system

Abstract

Provide a system. A method for collecting task data includes: a means for classifying the collected task data using natural language processing and machine learning algorithms; A means for visualizing the classification results; a means of collecting employee data; a means for integrating the collected employee data and the classified task data using a matching algorithm; A means of assigning tasks to the best employees; a means for notifying the allocation result; A means of collecting and updating progress A system including:

Description

[Technical Field]

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

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

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

[0004] In modern companies, task management and appropriate personnel allocation are essential to improving productivity. However, in conventional systems, task classification and assignment to employees are often done manually, which is time-consuming and labor-intensive and prone to human error. Furthermore, it is difficult to grasp the progress of tasks in real time, making overall business management difficult. To solve these problems, there is a need for a system that can efficiently and automatically classify tasks, assign them to employees, and manage their progress. [Means for solving the problem]

[0005] The present invention provides a system that collects task data, classifies it using natural language processing and machine learning algorithms, and visualizes the classification results. The system displays the collected task data on a dashboard, collects employee data, and assigns tasks to appropriate employees using a matching algorithm. The system also notifies the assignment results and collects and updates progress status. This improves the efficiency of task management within a company, reduces human error, and enables real-time visualization of overall work progress.

[0006] "Task data" is a general term for information related to work and projects carried out within an organization, and is data that includes attributes such as task titles, descriptions, deadlines, priorities, required skills, and dependencies.

[0007] "Means of collection" is a general term for interfaces and processes for centrally receiving task data and employee data, and includes mechanisms for obtaining data from user input and other systems.

[0008] "Natural language processing" is a general term for techniques and methodologies that enable computers to understand, interpret, and generate human language, and includes processes such as text tokenization and keyword extraction.

[0009] "Machine learning algorithms" is a general term for algorithms that learn patterns from large amounts of data and perform predictions and classifications, and includes techniques such as regression analysis, classification, and clustering.

[0010] "Classification methods" refers to a general term for methods or processes for dividing collected task data into categories based on specific criteria, including the application of natural language processing and machine learning algorithms.

[0011] "Visualization means" is a general term for technologies and tools for visually displaying data, and includes systems that use dashboards, graphs, charts, etc. to present information in an easy-to-read format.

[0012] "Employee data" is a collective term for information about employees, including attributes such as skill sets, work history, and current task load.

[0013] "Matching algorithm" is a general term for algorithms that optimally combine multiple elements, and in the present invention, it is used to make appropriate allocations by taking into account the tasks, employee skills, and workloads.

[0014] An "assignment method" is a general term for the process or method by which tasks are assigned to specific employees, and is done automatically based on an algorithm.

[0015] "Notification methods" refers to the methods and tools used to notify employees of newly assigned tasks, including emails, messages, pop-up notifications, etc.

[0016] "Progress" is a general term for information that indicates how much of a task has been completed or the current state of work, and includes data such as the progress rate, progress during the work, and problems.

[0017] "Means of collection and updating" is a general term for methods and systems for continuously obtaining progress status and keeping it up to date, including user input and automatic collection systems. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The system of this invention uses AI to visualize and classify tasks across the entire company and appropriately assign them to each employee, using a generative AI interface. This system can be realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[0040] System Overview

[0041] The system provides the following main functions:

[0042] 1. Collecting and saving task data

[0043] 2. Classification and visualization of task data

[0044] 3. Collection and storage of employee data

[0045] 4. Matching tasks with employees

[0046] 5. Notification after task assignment

[0047] 6. Real-time management of task progress

[0048] What the program does

[0049] 1. Collecting and saving task data

[0050] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[0051] The server stores the received task data in a database.

[0052] 2. Classification and visualization of task data

[0053] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[0054] The server uses machine learning algorithms to categorize tasks.

[0055] The server displays the classified task data on a dashboard for the user to review.

[0056] 3. Collection and storage of employee data

[0057] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[0058] The server stores the received employee data in a database.

[0059] 4. Matching tasks with employees

[0060] The server combines task data with employee data and applies a matching algorithm that takes into account the required skills and priority of the task, the employee's skill set, and their current task load to calculate the optimal match.

[0061] The server determines the optimal task-employee pair and assigns the task to the corresponding employee.

[0062] 5. Notification after task assignment

[0063] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0064] The terminal receives the notification and informs the user that a task has been assigned to them.

[0065] 6. Real-time management of task progress

[0066] Users (employees) use terminals to input task progress in real time, reporting progress rates, task progress, problems, etc.

[0067] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[0068] Specific examples

[0069] Example 1: New project task assignments

[0070] 1. Enter task data

[0071] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[0072] The server receives this task data and stores it in a database.

[0073] 2. Task categorization

[0074] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0075] The server displays the classification results on a dashboard.

[0076] 3. Enter employee data

[0077] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[0078] 4. Matching tasks with employees

[0079] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[0080] 5. Sending notifications

[0081] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[0082] 6. Progress Management

[0083] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[0084] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[0085] The above is a description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, and visualizing the overall progress of work in real time.

[0086] The processing flow will be explained below.

[0087] Step 1:

[0088] The user uses the terminal to input the details of a new task (title, description, deadline, priority, required skills, dependencies, etc.) After completing the input, the terminal sends this data to the server.

[0089] Step 2:

[0090] The server receives task data sent from the device and stores it in a database. The format of the task data is standardized, and missing or abnormal values ​​are complemented and corrected.

[0091] Step 3:

[0092] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[0093] Step 4:

[0094] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[0095] Step 5:

[0096] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[0097] Step 6:

[0098] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[0099] Step 7:

[0100] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[0101] Step 8:

[0102] The server merges the task data with the employee data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, and their current task load.

[0103] Step 9:

[0104] The server uses a matching algorithm to determine the best task-employee pair, e.g., task "market research" is assigned to employee X.

[0105] Step 10:

[0106] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0107] Step 11:

[0108] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. The notifications are delivered via a pop-up message, email, or messaging app.

[0109] Step 12:

[0110] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[0111] Step 13:

[0112] The terminal transmits the input progress data to the server.

[0113] Step 14:

[0114] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[0115] Step 15:

[0116] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[0117] The above are the specific processing steps of the system of the present invention. This system has the effect of improving the efficiency of task management within a company, reducing human error, and visualizing the overall progress of work in real time.

[0118] Example 1

[0119] 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."

[0120] In modern companies, effectively managing diverse tasks and assigning them to the right employees is extremely difficult. Especially in large organizations, manual task assignment requires a tremendous amount of time and effort due to the complexity of tasks and the diversity of employees. Furthermore, improper task assignment can lead to reduced work efficiency and disrupted employee workloads. Furthermore, manually tracking the progress of tasks across the company in real time is difficult, making an appropriate task management system essential to prevent project delays and errors.

[0121] 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.

[0122] In this invention, the server includes means for collecting task data, means for analyzing the collected task data using natural language processing and machine learning algorithms and extracting keywords and important phrases, means for classifying the task data using the extracted data, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm and calculating the optimal combination taking into account the required skills of the task, priority, employee skill sets, and task load, means for assigning tasks to the optimal employee, means for notifying the assignment results, and means for collecting progress status in real time, storing it in a database, and displaying it on a dashboard, thereby enabling efficient task management and visualization of progress status in real time.

[0123] "Task data" refers to data that includes detailed information related to a task, such as a title, description, deadline, priority, required skills, and dependencies.

[0124] "Natural language processing" is the technology used by computers to understand, analyze, and generate human language.

[0125] A "machine learning algorithm" is an algorithm that learns patterns from data and uses that knowledge to make decisions and predictions based on new data.

[0126] "Keywords" refer to important words or concepts extracted from documents or text data.

[0127] An "important phrase" is a series of words in text data that are particularly important in terms of meaning or content.

[0128] "Classification" is the process of sorting data into categories or groups based on certain criteria.

[0129] "Visualization" refers to the presentation of data or information using visual representations such as graphs and diagrams.

[0130] "Employee data" is data that includes information such as an employee's skill set, work history, and current task status.

[0131] A "matching algorithm" refers to a method or calculation procedure for finding the optimal combination between multiple elements.

[0132] "Progress" is information that indicates the current degree of achievement or completion of a task or project.

[0133] "Real-time" refers to immediate updates or processing at the current moment or time.

[0134] A "dashboard" is an interface or tool that displays various data and information in a centralized manner, making it easier for administrators to grasp the situation.

[0135] The system of the present invention is designed to improve the efficiency of task management within a company, and is realized through the cooperation of a server, terminals, and users. The processing of the system program will be specifically described below.

[0136] System configuration and functions

[0137] The system provides the following main functions:

[0138] 1. Collecting and saving task data

[0139] A user uses a terminal to enter task data, including details such as the task title, description, deadline, priority, required skills, and dependencies.

[0140] The device sends this task data to the server using an encrypted communication protocol (e.g., HTTPS).

[0141] The server stores the received task data in a relational database management system (RDBMS: e.g., MySQL (registered trademark) or PostgreSQL).

[0142] 2. Task Data Analysis and Classification

[0143] The server analyzes the saved task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) to extract keywords and important phrases.

[0144] The server uses machine learning algorithms (e.g., K-means clustering or support vector machines) to classify tasks into categories.

[0145] The server displays the classified task data on a web dashboard (e.g., Grafana or Tableau) for easy user review.

[0146] 3. Collection and storage of employee data

[0147] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[0148] The terminal transmits the entered employee data to the server.

[0149] The server stores the received employee data in a database.

[0150] 4. Matching tasks with employees

[0151] The server combines task data with employee data and applies a matching algorithm (e.g., a recommendation system) that takes into account the task's required skills, priority, employee skill set, and current task load to calculate the optimal match.

[0152] The server determines the optimal task-employee pair, assigns the corresponding task to the appropriate employee, and records this information in a database.

[0153] 5. Notification after task assignment

[0154] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0155] The terminal receives this notification and informs the user that a task has been assigned to him.

[0156] 6. Real-time management of task progress

[0157] Users (employees) use their own devices to input task progress in real time, reporting progress rates, progress during tasks, problems, etc.

[0158] The terminal transmits the input progress information to the server.

[0159] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[0160] Example: Assigning tasks to a new project

[0161] Example 1: Task assignment for Project "A"

[0162] 1. Enter task data

[0163] The user (project manager) uses a terminal to input the tasks for project "A": "market research," "prototype design," and "client meeting."

[0164] The terminal transmits these task data to the server, which stores the received data in a database.

[0165] 2. Task categorization

[0166] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0167] The server displays the classification results on a dashboard.

[0168] 3. Enter employee data

[0169] Users (employees X, Y, Z) enter their skill sets and work history into a terminal, which then sends it to the server.

[0170] The server stores the received data in a database.

[0171] 4. Matching tasks with employees

[0172] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[0173] 5. Sending notifications

[0174] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[0175] 6. Progress Management

[0176] Users (employees X, Y, and Z) use their own terminals to input the progress of their tasks, and the terminals send the progress data to the server.

[0177] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing users to grasp the overall progress status in real time.

[0178] Example of generative AI model and prompt

[0179] The system uses a generative AI model to match tasks with employees. Here are some example prompts:

[0180] Prompt Sentence Examples

[0181] "A new task has been created. The task title is 'Market Research' and the required skill is 'Data Analysis'. Please assign an employee with the relevant skills."

[0182] The above is a specific description of the embodiment of the invention.

[0183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0184] Step 1: Enter task data

[0185] A user (e.g., a project manager) uses a terminal to enter task information (title, description, deadline, priority, required skills, dependencies, etc.) into the system. Task data is entered using a web form.

[0186] Inputs: Task title, task description, due date, priority, required skills, dependencies.

[0187] How it works: The terminal receives input data from the user and verifies the data integrity, for example, whether deadlines are entered in the correct format, whether required skills follow the list format, etc.

[0188] Output: The validated task data.

[0189] Step 2: Sending task data

[0190] The device sends the verified task data to the server using an encrypted protocol (e.g., HTTPS).

[0191] Input: Validated task data.

[0192] How it works: The device sends task data to the server using the HTTPS protocol.

[0193] Output: The task data sent to the server.

[0194] Step 3: Save the task data

[0195] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[0196] Input: The submitted task data.

[0197] What it does: The server opens a database connection and saves the task data, generating a unique task ID and recording it along with the data.

[0198] Output: Task data stored in the database (including task ID).

[0199] Step 4: Analyzing task data

[0200] The server analyzes the stored task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) libraries to extract keywords and important phrases.

[0201] Input: Saved task data.

[0202] How it works: It uses an NLP library to tokenize (break down) a task description into words and extract important keywords and phrases, such as the phrase "market research."

[0203] Output: Extracted keywords and key phrases.

[0204] Step 5: Classify task data

[0205] The server categorizes tasks based on the extracted keywords and phrases using machine learning algorithms (e.g., K-means clustering and support vector machines).

[0206] Input: Extracted keywords and key phrases.

[0207] How it works: Using a machine learning algorithm, the system classifies a task, for example "market research," into the "research" category, assigns a category label, and updates the results to the database.

[0208] Output: Classification results (task data including category labels).

[0209] Step 6: Visualize task data

[0210] The server prepares the classified task data for display on a web dashboard (e.g., Grafana or Tableau).

[0211] Input: Classified task data.

[0212] Action: The data is converted into a format specified by the visualization tool and displayed on a dashboard. For example, tasks in the "Investigation" category are displayed as a bar graph.

[0213] Output: A visualized dashboard.

[0214] Step 7: Enter employee data

[0215] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[0216] Inputs: Skill set, work history, current task status.

[0217] How it works: The terminal receives employee data and verifies data integrity, e.g., that skill sets are entered in the proper format.

[0218] Output: Validated employee data.

[0219] Step 8: Submit employee data

[0220] The terminal transmits the verified employee data to the server.

[0221] Input: Validated employee data.

[0222] How it works: The device sends employee data to the server using the HTTPS protocol.

[0223] Output: Employee data sent to the server.

[0224] Step 9: Save employee data

[0225] The server stores the received employee data in a database.

[0226] Input: Submitted employee data.

[0227] What happens: The server opens a database connection and saves the employee data, generating a unique employee ID and recording it along with the data.

[0228] Output: Employee data stored in the database, including employee ID.

[0229] Step 10: Applying the matching algorithm

[0230] The server combines the task data with the employee data and applies a matching algorithm (e.g., a recommendation system).

[0231] Input: Classified task data, saved employee data.

[0232] How it works: Calculate the optimal combination by taking into account the required skills of the task, priority, employee skill sets, current task load, etc. For example, use a recommendation system to select employee X who is best suited for the task "market research."

[0233] Output: Matching results (task-employee pairs).

[0234] Step 11: Assign tasks

[0235] The server determines the best task-employee pair and updates the task record in the database.

[0236] Input: Matching results.

[0237] What it does: Accesses the database and updates the task record, recording the ID of the assigned employee and changing the task state to "Assigned."

[0238] Output: The updated task record.

[0239] Step 12: Generate notifications

[0240] The server generates a notification to the employee who has been newly assigned the task.

[0241] Input: The updated task record.

[0242] What it does: Triggers the notification mechanism and generates a notification containing task details and deadlines.

[0243] Output: The generated notification.

[0244] Step 13: Sending notifications

[0245] The server sends the generated notification to the terminal, which receives the notification and displays it to the user.

[0246] Input: The generated notification.

[0247] How it works: The server sends notifications to the device via email or push notification. The device receives the notifications and notifies the user via a screen display or audio alarm.

[0248] Output: The notification displayed to the user.

[0249] Step 14: Enter your progress

[0250] Users (employees) use their own devices to input task progress in real time.

[0251] Input: Progress data (progress rate, progress, issues, etc.).

[0252] Action: The user enters progress data, and the terminal verifies the data integrity, e.g., checks that the progress rate is within the range 0-100%.

[0253] Output: Progress data of the completed validation.

[0254] Step 15: Sending progress data

[0255] The terminal transmits progress information indicating that the verification has been completed to the server.

[0256] Input: Verified progress data.

[0257] How it works: The device sends progress data to the server using the HTTPS protocol.

[0258] Output: Progress data sent to the server.

[0259] Step 16: Saving and Counting Progress Data

[0260] The server stores the received progress data in a database and aggregates the progress status.

[0261] Input: The progress data submitted.

[0262] What it does: The server opens a database connection, stores the progress data, and performs aggregations, such as calculating the overall progress of tasks and assessing the overall progress of the project.

