization request including the user identifier to the server.

[0530] Step 9:

[0531] The server receives the request and retrieves all tasks corresponding to that user identifier from the database.

[0532] Step 10:

[0533] The server inputs the acquired tasks into a generative model, which then sorts the tasks into an optimal order.

[0534] Step 11:

[0535] The server returns the optimized task order provided by the generative model to the terminal as a response.

[0536] Step 12:

[0537] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[0538] Step 13:

[0539] The user can efficiently proceed with the task based on the optimal order displayed.

[0540] Example 1

[0541] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0542] Current task management systems are complex to input and manage tasks, lack the ability to optimize and prioritize tasks, and lack support for users to effectively complete their work. Furthermore, they are slow to respond in real time when new tasks are added, preventing them from contributing to improved user productivity.

[0543] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0544] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by a user and saving the tasks in a database, means for acquiring tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered tasks, and means for analyzing new tasks in real time and dynamically updating the order of tasks. This allows users to easily input and manage tasks and perform them in an optimal order, thereby enabling efficient work.

[0545] A "Login Request" is a user's attempt to access a system and provide information to identify themselves.

[0546] A "user identifier" is information used to uniquely identify a user when logging in to a system.

[0547] "Database" means a system for systematically storing and managing task and user information.

[0548] A "task" is a specific job or piece of work that a user must complete.

[0549] A "generative model" is an AI model that is trained and used to determine the optimal sequence of tasks.

[0550] "Generating an order" is the process of arranging multiple tasks in an optimal order.

[0551] "Notification means" refers to a method or device for providing information to a user.

[0552] "Real-time analysis" means processing and analyzing new information as soon as it is entered.

[0553] "Dynamic updating" means changing or modifying data or settings in a timely manner in response to changes in circumstances or conditions.

[0554] A "prompt sentence" is an input sentence that instructs a generative AI model on how to process something.

[0555] The present invention relates to a system for supporting users to perform their work effectively. Specific embodiments for implementing this system will be described below.

[0556] System configuration

[0557] This system is mainly composed of three entities: a server, a terminal, and a user. The server processes and manages data, while the terminal provides an interface with the user, who inputs and manages business tasks. The server is equipped with a database and generative AI model, and HTTPS is used as the communication protocol.

[0558] Example of login process

[0559] The user logs in to the system using their own terminal. The user accesses the login page and enters their user identifier and password. The terminal sends this information to the server via the HTTPS protocol. The server compares the received information with the database, and if authentication is successful, it generates a session ID and sends it back to the terminal. Authentication is now complete.

[0560] Example of task entry

[0561] After logging in, the user accesses the task input form and inputs specific work tasks such as "create a report" or "reply to a client's email." The device sends this task information and the user identifier to the server. The server stores the received task information in a database and returns a status indicating that the information has been saved to the device.

[0562] Task optimization example

[0563] The server retrieves the user's task information from the database. It then inputs the retrieved task information into the generative AI model. The generative AI model learns from the behavior of individuals with the top 1% performance and determines the optimal order of tasks. The following prompts are used:

[0564] text

[0565] User A has the following tasks:

[0566] 1. Report preparation

[0567] 2. Reply to client emails

[0568] 3. Scheduling team meetings

[0569] Sort them in the order that works best for you.

[0570] The generative AI model generates the optimal sequence of tasks based on these prompts and returns the results to the server.

[0571] Example of notification of optimization results

[0572] The server sends the generated optimal task order to the user's device, which receives the information and displays it to the user via a pop-up notification or dashboard. The user can then check the notification and start working according to the priority tasks.

[0573] Specific example explanation

[0574] For example, if a user has the following tasks:

[0575] 1. Report preparation

[0576] 2. Reply to client emails

[0577] 3. Scheduling team meetings

[0578] The user inputs these tasks into the system, which the generative AI model takes and provides an optimized sequence that looks like this:

[0579] 1. Reply to client emails

[0580] 2. Scheduling team meetings

[0581] 3. Report preparation

[0582] By notifying the user of these results, they can efficiently tackle the most important and urgent tasks first.

[0583] Through these processes, the system aims to improve work productivity by allowing users to easily input and manage tasks and carry out tasks in the optimal order.

[0584] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0585] Step 1:

[0586] User Login

[0587] A user uses a terminal to access the system's login page and enters a user identifier and password. This input information is sent to the server using the HTTPS protocol. The server receives this login request and checks the user identifier and password in the database. If the check is successful, the server generates a new session ID and sends it back to the terminal. This allows the user to log in to the system.

[0588] Input: User ID, Password

[0589] Output: Session ID

[0590] Step 2:

[0591] Task Input

[0592] After logging in, the user accesses the task input form and inputs a specific work task (e.g., "create a report," "reply to a client's email," etc.). This task information is sent to the server via the terminal. The server stores the received task information in a database together with the user's identifier. A save completion status is returned to the terminal, allowing the user to confirm that the task has been saved correctly.

[0593] Input: Task information, user identifier

[0594] Output: Save completion status

[0595] Step 3:

[0596] Task optimization

[0597] The server retrieves the task information of the user from the database. The retrieved task information is input into the generative AI model. The generative model learns from the movements of individuals with the top 1% performance and calculates the optimal order. The generative model is input with the following prompt:

[0598] text

[0599] User A has the following tasks:

[0600] 1. Report preparation

[0601] 2. Reply to client emails

[0602] 3. Scheduling team meetings

[0603] Sort them in the order that works best for you.

[0604] The generative model generates an optimal ordering of tasks based on the prompts, which is returned to the server.

[0605] Input: Task information, prompt

[0606] Output: Optimal task ordering

[0607] Step 4:

[0608] Notification of optimization results

[0609] The server sends the generated optimal task order to the user's device. The device receives this information and displays it to the user via a pop-up notification or dashboard. The user can check the notification content and perform their work efficiently by following the optimized order.

[0610] Input: Optimal task ordering

[0611] Output: Notification (pop-up or dashboard display)

[0612] Step 5:

[0613] Real-time analysis and management of new tasks

[0614] When a user adds a new task, the device immediately sends the task information to the server. The server saves this new task in the database and inputs it back into the generative AI model to reevaluate the current task order. The generative AI model then recalculates the optimal order of all tasks, including the new task, and returns this new order to the server. The optimization result is then notified to the device.

[0615] Input: New task information

[0616] Output: Updated optimal task ordering

[0617] (Application example 1)

[0618] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0619] Conventional task management systems simply manage tasks entered by users as a list, and often lack an efficient method for executing tasks in the optimal order. Furthermore, automated machinery in factories does not properly manage task order or priority, resulting in reduced work efficiency. A particular issue is that real-time task additions and changes are not quickly reflected in the system. This makes it difficult to maintain high productivity, and there is a risk of increased operational costs and production delays.

[0620] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0621] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered task information, means for transmitting login information, task information, and task optimization results from the user's terminal to the server, and means for distributing the generated optimal task order to automated machines in a factory. This makes it possible to efficiently manage tasks entered by users and execute them in an optimal order, significantly improving the work efficiency of automated machines in a factory. Furthermore, since task additions and changes are reflected in real time, high productivity can be maintained.

[0622] A "Login Request" is a request by a User to submit authentication information necessary to access a System.

[0623] A "user identifier" is identification information for uniquely identifying each user.

[0624] A "database" is a system for storing, managing, and searching data.

[0625] A "task" refers to a specific job or operation, and is the specific content that a user inputs into the system.

[0626] A "generative model" is a system that uses machine learning or other algorithms to generate optimal outputs from input data.

[0627] The "optimal order" is the order in which tasks are rearranged to achieve maximum efficiency.

[0628] A "terminal" refers to a device that a user uses to access the system, such as a PC or smartphone.

[0629] "Notification means" means the method by which the system communicates information to the user, including pop-up notifications and dashboard displays.

[0630] A "server" is a computer system that processes and stores data and fulfills user requests.

[0631] "Factory automation machinery" refers to machinery and equipment used to automatically carry out manufacturing processes.

[0632] The "task optimization result" is a list of tasks whose optimal order has been determined by the generative model.

[0633] "Real time" is a concept that refers to processing being carried out immediately without delay.

[0634] As an embodiment of the present invention, a system is described that aims to improve the work efficiency of automated machines in a factory by utilizing means for processing login requests, task entry, task optimization, notifications, and real-time updates.

[0635] System Overview

[0636] This system consists of a server, terminals, and users. The server generates the optimal work sequence based on the tasks entered by the user and distributes it to the automated machines in the factory.

[0637] Hardware and software used

[0638] Server: A computer system that processes and stores data and handles user requests.

[0639] Terminal: The device (computer, smartphone, etc.) through which a user accesses the system.

[0640] Automation machinery: Machinery and equipment used to carry out manufacturing processes automatically.

[0641] Database: A system for storing, managing, and retrieving data.

[0642] Generative model: A system that uses machine learning algorithms to learn by looking at the behavior of top-performing individuals.

[0643] Notification methods: How information is communicated to users through pop-up notifications and dashboard displays.

[0644] Processing a login request

[0645] A user logs into the system using a terminal. The login request is sent to the server, which registers the user identifier in a database, making it possible to uniquely identify the user within the system.

[0646] Task Input

[0647] After logging in, the user inputs the task from the terminal. For example, this is a specific task such as "transporting parts" or "machine maintenance." The task information is sent to the server and stored in a database based on the user identifier.

[0648] Task optimization

[0649] The server retrieves tasks from the database and generates an optimal task sequence using a generative model. This generative model is trained by referencing the behavior of top-performing individuals. Generating an optimal task sequence is a key step in achieving an efficient workflow.

[0650] Notification and Delivery

[0651] The server sends the generated optimal task sequence to the user's device and simultaneously distributes it to the automated machines in the factory. The user is informed through pop-up notifications and dashboard displays, allowing the user and the automated machines to execute tasks in the optimal sequence.

[0652] Real-time updates

[0653] New tasks added by users are analyzed in real time, and the generative model dynamically updates the task order, which is then immediately reflected in the automated machine, ensuring a constantly up-to-date workflow.

[0654] Specific examples

[0655] For example, a factory worker might enter the following task:

[0656] 1. Parts transportation

[0657] 2. Machine maintenance

[0658] 3. Quality check

[0659] The generative model takes these tasks and produces an optimized result in the following order:

[0660] 1. Quality check

[0661] 2. Parts transportation

[0662] 3. Machine maintenance

[0663] The results are communicated to users and automated machines to ensure optimal workflow.

[0664] Example prompt sentence:

[0665] "Generate a new task sequence. Input tasks are: Parts transport, Machine maintenance, and Quality check."

[0666] In this way, the system generates the optimal work sequence based on the tasks entered by the user, realizing an efficient work flow.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] User login

[0670] A user accesses the system using a terminal and sends a login request. The server receives this request and registers the user identifier in the database. The input information is the user identifier, and the output is the user identifier registered in the database. This process allows the user to be uniquely identified within the system.

[0671] Step 2:

[0672] Task Input

[0673] After logging in, the user inputs specific work tasks from the terminal. For example, task information such as "transport parts" or "machine maintenance" is input. The server receives this task information and stores it in a database along with the user identifier. The input information is the user identifier and task details, and the output is the task information stored in the database.

[0674] Step 3:

[0675] Getting a task

[0676] The server retrieves the task entered by the user from the database, and the retrieved task information is used in the next step. The input information is the user identifier, and the output is the task information retrieved from the database.

[0677] Step 4:

[0678] Task optimization

[0679] The server inputs the acquired task information into a generative model to generate the optimal task order. This generative model learns by referencing the movements of individuals with top performance. The input information is task information, and the output is the optimal task order. Specifically, task information is input into the generative model, and the optimal order is calculated using a machine learning algorithm.

[0680] Step 5:

[0681] Notification of optimization results

[0682] The server sends the generated optimal task sequence to the user's device. The user receives this information on the device through a pop-up notification or dashboard display. At the same time, the optimal task sequence is also distributed to the automated machines in the factory. The input information is the optimal task sequence, and the output is the task sequence sent to the user's device and the automated machines. Specifically, information is transmitted using a notification API or protocol.

[0683] Step 6:

[0684] Real-time updates

[0685] When a user adds a new task, the terminal sends this information to the server. The server analyzes the new task information in real time and dynamically updates the task order. The updated task order is then distributed to the user terminal and the automated machine again. The input information is the new task information, and the output is the updated task order. Specifically, the new task is input into the generative model, integrated with the existing task order, and recalculated.

[0686] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0687] The present invention relates to a system for improving a user's work efficiency. This system has the function of sorting tasks entered by the user into an optimal order and notifying the user, as well as the function of recognizing the user's emotions and reflecting that information in a generative model. The following describes an embodiment of this system.