[0263] Output: Aggregated progress data in a database.

[0264] Step 17: View progress on a dashboard

[0265] The server displays the aggregated progress data on a dashboard (e.g., Grafana or Tableau).

[0266] Input: Aggregated progress data.

[0267] How it works: The server converts the data into a format required by the visualization tool and displays it on a dashboard, such as a pie chart or bar graph showing the progress of a project.

[0268] Output: Progress displayed in a visualized dashboard.

[0269] This enables consistent system processing from collecting task data and employee data to assigning tasks and managing progress, making task management within a company more efficient.

[0270] (Application example 1)

[0271] 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."

[0272] In factories, many work devices (e.g., robots) are operating simultaneously, and there is a need to improve the efficiency and optimization of work. However, in current systems, tasks are often assigned to each work device manually, which leads to problems such as human error and complicated task management. In addition, it is difficult to manage progress in real time, which is a cause of reduced overall work efficiency.

[0273] 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.

[0274] In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting data on maintenance devices, means for integrating the collected data on maintenance devices and the classified task data using a matching algorithm, means for assigning tasks to the most appropriate maintenance device, means for notifying the assignment results, and means for collecting and updating progress status, thereby enabling automatic assignment of tasks to each maintenance device and real-time progress management.

[0275] "Task data" is data that contains information about a particular task or project.

[0276] "Natural language processing" is a technology that allows computers to understand and process natural language used by humans.

[0277] A "machine learning algorithm" is a computational method for learning patterns from data and making predictions and classifications.

[0278] "Visualization" is a method of visually displaying data and information to make it easier to understand.

[0279] "Work equipment" refers to automated machines, robots, and other equipment used in factories and work sites.

[0280] A "matching algorithm" is a computational method for finding optimal pairings based on specific criteria.

[0281] "Assignment" is the act of distributing a specific task to a corresponding work device or person.

[0282] "Notification" is the act or system of informing interested parties of important information or updates.

[0283] "Progress" is information that indicates how far a task or project has progressed.

[0284] "Collection methods" are the methods and techniques used to gather the necessary data and information.

[0285] "Integration means" are methods and technologies that bring together different data and systems to make them usable.

[0286] This invention is a system for streamlining task management for work equipment in a factory, and is realized through the cooperation of a server, terminals, and users. This system provides the following main functions: collecting and saving task data, classifying and visualizing task data, collecting and saving data on work equipment, matching tasks with work equipment, notifying users after task assignment, and managing task progress in real time.

[0287] Hardware and Software Configuration

[0288] 1. Hardware: Servers, tablets, factory robots.

[0289] 2. Software: Python (backend), Django (web framework), NLP library (e.g. spaCy), machine learning library (e.g. TENSORFLOW (registered trademark)), database (e.g. PostgreSQL), dashboard tool (e.g. Grafana).

[0290] Program processing and natural language explanation

[0291] Collecting and storing task data

[0292] A user (factory manager) uses a tablet to input information about a specific task or project, including the task title, description, deadline, priority, required skills, and dependencies. The server receives this task data and stores it in a database.

[0293] Classifying and visualizing task data

[0294] The server analyzes the received task data using natural language processing (NLP) to extract keywords and important phrases. It then uses machine learning algorithms to categorize the tasks. The results are then visualized on a dashboard for users to review.

[0295] Work equipment data collection and storage

[0296] The user (factory manager) uses a tablet to input the capabilities, current operating status, and skill set of each work device (factory robot). The server receives this data on the work device and stores it in a database.

[0297] Matching tasks and work equipment

[0298] The server combines the task data and the work equipment data and applies a matching algorithm that takes into account the required skills and priorities of the tasks and the current task load of the work equipment to calculate the optimal combination. The optimal work equipment is then assigned to the task.

[0299] Notification after task assignment

[0300] The server generates a notification for the manager of the work device to which the new task has been assigned and sends it to the tablet. The notification includes detailed information about the task and its deadline, and the device receives it to inform the user that a task has been assigned to them.

[0301] Real-time management of task progress

[0302] The user (factory manager) uses a tablet to input task progress status in real time. Progress rates, task progress, problems, etc. are reported, and the server receives, stores, and aggregates this data. The server displays the overall progress status on a dashboard and manages the situation in real time.

[0303] Specific examples

[0304] Prompt Sentence Examples

[0305] Task data input prompt example

[0306] Enter the following task:

[0307] 1. Task title: Inspection work

[0308] 2. Task Description: Inspect product X

[0309] 3. Deadline: 2023-12-01

[0310] 4. Priority: High

[0311] 5. Required Skills: Inspection

[0312] Example of a progress report prompt

[0313] Progress Report:

[0314] 1. Task title: Inspection work

[0315] 2. Progress: 50%

[0316] 3. Current status: Under testing

[0317] 4. Issues: None

[0318] As described above, this system enables efficient task management of work equipment within a factory. Users can easily input task data and progress status via tablet, and the server compiles, analyzes, and visualizes the data, achieving work efficiency and real-time management.

[0319] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0320] Step 1:

[0321] The user (factory manager) uses a tablet to input task data. Detailed information such as the task title, description, deadline, priority, required skills, and dependencies are entered into the tablet. This becomes the input data to the server. The server stores this input data in a database.

[0322] Step 2:

[0323] The server analyzes the stored task data using natural language processing (NLP). Keywords and important phrases are extracted from the task data. The extracted keywords become the output data of the NLP process.

[0324] Step 3:

[0325] The server uses a machine learning algorithm to classify tasks based on the extracted keywords and phrases, generates classified task data, and stores the results in a database. The classification results become the server's output data.

[0326] Step 4:

[0327] The server displays the classified task data on a dashboard. The visualized task data is output to the screen of a display device (e.g., a tablet or PC). Through this dashboard, users can check the task classification results in real time.

[0328] Step 5:

[0329] The user (factory manager) uses a tablet to input data for each work tool (capabilities, skill set, current operating status). This data is input to the server, which then stores the received work tool data in a database.

[0330] Step 6:

[0331] The server integrates the stored task data and data on the work equipment. It applies a dedicated matching algorithm to calculate the optimal combination, taking into account the required skills and priority of the task and the current task load of the work equipment. The calculation results in an optimal task allocation to the work equipment. This allocation result becomes the server's output data.

[0332] Step 7:

[0333] The server generates a notification of the task assignment result and sends it to the device (tablet). The device receives the notification and notifies the user that a new task has been assigned. The user can then check the notification content on the device.

[0334] Step 8:

[0335] The user (factory manager) uses a tablet to input task progress information. This includes detailed progress information such as the progress rate, progress during the task, and any problems. This data is input to the server. The server stores the received progress data in a database and updates the progress status in real time.

[0336] Step 9:

[0337] The server aggregates the saved progress data and displays it on a dashboard, allowing users to check the overall progress in real time. The dashboard visually displays the progress of each task.

[0338] The above are the specific processing steps of the system program that realizes the application example. This flow allows efficient real-time task management of work equipment in a factory.

[0339] 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.

[0340] The system of this invention uses a generative AI interface to visualize and classify tasks across the entire company and assign them appropriately to each employee. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, task allocation takes into account the emotional state of employees. This system is realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[0341] System Overview

[0342] The system provides the following main functions:

[0343] 1. Collecting and saving task data

[0344] 2. Classification and visualization of task data

[0345] 3. Collection and storage of employee data

[0346] 4. Matching tasks with employees

[0347] 5. Collecting and analyzing the user's emotional state

[0348] 6. Notification after task assignment

[0349] 7. Considering emotional states when assigning tasks

[0350] 8. Real-time management of task progress

[0351] What the program does

[0352] 1. Collecting and saving task data

[0353] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[0354] The server stores the received task data in a database.

[0355] 2. Classification and visualization of task data

[0356] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[0357] The server uses machine learning algorithms to categorize tasks.

[0358] The server displays the classified task data on a dashboard for the user to review.

[0359] 3. Collection and storage of employee data

[0360] A user (employee or manager) uses a terminal to enter individual data such as skill set, work history, and current task status.

[0361] The server stores the received employee data in a database.

[0362] 4. Collecting and analyzing the user's emotional state

[0363] The terminal transmits the emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user to the server via the emotion engine.

[0364] The server analyzes the received emotion data in real time and stores it in a database.

[0365] 5. Matching tasks with employees

[0366] The server integrates task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[0367] The server determines the optimal task-employee pair, for example, the task "market research" is assigned to employee X, while also taking into account employee X's emotional state.

[0368] 6. Notification after task assignment

[0369] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0370] The terminal receives the notification and informs the user that a task has been assigned to them.

[0371] 7. Real-time management of task progress

[0372] Users (employees) use terminals to input task progress in real time, and provide detailed reports on progress rates, progress during tasks, problems, etc.

[0373] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[0374] Specific examples

[0375] Example 1: New project task assignments

[0376] 1. Enter task data

[0377] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[0378] The server receives this task data and stores it in a database.

[0379] 2. Task categorization

[0380] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0381] The server displays the classification results on a dashboard.

[0382] 3. Enter employee data

[0383] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[0384] 4. Entering Emotion Data

[0385] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[0386] 5. Matching tasks with employees and considering their emotional state

[0387] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z, while taking into account the emotional state of the employees.

[0388] 6. Sending Notifications

[0389] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[0390] 7. Progress Management

[0391] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[0392] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[0393] This concludes the description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, achieving more appropriate task allocation by taking into account the emotional state of employees, and visualizing the overall progress of work in real time.

[0394] The processing flow will be explained below.

[0395] Step 1:

[0396] The user uses the terminal to input details of the new task, such as the title, description, deadline, priority, required skills, dependencies, etc. After completing the input, the terminal sends this data to the server.

[0397] Step 2:

[0398] The server receives task data sent from the terminal and stores it in a database. The server unifies the data format and complements and corrects missing or abnormal values.

[0399] Step 3:

[0400] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[0401] Step 4:

[0402] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[0403] Step 5:

[0404] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[0405] Step 6:

[0406] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[0407] Step 7:

[0408] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[0409] Step 8:

[0410] The user (employee) inputs their emotional state (e.g., stress level, fatigue level, motivation, etc.) into the terminal, which then transmits this emotional data to the server.

[0411] Step 9:

[0412] The server analyzes the emotional state data sent from the device using an emotion engine and generates analysis results in real time. The emotional data is stored in a database.

[0413] Step 10:

[0414] The server combines task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[0415] Step 11:

[0416] The server determines the optimal task-employee pair and assigns the task, for example, assigning the task "market research" to employee X, taking into account employee X's emotional state.

[0417] Step 12:

[0418] The server generates a notification to the employee who has been assigned a new task, including details about the task and its due date, and sends the notification to the device.

[0419] Step 13:

[0420] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. Notifications are delivered via pop-up messages, emails, or messaging apps.

[0421] Step 14:

[0422] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[0423] Step 15:

[0424] The terminal transmits the input progress data to the server.

[0425] Step 16:

[0426] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[0427] Step 17:

[0428] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[0429] Example 2

[0430] 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."

[0431] In corporate task management, it is important to appropriately assign tasks and track progress. However, conventional task management systems often struggle to assign tasks that take into account the emotional state of individual employees, resulting in inefficient work. Furthermore, insufficient task classification and visualization make it difficult to track overall work progress. The present invention aims to solve these problems and improve the efficiency of task management across the entire company.

[0432] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting task information, a means for classifying the collected task information using natural language processing and machine learning algorithms, a means for collecting employee information, a means for collecting and analyzing employee emotional states, a means for integrating the collected employee information and the task information classified with the emotional states using a matching algorithm, and a means for assigning tasks to the most suitable employee. This enables efficient classification, visualization, and assignment of tasks to appropriate employees, consideration of emotional states, and real-time progress management.

[0433] "Task information" refers to detailed information about specific work, such as the content of the work, deadlines, priorities, required skills, and dependencies.

[0434] "Natural language processing" refers to the technology that allows computers to analyze, understand, and appropriately process human language.

[0435] A "machine learning algorithm" refers to a computational method that allows a computer to learn on its own based on data and make predictions and classifications.

[0436] "Employee information" refers to detailed data about individual employees, such as their skill sets, work history, and current task status.

[0437] "Emotional state" refers to information that indicates an employee's psychological and emotional state, such as stress level, fatigue level, and motivation.

[0438] A "matching algorithm" refers to a computational method for determining the optimal task-employee pair based on collected task and employee information.

[0439] "Visualization means" refers to methods or tools for visually displaying data, typically in the form of a dashboard or similar.

[0440] "Communication methods" refer to the methods and tools used to communicate information about assigned tasks to employees.

[0441] "Progress" refers to information that indicates the progress of work, such as how much of a task has been completed or what problems have arisen along the way.

[0442] The system of the present invention uses AI to visualize and classify tasks within a company and appropriately assign them to employees, while also using an emotion engine to allocate tasks while taking into account the emotional state of employees. This system is realized through the cooperation of a server, terminals, and users. The system's program processing is explained below, along with specific examples.

[0443] System Program Processing

[0444] 1. Collecting and saving task information

[0445] The user inputs task information using a terminal, including details such as the specific task title, description, deadline, priority, required skills, and dependencies, and sends them to the server.

[0446] The terminal transmits this information to the server.

[0447] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[0448] 2. Classification and visualization of task information

[0449] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[0450] The server extracts important keywords and phrases and categorizes tasks using machine learning algorithms (e.g., k-means clustering).

[0451] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[0452] 3. Collection and storage of employee information

[0453] A user (employee or manager) uses a terminal to input information such as skill set, work history, and current task status.

[0454] The terminal transmits this information to the server.

[0455] The server stores the received employee information in a database.

[0456] 4. Collecting and analyzing employees' emotional states

[0457] The device collects emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user. The emotional state data is analyzed through an emotion engine (e.g., Microsoft® Azure® Emotion API).

[0458] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[0459] The server analyzes the received emotional data in real time and stores it in a database.

[0460] 5. Matching tasks with employees

[0461] The server integrates task information, employee information, and emotional state and applies a matching algorithm (e.g., linear regression model or decision tree).

[0462] The server determines the optimal task-employee pair.

[0463] 6. Notification after task assignment

[0464] The server generates a notification to the employee who has been newly assigned the task.

[0465] The terminal receives the notification and informs the user that a task has been assigned to them.

[0466] 7. Real-time management of task progress

[0467] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[0468] The device sends progress data to the server.

[0469] The server stores the received progress data in a database and updates the dashboard in real time.

[0470] Specific examples

[0471] Example 1: New project task assignments

[0472] Entering task information

[0473] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[0474] The server receives this task information and stores it in a database.

[0475] Task Classification

[0476] The server uses natural language processing to analyze the input task description and categorize "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0477] The server displays the classification results on a dashboard.

[0478] Entering employee information

[0479] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[0480] Entering emotion data

[0481] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[0482] Matching tasks and employees and considering their emotional state

[0483] The server runs a matching algorithm based on task information, employee information, and emotional state data, assigning, for example, "market research" to employee X, "prototype design" to employee Y, and "client meetings" to employee Z.

[0484] Sending notifications

[0485] The server generates the assignment results and sends notifications to the terminals, which then notify each employee that a new task has been assigned to them.

[0486] Progress Management

[0487] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[0488] The server displays the overall progress in real time on a dashboard and manages the status of tasks.

[0489] Prompt Sentence Examples

[0490] "Find an employee to handle market research. The skills needed are data analysis and market research experience."

[0491] "Select an employee to be tasked with designing a prototype. Their skill set should include design experience and 3D modeling. Also, consider their motivation and stress level."

[0492] "Select employees who can conduct client meetings effectively. Communication and presentation skills are essential. Also, check their emotional state."

[0493] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0494] Step 1: Collect and save task information

[0495] The user uses the device to input task information, including details such as the task title (e.g., "Market Research"), description (e.g., "Collect the latest market data"), deadline (e.g., "2023-10-31"), priority (e.g., "High"), required skills (e.g., "Data Analysis"), and dependencies.

[0496] The terminal transmits the input task information to the server.

[0497] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[0498] Input: Task information entered by the user.

[0499] Output: Saved task information.

[0500] Specific behavior:

[0501] The user enters task information into a web form on the device and clicks the "Submit" button.

[0502] The device sends an HTTP request to the server and provides task information.

[0503] The server executes an SQL query to store the task information in a database.