[0688] System Overview

[0689] The system handles login requests, inputs and saves tasks, optimizes tasks using a generative model, and provides notifications. Furthermore, by incorporating an emotion engine, task management takes into account the user's emotional state.

[0690] Login process

[0691] First, a user accesses the system using their own terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This enables the user to be identified and allows them to start using the system.

[0692] Entering and saving a task

[0693] After logging in, a user inputs tasks from their device, such as writing a report, replying to a client's email, or scheduling a team meeting. The device sends these task information to the server, which then stores the received tasks in a database based on the user's identifier.

[0694] Emotion Engine Functions

[0695] This system incorporates an emotion engine that acquires emotional information from user input and behavior. It then estimates emotions based on the time of day and activity status, and provides the estimation results to the generative model.

[0696] Task optimization

[0697] The server retrieves the user's tasks and emotional information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. The generative model, which learns the movements of top-performing individuals, provides the optimal task sequence that reflects the emotional information, enabling task management that is appropriate for the user's current emotional state.

[0698] Notification of optimization results

[0699] The server sends the generated optimal task order to the device. The device receives it and visually notifies the user. For example, the results can be displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to check which tasks should be prioritized and work more efficiently.

[0700] Specific examples

[0701] For example, if a user has the following tasks:

[0702] 1. Report preparation

[0703] 2. Reply to client emails

[0704] 3. Scheduling team meetings

[0705] Furthermore, suppose the emotion engine recognizes the user's emotion as "stressed and anxious." Based on this information, the generative model might provide the following sequence:

[0706] 1. Responding to client emails (a quick task)

[0707] 2. Scheduling team meetings (tasks that require collaboration)

[0708] 3. Report writing (a task that requires concentration)

[0709] This allows for efficient task management that takes into account the user's emotional state.

[0710] The above is an embodiment of the present invention. The purpose of this system is to improve the work efficiency and satisfaction of users through the processes of login, task input, emotion recognition, task optimization, and notification.

[0711] The processing flow will be explained below.

[0712] Step 1:

[0713] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[0714] Step 2:

[0715] The terminal sends a login request including the user identifier to the server.

[0716] Step 3:

[0717] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[0718] Step 4:

[0719] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[0720] Step 5:

[0721] The terminal sends a request including the input task information and the user identifier to the server.

[0722] Step 6:

[0723] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[0724] Step 7:

[0725] Users can input their emotions using the terminal, or the emotion engine can automatically obtain emotion information from the user's actions and inputs.

[0726] Step 8:

[0727] The device sends emotion information to the server, including when the user manually inputs an emotion.

[0728] Step 9:

[0729] The server receives the user's emotion information and stores it in a database. The emotion engine can also provide emotion information in real time.

[0730] Step 10:

[0731] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[0732] Step 11:

[0733] The terminal sends a task optimization request including the user identifier to the server.

[0734] Step 12:

[0735] The server receives the request and retrieves all task information and emotion information corresponding to the user identifier from the database.

[0736] Step 13:

[0737] The server inputs the acquired task information and emotion information into the generative model, which then generates the optimal task order based on this information. Because the generative model learns from the movements of individuals with top performance, it generates an order that reflects the user's situation and emotions.

[0738] Step 14:

[0739] The server returns the optimized task order provided by the generative model to the terminal as a response.

[0740] Step 15:

[0741] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[0742] Step 16:

[0743] The user can efficiently proceed with the task based on the optimal order displayed.

[0744] As a concrete example, if a user inputs the tasks "Write a report," "Reply to client email," and "Schedule a team meeting," and the emotion engine detects "Stress," the generative model might provide the following optimization sequence:

[0745] 1. Responding to client emails (a quick task)

[0746] 2. Scheduling team meetings (tasks that require collaboration)

[0747] 3. Report writing (a task that requires concentration)

[0748] This allows users to manage tasks efficiently while taking into account their emotional state.

[0749] Example 2

[0750] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0751] Conventional task management systems have the problem that they determine task order without considering the user's emotional state, making it difficult to maximize the user's work efficiency. Furthermore, they are unable to dynamically update task order in real time, making it difficult to adapt to changing work environments. Therefore, there is a need for a system that can reflect the user's emotional state and enable efficient task management.

[0752] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0753] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for acquiring emotional information from the user's input and actions and estimating the emotional state with an emotion engine, means for acquiring tasks and emotional information from the database and generating an optimal order based on that information with a generative model, and means for notifying the user of the optimally ordered task information using a terminal or notification device. This enables efficient task management that takes into account the user's emotional state in real time and adapts to changing work environments.

[0754] A "login request" is an operation in which a user accesses a system and attempts to log in to the system by submitting authentication information.

[0755] A "user identifier" is information for uniquely identifying a user, and typically includes an ID and password.

[0756] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved efficiently.

[0757] A "task" is an item of work or activity that a user inputs into the system.

[0758] "Emotion information" is data that indicates the user's emotional state, and is estimated based on the tone of the text, behavioral patterns, and the like.

[0759] An "emotion engine" is an algorithm or system for inferring a user's emotional state from their input and behavior.

[0760] A "generative model" is an algorithm or artificial intelligence (AI) model that generates optimal task sequences based on acquired data.

[0761] The "optimal order" is the order of task execution determined by the generative model in order to maximize the user's work efficiency.

[0762] The "notification means" refers to a method for notifying the user of the generated task sequence visually or in another form, and includes terminal display, push notification, and the like.

[0763] MODE FOR CARRYING OUT THE INVENTION

[0764] System Configuration

[0765] This invention relates to a system for improving user work efficiency. This system has the functions of sorting tasks entered by the user into an optimal order and notifying the user, as well as recognizing the user's emotions and incorporating that information into a generative model.

[0766] Hardware and Software Configuration

[0767] The system includes the following major components:

[0768] 1. Device (PC, smartphone, etc.):

[0769] It provides a user interface and accepts user operations.

[0770] A screen for entering a user identifier and task information is displayed.

[0771] 2. Server:

[0772] A login request is received and the user identifier is registered in the database.

[0773] Receives task information entered by the user and stores it in a database.

[0774] It incorporates an emotion engine that obtains emotional information from user input and actions.

[0775] Task and emotion information is obtained from the database and input into the generative model.

[0776] Generate optimal task sequences using a generative model.

[0777] The generated optimal task order is notified to the terminal.

[0778] 3. Database (e.g. MySQL, MongoDB):

[0779] Stores user identifier and task information.

[0780] 4. Generative models (e.g. GPT-4):

[0781] The optimal task sequence is generated based on the user's task information and emotional information.

[0782] 5. Emotion Engine:

[0783] Analyze and estimate emotional information from user input and behavior.

[0784] How it works

[0785] Login Procedure

[0786] A user accesses the system using a terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in a database.

[0787] Entering and saving a task

[0788] After the user logs in, the device provides a task input screen through a user interface. The user inputs tasks such as writing a report, replying to a client's email, scheduling a team meeting, etc. The device sends this task information to the server, which then stores the task information in a database.

[0789] emotion recognition

[0790] The server uses an emotion engine to obtain emotional information from the user's input and actions, for example, by using the context of the user's messages or a facial recognition camera to estimate the user's emotional state. This emotional information is then used for subsequent task generation.

[0791] Task optimization

[0792] The server retrieves the user's tasks and emotional information from the database and inputs this into a generative model. The generative model (e.g., GPT-4) generates the optimal task sequence based on this information. This generative model learns the behavior of top-performing individuals and incorporates emotional information to maximize the user's work efficiency.

[0793] Specific examples

[0794] For example, if a user has the following tasks:

[0795] 1. Report preparation

[0796] 2. Reply to client emails

[0797] 3. Scheduling team meetings

[0798] Furthermore, suppose the emotion engine recognizes the user's emotion as "stress and anxiety." Based on this information, the generative model might provide the following sequence:

[0799] 1. Responding to client emails (a quick task)

[0800] 2. Scheduling team meetings (tasks that require collaboration)

[0801] 3. Report writing (a task that requires concentration)

[0802] This allows for efficient task management that takes into account the user's emotional state.

[0803] Prompt Sentence Examples

[0804] "A user has the following tasks: write a report, reply to a client email, schedule a team meeting. And the user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[0805] The above is a specific embodiment for carrying out the present invention. The present system takes into account the user's emotional state in real time, enabling efficient and flexible task management.

[0806] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0807] Specific processing steps of the program

[0808] Step 1: Submit a login request

[0809] The user accesses the login page using their own device and enters the user identifier (ID and password). The device receives this and sends it to the server.

[0810] Input: User ID (ID and password)

[0811] Output: Login request sent to the server

[0812] Specific actions: Enter your ID and password in the text boxes and click the login button.

[0813] Step 2: User identity authentication and registration

[0814] The server receives the login request, authenticates the user by checking the user's identifier against a database, and if authentication is successful, records the user as authenticated in the database.

[0815] Input: User identifier sent to the server

[0816] Output: Authentication results registered in the database

[0817] Specific operation: The server performs an authentication query on the database, receives the result, and if successful, sends a login success message to the terminal.

[0818] Step 3: Entering the task

[0819] Users use their devices to access a task entry screen, specifically to enter tasks such as writing a report, replying to a client email, or scheduling a team meeting.

[0820] Input: Task information entered by the user

[0821] Output: Task information sent from the device to the server

[0822] Specific actions: Enter the task details in the text box and click the Save button.

[0823] Step 4: Save task information

[0824] The server receives the task information sent from the terminal and stores it in a database together with the user identifier.

[0825] Input: Task information and user identifier sent from the device

[0826] Output: Task information stored in the database

[0827] Specific operation: The server executes the stored query against the database and receives the stored results.

[0828] Step 5: Acquiring emotional information

[0829] The emotion engine on the server obtains the user's emotional information from the behavioral data and input data when the user enters a task. For example, emotions are estimated from the context of the text and the speed of input.

[0830] Input: User behavior and input data

[0831] Output: Estimated emotion information

[0832] Specific operation: The server analyzes the input data and applies the emotion estimation algorithm to obtain the result.

[0833] Step 6: Storing Emotional Information

[0834] The server stores the estimated emotion information in a database.

[0835] Input: Estimated emotion information

[0836] Output: Emotion information stored in a database

[0837] Specific operation: The server executes a query to the database to store emotion information.

[0838] Step 7: Acquiring task and emotional information

[0839] The server obtains the user's task information and emotion information from the database.

[0840] Input: Task information and emotion information stored in a database

[0841] Output: Obtained task information and emotion information

[0842] Specific operation: The server executes a query to the database to obtain task and emotion information.

[0843] Step 8: Optimize task order

[0844] The server inputs the acquired task information and emotion information into a generative model to generate the optimal task order. The generative model (e.g., GPT-4) analyzes the input data and calculates the optimal task execution order.

[0845] Input: Task information and emotion information

[0846] Output: The generated optimal task order

[0847] Specific operation: The server sends data to the generative model and receives a response from the model.

[0848] Step 9: Notification of optimization results

[0849] The server notifies the device of the optimal task order, which the device receives and visually notifies the user (e.g., pop-up notification or dashboard display).

[0850] Input: The generated optimal task order

[0851] Output: The optimal task order reported to the device.

[0852] Specific operation: The server sends notification data to the device, and the device displays the notification.

[0853] Specific examples

[0854] Example prompt: "A user has the following tasks: write a report, respond to a client email, and schedule a team meeting. The user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[0855] (Application example 2)

[0856] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0857] In modern factories and production lines, maximizing work efficiency is essential, but the emotional state and fatigue level of workers are often not taken into consideration. As a result, worker stress and fatigue can lead to reduced work efficiency, resulting in reduced productivity. Furthermore, the lack of effective coordination between worker and machine task management has led to numerous problems. Therefore, an optimal task management system that takes into account the emotional state of workers is needed.

[0858] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0859] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving the tasks from the database and generating an optimal order based on the tasks using a generative model, notification means for providing the user with optimally ordered task information, an emotion engine for recognizing the user's emotional state and reflecting that information in the generative model, and means for determining and notifying the user of the optimal task order based on the emotion information. This enables efficient task management that takes into account the emotional state of the worker, reducing worker stress and fatigue and improving productivity.

[0860] "Login Request" means a request by a User to submit authentication information necessary to access the System.

[0861] "User identifier" means unique information that identifies a specific user. This typically includes a user ID or email address.

[0862] "Database" means a data structure that enables information to be managed in an organized manner and quickly searched and updated.

[0863] A "task" is a specific task or activity that a user must perform. Examples include writing a report or replying to an email.

[0864] A "generative model" refers to an algorithm or system that generates new data or procedures based on input information.

[0865] "Optimal order" refers to the order in which tasks are executed that is most effective for a particular purpose.

[0866] "Notification Method" means any method for conveying information to a user. Examples include pop-up notifications and email notifications.

[0867] "Emotional state" refers to the user's current emotional and psychological state, including stress and fatigue levels.

[0868] "Emotion engine" refers to a system that recognizes and analyzes the user's emotional state and generates information based on that.

[0869] "Means for determining optimal task order" refers to a process or device for optimizing the order in which tasks are executed based on the user's emotional state and other information.

[0870] The present invention relates to a system that rearranges the optimal order of tasks for work robots and workers in a factory, thereby supporting efficient work. The system includes the following elements:

[0871] Login process

[0872] First, a login request is received from the work robot and worker to log in to the system individually. The server registers the user identifier in a database and identifies the worker and robot. This process uses a common login authentication method. For example, workers log in using individual ID cards or biometric authentication.

[0873] Entering and saving a task

[0874] After logging in, workers and managers input work tasks into their terminals. This information includes a wide variety of tasks, such as assembling parts or performing maintenance work. The terminals then send this task information to the server, which then stores the tasks in a database.

[0875] Emotion Engine Functions

[0876] The system incorporates an emotion engine that recognizes the user's emotional state. The emotion engine infers emotions based on the user's inputs and actions, as well as the time of day and activity status. This emotion information is provided to a generative model, which then reflects it in generating the optimal task sequence.

[0877] Task optimization

[0878] The server retrieves task and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. In this process, the generative model learns by referencing the movements of individuals with top performance, enabling effective task management.

[0879] Notification of optimization results

[0880] The server sends the generated optimal task order to the terminal, which receives this information and notifies the worker or robot visually or audibly, such as through a pop-up notification, an alarm, or a display on a dashboard.

[0881] Specific examples

[0882] For example, if you have a task like this:

[0883] Assembling the parts (Time required: 60 minutes)

[0884] Quality inspection (time required: 30 minutes)

[0885] Line maintenance (time required: 15 minutes)

[0886] Furthermore, let's say the emotion engine recognizes the worker's emotional state as "Stress 5, Fatigue 7." Based on this prompt, the generative AI model will provide the optimal task sequence as follows:

[0887] 1. Line maintenance

[0888] 2. Quality Inspection

[0889] 3. Assembling the parts

[0890] This optimization result allows for efficient task management that takes into account the emotional state of the worker.

[0891] Example prompt sentence:

[0892] Emotional state: {'Stress': 5, 'Fatigue': 7}

[0893] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[0894] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0895] Step 1:

[0896] The server receives login requests from the work robot and worker, and registers the user identifier in the database. At this time, information such as the worker's ID card or biometric authentication is entered. The server verifies the authentication information and saves the user identifier in the database. This completes the identification of the worker and robot, and the system can begin to be used.

[0897] Input: Worker authentication information (ID card, biometrics, etc.)

[0898] Output: User ID registered in the database

[0899] Step 2:

[0900] The terminal sends work tasks entered by workers or managers to the server. Tasks include information such as parts assembly and maintenance work. The server receives this task information and stores it in a database. This allows for centralized management of task information.

[0901] Input: Work task information (task name, required time, etc.)

[0902] Output: Task information stored in the database

[0903] Step 3:

[0904] The device provides the user's input and actions to the emotion engine, which recognizes and analyzes the user's emotional state. The emotion engine infers emotional information based on the time of day and activity status. The inferred emotional information is provided to a generative model, which generates the optimal task sequence based on this information.

[0905] Input: User input information, behavioral data, time period, activity status

[0906] Output: Emotional information (stress, fatigue, etc.)

[0907] Step 4:

[0908] The server retrieves task information and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task order based on the emotion information. During this process, the model learns by referencing the behavior of individuals with top performance, enabling effective task management.

[0909] Input: Task information and emotion information from the database

[0910] Output: Optimal task ordering

[0911] Step 5:

[0912] The server sends the generated optimal task order to the terminal, which then receives it and notifies the worker or robot visually or audibly, such as by pop-up notification, alarm, or display on the dashboard.

[0913] Input: Optimal task ordering

[0914] Output: Notifications to workers and robots (pop-up notifications, alarms, etc.)

[0915] Step 6:

[0916] The server collects the tasks performed and the feedback of the workers and stores it in a database, which allows for continuous evaluation of task management performance and helps improve the generative model.

[0917] Input: Task information, worker feedback

[0918] Output: Task execution information and feedback stored in a database

[0919] Example prompt

[0920] Here is an example of a real input prompt:

[0921] Emotional state: {'Stress': 5, 'Fatigue': 7}

[0922] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[0923] Based on this prompt, the generative model can generate the optimal task sequence as follows:

[0924] 1. Line maintenance

[0925] 2. Quality Inspection

[0926] 3. Assembling the parts

[0927] This order is determined taking into account the emotional state of the worker.

[0928] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0929] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0930] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0931] [Third embodiment]

[0932] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0933] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0934] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0935] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0936] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0937] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0938] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0939] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0940] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0941] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0942] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0943] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0944] The present invention relates to a system that enables a user to perform a task effectively. Hereinafter, an embodiment of the system will be described.

[0945] System Overview

[0946] This system allows users to log in, input and manage their own tasks, and then generates an optimal task sequence based on that information and provides notifications. The system is mainly composed of a server, terminals, and users.

[0947] Login process

[0948] First, a user logs into the system using their own terminal. The user accesses the login page and enters their user identifier. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This process makes it possible to identify the user.

[0949] Task Input

[0950] After logging in, a user inputs tasks from their device, such as specific tasks like "writing a report" or "replying to a client's email." The device sends this task information to the server, which receives it and stores the tasks in a database based on the user's identifier.

[0951] Task optimization

[0952] The tasks entered by the user are optimized by the server's generative model. The generative model learns from the movements and performance of individuals who are able to perform the top 1% of tasks. The server retrieves the user's tasks from the database and inputs them into the generative model. The generative model generates the optimal order of the tasks and returns the results to the server.

[0953] Notification of optimization results

[0954] The server sends the generated optimal task order to the user's device. The device receives it and notifies the user. Specifically, the results are displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to immediately understand which tasks should be prioritized and work more efficiently.

[0955] Specific examples

[0956] For example, if a user has the following task:

[0957] 1. Report preparation

[0958] 2. Reply to client emails

[0959] 3. Scheduling team meetings

[0960] The user inputs these tasks into the system, and the generative model takes this and might provide an optimized sequence, for example:

[0961] 1. Reply to client emails

[0962] 2. Scheduling team meetings

[0963] 3. Report preparation

[0964] By notifying the user of these results, the user can efficiently tackle the most important and urgent tasks.

[0965] The above is an embodiment of the present invention. The purpose of this system is to enable users to efficiently manage tasks and improve productivity through the processes of login, task input, optimization, and notification.

[0966] The processing flow will be explained below.

[0967] Step 1:

[0968] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[0969] Step 2:

[0970] The terminal sends a login request including the user identifier to the server.

[0971] Step 3:

[0972] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[0973] Step 4:

[0974] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[0975] Step 5:

[0976] The terminal sends a request including the input task information and the user identifier to the server.

[0977] Step 6:

[0978] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[0979] Step 7:

[0980] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[0981] Step 8:

[0982] The terminal sends a task optimization request including the user identifier to the server.

[0983] Step 9:

[0984] The server receives the request and retrieves all tasks corresponding to that user identifier from the database.

[0985] Step 10:

[0986] The server inputs the acquired tasks into a generative model, which then sorts the tasks into an optimal order.

[0987] Step 11:

[0988] The server returns the optimized task order provided by the generative model to the terminal as a response.

[0989] Step 12:

[0990] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[0991] Step 13:

[0992] The user can efficiently proceed with the task based on the optimal order displayed.

[0993] Example 1

[0994] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0995] Current task management systems are complex to input and manage tasks, lack the ability to optimize and prioritize tasks, and lack support for users to effectively complete their work. Furthermore, they are slow to respond in real time when new tasks are added, preventing them from contributing to improved user productivity.

[0996] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0997] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by a user and saving the tasks in a database, means for acquiring tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered tasks, and means for analyzing new tasks in real time and dynamically updating the order of tasks. This allows users to easily input and manage tasks and perform them in an optimal order, thereby enabling efficient work.

[0998] A "Login Request" is a user's attempt to access a system and provide information to identify themselves.

[0999] A "user identifier" is information used to uniquely identify a user when logging in to a system.

[1000] "Database" means a system for systematically storing and managing task and user information.

[1001] A "task" is a specific job or piece of work that a user must complete.

[1002] A "generative model" is an AI model that is trained and used to determine the optimal sequence of tasks.

[1003] "Generating an order" is the process of arranging multiple tasks in an optimal order.

[1004] "Notification means" refers to a method or device for providing information to a user.

[1005] "Real-time analysis" means processing and analyzing new information as soon as it is entered.

[1006] "Dynamic updating" means changing or modifying data or settings in a timely manner in response to changes in circumstances or conditions.

[1007] A "prompt sentence" is an input sentence that instructs a generative AI model on how to process something.

[1008] The present invention relates to a system for supporting users to perform their work effectively. Specific embodiments for implementing this system will be described below.

[1009] System configuration

[1010] This system is mainly composed of three entities: a server, a terminal, and a user. The server processes and manages data, while the terminal provides an interface with the user, who inputs and manages business tasks. The server is equipped with a database and generative AI model, and HTTPS is used as the communication protocol.

[1011] Example of login process

[1012] The user logs in to the system using their own terminal. The user accesses the login page and enters their user identifier and password. The terminal sends this information to the server via the HTTPS protocol. The server compares the received information with the database, and if authentication is successful, it generates a session ID and sends it back to the terminal. Authentication is now complete.

[1013] Example of task entry

[1014] After logging in, the user accesses the task input form and inputs specific work tasks such as "create a report" or "reply to a client's email." The device sends this task information and the user identifier to the server. The server stores the received task information in a database and returns a status indicating that the information has been saved to the device.

[1015] Task optimization example

[1016] The server retrieves the user's task information from the database. It then inputs the retrieved task information into the generative AI model. The generative AI model learns from the behavior of individuals with the top 1% performance and determines the optimal order of tasks. The following prompts are used:

[1017] text

[1018] User A has the following tasks:

[1019] 1. Report preparation

[1020] 2. Reply to client emails

[1021] 3. Scheduling team meetings

[1022] Sort them in the order that works best for you.

[1023] The generative AI model generates the optimal sequence of tasks based on these prompts and returns the results to the server.

[1024] Example of notification of optimization results

[1025] The server sends the generated optimal task order to the user's device, which receives the information and displays it to the user via a pop-up notification or dashboard. The user can then check the notification and start working according to the priority tasks.

[1026] Specific example explanation

[1027] For example, if a user has the following tasks:

[1028] 1. Report preparation

[1029] 2. Reply to client emails

[1030] 3. Scheduling team meetings

[1031] The user inputs these tasks into the system, which the generative AI model takes and provides an optimized sequence that looks like this:

[1032] 1. Reply to client emails

[1033] 2. Scheduling team meetings

[1034] 3. Report preparation

[1035] By notifying the user of these results, they can efficiently tackle the most important and urgent tasks first.

[1036] Through these processes, the system aims to improve work productivity by allowing users to easily input and manage tasks and carry out tasks in the optimal order.

[1037] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1038] Step 1:

[1039] User Login

[1040] A user uses a terminal to access the system's login page and enters a user identifier and password. This input information is sent to the server using the HTTPS protocol. The server receives this login request and checks the user identifier and password in the database. If the check is successful, the server generates a new session ID and sends it back to the terminal. This allows the user to log in to the system.

[1041] Input: User ID, Password

[1042] Output: Session ID

[1043] Step 2:

[1044] Task Input

[1045] After logging in, the user accesses the task input form and inputs a specific work task (e.g., "create a report," "reply to a client's email," etc.). This task information is sent to the server via the terminal. The server stores the received task information in a database together with the user's identifier. A save completion status is returned to the terminal, allowing the user to confirm that the task has been saved correctly.

[1046] Input: Task information, user identifier

[1047] Output: Save completion status

[1048] Step 3:

[1049] Task optimization

[1050] The server retrieves the task information of the user from the database. The retrieved task information is input into the generative AI model. The generative model learns from the movements of individuals with the top 1% performance and calculates the optimal order. The generative model is input with the following prompt:

[1051] text

[1052] User A has the following tasks:

[1053] 1. Report preparation

[1054] 2. Reply to client emails

[1055] 3. Scheduling team meetings

[1056] Sort them in the order that works best for you.

[1057] The generative model generates an optimal ordering of tasks based on the prompts, which is returned to the server.