[0504] Step 2: Classifying and visualizing task information

[0505] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[0506] The server extracts important keywords and phrases from the task description.

[0507] The server classifies tasks into categories using machine learning algorithms (e.g., k-means clustering).

[0508] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[0509] Input: Saved task information.

[0510] Output: Categorized task information and a dashboard visualizing it.

[0511] Specific behavior:

[0512] The server retrieves the task description and performs NLP analysis using a Python script.

[0513] The server extracts keywords from the NLP analysis results and performs classification processing.

[0514] The server sends the classification results to the visualization tool's API and displays them on a dashboard.

[0515] Step 3: Collect and store employee information

[0516] The user (employee or manager) uses the terminal to enter their skill set (e.g., "data analysis skills"), work history (e.g., "5 years of market research experience"), current task status (e.g., "current task: none"), etc.

[0517] The terminal transmits the entered employee information to the server.

[0518] The server stores the received employee information in a database.

[0519] Input: Employee information entered by the user.

[0520] Output: Saved employee information.

[0521] Specific behavior:

[0522] The user enters employee information into the form on the terminal and clicks the "Submit" button.

[0523] The device sends an HTTP request to the server, providing employee information.

[0524] The server executes the SQL query to save the employee information to the database.

[0525] Step 4: Collect and analyze employee emotional states

[0526] The device collects emotional state data entered by the user (e.g., "Stress level: high," "Motivation: low"), which is then analyzed through an emotion engine (e.g., Microsoft Azure's Emotion API).

[0527] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[0528] The server analyzes the received emotion data in real time and stores it in a database.

[0529] Input: Emotional state data entered by the user.

[0530] Output: Parsed emotion data and stored emotion data.

[0531] Specific behavior:

[0532] The user inputs the emotional state into the terminal and clicks the "send" button.

[0533] The device calls the emotion engine's API and analyzes the data.

[0534] The device sends the analysis results to the server, which stores them in a database.

[0535] Step 5: Matching tasks with employees

[0536] The server integrates task information, employee information, and emotional state data and applies a matching algorithm (e.g., linear regression model or decision tree).

[0537] The server determines the optimal task-employee pair.

[0538] Input: Task information, employee information, emotional state data.

[0539] Output: Optimal task-employee pairs.

[0540] Specific behavior:

[0541] The server retrieves task information, employee information, and emotional state data, and runs a matching algorithm using Python's scikit-learn library.

[0542] The server makes a decision as a matching result, for example, to assign "market research" to employee X.

[0543] Step 6: Notification after task assignment

[0544] The server generates a notification to the employee who has been newly assigned the task.

[0545] The terminal receives the notification and informs the user that a task has been assigned to them.

[0546] Input: Task assignment results.

[0547] Output: Notify employee.

[0548] Specific behavior:

[0549] The server generates a notification saying "Market research task assigned to employee X."

[0550] The device receives the notification and displays a pop-up message on the screen to notify the user.

[0551] Step 7: Real-time task progress management

[0552] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[0553] The device sends progress data to the server.

[0554] The server stores the received progress data in a database and updates the dashboard in real time.

[0555] Input: Task progress entered by the user.

[0556] Output: Updated progress data and a dashboard displayed in real time.

[0557] Specific behavior:

[0558] The user enters "Market research task progress: 50% complete, no problems" into the terminal and clicks the "Submit" button.

[0559] The device sends progress data to the server.

[0560] The server runs SQL queries to store progress data in a database and updates the dashboard in real time.

[0561] (Application example 2)

[0562] 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."

[0563] In recent years, the widespread adoption of autonomous vehicles has created a need for efficient management of a wide range of tasks, including vehicle charging, maintenance, and route management. However, appropriately assigning these tasks to employees and managing their progress in real time is complex and can lead to human error and reduced efficiency. Furthermore, task assignment without considering employees' emotional states can have a negative impact on work quality and efficiency. Therefore, there is a need for a system that efficiently assigns tasks and manages their progress while taking into account employees' skill sets and emotional states in autonomous vehicle task management.

[0564] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm, means for assigning tasks to the most suitable employee, means for notifying the assignment results, means for collecting and updating progress status, means for collecting task data of autonomous vehicles and classifying them into categories such as charging and maintenance, and means for analyzing the emotional states of employees and taking this into consideration when assigning tasks. This makes it possible to efficiently manage tasks for autonomous vehicles while taking into account the skill sets and emotional states of employees, and to visualize and manage progress status in real time.

[0565] "Task data" refers to data that includes various information required for work or tasks, and specifically includes task titles, descriptions, deadlines, priorities, required skills, and dependencies.

[0566] "Natural language processing" refers to the technology that allows computers to understand, generate, and analyze human language, extracting keywords and important phrases, and classifying data.

[0567] A "machine learning algorithm" is an algorithm that allows a computer to learn patterns from data and make predictions or classifications based on those patterns.

[0568] "Visualization" refers to a method of visually displaying data or information, for example, by using graphs or dashboards to make the information easy to understand.

[0569] "Employee Data" includes individual data such as an employee's skill set, work history, and current task status.

[0570] "Matching algorithm" refers to an algorithm that performs optimal pairing or matching based on collected data.

[0571] "Assignment" refers to the act of giving a specific task to a specific employee.

[0572] "Notification" refers to a message or alert that notifies the user of the existence of newly generated information or tasks.

[0573] "Progress" is information that indicates the degree of progress or completion status of a task at a certain point in time.

[0574] An "autonomous vehicle" is a vehicle that operates by its own self-control mechanism without the need for a human driver.

[0575] "Charging" refers to the process of powering an electric vehicle or other electrically powered device.

[0576] "Maintenance" refers to work such as inspection, adjustment, and repair to keep systems and equipment operating normally and prevent breakdowns and deterioration.

[0577] "Emotional state" is data that indicates the user's psychological and emotional condition, such as stress level, fatigue level, and motivation.

[0578] The system of the present invention streamlines task management for autonomous vehicles and optimally assigns tasks to employees, taking into account their skill sets and emotional states. The system comprehensively supports a series of processes, from collecting task data to managing progress.

[0579] System Configuration

[0580] Hardware and Software

[0581] This system is realized through the cooperation of servers, terminals, and users, and uses the following hardware and software.

[0582] Server: Collects and stores task and employee data, and runs natural language processing (NLP) and machine learning algorithms.

[0583] Terminal: A device such as a smartphone or tablet where a user enters and checks data.

[0584] Software: Server-side processing is implemented using Python and Django, and React and Vue.js are used for the front end.

[0585] Natural Language Processing: Use NLTK and spaCy to analyze task descriptions.

[0586] Machine learning algorithms: Data classification and predictions are performed using scikit-learn and TensorFlow.

[0587] Program processing description

[0588] 1. Collecting task data

[0589] The user (administrator) uses a terminal to input detailed task information. Specifically, data such as the task title, description, deadline, priority, required skills, and dependencies is sent to the server. The server then stores each piece of task data in a database.

[0590] 2. Task Data Analysis and Classification

[0591] The server analyzes the collected task data using natural language processing (NLP) to extract important keywords and phrases. It then uses machine learning algorithms to classify tasks into categories such as "charging" and "maintenance." The classification results are visually displayed through a dashboard.

[0592] 3. Employee Data Collection

[0593] Users (engineers) input data such as their skill sets, work history, and current task status through their terminals. The server stores this data in a database.

[0594] 4. Collecting and analyzing emotional states

[0595] The device acquires emotional data (e.g., stress level, fatigue level, motivation, etc.) entered by the user via an emotion engine and sends it to the server, which analyzes the emotional data in real time and stores it in a database.

[0596] 5. Task matching and assignment

[0597] The server integrates the collected task data, employee data, and emotional data and applies a matching algorithm that determines the optimal task-employee pairing, taking into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[0598] 6. Task assignment notifications

[0599] The server generates a notification for the employee who has been assigned a new task and sends it to the device, including the task details and deadline.

[0600] 7. Real-time progress management

[0601] Users (engineers) use their own devices to input the progress of tasks in real time. The server stores the received progress data in a database and visualizes the overall progress through a dashboard.

[0602] Examples of concrete examples and prompts

[0603] Specific examples

[0604] For example, a European city managing autonomous taxis could use the system to assign tasks to technicians who are responsible for charging vehicles when their batteries get low.

[0605] Prompt Sentence Examples

[0606] "Taking into account the suitability of technicians based on emotional data and assigning charging tasks to autonomous taxis with low battery levels."

[0607] The above is a description of an embodiment of the present invention. By using this system, task management for autonomous vehicles can be made more efficient and appropriate task allocation can be achieved taking into account the emotional state of employees.

[0608] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0609] Step 1:

[0610] Task data collection:

[0611] The user (administrator) uses a terminal to input detailed task information and send it to the server. This task data includes the task title, description, deadline, priority, required skills, and dependencies. The server stores this data in a database. The input is the task information that the user inputs into the terminal, and the output is the task data stored in the server's database.

[0612] Step 2:

[0613] Task data analysis and classification:

[0614] The server analyzes the collected task data using natural language processing (NLP) to extract important keywords and phrases. It then uses machine learning algorithms to classify the tasks into categories such as "charging" and "maintenance." The input is the collected task data, and the output is the task data classified by category.

[0615] Step 3:

[0616] Visualizing task data:

[0617] The server displays the classified task data on a dashboard so that the user can easily check it. The input is the classified task data, and the output is the task information displayed on the dashboard. Specifically, the server generates a web page using HTML and JavaScript (registered trademark) to visually display the task data.

[0618] Step 4:

[0619] Employee Data Collection:

[0620] Users (engineers) input their skill sets, work history, and current task status through their terminals. The server stores this data in a database. The input is the employee information that the user enters into the terminal, and the output is the employee data stored in the server's database.

[0621] Step 5:

[0622] Collecting and analyzing emotional states:

[0623] The device acquires emotional data (stress level, fatigue level, motivation, etc.) entered by the user via an emotion engine and sends it to a server. The server analyzes this data in real time and stores it in a database. The input is data that represents the emotional state, and the output is the analyzed emotional data. Specifically, the server uses the emotion engine to analyze the numerical data and evaluate the emotional state.

[0624] Step 6:

[0625] Matching tasks and employees:

[0626] The server integrates the collected task data, employee data, and emotional data and applies a matching algorithm to determine the optimal task-employee pair. This algorithm takes into account required skills, priority, current task load, and emotional state. The inputs are task data, employee data, and emotional data, and the output is the optimal task-employee pair. Specifically, the server uses a scoring system to select the optimal pair.

[0627] Step 7:

[0628] Task assignment notification:

[0629] The server creates a notification for an employee who has been assigned a new task and sends it to the employee's device. The notification includes detailed task information and a deadline. The input is the assigned task information, and the output is a notification that is displayed on the employee's device. Specifically, the server generates a notification message and sends a push notification to the device.

[0630] Step 8:

[0631] Real-time progress management:

[0632] The user (engineer) uses their own device to input the progress status of the task and sends it to the server. The server saves this progress data in a database and visualizes the overall progress status through a dashboard. The input is the progress data entered by the engineer, and the output is the progress status displayed on the dashboard. In concrete terms, the server processes the real-time data and updates the progress status.

[0633] Through these steps, the system of the present invention achieves efficient task management and task allocation that takes into account the emotional state of employees.

[0634] 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.

[0635] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0636] 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.

[0637] [Second embodiment]

[0638] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0639] 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.

[0640] 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).

[0641] 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.

[0642] 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.

[0643] 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).

[0644] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] 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."

[0650] The system of this invention uses AI to visualize and classify tasks across the entire company and appropriately assign them to each employee, using a generative AI interface. This system can be realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[0651] System Overview

[0652] The system provides the following main functions:

[0653] 1. Collecting and saving task data

[0654] 2. Classification and visualization of task data

[0655] 3. Collection and storage of employee data

[0656] 4. Matching tasks with employees

[0657] 5. Notification after task assignment

[0658] 6. Real-time management of task progress

[0659] What the program does

[0660] 1. Collecting and saving task data

[0661] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[0662] The server stores the received task data in a database.

[0663] 2. Classification and visualization of task data

[0664] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[0665] The server uses machine learning algorithms to categorize tasks.

[0666] The server displays the classified task data on a dashboard for the user to review.

[0667] 3. Collection and storage of employee data

[0668] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[0669] The server stores the received employee data in a database.

[0670] 4. Matching tasks with employees

[0671] The server combines task data with employee data and applies a matching algorithm that takes into account the required skills and priority of the task, the employee's skill set, and their current task load to calculate the optimal match.

[0672] The server determines the optimal task-employee pair and assigns the task to the corresponding employee.

[0673] 5. Notification after task assignment

[0674] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0675] The terminal receives the notification and informs the user that a task has been assigned to them.

[0676] 6. Real-time management of task progress

[0677] Users (employees) use terminals to input task progress in real time, reporting progress rates, task progress, problems, etc.

[0678] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[0679] Specific examples

[0680] Example 1: New project task assignments

[0681] 1. Enter task data

[0682] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[0683] The server receives this task data and stores it in a database.

[0684] 2. Task categorization

[0685] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0686] The server displays the classification results on a dashboard.

[0687] 3. Enter employee data

[0688] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[0689] 4. Matching tasks with employees

[0690] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[0691] 5. Sending notifications

[0692] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[0693] 6. Progress Management

[0694] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[0695] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[0696] The above is a description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, and visualizing the overall progress of work in real time.

[0697] The processing flow will be explained below.

[0698] Step 1:

[0699] The user uses the terminal to input the details of a new task (title, description, deadline, priority, required skills, dependencies, etc.) After completing the input, the terminal sends this data to the server.

[0700] Step 2:

[0701] The server receives task data sent from the device and stores it in a database. The format of the task data is standardized, and missing or abnormal values ​​are complemented and corrected.

[0702] Step 3:

[0703] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[0704] Step 4:

[0705] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[0706] Step 5:

[0707] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[0708] Step 6:

[0709] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[0710] Step 7:

[0711] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[0712] Step 8:

[0713] The server merges the task data with the employee data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, and their current task load.

[0714] Step 9:

[0715] The server uses a matching algorithm to determine the best task-employee pair, e.g., task "market research" is assigned to employee X.

[0716] Step 10:

[0717] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0718] Step 11:

[0719] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. The notifications are delivered via a pop-up message, email, or messaging app.

[0720] Step 12:

[0721] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[0722] Step 13:

[0723] The terminal transmits the input progress data to the server.

[0724] Step 14:

[0725] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[0726] Step 15:

[0727] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[0728] The above are the specific processing steps of the system of the present invention. This system has the effect of improving the efficiency of task management within a company, reducing human error, and visualizing the overall progress of work in real time.

[0729] Example 1

[0730] 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."

[0731] In modern companies, effectively managing diverse tasks and assigning them to the right employees is extremely difficult. Especially in large organizations, manual task assignment requires a tremendous amount of time and effort due to the complexity of tasks and the diversity of employees. Furthermore, improper task assignment can lead to reduced work efficiency and disrupted employee workloads. Furthermore, manually tracking the progress of tasks across the company in real time is difficult, making an appropriate task management system essential to prevent project delays and errors.

[0732] 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.

[0733] In this invention, the server includes means for collecting task data, means for analyzing the collected task data using natural language processing and machine learning algorithms and extracting keywords and important phrases, means for classifying the task data using the extracted data, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm and calculating the optimal combination taking into account the required skills of the task, priority, employee skill sets, and task load, means for assigning tasks to the optimal employee, means for notifying the assignment results, and means for collecting progress status in real time, storing it in a database, and displaying it on a dashboard, thereby enabling efficient task management and visualization of progress status in real time.

[0734] "Task data" refers to data that includes detailed information related to a task, such as a title, description, deadline, priority, required skills, and dependencies.

[0735] "Natural language processing" is the technology used by computers to understand, analyze, and generate human language.

[0736] A "machine learning algorithm" is an algorithm that learns patterns from data and uses that knowledge to make decisions and predictions based on new data.

[0737] "Keywords" refer to important words or concepts extracted from documents or text data.

[0738] An "important phrase" is a series of words in text data that are particularly important in terms of meaning or content.

[0739] "Classification" is the process of sorting data into categories or groups based on certain criteria.

[0740] "Visualization" refers to the presentation of data or information using visual representations such as graphs and diagrams.

[0741] "Employee data" is data that includes information such as an employee's skill set, work history, and current task status.