[1058] Input: Task information, prompt

[1059] Output: Optimal task ordering

[1060] Step 4:

[1061] Notification of optimization results

[1062] The server sends the generated optimal task order to the user's device. The device receives this information and displays it to the user via a pop-up notification or dashboard. The user can check the notification content and perform their work efficiently by following the optimized order.

[1063] Input: Optimal task ordering

[1064] Output: Notification (pop-up or dashboard display)

[1065] Step 5:

[1066] Real-time analysis and management of new tasks

[1067] When a user adds a new task, the device immediately sends the task information to the server. The server saves this new task in the database and inputs it back into the generative AI model to reevaluate the current task order. The generative AI model then recalculates the optimal order of all tasks, including the new task, and returns this new order to the server. The optimization result is then notified to the device.

[1068] Input: New task information

[1069] Output: Updated optimal task ordering

[1070] (Application example 1)

[1071] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1072] Conventional task management systems simply manage tasks entered by users as a list, and often lack an efficient method for executing tasks in the optimal order. Furthermore, automated machinery in factories does not properly manage task order or priority, resulting in reduced work efficiency. A particular issue is that real-time task additions and changes are not quickly reflected in the system. This makes it difficult to maintain high productivity, and there is a risk of increased operational costs and production delays.

[1073] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1074] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered task information, means for transmitting login information, task information, and task optimization results from the user's terminal to the server, and means for distributing the generated optimal task order to automated machines in a factory. This makes it possible to efficiently manage tasks entered by users and execute them in an optimal order, significantly improving the work efficiency of automated machines in a factory. Furthermore, since task additions and changes are reflected in real time, high productivity can be maintained.

[1075] A "Login Request" is a request by a User to submit authentication information necessary to access a System.

[1076] A "user identifier" is identification information for uniquely identifying each user.

[1077] A "database" is a system for storing, managing, and searching data.

[1078] A "task" refers to a specific job or operation, and is the specific content that a user inputs into the system.

[1079] A "generative model" is a system that uses machine learning or other algorithms to generate optimal outputs from input data.

[1080] The "optimal order" is the order in which tasks are rearranged to achieve maximum efficiency.

[1081] A "terminal" refers to a device that a user uses to access the system, such as a PC or smartphone.

[1082] "Notification means" means the method by which the system communicates information to the user, including pop-up notifications and dashboard displays.

[1083] A "server" is a computer system that processes and stores data and fulfills user requests.

[1084] "Factory automation machinery" refers to machinery and equipment used to automatically carry out manufacturing processes.

[1085] The "task optimization result" is a list of tasks whose optimal order has been determined by the generative model.

[1086] "Real time" is a concept that refers to processing being carried out immediately without delay.

[1087] As an embodiment of the present invention, a system is described that aims to improve the work efficiency of automated machines in a factory by utilizing means for processing login requests, task entry, task optimization, notifications, and real-time updates.

[1088] System Overview

[1089] This system consists of a server, terminals, and users. The server generates the optimal work sequence based on the tasks entered by the user and distributes it to the automated machines in the factory.

[1090] Hardware and software used

[1091] Server: A computer system that processes and stores data and handles user requests.

[1092] Terminal: The device (computer, smartphone, etc.) through which a user accesses the system.

[1093] Automation machinery: Machinery and equipment used to carry out manufacturing processes automatically.

[1094] Database: A system for storing, managing, and retrieving data.

[1095] Generative model: A system that uses machine learning algorithms to learn by looking at the behavior of top-performing individuals.

[1096] Notification methods: How information is communicated to users through pop-up notifications and dashboard displays.

[1097] Processing a login request

[1098] A user logs into the system using a terminal. The login request is sent to the server, which registers the user identifier in a database, making it possible to uniquely identify the user within the system.

[1099] Task Input

[1100] After logging in, the user inputs the task from the terminal. For example, this is a specific task such as "transporting parts" or "machine maintenance." The task information is sent to the server and stored in a database based on the user identifier.

[1101] Task optimization

[1102] The server retrieves tasks from the database and generates an optimal task sequence using a generative model. This generative model is trained by referencing the behavior of top-performing individuals. Generating an optimal task sequence is a key step in achieving an efficient workflow.

[1103] Notification and Delivery

[1104] The server sends the generated optimal task sequence to the user's device and simultaneously distributes it to the automated machines in the factory. The user is informed through pop-up notifications and dashboard displays, allowing the user and the automated machines to execute tasks in the optimal sequence.

[1105] Real-time updates

[1106] New tasks added by users are analyzed in real time, and the generative model dynamically updates the task order, which is then immediately reflected in the automated machine, ensuring a constantly up-to-date workflow.

[1107] Specific examples

[1108] For example, a factory worker might enter the following task:

[1109] 1. Parts transportation

[1110] 2. Machine maintenance

[1111] 3. Quality check

[1112] The generative model takes these tasks and produces an optimized result in the following order:

[1113] 1. Quality check

[1114] 2. Parts transportation

[1115] 3. Machine maintenance

[1116] The results are communicated to users and automated machines to ensure optimal workflow.

[1117] Example prompt sentence:

[1118] "Generate a new task sequence. Input tasks are: Parts transport, Machine maintenance, and Quality check."

[1119] In this way, the system generates the optimal work sequence based on the tasks entered by the user, realizing an efficient work flow.

[1120] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1121] Step 1:

[1122] User login

[1123] A user accesses the system using a terminal and sends a login request. The server receives this request and registers the user identifier in the database. The input information is the user identifier, and the output is the user identifier registered in the database. This process allows the user to be uniquely identified within the system.

[1124] Step 2:

[1125] Task Input

[1126] After logging in, the user inputs specific work tasks from the terminal. For example, task information such as "transport parts" or "machine maintenance" is input. The server receives this task information and stores it in a database along with the user identifier. The input information is the user identifier and task details, and the output is the task information stored in the database.

[1127] Step 3:

[1128] Getting a task

[1129] The server retrieves the task entered by the user from the database, and the retrieved task information is used in the next step. The input information is the user identifier, and the output is the task information retrieved from the database.

[1130] Step 4:

[1131] Task optimization

[1132] The server inputs the acquired task information into a generative model to generate the optimal task order. This generative model learns by referencing the movements of individuals with top performance. The input information is task information, and the output is the optimal task order. Specifically, task information is input into the generative model, and the optimal order is calculated using a machine learning algorithm.

[1133] Step 5:

[1134] Notification of optimization results

[1135] The server sends the generated optimal task sequence to the user's device. The user receives this information on the device through a pop-up notification or dashboard display. At the same time, the optimal task sequence is also distributed to the automated machines in the factory. The input information is the optimal task sequence, and the output is the task sequence sent to the user's device and the automated machines. Specifically, information is transmitted using a notification API or protocol.

[1136] Step 6:

[1137] Real-time updates

[1138] When a user adds a new task, the terminal sends this information to the server. The server analyzes the new task information in real time and dynamically updates the task order. The updated task order is then distributed to the user terminal and the automated machine again. The input information is the new task information, and the output is the updated task order. Specifically, the new task is input into the generative model, integrated with the existing task order, and recalculated.

[1139] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1140] The present invention relates to a system for improving a user's work efficiency. This system has the function of sorting tasks entered by the user into an optimal order and notifying the user, as well as the function of recognizing the user's emotions and reflecting that information in a generative model. The following describes an embodiment of this system.

[1141] System Overview

[1142] The system handles login requests, inputs and saves tasks, optimizes tasks using a generative model, and provides notifications. Furthermore, by incorporating an emotion engine, task management takes into account the user's emotional state.

[1143] Login process

[1144] First, a user accesses the system using their own terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This enables the user to be identified and allows them to start using the system.

[1145] Entering and saving a task

[1146] After logging in, a user inputs tasks from their device, such as writing a report, replying to a client's email, or scheduling a team meeting. The device sends these task information to the server, which then stores the received tasks in a database based on the user's identifier.

[1147] Emotion Engine Functions

[1148] This system incorporates an emotion engine that acquires emotional information from user input and behavior. It then estimates emotions based on the time of day and activity status, and provides the estimation results to the generative model.

[1149] Task optimization

[1150] The server retrieves the user's tasks and emotional information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. The generative model, which learns the movements of top-performing individuals, provides the optimal task sequence that reflects the emotional information, enabling task management that is appropriate for the user's current emotional state.

[1151] Notification of optimization results

[1152] The server sends the generated optimal task order to the device. The device receives it and visually notifies the user. For example, the results can be displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to check which tasks should be prioritized and work more efficiently.

[1153] Specific examples

[1154] For example, if a user has the following tasks:

[1155] 1. Report preparation

[1156] 2. Reply to client emails

[1157] 3. Scheduling team meetings

[1158] Furthermore, suppose the emotion engine recognizes the user's emotion as "stressed and anxious." Based on this information, the generative model might provide the following sequence:

[1159] 1. Responding to client emails (a quick task)

[1160] 2. Scheduling team meetings (tasks that require collaboration)

[1161] 3. Report writing (a task that requires concentration)

[1162] This allows for efficient task management that takes into account the user's emotional state.

[1163] The above is an embodiment of the present invention. The purpose of this system is to improve the work efficiency and satisfaction of users through the processes of login, task input, emotion recognition, task optimization, and notification.

[1164] The processing flow will be explained below.

[1165] Step 1:

[1166] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[1167] Step 2:

[1168] The terminal sends a login request including the user identifier to the server.

[1169] Step 3:

[1170] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[1171] Step 4:

[1172] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[1173] Step 5:

[1174] The terminal sends a request including the input task information and the user identifier to the server.

[1175] Step 6:

[1176] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[1177] Step 7:

[1178] Users can input their emotions using the terminal, or the emotion engine can automatically obtain emotion information from the user's actions and inputs.

[1179] Step 8:

[1180] The device sends emotion information to the server, including when the user manually inputs an emotion.

[1181] Step 9:

[1182] The server receives the user's emotion information and stores it in a database. The emotion engine can also provide emotion information in real time.

[1183] Step 10:

[1184] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[1185] Step 11:

[1186] The terminal sends a task optimization request including the user identifier to the server.

[1187] Step 12:

[1188] The server receives the request and retrieves all task information and emotion information corresponding to the user identifier from the database.

[1189] Step 13:

[1190] The server inputs the acquired task information and emotion information into the generative model, which then generates the optimal task order based on this information. Because the generative model learns from the movements of individuals with top performance, it generates an order that reflects the user's situation and emotions.

[1191] Step 14:

[1192] The server returns the optimized task order provided by the generative model to the terminal as a response.

[1193] Step 15:

[1194] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[1195] Step 16:

[1196] The user can efficiently proceed with the task based on the optimal order displayed.

[1197] As a concrete example, if a user inputs the tasks "Write a report," "Reply to client email," and "Schedule a team meeting," and the emotion engine detects "Stress," the generative model might provide the following optimization sequence:

[1198] 1. Responding to client emails (a quick task)

[1199] 2. Scheduling team meetings (tasks that require collaboration)

[1200] 3. Report writing (a task that requires concentration)

[1201] This allows users to manage tasks efficiently while taking into account their emotional state.

[1202] Example 2

[1203] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1204] Conventional task management systems have the problem that they determine task order without considering the user's emotional state, making it difficult to maximize the user's work efficiency. Furthermore, they are unable to dynamically update task order in real time, making it difficult to adapt to changing work environments. Therefore, there is a need for a system that can reflect the user's emotional state and enable efficient task management.

[1205] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1206] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for acquiring emotional information from the user's input and actions and estimating the emotional state with an emotion engine, means for acquiring tasks and emotional information from the database and generating an optimal order based on that information with a generative model, and means for notifying the user of the optimally ordered task information using a terminal or notification device. This enables efficient task management that takes into account the user's emotional state in real time and adapts to changing work environments.

[1207] A "login request" is an operation in which a user accesses a system and attempts to log in to the system by submitting authentication information.

[1208] A "user identifier" is information for uniquely identifying a user, and typically includes an ID and password.

[1209] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved efficiently.

[1210] A "task" is an item of work or activity that a user inputs into the system.

[1211] "Emotion information" is data that indicates the user's emotional state, and is estimated based on the tone of the text, behavioral patterns, and the like.

[1212] An "emotion engine" is an algorithm or system for inferring a user's emotional state from their input and behavior.

[1213] A "generative model" is an algorithm or artificial intelligence (AI) model that generates optimal task sequences based on acquired data.

[1214] The "optimal order" is the order of task execution determined by the generative model in order to maximize the user's work efficiency.

[1215] The "notification means" refers to a method for notifying the user of the generated task sequence visually or in another form, and includes terminal display, push notification, and the like.