[0742] A "matching algorithm" refers to a method or calculation procedure for finding the optimal combination between multiple elements.

[0743] "Progress" is information that indicates the current degree of achievement or completion of a task or project.

[0744] "Real-time" refers to immediate updates or processing at the current moment or time.

[0745] A "dashboard" is an interface or tool that displays various data and information in a centralized manner, making it easier for administrators to grasp the situation.

[0746] The system of the present invention is designed to improve the efficiency of task management within a company, and is realized through the cooperation of a server, terminals, and users. The processing of the system program will be specifically described below.

[0747] System configuration and functions

[0748] The system provides the following main functions:

[0749] 1. Collecting and saving task data

[0750] A user uses a terminal to enter task data, including details such as the task title, description, deadline, priority, required skills, and dependencies.

[0751] The device sends this task data to the server using an encrypted communication protocol (e.g., HTTPS).

[0752] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[0753] 2. Task Data Analysis and Classification

[0754] The server analyzes the saved task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) to extract keywords and important phrases.

[0755] The server uses machine learning algorithms (e.g., K-means clustering or support vector machines) to classify tasks into categories.

[0756] The server displays the classified task data on a web dashboard (e.g., Grafana or Tableau) for easy user review.

[0757] 3. Collection and storage of employee data

[0758] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[0759] The terminal transmits the entered employee data to the server.

[0760] The server stores the received employee data in a database.

[0761] 4. Matching tasks with employees

[0762] The server combines task data with employee data and applies a matching algorithm (e.g., a recommendation system) that takes into account the task's required skills, priority, employee skill set, and current task load to calculate the optimal match.

[0763] The server determines the optimal task-employee pair, assigns the corresponding task to the appropriate employee, and records this information in a database.

[0764] 5. Notification after task assignment

[0765] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0766] The terminal receives this notification and informs the user that a task has been assigned to him.

[0767] 6. Real-time management of task progress

[0768] Users (employees) use their own devices to input task progress in real time, reporting progress rates, progress during tasks, problems, etc.

[0769] The terminal transmits the input progress information to the server.

[0770] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[0771] Example: Assigning tasks to a new project

[0772] Example 1: Task assignment for Project "A"

[0773] 1. Enter task data

[0774] The user (project manager) uses a terminal to input the tasks for project "A": "market research," "prototype design," and "client meeting."

[0775] The terminal transmits these task data to the server, which stores the received data in a database.

[0776] 2. Task categorization

[0777] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0778] The server displays the classification results on a dashboard.

[0779] 3. Enter employee data

[0780] Users (employees X, Y, Z) enter their skill sets and work history into a terminal, which then sends it to the server.

[0781] The server stores the received data in a database.

[0782] 4. Matching tasks with employees

[0783] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[0784] 5. Sending notifications

[0785] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[0786] 6. Progress Management

[0787] Users (employees X, Y, and Z) use their own terminals to input the progress of their tasks, and the terminals send the progress data to the server.

[0788] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing users to grasp the overall progress status in real time.

[0789] Example of generative AI model and prompt

[0790] The system uses a generative AI model to match tasks with employees. Here are some example prompts:

[0791] Prompt Sentence Examples

[0792] "A new task has been created. The task title is 'Market Research' and the required skill is 'Data Analysis'. Please assign an employee with the relevant skills."

[0793] The above is a specific description of the embodiment of the invention.

[0794] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0795] Step 1: Enter task data

[0796] A user (e.g., a project manager) uses a terminal to enter task information (title, description, deadline, priority, required skills, dependencies, etc.) into the system. Task data is entered using a web form.

[0797] Inputs: Task title, task description, due date, priority, required skills, dependencies.

[0798] How it works: The terminal receives input data from the user and verifies the data integrity, for example, whether deadlines are entered in the correct format, whether required skills follow the list format, etc.

[0799] Output: The validated task data.

[0800] Step 2: Sending task data

[0801] The device sends the verified task data to the server using an encrypted protocol (e.g., HTTPS).

[0802] Input: Validated task data.

[0803] How it works: The device sends task data to the server using the HTTPS protocol.

[0804] Output: The task data sent to the server.

[0805] Step 3: Save the task data

[0806] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[0807] Input: The submitted task data.

[0808] What it does: The server opens a database connection and saves the task data, generating a unique task ID and recording it along with the data.

[0809] Output: Task data stored in the database (including task ID).

[0810] Step 4: Analyzing task data

[0811] The server analyzes the stored task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) libraries to extract keywords and important phrases.

[0812] Input: Saved task data.

[0813] How it works: It uses an NLP library to tokenize (break down) a task description into words and extract important keywords and phrases, such as the phrase "market research."

[0814] Output: Extracted keywords and key phrases.

[0815] Step 5: Classify task data

[0816] The server categorizes tasks based on the extracted keywords and phrases using machine learning algorithms (e.g., K-means clustering and support vector machines).

[0817] Input: Extracted keywords and key phrases.

[0818] How it works: Using a machine learning algorithm, the system classifies a task, for example "market research," into the "research" category, assigns a category label, and updates the results to the database.

[0819] Output: Classification results (task data including category labels).

[0820] Step 6: Visualize task data

[0821] The server prepares the classified task data for display on a web dashboard (e.g., Grafana or Tableau).

[0822] Input: Classified task data.

[0823] Action: The data is converted into a format specified by the visualization tool and displayed on a dashboard. For example, tasks in the "Investigation" category are displayed as a bar graph.

[0824] Output: A visualized dashboard.

[0825] Step 7: Enter employee data

[0826] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[0827] Inputs: Skill set, work history, current task status.

[0828] How it works: The terminal receives employee data and verifies data integrity, e.g., that skill sets are entered in the proper format.

[0829] Output: Validated employee data.

[0830] Step 8: Submit employee data

[0831] The terminal transmits the verified employee data to the server.

[0832] Input: Validated employee data.

[0833] How it works: The device sends employee data to the server using the HTTPS protocol.

[0834] Output: Employee data sent to the server.

[0835] Step 9: Save employee data

[0836] The server stores the received employee data in a database.

[0837] Input: Submitted employee data.

[0838] What happens: The server opens a database connection and saves the employee data, generating a unique employee ID and recording it along with the data.

[0839] Output: Employee data stored in the database, including employee ID.

[0840] Step 10: Applying the matching algorithm

[0841] The server combines the task data with the employee data and applies a matching algorithm (e.g., a recommendation system).

[0842] Input: Classified task data, saved employee data.

[0843] How it works: Calculate the optimal combination by taking into account the required skills of the task, priority, employee skill sets, current task load, etc. For example, use a recommendation system to select employee X who is best suited for the task "market research."

[0844] Output: Matching results (task-employee pairs).

[0845] Step 11: Assign tasks

[0846] The server determines the best task-employee pair and updates the task record in the database.

[0847] Input: Matching results.

[0848] What it does: Accesses the database and updates the task record, recording the ID of the assigned employee and changing the task state to "Assigned."

[0849] Output: The updated task record.

[0850] Step 12: Generate notifications

[0851] The server generates a notification to the employee who has been newly assigned the task.

[0852] Input: The updated task record.

[0853] What it does: Triggers the notification mechanism and generates a notification containing task details and deadlines.

[0854] Output: The generated notification.

[0855] Step 13: Sending notifications

[0856] The server sends the generated notification to the terminal, which receives the notification and displays it to the user.

[0857] Input: The generated notification.

[0858] How it works: The server sends notifications to the device via email or push notification. The device receives the notifications and notifies the user via a screen display or audio alarm.

[0859] Output: The notification displayed to the user.

[0860] Step 14: Enter your progress

[0861] Users (employees) use their own devices to input task progress in real time.

[0862] Input: Progress data (progress rate, progress, issues, etc.).

[0863] Action: The user enters progress data, and the terminal verifies the data integrity, e.g., checks that the progress rate is within the range 0-100%.

[0864] Output: Progress data of the completed validation.

[0865] Step 15: Sending progress data

[0866] The terminal transmits progress information indicating that the verification has been completed to the server.

[0867] Input: Verified progress data.

[0868] How it works: The device sends progress data to the server using the HTTPS protocol.

[0869] Output: Progress data sent to the server.

[0870] Step 16: Saving and Counting Progress Data

[0871] The server stores the received progress data in a database and aggregates the progress status.

[0872] Input: The progress data submitted.

[0873] What it does: The server opens a database connection, stores the progress data, and performs aggregations, such as calculating the overall progress of tasks and assessing the overall progress of the project.

[0874] Output: Aggregated progress data in a database.

[0875] Step 17: View progress on a dashboard

[0876] The server displays the aggregated progress data on a dashboard (e.g., Grafana or Tableau).

[0877] Input: Aggregated progress data.

[0878] How it works: The server converts the data into a format required by the visualization tool and displays it on a dashboard, such as a pie chart or bar graph showing the progress of a project.

[0879] Output: Progress displayed in a visualized dashboard.

[0880] This enables consistent system processing from collecting task data and employee data to assigning tasks and managing progress, making task management within a company more efficient.

[0881] (Application example 1)

[0882] 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."

[0883] In factories, many work devices (e.g., robots) are operating simultaneously, and there is a need to improve the efficiency and optimization of work. However, in current systems, tasks are often assigned to each work device manually, which leads to problems such as human error and complicated task management. In addition, it is difficult to manage progress in real time, which is a cause of reduced overall work efficiency.

[0884] 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.

[0885] In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting data on maintenance devices, means for integrating the collected data on maintenance devices and the classified task data using a matching algorithm, means for assigning tasks to the most appropriate maintenance device, means for notifying the assignment results, and means for collecting and updating progress status, thereby enabling automatic assignment of tasks to each maintenance device and real-time progress management.

[0886] "Task data" is data that contains information about a particular task or project.

[0887] "Natural language processing" is a technology that allows computers to understand and process natural language used by humans.

[0888] A "machine learning algorithm" is a computational method for learning patterns from data and making predictions and classifications.

[0889] "Visualization" is a method of visually displaying data and information to make it easier to understand.

[0890] "Work equipment" refers to automated machines, robots, and other equipment used in factories and work sites.

[0891] A "matching algorithm" is a computational method for finding optimal pairings based on specific criteria.

[0892] "Assignment" is the act of distributing a specific task to a corresponding work device or person.

[0893] "Notification" is the act or system of informing interested parties of important information or updates.

[0894] "Progress" is information that indicates how far a task or project has progressed.

[0895] "Collection methods" are the methods and techniques used to gather the necessary data and information.

[0896] "Integration means" are methods and technologies that bring together different data and systems to make them usable.

[0897] This invention is a system for streamlining task management for work equipment in a factory, and is realized through the cooperation of a server, terminals, and users. This system provides the following main functions: collecting and saving task data, classifying and visualizing task data, collecting and saving data on work equipment, matching tasks with work equipment, notifying users after task assignment, and managing task progress in real time.

[0898] Hardware and Software Configuration

[0899] 1. Hardware: Servers, tablets, factory robots.

[0900] 2. Software: Python (backend), Django (web framework), NLP library (e.g. spaCy), machine learning library (e.g. TensorFlow), database (e.g. PostgreSQL), dashboard tool (e.g. Grafana).

[0901] Program processing and natural language explanation

[0902] Collecting and storing task data

[0903] A user (factory manager) uses a tablet to input information about a specific task or project, including the task title, description, deadline, priority, required skills, and dependencies. The server receives this task data and stores it in a database.

[0904] Classifying and visualizing task data

[0905] The server analyzes the received task data using natural language processing (NLP) to extract keywords and important phrases. It then uses machine learning algorithms to categorize the tasks. The results are then visualized on a dashboard for users to review.

[0906] Work equipment data collection and storage

[0907] The user (factory manager) uses a tablet to input the capabilities, current operating status, and skill set of each work device (factory robot). The server receives this data on the work device and stores it in a database.

[0908] Matching tasks and work equipment

[0909] The server combines the task data and the work equipment data and applies a matching algorithm that takes into account the required skills and priorities of the tasks and the current task load of the work equipment to calculate the optimal combination. The optimal work equipment is then assigned to the task.

[0910] Notification after task assignment

[0911] The server generates a notification for the manager of the work device to which the new task has been assigned and sends it to the tablet. The notification includes detailed information about the task and its deadline, and the device receives it to inform the user that a task has been assigned to them.

[0912] Real-time management of task progress

[0913] The user (factory manager) uses a tablet to input task progress status in real time. Progress rates, task progress, problems, etc. are reported, and the server receives, stores, and aggregates this data. The server displays the overall progress status on a dashboard and manages the situation in real time.

[0914] Specific examples

[0915] Prompt Sentence Examples

[0916] Task data input prompt example

[0917] Enter the following task:

[0918] 1. Task title: Inspection work

[0919] 2. Task Description: Inspect product X

[0920] 3. Deadline: 2023-12-01

[0921] 4. Priority: High

[0922] 5. Required Skills: Inspection

[0923] Example of a progress report prompt

[0924] Progress Report:

[0925] 1. Task title: Inspection work

[0926] 2. Progress: 50%

[0927] 3. Current status: Under testing

[0928] 4. Issues: None

[0929] As described above, this system enables efficient task management of work equipment within a factory. Users can easily input task data and progress status via tablet, and the server compiles, analyzes, and visualizes the data, achieving work efficiency and real-time management.

[0930] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0931] Step 1:

[0932] The user (factory manager) uses a tablet to input task data. Detailed information such as the task title, description, deadline, priority, required skills, and dependencies are entered into the tablet. This becomes the input data to the server. The server stores this input data in a database.

[0933] Step 2:

[0934] The server analyzes the stored task data using natural language processing (NLP). Keywords and important phrases are extracted from the task data. The extracted keywords become the output data of the NLP process.

[0935] Step 3:

[0936] The server uses a machine learning algorithm to classify tasks based on the extracted keywords and phrases, generates classified task data, and stores the results in a database. The classification results become the server's output data.

[0937] Step 4:

[0938] The server displays the classified task data on a dashboard. The visualized task data is output to the screen of a display device (e.g., a tablet or PC). Through this dashboard, users can check the task classification results in real time.

[0939] Step 5:

[0940] The user (factory manager) uses a tablet to input data for each work tool (capabilities, skill set, current operating status). This data is input to the server, which then stores the received work tool data in a database.

[0941] Step 6:

[0942] The server integrates the stored task data and data on the work equipment. It applies a dedicated matching algorithm to calculate the optimal combination, taking into account the required skills and priority of the task and the current task load of the work equipment. The calculation results in an optimal task allocation to the work equipment. This allocation result becomes the server's output data.

[0943] Step 7:

[0944] The server generates a notification of the task assignment result and sends it to the device (tablet). The device receives the notification and notifies the user that a new task has been assigned. The user can then check the notification content on the device.

[0945] Step 8:

[0946] The user (factory manager) uses a tablet to input task progress information. This includes detailed progress information such as the progress rate, progress during the task, and any problems. This data is input to the server. The server stores the received progress data in a database and updates the progress status in real time.

[0947] Step 9:

[0948] The server aggregates the saved progress data and displays it on a dashboard, allowing users to check the overall progress in real time. The dashboard visually displays the progress of each task.

[0949] The above are the specific processing steps of the system program that realizes the application example. This flow allows efficient real-time task management of work equipment in a factory.

[0950] 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.

[0951] The system of this invention uses a generative AI interface to visualize and classify tasks across the entire company and assign them appropriately to each employee. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, task allocation takes into account the emotional state of employees. This system is realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[0952] System Overview

[0953] The system provides the following main functions:

[0954] 1. Collecting and saving task data

[0955] 2. Classification and visualization of task data

[0956] 3. Collection and storage of employee data

[0957] 4. Matching tasks with employees

[0958] 5. Collecting and analyzing the user's emotional state

[0959] 6. Notification after task assignment

[0960] 7. Considering emotional states when assigning tasks

[0961] 8. Real-time management of task progress

[0962] What the program does

[0963] 1. Collecting and saving task data

[0964] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[0965] The server stores the received task data in a database.

[0966] 2. Classification and visualization of task data

[0967] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[0968] The server uses machine learning algorithms to categorize tasks.

[0969] The server displays the classified task data on a dashboard for the user to review.

[0970] 3. Collection and storage of employee data

[0971] A user (employee or manager) uses a terminal to enter individual data such as skill set, work history, and current task status.

[0972] The server stores the received employee data in a database.

[0973] 4. Collecting and analyzing the user's emotional state

[0974] The terminal transmits the emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user to the server via the emotion engine.