[1216] MODE FOR CARRYING OUT THE INVENTION

[1217] System Configuration

[1218] This invention relates to a system for improving user work efficiency. This system has the functions of sorting tasks entered by the user into an optimal order and notifying the user, as well as recognizing the user's emotions and incorporating that information into a generative model.

[1219] Hardware and Software Configuration

[1220] The system includes the following major components:

[1221] 1. Device (PC, smartphone, etc.):

[1222] It provides a user interface and accepts user operations.

[1223] A screen for entering a user identifier and task information is displayed.

[1224] 2. Server:

[1225] A login request is received and the user identifier is registered in the database.

[1226] Receives task information entered by the user and stores it in a database.

[1227] It incorporates an emotion engine that obtains emotional information from user input and actions.

[1228] Task and emotion information is obtained from the database and input into the generative model.

[1229] Generate optimal task sequences using a generative model.

[1230] The generated optimal task order is notified to the terminal.

[1231] 3. Database (e.g. MySQL, MongoDB):

[1232] Stores user identifier and task information.

[1233] 4. Generative models (e.g. GPT-4):

[1234] The optimal task sequence is generated based on the user's task information and emotional information.

[1235] 5. Emotion Engine:

[1236] Analyze and estimate emotional information from user input and behavior.

[1237] How it works

[1238] Login Procedure

[1239] A user accesses the system using a terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in a database.

[1240] Entering and saving a task

[1241] After the user logs in, the device provides a task input screen through a user interface. The user inputs tasks such as writing a report, replying to a client's email, scheduling a team meeting, etc. The device sends this task information to the server, which then stores the task information in a database.

[1242] emotion recognition

[1243] The server uses an emotion engine to obtain emotional information from the user's input and actions, for example, by using the context of the user's messages or a facial recognition camera to estimate the user's emotional state. This emotional information is then used for subsequent task generation.

[1244] Task optimization

[1245] The server retrieves the user's tasks and emotional information from the database and inputs this into a generative model. The generative model (e.g., GPT-4) generates the optimal task sequence based on this information. This generative model learns the behavior of top-performing individuals and incorporates emotional information to maximize the user's work efficiency.

[1246] Specific examples

[1247] For example, if a user has the following tasks:

[1248] 1. Report preparation

[1249] 2. Reply to client emails

[1250] 3. Scheduling team meetings

[1251] Furthermore, suppose the emotion engine recognizes the user's emotion as "stress and anxiety." Based on this information, the generative model might provide the following sequence:

[1252] 1. Responding to client emails (a quick task)

[1253] 2. Scheduling team meetings (tasks that require collaboration)

[1254] 3. Report writing (a task that requires concentration)

[1255] This allows for efficient task management that takes into account the user's emotional state.

[1256] Prompt Sentence Examples

[1257] "A user has the following tasks: write a report, reply to a client email, schedule a team meeting. And the user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[1258] The above is a specific embodiment for carrying out the present invention. The present system takes into account the user's emotional state in real time, enabling efficient and flexible task management.

[1259] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1260] Specific processing steps of the program

[1261] Step 1: Submit a login request

[1262] The user accesses the login page using their own device and enters the user identifier (ID and password). The device receives this and sends it to the server.

[1263] Input: User ID (ID and password)

[1264] Output: Login request sent to the server

[1265] Specific actions: Enter your ID and password in the text boxes and click the login button.

[1266] Step 2: User identity authentication and registration

[1267] The server receives the login request, authenticates the user by checking the user's identifier against a database, and if authentication is successful, records the user as authenticated in the database.

[1268] Input: User identifier sent to the server

[1269] Output: Authentication results registered in the database

[1270] Specific operation: The server performs an authentication query on the database, receives the result, and if successful, sends a login success message to the terminal.

[1271] Step 3: Entering the task

[1272] Users use their devices to access a task entry screen, specifically to enter tasks such as writing a report, replying to a client email, or scheduling a team meeting.

[1273] Input: Task information entered by the user

[1274] Output: Task information sent from the device to the server

[1275] Specific actions: Enter the task details in the text box and click the Save button.

[1276] Step 4: Save task information

[1277] The server receives the task information sent from the terminal and stores it in a database together with the user identifier.

[1278] Input: Task information and user identifier sent from the device

[1279] Output: Task information stored in the database

[1280] Specific operation: The server executes the stored query against the database and receives the stored results.

[1281] Step 5: Acquiring emotional information

[1282] The emotion engine on the server obtains the user's emotional information from the behavioral data and input data when the user enters a task. For example, emotions are estimated from the context of the text and the speed of input.

[1283] Input: User behavior and input data

[1284] Output: Estimated emotion information

[1285] Specific operation: The server analyzes the input data and applies the emotion estimation algorithm to obtain the result.

[1286] Step 6: Storing Emotional Information

[1287] The server stores the estimated emotion information in a database.

[1288] Input: Estimated emotion information

[1289] Output: Emotion information stored in a database

[1290] Specific operation: The server executes a query to the database to store emotion information.

[1291] Step 7: Acquiring task and emotional information

[1292] The server obtains the user's task information and emotion information from the database.

[1293] Input: Task information and emotion information stored in a database

[1294] Output: Obtained task information and emotion information

[1295] Specific operation: The server executes a query to the database to obtain task and emotion information.

[1296] Step 8: Optimize task order

[1297] The server inputs the acquired task information and emotion information into a generative model to generate the optimal task order. The generative model (e.g., GPT-4) analyzes the input data and calculates the optimal task execution order.

[1298] Input: Task information and emotion information

[1299] Output: The generated optimal task order

[1300] Specific operation: The server sends data to the generative model and receives a response from the model.

[1301] Step 9: Notification of optimization results

[1302] The server notifies the device of the optimal task order, which the device receives and visually notifies the user (e.g., pop-up notification or dashboard display).

[1303] Input: The generated optimal task order

[1304] Output: The optimal task order reported to the device.

[1305] Specific operation: The server sends notification data to the device, and the device displays the notification.

[1306] Specific examples

[1307] Example prompt: "A user has the following tasks: write a report, respond to a client email, and schedule a team meeting. The user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[1308] (Application example 2)

[1309] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1310] In modern factories and production lines, maximizing work efficiency is essential, but the emotional state and fatigue level of workers are often not taken into consideration. As a result, worker stress and fatigue can lead to reduced work efficiency, resulting in reduced productivity. Furthermore, the lack of effective coordination between worker and machine task management has led to numerous problems. Therefore, an optimal task management system that takes into account the emotional state of workers is needed.

[1311] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1312] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving the tasks from the database and generating an optimal order based on the tasks using a generative model, notification means for providing the user with optimally ordered task information, an emotion engine for recognizing the user's emotional state and reflecting that information in the generative model, and means for determining and notifying the user of the optimal task order based on the emotion information. This enables efficient task management that takes into account the emotional state of the worker, reducing worker stress and fatigue and improving productivity.

[1313] "Login Request" means a request by a User to submit authentication information necessary to access the System.

[1314] "User identifier" means unique information that identifies a specific user. This typically includes a user ID or email address.

[1315] "Database" means a data structure that enables information to be managed in an organized manner and quickly searched and updated.

[1316] A "task" is a specific task or activity that a user must perform. Examples include writing a report or replying to an email.

[1317] A "generative model" refers to an algorithm or system that generates new data or procedures based on input information.

[1318] "Optimal order" refers to the order in which tasks are executed that is most effective for a particular purpose.

[1319] "Notification Method" means any method for conveying information to a user. Examples include pop-up notifications and email notifications.

[1320] "Emotional state" refers to the user's current emotional and psychological state, including stress and fatigue levels.

[1321] "Emotion engine" refers to a system that recognizes and analyzes the user's emotional state and generates information based on that.

[1322] "Means for determining optimal task order" refers to a process or device for optimizing the order in which tasks are executed based on the user's emotional state and other information.

[1323] The present invention relates to a system that rearranges the optimal order of tasks for work robots and workers in a factory, thereby supporting efficient work. The system includes the following elements:

[1324] Login process

[1325] First, a login request is received from the work robot and worker to log in to the system individually. The server registers the user identifier in a database and identifies the worker and robot. This process uses a common login authentication method. For example, workers log in using individual ID cards or biometric authentication.

[1326] Entering and saving a task

[1327] After logging in, workers and managers input work tasks into their terminals. This information includes a wide variety of tasks, such as assembling parts or performing maintenance work. The terminals then send this task information to the server, which then stores the tasks in a database.

[1328] Emotion Engine Functions

[1329] The system incorporates an emotion engine that recognizes the user's emotional state. The emotion engine infers emotions based on the user's inputs and actions, as well as the time of day and activity status. This emotion information is provided to a generative model, which then reflects it in generating the optimal task sequence.

[1330] Task optimization

[1331] The server retrieves task and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. In this process, the generative model learns by referencing the movements of individuals with top performance, enabling effective task management.

[1332] Notification of optimization results

[1333] The server sends the generated optimal task order to the terminal, which receives this information and notifies the worker or robot visually or audibly, such as through a pop-up notification, an alarm, or a display on a dashboard.

[1334] Specific examples

[1335] For example, if you have a task like this:

[1336] Assembling the parts (Time required: 60 minutes)

[1337] Quality inspection (time required: 30 minutes)

[1338] Line maintenance (time required: 15 minutes)

[1339] Furthermore, let's say the emotion engine recognizes the worker's emotional state as "Stress 5, Fatigue 7." Based on this prompt, the generative AI model will provide the optimal task sequence as follows:

[1340] 1. Line maintenance

[1341] 2. Quality Inspection

[1342] 3. Assembling the parts

[1343] This optimization result allows for efficient task management that takes into account the emotional state of the worker.

[1344] Example prompt sentence:

[1345] Emotional state: {'Stress': 5, 'Fatigue': 7}

[1346] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[1347] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1348] Step 1:

[1349] The server receives login requests from the work robot and worker, and registers the user identifier in the database. At this time, information such as the worker's ID card or biometric authentication is entered. The server verifies the authentication information and saves the user identifier in the database. This completes the identification of the worker and robot, and the system can begin to be used.

[1350] Input: Worker authentication information (ID card, biometrics, etc.)

[1351] Output: User ID registered in the database

[1352] Step 2:

[1353] The terminal sends work tasks entered by workers or managers to the server. Tasks include information such as parts assembly and maintenance work. The server receives this task information and stores it in a database. This allows for centralized management of task information.

[1354] Input: Work task information (task name, required time, etc.)

[1355] Output: Task information stored in the database

[1356] Step 3:

[1357] The device provides the user's input and actions to the emotion engine, which recognizes and analyzes the user's emotional state. The emotion engine infers emotional information based on the time of day and activity status. The inferred emotional information is provided to a generative model, which generates the optimal task sequence based on this information.

[1358] Input: User input information, behavioral data, time period, activity status

[1359] Output: Emotional information (stress, fatigue, etc.)

[1360] Step 4:

[1361] The server retrieves task information and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task order based on the emotion information. During this process, the model learns by referencing the behavior of individuals with top performance, enabling effective task management.

[1362] Input: Task information and emotion information from the database

[1363] Output: Optimal task ordering

[1364] Step 5:

[1365] The server sends the generated optimal task order to the terminal, which then receives it and notifies the worker or robot visually or audibly, such as by pop-up notification, alarm, or display on the dashboard.

[1366] Input: Optimal task ordering

[1367] Output: Notifications to workers and robots (pop-up notifications, alarms, etc.)

[1368] Step 6:

[1369] The server collects the tasks performed and the feedback of the workers and stores it in a database, which allows for continuous evaluation of task management performance and helps improve the generative model.

[1370] Input: Task information, worker feedback

[1371] Output: Task execution information and feedback stored in a database

[1372] Example prompt

[1373] Here is an example of a real input prompt:

[1374] Emotional state: {'Stress': 5, 'Fatigue': 7}

[1375] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[1376] Based on this prompt, the generative model can generate the optimal task sequence as follows:

[1377] 1. Line maintenance

[1378] 2. Quality Inspection

[1379] 3. Assembling the parts

[1380] This order is determined taking into account the emotional state of the worker.

[1381] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1382] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1383] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1384] [Fourth embodiment]

[1385] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1386] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1387] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1388] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1389] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1390] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1391] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1392] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1393] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1394] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1395] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1396] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1397] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1398] The present invention relates to a system that enables a user to perform a task effectively. Hereinafter, an embodiment of the system will be described.

[1399] System Overview

[1400] This system allows users to log in, input and manage their own tasks, and then generates an optimal task sequence based on that information and provides notifications. The system is mainly composed of a server, terminals, and users.

[1401] Login process

[1402] First, a user logs into the system using their own terminal. The user accesses the login page and enters their user identifier. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This process makes it possible to identify the user.

[1403] Task Input

[1404] After logging in, a user inputs tasks from their device, such as specific tasks like "writing a report" or "replying to a client's email." The device sends this task information to the server, which receives it and stores the tasks in a database based on the user's identifier.

[1405] Task optimization

[1406] The tasks entered by the user are optimized by the server's generative model. The generative model learns from the movements and performance of individuals who are able to perform the top 1% of tasks. The server retrieves the user's tasks from the database and inputs them into the generative model. The generative model generates the optimal order of the tasks and returns the results to the server.

[1407] Notification of optimization results

[1408] The server sends the generated optimal task order to the user's device. The device receives it and notifies the user. Specifically, the results are displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to immediately understand which tasks should be prioritized and work more efficiently.

[1409] Specific examples

[1410] For example, if a user has the following task:

[1411] 1. Report preparation

[1412] 2. Reply to client emails

[1413] 3. Scheduling team meetings

[1414] The user inputs these tasks into the system, and the generative model takes this and might provide an optimized sequence, for example:

[1415] 1. Reply to client emails

[1416] 2. Scheduling team meetings

[1417] 3. Report preparation

[1418] By notifying the user of these results, the user can efficiently tackle the most important and urgent tasks.

[1419] The above is an embodiment of the present invention. The purpose of this system is to enable users to efficiently manage tasks and improve productivity through the processes of login, task input, optimization, and notification.

[1420] The processing flow will be explained below.

[1421] Step 1:

[1422] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[1423] Step 2:

[1424] The terminal sends a login request including the user identifier to the server.

[1425] Step 3:

[1426] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[1427] Step 4:

[1428] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[1429] Step 5:

[1430] The terminal sends a request including the input task information and the user identifier to the server.

[1431] Step 6:

[1432] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[1433] Step 7:

[1434] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[1435] Step 8:

[1436] The terminal sends a task optimization request including the user identifier to the server.

[1437] Step 9:

[1438] The server receives the request and retrieves all tasks corresponding to that user identifier from the database.

[1439] Step 10:

[1440] The server inputs the acquired tasks into a generative model, which then sorts the tasks into an optimal order.

[1441] Step 11:

[1442] The server returns the optimized task order provided by the generative model to the terminal as a response.

[1443] Step 12:

[1444] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[1445] Step 13:

[1446] The user can efficiently proceed with the task based on the optimal order displayed.

[1447] Example 1

[1448] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1449] Current task management systems are complex to input and manage tasks, lack the ability to optimize and prioritize tasks, and lack support for users to effectively complete their work. Furthermore, they are slow to respond in real time when new tasks are added, preventing them from contributing to improved user productivity.

[1450] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1451] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by a user and saving the tasks in a database, means for acquiring tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered tasks, and means for analyzing new tasks in real time and dynamically updating the order of tasks. This allows users to easily input and manage tasks and perform them in an optimal order, thereby enabling efficient work.

[1452] A "Login Request" is a user's attempt to access a system and provide information to identify themselves.

[1453] A "user identifier" is information used to uniquely identify a user when logging in to a system.

[1454] "Database" means a system for systematically storing and managing task and user information.

[1455] A "task" is a specific job or piece of work that a user must complete.

[1456] A "generative model" is an AI model that is trained and used to determine the optimal sequence of tasks.

[1457] "Generating an order" is the process of arranging multiple tasks in an optimal order.

[1458] "Notification means" refers to a method or device for providing information to a user.

[1459] "Real-time analysis" means processing and analyzing new information as soon as it is entered.

[1460] "Dynamic updating" means changing or modifying data or settings in a timely manner in response to changes in circumstances or conditions.

[1461] A "prompt sentence" is an input sentence that instructs a generative AI model on how to process something.

[1462] The present invention relates to a system for supporting users to perform their work effectively. Specific embodiments for implementing this system will be described below.

[1463] System configuration

[1464] This system is mainly composed of three entities: a server, a terminal, and a user. The server processes and manages data, while the terminal provides an interface with the user, who inputs and manages business tasks. The server is equipped with a database and generative AI model, and HTTPS is used as the communication protocol.

[1465] Example of login process

[1466] The user logs in to the system using their own terminal. The user accesses the login page and enters their user identifier and password. The terminal sends this information to the server via the HTTPS protocol. The server compares the received information with the database, and if authentication is successful, it generates a session ID and sends it back to the terminal. Authentication is now complete.

[1467] Example of task entry

[1468] After logging in, the user accesses the task input form and inputs specific work tasks such as "create a report" or "reply to a client's email." The device sends this task information and the user identifier to the server. The server stores the received task information in a database and returns a status indicating that the information has been saved to the device.

[1469] Task optimization example

[1470] The server retrieves the user's task information from the database. It then inputs the retrieved task information into the generative AI model. The generative AI model learns from the behavior of individuals with the top 1% performance and determines the optimal order of tasks. The following prompts are used:

[1471] text

[1472] User A has the following tasks:

[1473] 1. Report preparation

[1474] 2. Reply to client emails

[1475] 3. Scheduling team meetings

[1476] Sort them in the order that works best for you.

[1477] The generative AI model generates the optimal sequence of tasks based on these prompts and returns the results to the server.

[1478] Example of notification of optimization results

[1479] The server sends the generated optimal task order to the user's device, which receives the information and displays it to the user via a pop-up notification or dashboard. The user can then check the notification and start working according to the priority tasks.

[1480] Specific example explanation

[1481] For example, if a user has the following tasks:

[1482] 1. Report preparation

[1483] 2. Reply to client emails

[1484] 3. Scheduling team meetings

[1485] The user inputs these tasks into the system, which the generative AI model takes and provides an optimized sequence that looks like this:

[1486] 1. Reply to client emails

[1487] 2. Scheduling team meetings

[1488] 3. Report preparation

[1489] By notifying the user of these results, they can efficiently tackle the most important and urgent tasks first.

[1490] Through these processes, the system aims to improve work productivity by allowing users to easily input and manage tasks and carry out tasks in the optimal order.

[1491] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1492] Step 1:

[1493] User Login

[1494] A user uses a terminal to access the system's login page and enters a user identifier and password. This input information is sent to the server using the HTTPS protocol. The server receives this login request and checks the user identifier and password in the database. If the check is successful, the server generates a new session ID and sends it back to the terminal. This allows the user to log in to the system.

[1495] Input: User ID, Password

[1496] Output: Session ID

[1497] Step 2:

[1498] Task Input

[1499] After logging in, the user accesses the task input form and inputs a specific work task (e.g., "create a report," "reply to a client's email," etc.). This task information is sent to the server via the terminal. The server stores the received task information in a database together with the user's identifier. A save completion status is returned to the terminal, allowing the user to confirm that the task has been saved correctly.

[1500] Input: Task information, user identifier

[1501] Output: Save completion status

[1502] Step 3:

[1503] Task optimization

[1504] The server retrieves the task information of the user from the database. The retrieved task information is input into the generative AI model. The generative model learns from the movements of individuals with the top 1% performance and calculates the optimal order. The generative model is input with the following prompt:

[1505] text

[1506] User A has the following tasks:

[1507] 1. Report preparation

[1508] 2. Reply to client emails

[1509] 3. Scheduling team meetings

[1510] Sort them in the order that works best for you.

[1511] The generative model generates an optimal ordering of tasks based on the prompts, which is returned to the server.

[1512] Input: Task information, prompt

[1513] Output: Optimal task ordering

[1514] Step 4:

[1515] Notification of optimization results

[1516] The server sends the generated optimal task order to the user's device. The device receives this information and displays it to the user via a pop-up notification or dashboard. The user can check the notification content and perform their work efficiently by following the optimized order.

[1517] Input: Optimal task ordering

[1518] Output: Notification (pop-up or dashboard display)

[1519] Step 5:

[1520] Real-time analysis and management of new tasks

[1521] When a user adds a new task, the device immediately sends the task information to the server. The server saves this new task in the database and inputs it back into the generative AI model to reevaluate the current task order. The generative AI model then recalculates the optimal order of all tasks, including the new task, and returns this new order to the server. The optimization result is then notified to the device.

[1522] Input: New task information

[1523] Output: Updated optimal task ordering

[1524] (Application example 1)

[1525] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1526] Conventional task management systems simply manage tasks entered by users as a list, and often lack an efficient method for executing tasks in the optimal order. Furthermore, automated machinery in factories does not properly manage task order or priority, resulting in reduced work efficiency. A particular issue is that real-time task additions and changes are not quickly reflected in the system. This makes it difficult to maintain high productivity, and there is a risk of increased operational costs and production delays.

[1527] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1528] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving tasks from the database and generating an optimal order based on the tasks using a generative model, means for notifying the user of the optimally ordered task information, means for transmitting login information, task information, and task optimization results from the user's terminal to the server, and means for distributing the generated optimal task order to automated machines in a factory. This makes it possible to efficiently manage tasks entered by users and execute them in an optimal order, significantly improving the work efficiency of automated machines in a factory. Furthermore, since task additions and changes are reflected in real time, high productivity can be maintained.

[1529] A "Login Request" is a request by a User to submit authentication information necessary to access a System.

[1530] A "user identifier" is identification information for uniquely identifying each user.

[1531] A "database" is a system for storing, managing, and searching data.

[1532] A "task" refers to a specific job or operation, and is the specific content that a user inputs into the system.

[1533] A "generative model" is a system that uses machine learning or other algorithms to generate optimal outputs from input data.

[1534] The "optimal order" is the order in which tasks are rearranged to achieve maximum efficiency.

[1535] A "terminal" refers to a device that a user uses to access the system, such as a PC or smartphone.

[1536] "Notification means" means the method by which the system communicates information to the user, including pop-up notifications and dashboard displays.

[1537] A "server" is a computer system that processes and stores data and fulfills user requests.

[1538] "Factory automation machinery" refers to machinery and equipment used to automatically carry out manufacturing processes.

[1539] The "task optimization result" is a list of tasks whose optimal order has been determined by the generative model.

[1540] "Real time" is a concept that refers to processing being carried out immediately without delay.

[1541] As an embodiment of the present invention, a system is described that aims to improve the work efficiency of automated machines in a factory by utilizing means for processing login requests, task entry, task optimization, notifications, and real-time updates.

[1542] System Overview

[1543] This system consists of a server, terminals, and users. The server generates the optimal work sequence based on the tasks entered by the user and distributes it to the automated machines in the factory.

[1544] Hardware and software used

[1545] Server: A computer system that processes and stores data and handles user requests.

[1546] Terminal: The device (computer, smartphone, etc.) through which a user accesses the system.

[1547] Automation machinery: Machinery and equipment used to carry out manufacturing processes automatically.

[1548] Database: A system for storing, managing, and retrieving data.

[1549] Generative model: A system that uses machine learning algorithms to learn by looking at the behavior of top-performing individuals.

[1550] Notification methods: How information is communicated to users through pop-up notifications and dashboard displays.

[1551] Processing a login request

[1552] A user logs into the system using a terminal. The login request is sent to the server, which registers the user identifier in a database, making it possible to uniquely identify the user within the system.

[1553] Task Input

[1554] After logging in, the user inputs the task from the terminal. For example, this is a specific task such as "transporting parts" or "machine maintenance." The task information is sent to the server and stored in a database based on the user identifier.

[1555] Task optimization

[1556] The server retrieves tasks from the database and generates an optimal task sequence using a generative model. This generative model is trained by referencing the behavior of top-performing individuals. Generating an optimal task sequence is a key step in achieving an efficient workflow.

[1557] Notification and Delivery

[1558] The server sends the generated optimal task sequence to the user's device and simultaneously distributes it to the automated machines in the factory. The user is informed through pop-up notifications and dashboard displays, allowing the user and the automated machines to execute tasks in the optimal sequence.

[1559] Real-time updates

[1560] New tasks added by users are analyzed in real time, and the generative model dynamically updates the task order, which is then immediately reflected in the automated machine, ensuring a constantly up-to-date workflow.

[1561] Specific examples

[1562] For example, a factory worker might enter the following task:

[1563] 1. Parts transportation

[1564] 2. Machine maintenance

[1565] 3. Quality check

[1566] The generative model takes these tasks and produces an optimized result in the following order:

[1567] 1. Quality check

[1568] 2. Parts transportation

[1569] 3. Machine maintenance

[1570] The results are communicated to users and automated machines to ensure optimal workflow.

[1571] Example prompt sentence:

[1572] "Generate a new task sequence. Input tasks are: Parts transport, Machine maintenance, and Quality check."

[1573] In this way, the system generates the optimal work sequence based on the tasks entered by the user, realizing an efficient work flow.