[0975] The server analyzes the received emotion data in real time and stores it in a database.

[0976] 5. Matching tasks with employees

[0977] The server integrates task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[0978] The server determines the optimal task-employee pair, for example, the task "market research" is assigned to employee X, while also taking into account employee X's emotional state.

[0979] 6. Notification after task assignment

[0980] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[0981] The terminal receives the notification and informs the user that a task has been assigned to them.

[0982] 7. Real-time management of task progress

[0983] Users (employees) use terminals to input task progress in real time, and provide detailed reports on progress rates, progress during tasks, problems, etc.

[0984] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[0985] Specific examples

[0986] Example 1: New project task assignments

[0987] 1. Enter task data

[0988] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[0989] The server receives this task data and stores it in a database.

[0990] 2. Task categorization

[0991] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[0992] The server displays the classification results on a dashboard.

[0993] 3. Enter employee data

[0994] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[0995] 4. Entering Emotion Data

[0996] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[0997] 5. Matching tasks with employees and considering their emotional state

[0998] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z, while taking into account the emotional state of the employees.

[0999] 6. Sending Notifications

[1000] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[1001] 7. Progress Management

[1002] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[1003] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[1004] This concludes the description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, achieving more appropriate task allocation by taking into account the emotional state of employees, and visualizing the overall progress of work in real time.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user uses the terminal to input details of the new task, such as the title, description, deadline, priority, required skills, dependencies, etc. After completing the input, the terminal sends this data to the server.

[1008] Step 2:

[1009] The server receives task data sent from the terminal and stores it in a database. The server unifies the data format and complements and corrects missing or abnormal values.

[1010] Step 3:

[1011] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[1012] Step 4:

[1013] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[1014] Step 5:

[1015] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[1016] Step 6:

[1017] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[1018] Step 7:

[1019] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[1020] Step 8:

[1021] The user (employee) inputs their emotional state (e.g., stress level, fatigue level, motivation, etc.) into the terminal, which then transmits this emotional data to the server.

[1022] Step 9:

[1023] The server analyzes the emotional state data sent from the device using an emotion engine and generates analysis results in real time. The emotional data is stored in a database.

[1024] Step 10:

[1025] The server combines task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[1026] Step 11:

[1027] The server determines the optimal task-employee pair and assigns the task, for example, assigning the task "market research" to employee X, taking into account employee X's emotional state.

[1028] Step 12:

[1029] The server generates a notification to the employee who has been assigned a new task, including details about the task and its due date, and sends the notification to the device.

[1030] Step 13:

[1031] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. Notifications are delivered via pop-up messages, emails, or messaging apps.

[1032] Step 14:

[1033] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[1034] Step 15:

[1035] The terminal transmits the input progress data to the server.

[1036] Step 16:

[1037] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[1038] Step 17:

[1039] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[1040] Example 2

[1041] 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."

[1042] In corporate task management, it is important to appropriately assign tasks and track progress. However, conventional task management systems often struggle to assign tasks that take into account the emotional state of individual employees, resulting in inefficient work. Furthermore, insufficient task classification and visualization make it difficult to track overall work progress. The present invention aims to solve these problems and improve the efficiency of task management across the entire company.

[1043] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting task information, a means for classifying the collected task information using natural language processing and machine learning algorithms, a means for collecting employee information, a means for collecting and analyzing employee emotional states, a means for integrating the collected employee information and the task information classified with the emotional states using a matching algorithm, and a means for assigning tasks to the most suitable employee. This enables efficient classification, visualization, and assignment of tasks to appropriate employees, consideration of emotional states, and real-time progress management.

[1044] "Task information" refers to detailed information about specific work, such as the content of the work, deadlines, priorities, required skills, and dependencies.

[1045] "Natural language processing" refers to the technology that allows computers to analyze, understand, and appropriately process human language.

[1046] A "machine learning algorithm" refers to a computational method that allows a computer to learn on its own based on data and make predictions and classifications.

[1047] "Employee information" refers to detailed data about individual employees, such as their skill sets, work history, and current task status.

[1048] "Emotional state" refers to information that indicates an employee's psychological and emotional state, such as stress level, fatigue level, and motivation.

[1049] A "matching algorithm" refers to a computational method for determining the optimal task-employee pair based on collected task and employee information.

[1050] "Visualization means" refers to methods or tools for visually displaying data, typically in the form of a dashboard or similar.

[1051] "Communication methods" refer to the methods and tools used to communicate information about assigned tasks to employees.

[1052] "Progress" refers to information that indicates the progress of work, such as how much of a task has been completed or what problems have arisen along the way.

[1053] The system of the present invention uses AI to visualize and classify tasks within a company and appropriately assign them to employees, while also using an emotion engine to allocate tasks while taking into account the emotional state of employees. This system is realized through the cooperation of a server, terminals, and users. The system's program processing is explained below, along with specific examples.

[1054] System Program Processing

[1055] 1. Collecting and saving task information

[1056] The user inputs task information using a terminal, including details such as the specific task title, description, deadline, priority, required skills, and dependencies, and sends them to the server.

[1057] The terminal transmits this information to the server.

[1058] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[1059] 2. Classification and visualization of task information

[1060] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[1061] The server extracts important keywords and phrases and categorizes tasks using machine learning algorithms (e.g., k-means clustering).

[1062] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[1063] 3. Collection and storage of employee information

[1064] A user (employee or manager) uses a terminal to input information such as skill set, work history, and current task status.

[1065] The terminal transmits this information to the server.

[1066] The server stores the received employee information in a database.

[1067] 4. Collecting and analyzing employees' emotional states

[1068] The device collects emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user, which is then analyzed through an emotion engine (e.g., Microsoft Azure's Emotion API).

[1069] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[1070] The server analyzes the received emotional data in real time and stores it in a database.

[1071] 5. Matching tasks with employees

[1072] The server integrates task information, employee information, and emotional state and applies a matching algorithm (e.g., linear regression model or decision tree).

[1073] The server determines the optimal task-employee pair.

[1074] 6. Notification after task assignment

[1075] The server generates a notification to the employee who has been newly assigned the task.

[1076] The terminal receives the notification and informs the user that a task has been assigned to them.

[1077] 7. Real-time management of task progress

[1078] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[1079] The device sends progress data to the server.

[1080] The server stores the received progress data in a database and updates the dashboard in real time.

[1081] Specific examples

[1082] Example 1: New project task assignments

[1083] Entering task information

[1084] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[1085] The server receives this task information and stores it in a database.

[1086] Task Classification

[1087] The server uses natural language processing to analyze the input task description and categorize "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[1088] The server displays the classification results on a dashboard.

[1089] Entering employee information

[1090] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[1091] Entering emotion data

[1092] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[1093] Matching tasks and employees and considering their emotional state

[1094] The server runs a matching algorithm based on task information, employee information, and emotional state data, assigning, for example, "market research" to employee X, "prototype design" to employee Y, and "client meetings" to employee Z.

[1095] Sending notifications

[1096] The server generates the assignment results and sends notifications to the terminals, which then notify each employee that a new task has been assigned to them.

[1097] Progress Management

[1098] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[1099] The server displays the overall progress in real time on a dashboard and manages the status of tasks.

[1100] Prompt Sentence Examples

[1101] "Find an employee to handle market research. The skills needed are data analysis and market research experience."

[1102] "Select an employee to be tasked with designing a prototype. Their skill set should include design experience and 3D modeling. Also, consider their motivation and stress level."

[1103] "Select employees who can conduct client meetings effectively. Communication and presentation skills are essential. Also, check their emotional state."

[1104] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1105] Step 1: Collect and save task information

[1106] The user uses the device to input task information, including details such as the task title (e.g., "Market Research"), description (e.g., "Collect the latest market data"), deadline (e.g., "2023-10-31"), priority (e.g., "High"), required skills (e.g., "Data Analysis"), and dependencies.

[1107] The terminal transmits the input task information to the server.

[1108] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[1109] Input: Task information entered by the user.

[1110] Output: Saved task information.

[1111] Specific behavior:

[1112] The user enters task information into a web form on the device and clicks the "Submit" button.

[1113] The device sends an HTTP request to the server and provides task information.

[1114] The server executes an SQL query to store the task information in a database.

[1115] Step 2: Classifying and visualizing task information

[1116] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[1117] The server extracts important keywords and phrases from the task description.

[1118] The server classifies tasks into categories using machine learning algorithms (e.g., k-means clustering).

[1119] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[1120] Input: Saved task information.

[1121] Output: Categorized task information and a dashboard visualizing it.

[1122] Specific behavior:

[1123] The server retrieves the task description and performs NLP analysis using a Python script.

[1124] The server extracts keywords from the NLP analysis results and performs classification processing.

[1125] The server sends the classification results to the visualization tool's API and displays them on a dashboard.

[1126] Step 3: Collect and store employee information

[1127] The user (employee or manager) uses the terminal to enter their skill set (e.g., "data analysis skills"), work history (e.g., "5 years of market research experience"), current task status (e.g., "current task: none"), etc.

[1128] The terminal transmits the entered employee information to the server.

[1129] The server stores the received employee information in a database.

[1130] Input: Employee information entered by the user.

[1131] Output: Saved employee information.

[1132] Specific behavior:

[1133] The user enters employee information into the form on the terminal and clicks the "Submit" button.

[1134] The device sends an HTTP request to the server, providing employee information.

[1135] The server executes the SQL query to save the employee information to the database.

[1136] Step 4: Collect and analyze employee emotional states

[1137] The device collects emotional state data entered by the user (e.g., "Stress level: high," "Motivation: low"), which is then analyzed through an emotion engine (e.g., Microsoft Azure's Emotion API).

[1138] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[1139] The server analyzes the received emotion data in real time and stores it in a database.

[1140] Input: Emotional state data entered by the user.

[1141] Output: Parsed emotion data and stored emotion data.

[1142] Specific behavior:

[1143] The user inputs the emotional state into the terminal and clicks the "send" button.

[1144] The device calls the emotion engine's API and analyzes the data.

[1145] The device sends the analysis results to the server, which stores them in a database.

[1146] Step 5: Matching tasks with employees

[1147] The server integrates task information, employee information, and emotional state data and applies a matching algorithm (e.g., linear regression model or decision tree).

[1148] The server determines the optimal task-employee pair.

[1149] Input: Task information, employee information, emotional state data.

[1150] Output: Optimal task-employee pairs.

[1151] Specific behavior:

[1152] The server retrieves task information, employee information, and emotional state data, and runs a matching algorithm using Python's scikit-learn library.

[1153] The server makes a decision as a matching result, for example, to assign "market research" to employee X.

[1154] Step 6: Notification after task assignment

[1155] The server generates a notification to the employee who has been newly assigned the task.

[1156] The terminal receives the notification and informs the user that a task has been assigned to them.

[1157] Input: Task assignment results.

[1158] Output: Notify employee.

[1159] Specific behavior:

[1160] The server generates a notification saying "Market research task assigned to employee X."

[1161] The device receives the notification and displays a pop-up message on the screen to notify the user.

[1162] Step 7: Real-time task progress management

[1163] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[1164] The device sends progress data to the server.

[1165] The server stores the received progress data in a database and updates the dashboard in real time.

[1166] Input: Task progress entered by the user.

[1167] Output: Updated progress data and a dashboard displayed in real time.

[1168] Specific behavior:

[1169] The user enters "Market research task progress: 50% complete, no problems" into the terminal and clicks the "Submit" button.

[1170] The device sends progress data to the server.

[1171] The server runs SQL queries to store progress data in a database and updates the dashboard in real time.

[1172] (Application example 2)

[1173] 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."

[1174] In recent years, the widespread adoption of autonomous vehicles has created a need for efficient management of a wide range of tasks, including vehicle charging, maintenance, and route management. However, appropriately assigning these tasks to employees and managing their progress in real time is complex and can lead to human error and reduced efficiency. Furthermore, task assignment without considering employees' emotional states can have a negative impact on work quality and efficiency. Therefore, there is a need for a system that efficiently assigns tasks and manages their progress while taking into account employees' skill sets and emotional states in autonomous vehicle task management.

[1175] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm, means for assigning tasks to the most suitable employee, means for notifying the assignment results, means for collecting and updating progress status, means for collecting task data of autonomous vehicles and classifying them into categories such as charging and maintenance, and means for analyzing the emotional states of employees and taking this into consideration when assigning tasks. This makes it possible to efficiently manage tasks for autonomous vehicles while taking into account the skill sets and emotional states of employees, and to visualize and manage progress status in real time.

[1176] "Task data" refers to data that includes various information required for work or tasks, and specifically includes task titles, descriptions, deadlines, priorities, required skills, and dependencies.

[1177] "Natural language processing" refers to the technology that allows computers to understand, generate, and analyze human language, extracting keywords and important phrases, and classifying data.

[1178] A "machine learning algorithm" is an algorithm that allows a computer to learn patterns from data and make predictions or classifications based on those patterns.

[1179] "Visualization" refers to a method of visually displaying data or information, for example, by using graphs or dashboards to make the information easy to understand.

[1180] "Employee Data" includes individual data such as an employee's skill set, work history, and current task status.

[1181] "Matching algorithm" refers to an algorithm that performs optimal pairing or matching based on collected data.

[1182] "Assignment" refers to the act of giving a specific task to a specific employee.

[1183] "Notification" refers to a message or alert that notifies the user of the existence of newly generated information or tasks.

[1184] "Progress" is information that indicates the degree of progress or completion status of a task at a certain point in time.

[1185] An "autonomous vehicle" is a vehicle that operates by its own self-control mechanism without the need for a human driver.

[1186] "Charging" refers to the process of powering an electric vehicle or other electrically powered device.

[1187] "Maintenance" refers to work such as inspection, adjustment, and repair to keep systems and equipment operating normally and prevent breakdowns and deterioration.

[1188] "Emotional state" is data that indicates the user's psychological and emotional condition, such as stress level, fatigue level, and motivation.

[1189] The system of the present invention streamlines task management for autonomous vehicles and optimally assigns tasks to employees, taking into account their skill sets and emotional states. The system comprehensively supports a series of processes, from collecting task data to managing progress.

[1190] System Configuration

[1191] Hardware and Software

[1192] This system is realized through the cooperation of servers, terminals, and users, and uses the following hardware and software.

[1193] Server: Collects and stores task and employee data, and runs natural language processing (NLP) and machine learning algorithms.

[1194] Terminal: A device such as a smartphone or tablet where a user enters and checks data.

[1195] Software: Server-side processing is implemented using Python and Django, and React and Vue.js are used for the front end.

[1196] Natural Language Processing: Use NLTK and spaCy to analyze task descriptions.

[1197] Machine learning algorithms: Data classification and predictions are performed using scikit-learn and TensorFlow.

[1198] Program processing description

[1199] 1. Collecting task data

[1200] The user (administrator) uses a terminal to input detailed task information. Specifically, data such as the task title, description, deadline, priority, required skills, and dependencies is sent to the server. The server then stores each piece of task data in a database.

[1201] 2. Task Data Analysis and Classification

[1202] The server analyzes the collected task data using natural language processing (NLP) to extract important keywords and phrases. It then uses machine learning algorithms to classify tasks into categories such as "charging" and "maintenance." The classification results are visually displayed through a dashboard.

[1203] 3. Employee Data Collection

[1204] Users (engineers) input data such as their skill sets, work history, and current task status through their terminals. The server stores this data in a database.

[1205] 4. Collecting and analyzing emotional states

[1206] The device acquires emotional data (e.g., stress level, fatigue level, motivation, etc.) entered by the user via an emotion engine and sends it to the server, which analyzes the emotional data in real time and stores it in a database.

[1207] 5. Task matching and assignment

[1208] The server integrates the collected task data, employee data, and emotional data and applies a matching algorithm that determines the optimal task-employee pairing, taking into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[1209] 6. Task assignment notifications

[1210] The server generates a notification for the employee who has been assigned a new task and sends it to the device, including the task details and deadline.

[1211] 7. Real-time progress management

[1212] Users (engineers) use their own devices to input the progress of tasks in real time. The server stores the received progress data in a database and visualizes the overall progress through a dashboard.

[1213] Examples of concrete examples and prompts

[1214] Specific examples

[1215] For example, a European city managing autonomous taxis could use the system to assign tasks to technicians who are responsible for charging vehicles when their batteries get low.

[1216] Prompt Sentence Examples

[1217] "Taking into account the suitability of technicians based on emotional data and assigning charging tasks to autonomous taxis with low battery levels."

[1218] The above is a description of an embodiment of the present invention. By using this system, task management for autonomous vehicles can be made more efficient and appropriate task allocation can be achieved taking into account the emotional state of employees.

[1219] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1220] Step 1:

[1221] Task data collection:

[1222] The user (administrator) uses a terminal to input detailed task information and send it to the server. This task data includes the task title, description, deadline, priority, required skills, and dependencies. The server stores this data in a database. The input is the task information that the user inputs into the terminal, and the output is the task data stored in the server's database.

[1223] Step 2:

[1224] Task data analysis and classification:

[1225] The server analyzes the collected task data using natural language processing (NLP) to extract important keywords and phrases. It then uses machine learning algorithms to classify the tasks into categories such as "charging" and "maintenance." The input is the collected task data, and the output is the task data classified by category.

[1226] Step 3:

[1227] Visualizing task data:

[1228] The server displays the classified task data on a dashboard so that the user can easily check it. The input is the classified task data, and the output is the task information displayed on the dashboard. Specifically, the server generates a web page using HTML and JavaScript to visually display the task data.

[1229] Step 4:

[1230] Employee Data Collection:

[1231] Users (engineers) input their skill sets, work history, and current task status through their terminals. The server stores this data in a database. The input is the employee information that the user enters into the terminal, and the output is the employee data stored in the server's database.

[1232] Step 5:

[1233] Collecting and analyzing emotional states:

[1234] The device acquires emotional data (stress level, fatigue level, motivation, etc.) entered by the user via an emotion engine and sends it to a server. The server analyzes this data in real time and stores it in a database. The input is data that represents the emotional state, and the output is the analyzed emotional data. Specifically, the server uses the emotion engine to analyze the numerical data and evaluate the emotional state.

[1235] Step 6:

[1236] Matching tasks and employees:

[1237] The server integrates the collected task data, employee data, and emotional data and applies a matching algorithm to determine the optimal task-employee pair. This algorithm takes into account required skills, priority, current task load, and emotional state. The inputs are task data, employee data, and emotional data, and the output is the optimal task-employee pair. Specifically, the server uses a scoring system to select the optimal pair.

[1238] Step 7:

[1239] Task assignment notification:

[1240] The server creates a notification for an employee who has been assigned a new task and sends it to the employee's device. The notification includes detailed task information and a deadline. The input is the assigned task information, and the output is a notification that is displayed on the employee's device. Specifically, the server generates a notification message and sends a push notification to the device.

[1241] Step 8:

[1242] Real-time progress management:

[1243] The user (engineer) uses their own device to input the progress status of the task and sends it to the server. The server saves this progress data in a database and visualizes the overall progress status through a dashboard. The input is the progress data entered by the engineer, and the output is the progress status displayed on the dashboard. In concrete terms, the server processes the real-time data and updates the progress status.

[1244] Through these steps, the system of the present invention achieves efficient task management and task allocation that takes into account the emotional state of employees.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] [Third embodiment]

[1249] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1250] 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.

[1251] 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).

[1252] 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.

[1253] 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.

[1254] 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).

[1255] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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."

[1261] The system of this invention uses AI to visualize and classify tasks across the entire company and appropriately assign them to each employee, using a generative AI interface. This system can be realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[1262] System Overview

[1263] The system provides the following main functions:

[1264] 1. Collecting and saving task data

[1265] 2. Classification and visualization of task data

[1266] 3. Collection and storage of employee data

[1267] 4. Matching tasks with employees

[1268] 5. Notification after task assignment

[1269] 6. Real-time management of task progress

[1270] What the program does

[1271] 1. Collecting and saving task data

[1272] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[1273] The server stores the received task data in a database.

[1274] 2. Classification and visualization of task data

[1275] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[1276] The server uses machine learning algorithms to categorize tasks.

[1277] The server displays the classified task data on a dashboard for the user to review.

[1278] 3. Collection and storage of employee data

[1279] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[1280] The server stores the received employee data in a database.

[1281] 4. Matching tasks with employees

[1282] The server combines task data with employee data and applies a matching algorithm that takes into account the required skills and priority of the task, the employee's skill set, and their current task load to calculate the optimal match.

[1283] The server determines the optimal task-employee pair and assigns the task to the corresponding employee.

[1284] 5. Notification after task assignment

[1285] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1286] The terminal receives the notification and informs the user that a task has been assigned to them.

[1287] 6. Real-time management of task progress

[1288] Users (employees) use terminals to input task progress in real time, reporting progress rates, task progress, problems, etc.

[1289] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[1290] Specific examples

[1291] Example 1: New project task assignments

[1292] 1. Enter task data

[1293] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[1294] The server receives this task data and stores it in a database.

[1295] 2. Task categorization

[1296] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[1297] The server displays the classification results on a dashboard.

[1298] 3. Enter employee data

[1299] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[1300] 4. Matching tasks with employees

[1301] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[1302] 5. Sending notifications

[1303] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[1304] 6. Progress Management

[1305] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[1306] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[1307] The above is a description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, and visualizing the overall progress of work in real time.

[1308] The processing flow will be explained below.

[1309] Step 1:

[1310] The user uses the terminal to input the details of a new task (title, description, deadline, priority, required skills, dependencies, etc.) After completing the input, the terminal sends this data to the server.

[1311] Step 2:

[1312] The server receives task data sent from the device and stores it in a database. The format of the task data is standardized, and missing or abnormal values ​​are complemented and corrected.

[1313] Step 3:

[1314] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[1315] Step 4:

[1316] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[1317] Step 5:

[1318] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[1319] Step 6:

[1320] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[1321] Step 7:

[1322] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[1323] Step 8:

[1324] The server merges the task data with the employee data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, and their current task load.

[1325] Step 9:

[1326] The server uses a matching algorithm to determine the best task-employee pair, e.g., task "market research" is assigned to employee X.

[1327] Step 10:

[1328] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1329] Step 11:

[1330] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. The notifications are delivered via a pop-up message, email, or messaging app.

[1331] Step 12:

[1332] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[1333] Step 13:

[1334] The terminal transmits the input progress data to the server.

[1335] Step 14:

[1336] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[1337] Step 15:

[1338] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[1339] The above are the specific processing steps of the system of the present invention. This system has the effect of improving the efficiency of task management within a company, reducing human error, and visualizing the overall progress of work in real time.

[1340] Example 1

[1341] 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."

[1342] In modern companies, effectively managing diverse tasks and assigning them to the right employees is extremely difficult. Especially in large organizations, manual task assignment requires a tremendous amount of time and effort due to the complexity of tasks and the diversity of employees. Furthermore, improper task assignment can lead to reduced work efficiency and disrupted employee workloads. Furthermore, manually tracking the progress of tasks across the company in real time is difficult, making an appropriate task management system essential to prevent project delays and errors.

[1343] 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.

[1344] In this invention, the server includes means for collecting task data, means for analyzing the collected task data using natural language processing and machine learning algorithms and extracting keywords and important phrases, means for classifying the task data using the extracted data, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm and calculating the optimal combination taking into account the required skills of the task, priority, employee skill sets, and task load, means for assigning tasks to the optimal employee, means for notifying the assignment results, and means for collecting progress status in real time, storing it in a database, and displaying it on a dashboard, thereby enabling efficient task management and visualization of progress status in real time.

[1345] "Task data" refers to data that includes detailed information related to a task, such as a title, description, deadline, priority, required skills, and dependencies.

[1346] "Natural language processing" is the technology used by computers to understand, analyze, and generate human language.

[1347] A "machine learning algorithm" is an algorithm that learns patterns from data and uses that knowledge to make decisions and predictions based on new data.

[1348] "Keywords" refer to important words or concepts extracted from documents or text data.

[1349] An "important phrase" is a series of words in text data that are particularly important in terms of meaning or content.

[1350] "Classification" is the process of sorting data into categories or groups based on certain criteria.

[1351] "Visualization" refers to the presentation of data or information using visual representations such as graphs and diagrams.

[1352] "Employee data" is data that includes information such as an employee's skill set, work history, and current task status.

[1353] A "matching algorithm" refers to a method or calculation procedure for finding the optimal combination between multiple elements.

[1354] "Progress" is information that indicates the current degree of achievement or completion of a task or project.

[1355] "Real-time" refers to immediate updates or processing at the current moment or time.

[1356] A "dashboard" is an interface or tool that displays various data and information in a centralized manner, making it easier for administrators to grasp the situation.

[1357] The system of the present invention is designed to improve the efficiency of task management within a company, and is realized through the cooperation of a server, terminals, and users. The processing of the system program will be specifically described below.

[1358] System configuration and functions

[1359] The system provides the following main functions:

[1360] 1. Collecting and saving task data

[1361] A user uses a terminal to enter task data, including details such as the task title, description, deadline, priority, required skills, and dependencies.

[1362] The device sends this task data to the server using an encrypted communication protocol (e.g., HTTPS).

[1363] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[1364] 2. Task Data Analysis and Classification

[1365] The server analyzes the saved task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) to extract keywords and important phrases.

[1366] The server uses machine learning algorithms (e.g., K-means clustering or support vector machines) to classify tasks into categories.

[1367] The server displays the classified task data on a web dashboard (e.g., Grafana or Tableau) for easy user review.

[1368] 3. Collection and storage of employee data

[1369] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[1370] The terminal transmits the entered employee data to the server.

[1371] The server stores the received employee data in a database.

[1372] 4. Matching tasks with employees

[1373] The server combines task data with employee data and applies a matching algorithm (e.g., a recommendation system) that takes into account the task's required skills, priority, employee skill set, and current task load to calculate the optimal match.

[1374] The server determines the optimal task-employee pair, assigns the corresponding task to the appropriate employee, and records this information in a database.

[1375] 5. Notification after task assignment

[1376] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1377] The terminal receives this notification and informs the user that a task has been assigned to him.

[1378] 6. Real-time management of task progress

[1379] Users (employees) use their own devices to input task progress in real time, reporting progress rates, progress during tasks, problems, etc.

[1380] The terminal transmits the input progress information to the server.

[1381] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[1382] Example: Assigning tasks to a new project

[1383] Example 1: Task assignment for Project "A"

[1384] 1. Enter task data

[1385] The user (project manager) uses a terminal to input the tasks for project "A": "market research," "prototype design," and "client meeting."

[1386] The terminal transmits these task data to the server, which stores the received data in a database.

[1387] 2. Task categorization

[1388] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[1389] The server displays the classification results on a dashboard.

[1390] 3. Enter employee data

[1391] Users (employees X, Y, Z) enter their skill sets and work history into a terminal, which then sends it to the server.

[1392] The server stores the received data in a database.

[1393] 4. Matching tasks with employees

[1394] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[1395] 5. Sending notifications

[1396] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[1397] 6. Progress Management

[1398] Users (employees X, Y, and Z) use their own terminals to input the progress of their tasks, and the terminals send the progress data to the server.

[1399] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing users to grasp the overall progress status in real time.

[1400] Example of generative AI model and prompt

[1401] The system uses a generative AI model to match tasks with employees. Here are some example prompts:

[1402] Prompt Sentence Examples

[1403] "A new task has been created. The task title is 'Market Research' and the required skill is 'Data Analysis'. Please assign an employee with the relevant skills."

[1404] The above is a specific description of the embodiment of the invention.

[1405] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1406] Step 1: Enter task data

[1407] A user (e.g., a project manager) uses a terminal to enter task information (title, description, deadline, priority, required skills, dependencies, etc.) into the system. Task data is entered using a web form.

[1408] Inputs: Task title, task description, due date, priority, required skills, dependencies.

[1409] How it works: The terminal receives input data from the user and verifies the data integrity, for example, whether deadlines are entered in the correct format, whether required skills follow the list format, etc.

[1410] Output: The validated task data.

[1411] Step 2: Sending task data

[1412] The device sends the verified task data to the server using an encrypted protocol (e.g., HTTPS).

[1413] Input: Validated task data.

[1414] How it works: The device sends task data to the server using the HTTPS protocol.

[1415] Output: The task data sent to the server.

[1416] Step 3: Save the task data

[1417] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[1418] Input: The submitted task data.

[1419] What it does: The server opens a database connection and saves the task data, generating a unique task ID and recording it along with the data.

[1420] Output: Task data stored in the database (including task ID).

[1421] Step 4: Analyzing task data

[1422] The server analyzes the stored task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) libraries to extract keywords and important phrases.

[1423] Input: Saved task data.

[1424] How it works: It uses an NLP library to tokenize (break down) a task description into words and extract important keywords and phrases, such as the phrase "market research."

[1425] Output: Extracted keywords and key phrases.

[1426] Step 5: Classify task data

[1427] The server categorizes tasks based on the extracted keywords and phrases using machine learning algorithms (e.g., K-means clustering and support vector machines).

[1428] Input: Extracted keywords and key phrases.

[1429] How it works: Using a machine learning algorithm, the system classifies a task, for example "market research," into the "research" category, assigns a category label, and updates the results to the database.

[1430] Output: Classification results (task data including category labels).

[1431] Step 6: Visualize task data

[1432] The server prepares the classified task data for display on a web dashboard (e.g., Grafana or Tableau).

[1433] Input: Classified task data.

[1434] Action: The data is converted into a format specified by the visualization tool and displayed on a dashboard. For example, tasks in the "Investigation" category are displayed as a bar graph.

[1435] Output: A visualized dashboard.

[1436] Step 7: Enter employee data

[1437] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[1438] Inputs: Skill set, work history, current task status.

[1439] How it works: The terminal receives employee data and verifies data integrity, e.g., that skill sets are entered in the proper format.

[1440] Output: Validated employee data.

[1441] Step 8: Submit employee data

[1442] The terminal transmits the verified employee data to the server.

[1443] Input: Validated employee data.

[1444] How it works: The device sends employee data to the server using the HTTPS protocol.

[1445] Output: Employee data sent to the server.

[1446] Step 9: Save employee data

[1447] The server stores the received employee data in a database.

[1448] Input: Submitted employee data.

[1449] What happens: The server opens a database connection and saves the employee data, generating a unique employee ID and recording it along with the data.

[1450] Output: Employee data stored in the database, including employee ID.

[1451] Step 10: Applying the matching algorithm

[1452] The server combines the task data with the employee data and applies a matching algorithm (e.g., a recommendation system).

[1453] Input: Classified task data, saved employee data.

[1454] How it works: Calculate the optimal combination by taking into account the required skills of the task, priority, employee skill sets, current task load, etc. For example, use a recommendation system to select employee X who is best suited for the task "market research."

[1455] Output: Matching results (task-employee pairs).

[1456] Step 11: Assign tasks

[1457] The server determines the best task-employee pair and updates the task record in the database.

[1458] Input: Matching results.

[1459] What it does: Accesses the database and updates the task record, recording the ID of the assigned employee and changing the task state to "Assigned."

[1460] Output: The updated task record.

[1461] Step 12: Generate notifications

[1462] The server generates a notification to the employee who has been newly assigned the task.

[1463] Input: The updated task record.

[1464] What it does: Triggers the notification mechanism and generates a notification containing task details and deadlines.

[1465] Output: The generated notification.

[1466] Step 13: Sending notifications

[1467] The server sends the generated notification to the terminal, which receives the notification and displays it to the user.

[1468] Input: The generated notification.

[1469] How it works: The server sends notifications to the device via email or push notification. The device receives the notifications and notifies the user via a screen display or audio alarm.

[1470] Output: The notification displayed to the user.

[1471] Step 14: Enter your progress

[1472] Users (employees) use their own devices to input task progress in real time.

[1473] Input: Progress data (progress rate, progress, issues, etc.).

[1474] Action: The user enters progress data, and the terminal verifies the data integrity, e.g., checks that the progress rate is within the range 0-100%.

[1475] Output: Progress data of the completed validation.

[1476] Step 15: Sending progress data

[1477] The terminal transmits progress information indicating that the verification has been completed to the server.

[1478] Input: Verified progress data.

[1479] How it works: The device sends progress data to the server using the HTTPS protocol.

[1480] Output: Progress data sent to the server.

[1481] Step 16: Saving and Counting Progress Data

[1482] The server stores the received progress data in a database and aggregates the progress status.

[1483] Input: The progress data submitted.