[1574] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1575] Step 1:

[1576] User login

[1577] A user accesses the system using a terminal and sends a login request. The server receives this request and registers the user identifier in the database. The input information is the user identifier, and the output is the user identifier registered in the database. This process allows the user to be uniquely identified within the system.

[1578] Step 2:

[1579] Task Input

[1580] After logging in, the user inputs specific work tasks from the terminal. For example, task information such as "transport parts" or "machine maintenance" is input. The server receives this task information and stores it in a database along with the user identifier. The input information is the user identifier and task details, and the output is the task information stored in the database.

[1581] Step 3:

[1582] Getting a task

[1583] The server retrieves the task entered by the user from the database, and the retrieved task information is used in the next step. The input information is the user identifier, and the output is the task information retrieved from the database.

[1584] Step 4:

[1585] Task optimization

[1586] The server inputs the acquired task information into a generative model to generate the optimal task order. This generative model learns by referencing the movements of individuals with top performance. The input information is task information, and the output is the optimal task order. Specifically, task information is input into the generative model, and the optimal order is calculated using a machine learning algorithm.

[1587] Step 5:

[1588] Notification of optimization results

[1589] The server sends the generated optimal task sequence to the user's device. The user receives this information on the device through a pop-up notification or dashboard display. At the same time, the optimal task sequence is also distributed to the automated machines in the factory. The input information is the optimal task sequence, and the output is the task sequence sent to the user's device and the automated machines. Specifically, information is transmitted using a notification API or protocol.

[1590] Step 6:

[1591] Real-time updates

[1592] When a user adds a new task, the terminal sends this information to the server. The server analyzes the new task information in real time and dynamically updates the task order. The updated task order is then distributed to the user terminal and the automated machine again. The input information is the new task information, and the output is the updated task order. Specifically, the new task is input into the generative model, integrated with the existing task order, and recalculated.

[1593] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1594] The present invention relates to a system for improving a user's work efficiency. This system has the function of sorting tasks entered by the user into an optimal order and notifying the user, as well as the function of recognizing the user's emotions and reflecting that information in a generative model. The following describes an embodiment of this system.

[1595] System Overview

[1596] The system handles login requests, inputs and saves tasks, optimizes tasks using a generative model, and provides notifications. Furthermore, by incorporating an emotion engine, task management takes into account the user's emotional state.

[1597] Login process

[1598] First, a user accesses the system using their own terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in the database. This enables the user to be identified and allows them to start using the system.

[1599] Entering and saving a task

[1600] After logging in, a user inputs tasks from their device, such as writing a report, replying to a client's email, or scheduling a team meeting. The device sends these task information to the server, which then stores the received tasks in a database based on the user's identifier.

[1601] Emotion Engine Functions

[1602] This system incorporates an emotion engine that acquires emotional information from user input and behavior. It then estimates emotions based on the time of day and activity status, and provides the estimation results to the generative model.

[1603] Task optimization

[1604] The server retrieves the user's tasks and emotional information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. The generative model, which learns the movements of top-performing individuals, provides the optimal task sequence that reflects the emotional information, enabling task management that is appropriate for the user's current emotional state.

[1605] Notification of optimization results

[1606] The server sends the generated optimal task order to the device. The device receives it and visually notifies the user. For example, the results can be displayed in a pop-up notification or on a dashboard, allowing the user to understand them immediately. This notification allows the user to check which tasks should be prioritized and work more efficiently.

[1607] Specific examples

[1608] For example, if a user has the following tasks:

[1609] 1. Report preparation

[1610] 2. Reply to client emails

[1611] 3. Scheduling team meetings

[1612] Furthermore, suppose the emotion engine recognizes the user's emotion as "stressed and anxious." Based on this information, the generative model might provide the following sequence:

[1613] 1. Responding to client emails (a quick task)

[1614] 2. Scheduling team meetings (tasks that require collaboration)

[1615] 3. Report writing (a task that requires concentration)

[1616] This allows for efficient task management that takes into account the user's emotional state.

[1617] The above is an embodiment of the present invention. The purpose of this system is to improve the work efficiency and satisfaction of users through the processes of login, task input, emotion recognition, task optimization, and notification.

[1618] The processing flow will be explained below.

[1619] Step 1:

[1620] The user accesses the system using his / her terminal, enters a user identifier on the login page, and clicks the login button.

[1621] Step 2:

[1622] The terminal sends a login request including the user identifier to the server.

[1623] Step 3:

[1624] The server receives the login request, registers the user identifier in a database, and returns a login success response to the terminal.

[1625] Step 4:

[1626] After confirming the message that login was successful, the user moves to the task input page, inputs the task to be executed there, and clicks the Add button.

[1627] Step 5:

[1628] The terminal sends a request including the input task information and the user identifier to the server.

[1629] Step 6:

[1630] The server receives the request and saves the new task in a database in a corresponding entry based on the user identifier.

[1631] Step 7:

[1632] Users can input their emotions using the terminal, or the emotion engine can automatically obtain emotion information from the user's actions and inputs.

[1633] Step 8:

[1634] The device sends emotion information to the server, including when the user manually inputs an emotion.

[1635] Step 9:

[1636] The server receives the user's emotion information and stores it in a database. The emotion engine can also provide emotion information in real time.

[1637] Step 10:

[1638] After the user has inputted multiple tasks, he or she clicks the "Optimize" button.

[1639] Step 11:

[1640] The terminal sends a task optimization request including the user identifier to the server.

[1641] Step 12:

[1642] The server receives the request and retrieves all task information and emotion information corresponding to the user identifier from the database.

[1643] Step 13:

[1644] The server inputs the acquired task information and emotion information into the generative model, which then generates the optimal task order based on this information. Because the generative model learns from the movements of individuals with top performance, it generates an order that reflects the user's situation and emotions.

[1645] Step 14:

[1646] The server returns the optimized task order provided by the generative model to the terminal as a response.

[1647] Step 15:

[1648] The terminal receives the optimization results and visually displays them to the user, for example, as a pop-up notification or on the dashboard.

[1649] Step 16:

[1650] The user can efficiently proceed with the task based on the optimal order displayed.

[1651] As a concrete example, if a user inputs the tasks "Write a report," "Reply to client email," and "Schedule a team meeting," and the emotion engine detects "Stress," the generative model might provide the following optimization sequence:

[1652] 1. Responding to client emails (a quick task)

[1653] 2. Scheduling team meetings (tasks that require collaboration)

[1654] 3. Report writing (a task that requires concentration)

[1655] This allows users to manage tasks efficiently while taking into account their emotional state.

[1656] Example 2

[1657] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1658] Conventional task management systems have the problem that they determine task order without considering the user's emotional state, making it difficult to maximize the user's work efficiency. Furthermore, they are unable to dynamically update task order in real time, making it difficult to adapt to changing work environments. Therefore, there is a need for a system that can reflect the user's emotional state and enable efficient task management.

[1659] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1660] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for acquiring emotional information from the user's input and actions and estimating the emotional state with an emotion engine, means for acquiring tasks and emotional information from the database and generating an optimal order based on that information with a generative model, and means for notifying the user of the optimally ordered task information using a terminal or notification device. This enables efficient task management that takes into account the user's emotional state in real time and adapts to changing work environments.

[1661] A "login request" is an operation in which a user accesses a system and attempts to log in to the system by submitting authentication information.

[1662] A "user identifier" is information for uniquely identifying a user, and typically includes an ID and password.

[1663] A database is a system that systematically organizes and stores information, allowing it to be searched and retrieved efficiently.

[1664] A "task" is an item of work or activity that a user inputs into the system.

[1665] "Emotion information" is data that indicates the user's emotional state, and is estimated based on the tone of the text, behavioral patterns, and the like.

[1666] An "emotion engine" is an algorithm or system for inferring a user's emotional state from their input and behavior.

[1667] A "generative model" is an algorithm or artificial intelligence (AI) model that generates optimal task sequences based on acquired data.

[1668] The "optimal order" is the order of task execution determined by the generative model in order to maximize the user's work efficiency.

[1669] The "notification means" refers to a method for notifying the user of the generated task sequence visually or in another form, and includes terminal display, push notification, and the like.

[1670] MODE FOR CARRYING OUT THE INVENTION

[1671] System Configuration

[1672] This invention relates to a system for improving user work efficiency. This system has the functions of sorting tasks entered by the user into an optimal order and notifying the user, as well as recognizing the user's emotions and incorporating that information into a generative model.

[1673] Hardware and Software Configuration

[1674] The system includes the following major components:

[1675] 1. Device (PC, smartphone, etc.):

[1676] It provides a user interface and accepts user operations.

[1677] A screen for entering a user identifier and task information is displayed.

[1678] 2. Server:

[1679] A login request is received and the user identifier is registered in the database.

[1680] Receives task information entered by the user and stores it in a database.

[1681] It incorporates an emotion engine that obtains emotional information from user input and actions.

[1682] Task and emotion information is obtained from the database and input into the generative model.

[1683] Generate optimal task sequences using a generative model.

[1684] The generated optimal task order is notified to the terminal.

[1685] 3. Database (e.g. MySQL, MongoDB):

[1686] Stores user identifier and task information.

[1687] 4. Generative models (e.g. GPT-4):

[1688] The optimal task sequence is generated based on the user's task information and emotional information.

[1689] 5. Emotion Engine:

[1690] Analyze and estimate emotional information from user input and behavior.

[1691] How it works

[1692] Login Procedure

[1693] A user accesses the system using a terminal and enters a user identifier on the login page. The terminal sends this login information to the server. The server receives the login request and registers the user identifier in a database.

[1694] Entering and saving a task

[1695] After the user logs in, the device provides a task input screen through a user interface. The user inputs tasks such as writing a report, replying to a client's email, scheduling a team meeting, etc. The device sends this task information to the server, which then stores the task information in a database.

[1696] emotion recognition

[1697] The server uses an emotion engine to obtain emotional information from the user's input and actions, for example, by using the context of the user's messages or a facial recognition camera to estimate the user's emotional state. This emotional information is then used for subsequent task generation.

[1698] Task optimization

[1699] The server retrieves the user's tasks and emotional information from the database and inputs this into a generative model. The generative model (e.g., GPT-4) generates the optimal task sequence based on this information. This generative model learns the behavior of top-performing individuals and incorporates emotional information to maximize the user's work efficiency.

[1700] Specific examples

[1701] For example, if a user has the following tasks:

[1702] 1. Report preparation

[1703] 2. Reply to client emails

[1704] 3. Scheduling team meetings

[1705] Furthermore, suppose the emotion engine recognizes the user's emotion as "stress and anxiety." Based on this information, the generative model might provide the following sequence:

[1706] 1. Responding to client emails (a quick task)

[1707] 2. Scheduling team meetings (tasks that require collaboration)

[1708] 3. Report writing (a task that requires concentration)

[1709] This allows for efficient task management that takes into account the user's emotional state.

[1710] Prompt Sentence Examples

[1711] "A user has the following tasks: write a report, reply to a client email, schedule a team meeting. And the user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[1712] The above is a specific embodiment for carrying out the present invention. The present system takes into account the user's emotional state in real time, enabling efficient and flexible task management.

[1713] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1714] Specific processing steps of the program

[1715] Step 1: Submit a login request

[1716] The user accesses the login page using their own device and enters the user identifier (ID and password). The device receives this and sends it to the server.

[1717] Input: User ID (ID and password)

[1718] Output: Login request sent to the server

[1719] Specific actions: Enter your ID and password in the text boxes and click the login button.

[1720] Step 2: User identity authentication and registration

[1721] The server receives the login request, authenticates the user by checking the user's identifier against a database, and if authentication is successful, records the user as authenticated in the database.

[1722] Input: User identifier sent to the server

[1723] Output: Authentication results registered in the database

[1724] Specific operation: The server performs an authentication query on the database, receives the result, and if successful, sends a login success message to the terminal.

[1725] Step 3: Entering the task

[1726] Users use their devices to access a task entry screen, specifically to enter tasks such as writing a report, replying to a client email, or scheduling a team meeting.

[1727] Input: Task information entered by the user

[1728] Output: Task information sent from the device to the server

[1729] Specific actions: Enter the task details in the text box and click the Save button.

[1730] Step 4: Save task information

[1731] The server receives the task information sent from the terminal and stores it in a database together with the user identifier.

[1732] Input: Task information and user identifier sent from the device

[1733] Output: Task information stored in the database

[1734] Specific operation: The server executes the stored query against the database and receives the stored results.

[1735] Step 5: Acquiring emotional information

[1736] The emotion engine on the server obtains the user's emotional information from the behavioral data and input data when the user enters a task. For example, emotions are estimated from the context of the text and the speed of input.