[1484] What it does: The server opens a database connection, stores the progress data, and performs aggregations, such as calculating the overall progress of tasks and assessing the overall progress of the project.

[1485] Output: Aggregated progress data in a database.

[1486] Step 17: View progress on a dashboard

[1487] The server displays the aggregated progress data on a dashboard (e.g., Grafana or Tableau).

[1488] Input: Aggregated progress data.

[1489] How it works: The server converts the data into a format required by the visualization tool and displays it on a dashboard, such as a pie chart or bar graph showing the progress of a project.

[1490] Output: Progress displayed in a visualized dashboard.

[1491] This enables consistent system processing from collecting task data and employee data to assigning tasks and managing progress, making task management within a company more efficient.

[1492] (Application example 1)

[1493] 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."

[1494] In factories, many work devices (e.g., robots) are operating simultaneously, and there is a need to improve the efficiency and optimization of work. However, in current systems, tasks are often assigned to each work device manually, which leads to problems such as human error and complicated task management. In addition, it is difficult to manage progress in real time, which is a cause of reduced overall work efficiency.

[1495] 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.

[1496] In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting data on maintenance devices, means for integrating the collected data on maintenance devices and the classified task data using a matching algorithm, means for assigning tasks to the most appropriate maintenance device, means for notifying the assignment results, and means for collecting and updating progress status, thereby enabling automatic assignment of tasks to each maintenance device and real-time progress management.

[1497] "Task data" is data that contains information about a particular task or project.

[1498] "Natural language processing" is a technology that allows computers to understand and process natural language used by humans.

[1499] A "machine learning algorithm" is a computational method for learning patterns from data and making predictions and classifications.

[1500] "Visualization" is a method of visually displaying data and information to make it easier to understand.

[1501] "Work equipment" refers to automated machines, robots, and other equipment used in factories and work sites.

[1502] A "matching algorithm" is a computational method for finding optimal pairings based on specific criteria.

[1503] "Assignment" is the act of distributing a specific task to a corresponding work device or person.

[1504] "Notification" is the act or system of informing interested parties of important information or updates.

[1505] "Progress" is information that indicates how far a task or project has progressed.

[1506] "Collection methods" are the methods and techniques used to gather the necessary data and information.

[1507] "Integration means" are methods and technologies that bring together different data and systems to make them usable.

[1508] This invention is a system for streamlining task management for work equipment in a factory, and is realized through the cooperation of a server, terminals, and users. This system provides the following main functions: collecting and saving task data, classifying and visualizing task data, collecting and saving data on work equipment, matching tasks with work equipment, notifying users after task assignment, and managing task progress in real time.

[1509] Hardware and Software Configuration

[1510] 1. Hardware: Servers, tablets, factory robots.

[1511] 2. Software: Python (backend), Django (web framework), NLP library (e.g. spaCy), machine learning library (e.g. TensorFlow), database (e.g. PostgreSQL), dashboard tool (e.g. Grafana).

[1512] Program processing and natural language explanation

[1513] Collecting and storing task data

[1514] A user (factory manager) uses a tablet to input information about a specific task or project, including the task title, description, deadline, priority, required skills, and dependencies. The server receives this task data and stores it in a database.

[1515] Classifying and visualizing task data

[1516] The server analyzes the received task data using natural language processing (NLP) to extract keywords and important phrases. It then uses machine learning algorithms to categorize the tasks. The results are then visualized on a dashboard for users to review.

[1517] Work equipment data collection and storage

[1518] The user (factory manager) uses a tablet to input the capabilities, current operating status, and skill set of each work device (factory robot). The server receives this data on the work device and stores it in a database.

[1519] Matching tasks and work equipment

[1520] The server combines the task data and the work equipment data and applies a matching algorithm that takes into account the required skills and priorities of the tasks and the current task load of the work equipment to calculate the optimal combination. The optimal work equipment is then assigned to the task.

[1521] Notification after task assignment

[1522] The server generates a notification for the manager of the work device to which the new task has been assigned and sends it to the tablet. The notification includes detailed information about the task and its deadline, and the device receives it to inform the user that a task has been assigned to them.

[1523] Real-time management of task progress

[1524] The user (factory manager) uses a tablet to input task progress status in real time. Progress rates, task progress, problems, etc. are reported, and the server receives, stores, and aggregates this data. The server displays the overall progress status on a dashboard and manages the situation in real time.

[1525] Specific examples

[1526] Prompt Sentence Examples

[1527] Task data input prompt example

[1528] Enter the following task:

[1529] 1. Task title: Inspection work

[1530] 2. Task Description: Inspect product X

[1531] 3. Deadline: 2023-12-01

[1532] 4. Priority: High

[1533] 5. Required Skills: Inspection

[1534] Example of a progress report prompt

[1535] Progress Report:

[1536] 1. Task title: Inspection work

[1537] 2. Progress: 50%

[1538] 3. Current status: Under testing

[1539] 4. Issues: None

[1540] As described above, this system enables efficient task management of work equipment within a factory. Users can easily input task data and progress status via tablet, and the server compiles, analyzes, and visualizes the data, achieving work efficiency and real-time management.

[1541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1542] Step 1:

[1543] The user (factory manager) uses a tablet to input task data. Detailed information such as the task title, description, deadline, priority, required skills, and dependencies are entered into the tablet. This becomes the input data to the server. The server stores this input data in a database.

[1544] Step 2:

[1545] The server analyzes the stored task data using natural language processing (NLP). Keywords and important phrases are extracted from the task data. The extracted keywords become the output data of the NLP process.

[1546] Step 3:

[1547] The server uses a machine learning algorithm to classify tasks based on the extracted keywords and phrases, generates classified task data, and stores the results in a database. The classification results become the server's output data.

[1548] Step 4:

[1549] The server displays the classified task data on a dashboard. The visualized task data is output to the screen of a display device (e.g., a tablet or PC). Through this dashboard, users can check the task classification results in real time.

[1550] Step 5:

[1551] The user (factory manager) uses a tablet to input data for each work tool (capabilities, skill set, current operating status). This data is input to the server, which then stores the received work tool data in a database.

[1552] Step 6:

[1553] The server integrates the stored task data and data on the work equipment. It applies a dedicated matching algorithm to calculate the optimal combination, taking into account the required skills and priority of the task and the current task load of the work equipment. The calculation results in an optimal task allocation to the work equipment. This allocation result becomes the server's output data.

[1554] Step 7:

[1555] The server generates a notification of the task assignment result and sends it to the device (tablet). The device receives the notification and notifies the user that a new task has been assigned. The user can then check the notification content on the device.

[1556] Step 8:

[1557] The user (factory manager) uses a tablet to input task progress information. This includes detailed progress information such as the progress rate, progress during the task, and any problems. This data is input to the server. The server stores the received progress data in a database and updates the progress status in real time.

[1558] Step 9:

[1559] The server aggregates the saved progress data and displays it on a dashboard, allowing users to check the overall progress in real time. The dashboard visually displays the progress of each task.

[1560] The above are the specific processing steps of the system program that realizes the application example. This flow allows efficient real-time task management of work equipment in a factory.

[1561] 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.

[1562] The system of this invention uses a generative AI interface to visualize and classify tasks across the entire company and assign them appropriately to each employee. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, task allocation takes into account the emotional state of employees. This system is realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[1563] System Overview

[1564] The system provides the following main functions:

[1565] 1. Collecting and saving task data

[1566] 2. Classification and visualization of task data

[1567] 3. Collection and storage of employee data

[1568] 4. Matching tasks with employees

[1569] 5. Collecting and analyzing the user's emotional state

[1570] 6. Notification after task assignment

[1571] 7. Considering emotional states when assigning tasks

[1572] 8. Real-time management of task progress

[1573] What the program does

[1574] 1. Collecting and saving task data

[1575] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[1576] The server stores the received task data in a database.

[1577] 2. Classification and visualization of task data

[1578] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[1579] The server uses machine learning algorithms to categorize tasks.

[1580] The server displays the classified task data on a dashboard for the user to review.

[1581] 3. Collection and storage of employee data

[1582] A user (employee or manager) uses a terminal to enter individual data such as skill set, work history, and current task status.

[1583] The server stores the received employee data in a database.

[1584] 4. Collecting and analyzing the user's emotional state

[1585] The terminal transmits the emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user to the server via the emotion engine.

[1586] The server analyzes the received emotion data in real time and stores it in a database.

[1587] 5. Matching tasks with employees

[1588] The server integrates task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[1589] The server determines the optimal task-employee pair, for example, the task "market research" is assigned to employee X, while also taking into account employee X's emotional state.

[1590] 6. Notification after task assignment

[1591] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1592] The terminal receives the notification and informs the user that a task has been assigned to them.

[1593] 7. Real-time management of task progress

[1594] Users (employees) use terminals to input task progress in real time, and provide detailed reports on progress rates, progress during tasks, problems, etc.

[1595] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[1596] Specific examples

[1597] Example 1: New project task assignments

[1598] 1. Enter task data

[1599] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[1600] The server receives this task data and stores it in a database.

[1601] 2. Task categorization

[1602] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[1603] The server displays the classification results on a dashboard.

[1604] 3. Enter employee data

[1605] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[1606] 4. Entering Emotion Data

[1607] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[1608] 5. Matching tasks with employees and considering their emotional state

[1609] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z, while taking into account the emotional state of the employees.

[1610] 6. Sending Notifications

[1611] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[1612] 7. Progress Management

[1613] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[1614] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[1615] This concludes the description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, achieving more appropriate task allocation by taking into account the emotional state of employees, and visualizing the overall progress of work in real time.

[1616] The processing flow will be explained below.

[1617] Step 1:

[1618] The user uses the terminal to input details of the new task, such as the title, description, deadline, priority, required skills, dependencies, etc. After completing the input, the terminal sends this data to the server.

[1619] Step 2:

[1620] The server receives task data sent from the terminal and stores it in a database. The server unifies the data format and complements and corrects missing or abnormal values.

[1621] Step 3:

[1622] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[1623] Step 4:

[1624] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[1625] Step 5:

[1626] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[1627] Step 6:

[1628] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[1629] Step 7:

[1630] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[1631] Step 8:

[1632] The user (employee) inputs their emotional state (e.g., stress level, fatigue level, motivation, etc.) into the terminal, which then transmits this emotional data to the server.

[1633] Step 9:

[1634] The server analyzes the emotional state data sent from the device using an emotion engine and generates analysis results in real time. The emotional data is stored in a database.

[1635] Step 10:

[1636] The server combines task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[1637] Step 11:

[1638] The server determines the optimal task-employee pair and assigns the task, for example, assigning the task "market research" to employee X, taking into account employee X's emotional state.

[1639] Step 12:

[1640] The server generates a notification to the employee who has been assigned a new task, including details about the task and its due date, and sends the notification to the device.

[1641] Step 13:

[1642] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. Notifications are delivered via pop-up messages, emails, or messaging apps.

[1643] Step 14:

[1644] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[1645] Step 15:

[1646] The terminal transmits the input progress data to the server.

[1647] Step 16:

[1648] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[1649] Step 17:

[1650] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[1651] Example 2

[1652] 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."

[1653] In corporate task management, it is important to appropriately assign tasks and track progress. However, conventional task management systems often struggle to assign tasks that take into account the emotional state of individual employees, resulting in inefficient work. Furthermore, insufficient task classification and visualization make it difficult to track overall work progress. The present invention aims to solve these problems and improve the efficiency of task management across the entire company.

[1654] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting task information, a means for classifying the collected task information using natural language processing and machine learning algorithms, a means for collecting employee information, a means for collecting and analyzing employee emotional states, a means for integrating the collected employee information and the task information classified with the emotional states using a matching algorithm, and a means for assigning tasks to the most suitable employee. This enables efficient classification, visualization, and assignment of tasks to appropriate employees, consideration of emotional states, and real-time progress management.

[1655] "Task information" refers to detailed information about specific work, such as the content of the work, deadlines, priorities, required skills, and dependencies.

[1656] "Natural language processing" refers to the technology that allows computers to analyze, understand, and appropriately process human language.

[1657] A "machine learning algorithm" refers to a computational method that allows a computer to learn on its own based on data and make predictions and classifications.

[1658] "Employee information" refers to detailed data about individual employees, such as their skill sets, work history, and current task status.

[1659] "Emotional state" refers to information that indicates an employee's psychological and emotional state, such as stress level, fatigue level, and motivation.

[1660] A "matching algorithm" refers to a computational method for determining the optimal task-employee pair based on collected task and employee information.

[1661] "Visualization means" refers to methods or tools for visually displaying data, typically in the form of a dashboard or similar.

[1662] "Communication methods" refer to the methods and tools used to communicate information about assigned tasks to employees.

[1663] "Progress" refers to information that indicates the progress of work, such as how much of a task has been completed or what problems have arisen along the way.

[1664] The system of the present invention uses AI to visualize and classify tasks within a company and appropriately assign them to employees, while also using an emotion engine to allocate tasks while taking into account the emotional state of employees. This system is realized through the cooperation of a server, terminals, and users. The system's program processing is explained below, along with specific examples.

[1665] System Program Processing

[1666] 1. Collecting and saving task information

[1667] The user inputs task information using a terminal, including details such as the specific task title, description, deadline, priority, required skills, and dependencies, and sends them to the server.

[1668] The terminal transmits this information to the server.

[1669] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[1670] 2. Classification and visualization of task information

[1671] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[1672] The server extracts important keywords and phrases and categorizes tasks using machine learning algorithms (e.g., k-means clustering).

[1673] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[1674] 3. Collection and storage of employee information

[1675] A user (employee or manager) uses a terminal to input information such as skill set, work history, and current task status.

[1676] The terminal transmits this information to the server.

[1677] The server stores the received employee information in a database.

[1678] 4. Collecting and analyzing employees' emotional states

[1679] The device collects emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user, which is then analyzed through an emotion engine (e.g., Microsoft Azure's Emotion API).

[1680] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[1681] The server analyzes the received emotional data in real time and stores it in a database.

[1682] 5. Matching tasks with employees

[1683] The server integrates task information, employee information, and emotional state and applies a matching algorithm (e.g., linear regression model or decision tree).

[1684] The server determines the optimal task-employee pair.

[1685] 6. Notification after task assignment

[1686] The server generates a notification to the employee who has been newly assigned the task.

[1687] The terminal receives the notification and informs the user that a task has been assigned to them.

[1688] 7. Real-time management of task progress

[1689] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[1690] The device sends progress data to the server.

[1691] The server stores the received progress data in a database and updates the dashboard in real time.

[1692] Specific examples

[1693] Example 1: New project task assignments

[1694] Entering task information

[1695] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[1696] The server receives this task information and stores it in a database.

[1697] Task Classification

[1698] The server uses natural language processing to analyze the input task description and categorize "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[1699] The server displays the classification results on a dashboard.

[1700] Entering employee information

[1701] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[1702] Entering emotion data

[1703] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[1704] Matching tasks and employees and considering their emotional state

[1705] The server runs a matching algorithm based on task information, employee information, and emotional state data, assigning, for example, "market research" to employee X, "prototype design" to employee Y, and "client meetings" to employee Z.

[1706] Sending notifications

[1707] The server generates the assignment results and sends notifications to the terminals, which then notify each employee that a new task has been assigned to them.

[1708] Progress Management

[1709] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[1710] The server displays the overall progress in real time on a dashboard and manages the status of tasks.

[1711] Prompt Sentence Examples

[1712] "Find an employee to handle market research. The skills needed are data analysis and market research experience."

[1713] "Select an employee to be tasked with designing a prototype. Their skill set should include design experience and 3D modeling. Also, consider their motivation and stress level."

[1714] "Select employees who can conduct client meetings effectively. Communication and presentation skills are essential. Also, check their emotional state."

[1715] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1716] Step 1: Collect and save task information

[1717] The user uses the device to input task information, including details such as the task title (e.g., "Market Research"), description (e.g., "Collect the latest market data"), deadline (e.g., "2023-10-31"), priority (e.g., "High"), required skills (e.g., "Data Analysis"), and dependencies.

[1718] The terminal transmits the input task information to the server.

[1719] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[1720] Input: Task information entered by the user.

[1721] Output: Saved task information.

[1722] Specific behavior:

[1723] The user enters task information into a web form on the device and clicks the "Submit" button.

[1724] The device sends an HTTP request to the server and provides task information.

[1725] The server executes an SQL query to store the task information in a database.