[1737] Input: User behavior and input data

[1738] Output: Estimated emotion information

[1739] Specific operation: The server analyzes the input data and applies the emotion estimation algorithm to obtain the result.

[1740] Step 6: Storing Emotional Information

[1741] The server stores the estimated emotion information in a database.

[1742] Input: Estimated emotion information

[1743] Output: Emotion information stored in a database

[1744] Specific operation: The server executes a query to the database to store emotion information.

[1745] Step 7: Acquiring task and emotional information

[1746] The server obtains the user's task information and emotion information from the database.

[1747] Input: Task information and emotion information stored in a database

[1748] Output: Obtained task information and emotion information

[1749] Specific operation: The server executes a query to the database to obtain task and emotion information.

[1750] Step 8: Optimize task order

[1751] The server inputs the acquired task information and emotion information into a generative model to generate the optimal task order. The generative model (e.g., GPT-4) analyzes the input data and calculates the optimal task execution order.

[1752] Input: Task information and emotion information

[1753] Output: The generated optimal task order

[1754] Specific operation: The server sends data to the generative model and receives a response from the model.

[1755] Step 9: Notification of optimization results

[1756] The server notifies the device of the optimal task order, which the device receives and visually notifies the user (e.g., pop-up notification or dashboard display).

[1757] Input: The generated optimal task order

[1758] Output: The optimal task order reported to the device.

[1759] Specific operation: The server sends notification data to the device, and the device displays the notification.

[1760] Specific examples

[1761] Example prompt: "A user has the following tasks: write a report, respond to a client email, and schedule a team meeting. The user's emotion is identified as 'stressed and anxious.' Based on this information, generate the optimal task sequence."

[1762] (Application example 2)

[1763] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1764] In modern factories and production lines, maximizing work efficiency is essential, but the emotional state and fatigue level of workers are often not taken into consideration. As a result, worker stress and fatigue can lead to reduced work efficiency, resulting in reduced productivity. Furthermore, the lack of effective coordination between worker and machine task management has led to numerous problems. Therefore, an optimal task management system that takes into account the emotional state of workers is needed.

[1765] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1766] In this invention, the server includes means for receiving a login request and registering a user identifier in a database, means for receiving tasks entered by the user and saving the tasks in the database, means for retrieving the tasks from the database and generating an optimal order based on the tasks using a generative model, notification means for providing the user with optimally ordered task information, an emotion engine for recognizing the user's emotional state and reflecting that information in the generative model, and means for determining and notifying the user of the optimal task order based on the emotion information. This enables efficient task management that takes into account the emotional state of the worker, reducing worker stress and fatigue and improving productivity.

[1767] "Login Request" means a request by a User to submit authentication information necessary to access the System.

[1768] "User identifier" means unique information that identifies a specific user. This typically includes a user ID or email address.

[1769] "Database" means a data structure that enables information to be managed in an organized manner and quickly searched and updated.

[1770] A "task" is a specific task or activity that a user must perform. Examples include writing a report or replying to an email.

[1771] A "generative model" refers to an algorithm or system that generates new data or procedures based on input information.

[1772] "Optimal order" refers to the order in which tasks are executed that is most effective for a particular purpose.

[1773] "Notification Method" means any method for conveying information to a user. Examples include pop-up notifications and email notifications.

[1774] "Emotional state" refers to the user's current emotional and psychological state, including stress and fatigue levels.

[1775] "Emotion engine" refers to a system that recognizes and analyzes the user's emotional state and generates information based on that.

[1776] "Means for determining optimal task order" refers to a process or device for optimizing the order in which tasks are executed based on the user's emotional state and other information.

[1777] The present invention relates to a system that rearranges the optimal order of tasks for work robots and workers in a factory, thereby supporting efficient work. The system includes the following elements:

[1778] Login process

[1779] First, a login request is received from the work robot and worker to log in to the system individually. The server registers the user identifier in a database and identifies the worker and robot. This process uses a common login authentication method. For example, workers log in using individual ID cards or biometric authentication.

[1780] Entering and saving a task

[1781] After logging in, workers and managers input work tasks into their terminals. This information includes a wide variety of tasks, such as assembling parts or performing maintenance work. The terminals then send this task information to the server, which then stores the tasks in a database.

[1782] Emotion Engine Functions

[1783] The system incorporates an emotion engine that recognizes the user's emotional state. The emotion engine infers emotions based on the user's inputs and actions, as well as the time of day and activity status. This emotion information is provided to a generative model, which then reflects it in generating the optimal task sequence.

[1784] Task optimization

[1785] The server retrieves task and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task sequence based on this information. In this process, the generative model learns by referencing the movements of individuals with top performance, enabling effective task management.

[1786] Notification of optimization results

[1787] The server sends the generated optimal task order to the terminal, which receives this information and notifies the worker or robot visually or audibly, such as through a pop-up notification, an alarm, or a display on a dashboard.

[1788] Specific examples

[1789] For example, if you have a task like this:

[1790] Assembling the parts (Time required: 60 minutes)

[1791] Quality inspection (time required: 30 minutes)

[1792] Line maintenance (time required: 15 minutes)

[1793] Furthermore, let's say the emotion engine recognizes the worker's emotional state as "Stress 5, Fatigue 7." Based on this prompt, the generative AI model will provide the optimal task sequence as follows:

[1794] 1. Line maintenance

[1795] 2. Quality Inspection

[1796] 3. Assembling the parts

[1797] This optimization result allows for efficient task management that takes into account the emotional state of the worker.

[1798] Example prompt sentence:

[1799] Emotional state: {'Stress': 5, 'Fatigue': 7}

[1800] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[1801] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1802] Step 1:

[1803] The server receives login requests from the work robot and worker, and registers the user identifier in the database. At this time, information such as the worker's ID card or biometric authentication is entered. The server verifies the authentication information and saves the user identifier in the database. This completes the identification of the worker and robot, and the system can begin to be used.

[1804] Input: Worker authentication information (ID card, biometrics, etc.)

[1805] Output: User ID registered in the database

[1806] Step 2:

[1807] The terminal sends work tasks entered by workers or managers to the server. Tasks include information such as parts assembly and maintenance work. The server receives this task information and stores it in a database. This allows for centralized management of task information.

[1808] Input: Work task information (task name, required time, etc.)

[1809] Output: Task information stored in the database

[1810] Step 3:

[1811] The device provides the user's input and actions to the emotion engine, which recognizes and analyzes the user's emotional state. The emotion engine infers emotional information based on the time of day and activity status. The inferred emotional information is provided to a generative model, which generates the optimal task sequence based on this information.

[1812] Input: User input information, behavioral data, time period, activity status

[1813] Output: Emotional information (stress, fatigue, etc.)

[1814] Step 4:

[1815] The server retrieves task information and emotion information from the database and inputs it into the generative model. The generative model generates the optimal task order based on the emotion information. During this process, the model learns by referencing the behavior of individuals with top performance, enabling effective task management.

[1816] Input: Task information and emotion information from the database

[1817] Output: Optimal task ordering

[1818] Step 5:

[1819] The server sends the generated optimal task order to the terminal, which then receives it and notifies the worker or robot visually or audibly, such as by pop-up notification, alarm, or display on the dashboard.

[1820] Input: Optimal task ordering

[1821] Output: Notifications to workers and robots (pop-up notifications, alarms, etc.)

[1822] Step 6:

[1823] The server collects the tasks performed and the feedback of the workers and stores it in a database, which allows for continuous evaluation of task management performance and helps improve the generative model.

[1824] Input: Task information, worker feedback

[1825] Output: Task execution information and feedback stored in a database

[1826] Example prompt

[1827] Here is an example of a real input prompt:

[1828] Emotional state: {'Stress': 5, 'Fatigue': 7}

[1829] Tasks: [{'name': 'Parts Assembly', 'duration': 60}, {'name': 'Quality Inspection', 'duration': 30}, {'name': 'Line Maintenance', 'duration': 15}]

[1830] Based on this prompt, the generative model can generate the optimal task sequence as follows:

[1831] 1. Line maintenance

[1832] 2. Quality Inspection

[1833] 3. Assembling the parts

[1834] This order is determined taking into account the emotional state of the worker.

[1835] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1836] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1837] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1838] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1839] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1840] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1841] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1842] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1843] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1844] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1845] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1846] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1847] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1848] 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.

[1849] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1850] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1851] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1852] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1853] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1854] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1855] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1856] The following is further disclosed regarding the above embodiment.

[1857] (Claim 1)

[1858] means for receiving a login request and registering a user identifier in a database;

[1859] a means for receiving tasks entered by a user and storing the tasks in a database;

[1860] A means for retrieving tasks from the database and generating an optimal sequence based on the tasks using a generative model;

[1861] a notification means for providing optimally ordered task information to the user;

[1862] A system including:

[1863] (Claim 2)

[1864] The system of claim 1, wherein the generative model learns by referring to the movements of individuals with top performance.

[1865] (Claim 3)

[1866] 10. The system of claim 1, wherein the system analyzes new tasks added by a user in real time and dynamically updates the task order.

[1867] "Example 1"

[1868] (Claim 1)

[1869] means for receiving a login request and registering a user identifier in a database;

[1870] a means for receiving tasks entered by a user and storing the tasks in a database;

[1871] A means for retrieving tasks from the database and generating an optimal sequence based on the tasks using a generative model;

[1872] a notification means for providing optimally ordered task information to the user;

[1873] a means for analyzing new tasks in real time and dynamically updating the task order;

[1874] A system including:

[1875] (Claim 2)

[1876] The system of claim 1, wherein the generative model learns by referring to the movements of individuals with top performance.

[1877] (Claim 3)

[1878] 2. The system of claim 1, further comprising means for providing user task information as a prompt sentence as input to the generative model.

[1879] "Application Example 1"

[1880] (Claim 1)

[1881] means for receiving a login request and registering a user identifier in a database;

[1882] a means for receiving tasks entered by a user and storing the tasks in a database;

[1883] A means for retrieving tasks from the database and generating an optimal sequence based on the tasks using a generative model;

[1884] a notification means for providing optimally ordered task information to the user;

[1885] A means for transmitting login information, task information, and task optimization results from a user's terminal to a server;

[1886] a means for distributing the generated optimal task sequence to automated machines in the factory;

[1887] A system including:

[1888] (Claim 2)

[1889] The system of claim 1, wherein the generative model learns by referring to the movements of individuals with top performance.

[1890] (Claim 3)

[1891] 2. The system according to claim 1, wherein the system analyzes new tasks added by a user in real time, dynamically updates the order of tasks, and reflects the updated results in an automated machine.

[1892] "Example 2: Combining Emotion Engines"

[1893] (Claim 1)

[1894] means for receiving a login request and registering a user identifier in a database;

[1895] means for receiving tasks entered by a user and storing the tasks in a database;

[1896] A means for acquiring emotional information from a user's input or behavior and estimating the emotional state using an emotion engine;

[1897] A means for obtaining task and emotion information from the database, and for the generative model to generate an optimal sequence based on the information;

[1898] means for notifying a user of optimally ordered task information using a terminal or a notification device;

[1899] A system including:

[1900] (Claim 2)

[1901] The system of claim 1, wherein the generative model generates an optimal task sequence that reflects emotional information by learning from the movements of individuals with top performance.

[1902] (Claim 3)

[1903] 10. The system of claim 1, wherein the system uses a generative model that analyzes new tasks added by a user in real time and dynamically updates the task order.

[1904] "Application example 2 when combining emotion engines"

[1905] (Claim 1)

[1906] means for receiving a login request and registering a user identifier in a database;

[1907] a means for receiving tasks entered by a user and storing the tasks in a database;

[1908] A means for retrieving tasks from the database and generating an optimal sequence based on the tasks using a generative model;

[1909] a notification means for providing optimally ordered task information to the user;

[1910] An emotion engine that recognizes the user's emotional state and reflects that information in the generative model;

[1911] A means for determining and notifying the optimal task order based on emotional information;

[1912] A system including:

[1913] (Claim 2)

[1914] The system of claim 1, wherein the generative model learns by referring to the movements of individuals with top performance.

[1915] (Claim 3)

[1916] 10. The system of claim 1, wherein the system analyzes new tasks added by a user in real time and dynamically updates the task order. [Explanation of symbols]

[1917] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving a login request and registering a user identifier in a database; a means for receiving tasks entered by a user and storing the tasks in a database; A means for retrieving tasks from the database and generating an optimal sequence based on the tasks using a generative model; a notification means for providing optimally ordered task information to the user; A system including:

2. The system according to claim 1 , wherein the generative model learns by referring to the movements of individuals with top performance.

3. 2. The system of claim 1, wherein the system analyzes new tasks added by a user in real time and dynamically updates the order of tasks.

Images