[1726] Step 2: Classifying and visualizing task information

[1727] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[1728] The server extracts important keywords and phrases from the task description.

[1729] The server classifies tasks into categories using machine learning algorithms (e.g., k-means clustering).

[1730] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[1731] Input: Saved task information.

[1732] Output: Categorized task information and a dashboard visualizing it.

[1733] Specific behavior:

[1734] The server retrieves the task description and performs NLP analysis using a Python script.

[1735] The server extracts keywords from the NLP analysis results and performs classification processing.

[1736] The server sends the classification results to the visualization tool's API and displays them on a dashboard.

[1737] Step 3: Collect and store employee information

[1738] The user (employee or manager) uses the terminal to enter their skill set (e.g., "data analysis skills"), work history (e.g., "5 years of market research experience"), current task status (e.g., "current task: none"), etc.

[1739] The terminal transmits the entered employee information to the server.

[1740] The server stores the received employee information in a database.

[1741] Input: Employee information entered by the user.

[1742] Output: Saved employee information.

[1743] Specific behavior:

[1744] The user enters employee information into the form on the terminal and clicks the "Submit" button.

[1745] The device sends an HTTP request to the server, providing employee information.

[1746] The server executes the SQL query to save the employee information to the database.

[1747] Step 4: Collect and analyze employee emotional states

[1748] The device collects emotional state data entered by the user (e.g., "Stress level: high," "Motivation: low"), which is then analyzed through an emotion engine (e.g., Microsoft Azure's Emotion API).

[1749] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[1750] The server analyzes the received emotion data in real time and stores it in a database.

[1751] Input: Emotional state data entered by the user.

[1752] Output: Parsed emotion data and stored emotion data.

[1753] Specific behavior:

[1754] The user inputs the emotional state into the terminal and clicks the "send" button.

[1755] The device calls the emotion engine's API and analyzes the data.

[1756] The device sends the analysis results to the server, which stores them in a database.

[1757] Step 5: Matching tasks with employees

[1758] The server integrates task information, employee information, and emotional state data and applies a matching algorithm (e.g., linear regression model or decision tree).

[1759] The server determines the optimal task-employee pair.

[1760] Input: Task information, employee information, emotional state data.

[1761] Output: Optimal task-employee pairs.

[1762] Specific behavior:

[1763] The server retrieves task information, employee information, and emotional state data, and runs a matching algorithm using Python's scikit-learn library.

[1764] The server makes a decision as a matching result, for example, to assign "market research" to employee X.

[1765] Step 6: Notification after task assignment

[1766] The server generates a notification to the employee who has been newly assigned the task.

[1767] The terminal receives the notification and informs the user that a task has been assigned to them.

[1768] Input: Task assignment results.

[1769] Output: Notify employee.

[1770] Specific behavior:

[1771] The server generates a notification saying "Market research task assigned to employee X."

[1772] The device receives the notification and displays a pop-up message on the screen to notify the user.

[1773] Step 7: Real-time task progress management

[1774] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[1775] The device sends progress data to the server.

[1776] The server stores the received progress data in a database and updates the dashboard in real time.

[1777] Input: Task progress entered by the user.

[1778] Output: Updated progress data and a dashboard displayed in real time.

[1779] Specific behavior:

[1780] The user enters "Market research task progress: 50% complete, no problems" into the terminal and clicks the "Submit" button.

[1781] The device sends progress data to the server.

[1782] The server runs SQL queries to store progress data in a database and updates the dashboard in real time.

[1783] (Application example 2)

[1784] 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."

[1785] In recent years, the widespread adoption of autonomous vehicles has created a need for efficient management of a wide range of tasks, including vehicle charging, maintenance, and route management. However, appropriately assigning these tasks to employees and managing their progress in real time is complex and can lead to human error and reduced efficiency. Furthermore, task assignment without considering employees' emotional states can have a negative impact on work quality and efficiency. Therefore, there is a need for a system that efficiently assigns tasks and manages their progress while taking into account employees' skill sets and emotional states in autonomous vehicle task management.

[1786] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm, means for assigning tasks to the most suitable employee, means for notifying the assignment results, means for collecting and updating progress status, means for collecting task data of autonomous vehicles and classifying them into categories such as charging and maintenance, and means for analyzing the emotional states of employees and taking this into consideration when assigning tasks. This makes it possible to efficiently manage tasks for autonomous vehicles while taking into account the skill sets and emotional states of employees, and to visualize and manage progress status in real time.

[1787] "Task data" refers to data that includes various information required for work or tasks, and specifically includes task titles, descriptions, deadlines, priorities, required skills, and dependencies.

[1788] "Natural language processing" refers to the technology that allows computers to understand, generate, and analyze human language, extracting keywords and important phrases, and classifying data.

[1789] A "machine learning algorithm" is an algorithm that allows a computer to learn patterns from data and make predictions or classifications based on those patterns.

[1790] "Visualization" refers to a method of visually displaying data or information, for example, by using graphs or dashboards to make the information easy to understand.

[1791] "Employee Data" includes individual data such as an employee's skill set, work history, and current task status.

[1792] "Matching algorithm" refers to an algorithm that performs optimal pairing or matching based on collected data.

[1793] "Assignment" refers to the act of giving a specific task to a specific employee.

[1794] "Notification" refers to a message or alert that notifies the user of the existence of newly generated information or tasks.

[1795] "Progress" is information that indicates the degree of progress or completion status of a task at a certain point in time.

[1796] An "autonomous vehicle" is a vehicle that operates by its own self-control mechanism without the need for a human driver.

[1797] "Charging" refers to the process of powering an electric vehicle or other electrically powered device.

[1798] "Maintenance" refers to work such as inspection, adjustment, and repair to keep systems and equipment operating normally and prevent breakdowns and deterioration.

[1799] "Emotional state" is data that indicates the user's psychological and emotional condition, such as stress level, fatigue level, and motivation.

[1800] The system of the present invention streamlines task management for autonomous vehicles and optimally assigns tasks to employees, taking into account their skill sets and emotional states. The system comprehensively supports a series of processes, from collecting task data to managing progress.

[1801] System Configuration

[1802] Hardware and Software

[1803] This system is realized through the cooperation of servers, terminals, and users, and uses the following hardware and software.

[1804] Server: Collects and stores task and employee data, and runs natural language processing (NLP) and machine learning algorithms.

[1805] Terminal: A device such as a smartphone or tablet where a user enters and checks data.

[1806] Software: Server-side processing is implemented using Python and Django, and React and Vue.js are used for the front end.

[1807] Natural Language Processing: Use NLTK and spaCy to analyze task descriptions.

[1808] Machine learning algorithms: Data classification and predictions are performed using scikit-learn and TensorFlow.

[1809] Program processing description

[1810] 1. Collecting task data

[1811] The user (administrator) uses a terminal to input detailed task information. Specifically, data such as the task title, description, deadline, priority, required skills, and dependencies is sent to the server. The server then stores each piece of task data in a database.

[1812] 2. Task Data Analysis and Classification

[1813] The server analyzes the collected task data using natural language processing (NLP) to extract important keywords and phrases. It then uses machine learning algorithms to classify tasks into categories such as "charging" and "maintenance." The classification results are visually displayed through a dashboard.

[1814] 3. Employee Data Collection

[1815] Users (engineers) input data such as their skill sets, work history, and current task status through their terminals. The server stores this data in a database.

[1816] 4. Collecting and analyzing emotional states

[1817] The device acquires emotional data (e.g., stress level, fatigue level, motivation, etc.) entered by the user via an emotion engine and sends it to the server, which analyzes the emotional data in real time and stores it in a database.

[1818] 5. Task matching and assignment

[1819] The server integrates the collected task data, employee data, and emotional data and applies a matching algorithm that determines the optimal task-employee pairing, taking into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[1820] 6. Task assignment notifications

[1821] The server generates a notification for the employee who has been assigned a new task and sends it to the device, including the task details and deadline.

[1822] 7. Real-time progress management

[1823] Users (engineers) use their own devices to input the progress of tasks in real time. The server stores the received progress data in a database and visualizes the overall progress through a dashboard.

[1824] Examples of concrete examples and prompts

[1825] Specific examples

[1826] For example, a European city managing autonomous taxis could use the system to assign tasks to technicians who are responsible for charging vehicles when their batteries get low.

[1827] Prompt Sentence Examples

[1828] "Taking into account the suitability of technicians based on emotional data and assigning charging tasks to autonomous taxis with low battery levels."

[1829] The above is a description of an embodiment of the present invention. By using this system, task management for autonomous vehicles can be made more efficient and appropriate task allocation can be achieved taking into account the emotional state of employees.

[1830] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1831] Step 1:

[1832] Task data collection:

[1833] The user (administrator) uses a terminal to input detailed task information and send it to the server. This task data includes the task title, description, deadline, priority, required skills, and dependencies. The server stores this data in a database. The input is the task information that the user inputs into the terminal, and the output is the task data stored in the server's database.

[1834] Step 2:

[1835] Task data analysis and classification:

[1836] The server analyzes the collected task data using natural language processing (NLP) to extract important keywords and phrases. It then uses machine learning algorithms to classify the tasks into categories such as "charging" and "maintenance." The input is the collected task data, and the output is the task data classified by category.

[1837] Step 3:

[1838] Visualizing task data:

[1839] The server displays the classified task data on a dashboard so that the user can easily check it. The input is the classified task data, and the output is the task information displayed on the dashboard. Specifically, the server generates a web page using HTML and JavaScript to visually display the task data.

[1840] Step 4:

[1841] Employee Data Collection:

[1842] Users (engineers) input their skill sets, work history, and current task status through their terminals. The server stores this data in a database. The input is the employee information that the user enters into the terminal, and the output is the employee data stored in the server's database.

[1843] Step 5:

[1844] Collecting and analyzing emotional states:

[1845] The device acquires emotional data (stress level, fatigue level, motivation, etc.) entered by the user via an emotion engine and sends it to a server. The server analyzes this data in real time and stores it in a database. The input is data that represents the emotional state, and the output is the analyzed emotional data. Specifically, the server uses the emotion engine to analyze the numerical data and evaluate the emotional state.

[1846] Step 6:

[1847] Matching tasks and employees:

[1848] The server integrates the collected task data, employee data, and emotional data and applies a matching algorithm to determine the optimal task-employee pair. This algorithm takes into account required skills, priority, current task load, and emotional state. The inputs are task data, employee data, and emotional data, and the output is the optimal task-employee pair. Specifically, the server uses a scoring system to select the optimal pair.

[1849] Step 7:

[1850] Task assignment notification:

[1851] The server creates a notification for an employee who has been assigned a new task and sends it to the employee's device. The notification includes detailed task information and a deadline. The input is the assigned task information, and the output is a notification that is displayed on the employee's device. Specifically, the server generates a notification message and sends a push notification to the device.

[1852] Step 8:

[1853] Real-time progress management:

[1854] The user (engineer) uses their own device to input the progress status of the task and sends it to the server. The server saves this progress data in a database and visualizes the overall progress status through a dashboard. The input is the progress data entered by the engineer, and the output is the progress status displayed on the dashboard. In concrete terms, the server processes the real-time data and updates the progress status.

[1855] Through these steps, the system of the present invention achieves efficient task management and task allocation that takes into account the emotional state of employees.

[1856] 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.

[1857] 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.

[1858] 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.

[1859] [Fourth embodiment]

[1860] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1861] 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.

[1862] 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).

[1863] 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.

[1864] 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.

[1865] 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).

[1866] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] 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."

[1873] The system of this invention uses AI to visualize and classify tasks across the entire company and appropriately assign them to each employee, using a generative AI interface. This system can be realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[1874] System Overview

[1875] The system provides the following main functions:

[1876] 1. Collecting and saving task data

[1877] 2. Classification and visualization of task data

[1878] 3. Collection and storage of employee data

[1879] 4. Matching tasks with employees

[1880] 5. Notification after task assignment

[1881] 6. Real-time management of task progress

[1882] What the program does

[1883] 1. Collecting and saving task data

[1884] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[1885] The server stores the received task data in a database.

[1886] 2. Classification and visualization of task data

[1887] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[1888] The server uses machine learning algorithms to categorize tasks.

[1889] The server displays the classified task data on a dashboard for the user to review.

[1890] 3. Collection and storage of employee data

[1891] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[1892] The server stores the received employee data in a database.

[1893] 4. Matching tasks with employees

[1894] The server combines task data with employee data and applies a matching algorithm that takes into account the required skills and priority of the task, the employee's skill set, and their current task load to calculate the optimal match.

[1895] The server determines the optimal task-employee pair and assigns the task to the corresponding employee.

[1896] 5. Notification after task assignment

[1897] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1898] The terminal receives the notification and informs the user that a task has been assigned to them.

[1899] 6. Real-time management of task progress

[1900] Users (employees) use terminals to input task progress in real time, reporting progress rates, task progress, problems, etc.

[1901] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[1902] Specific examples

[1903] Example 1: New project task assignments

[1904] 1. Enter task data

[1905] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[1906] The server receives this task data and stores it in a database.

[1907] 2. Task categorization

[1908] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[1909] The server displays the classification results on a dashboard.

[1910] 3. Enter employee data

[1911] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[1912] 4. Matching tasks with employees

[1913] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[1914] 5. Sending notifications

[1915] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[1916] 6. Progress Management

[1917] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[1918] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[1919] The above is a description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, and visualizing the overall progress of work in real time.

[1920] The processing flow will be explained below.

[1921] Step 1:

[1922] The user uses the terminal to input the details of a new task (title, description, deadline, priority, required skills, dependencies, etc.) After completing the input, the terminal sends this data to the server.

[1923] Step 2:

[1924] The server receives task data sent from the device and stores it in a database. The format of the task data is standardized, and missing or abnormal values ​​are complemented and corrected.

[1925] Step 3:

[1926] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[1927] Step 4:

[1928] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[1929] Step 5:

[1930] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[1931] Step 6:

[1932] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[1933] Step 7:

[1934] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[1935] Step 8:

[1936] The server merges the task data with the employee data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, and their current task load.

[1937] Step 9:

[1938] The server uses a matching algorithm to determine the best task-employee pair, e.g., task "market research" is assigned to employee X.

[1939] Step 10:

[1940] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1941] Step 11:

[1942] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. The notifications are delivered via a pop-up message, email, or messaging app.

[1943] Step 12:

[1944] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[1945] Step 13:

[1946] The terminal transmits the input progress data to the server.

[1947] Step 14:

[1948] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[1949] Step 15:

[1950] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[1951] The above are the specific processing steps of the system of the present invention. This system has the effect of improving the efficiency of task management within a company, reducing human error, and visualizing the overall progress of work in real time.

[1952] Example 1

[1953] 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."

[1954] In modern companies, effectively managing diverse tasks and assigning them to the right employees is extremely difficult. Especially in large organizations, manual task assignment requires a tremendous amount of time and effort due to the complexity of tasks and the diversity of employees. Furthermore, improper task assignment can lead to reduced work efficiency and disrupted employee workloads. Furthermore, manually tracking the progress of tasks across the company in real time is difficult, making an appropriate task management system essential to prevent project delays and errors.

[1955] 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.

[1956] In this invention, the server includes means for collecting task data, means for analyzing the collected task data using natural language processing and machine learning algorithms and extracting keywords and important phrases, means for classifying the task data using the extracted data, means for visualizing the classification results, means for collecting employee data, means for integrating the collected employee data and the classified task data using a matching algorithm and calculating the optimal combination taking into account the required skills of the task, priority, employee skill sets, and task load, means for assigning tasks to the optimal employee, means for notifying the assignment results, and means for collecting progress status in real time, storing it in a database, and displaying it on a dashboard, thereby enabling efficient task management and visualization of progress status in real time.

[1957] "Task data" refers to data that includes detailed information related to a task, such as a title, description, deadline, priority, required skills, and dependencies.

[1958] "Natural language processing" is the technology used by computers to understand, analyze, and generate human language.

[1959] A "machine learning algorithm" is an algorithm that learns patterns from data and uses that knowledge to make decisions and predictions based on new data.

[1960] "Keywords" refer to important words or concepts extracted from documents or text data.

[1961] An "important phrase" is a series of words in text data that are particularly important in terms of meaning or content.

[1962] "Classification" is the process of sorting data into categories or groups based on certain criteria.

[1963] "Visualization" refers to the presentation of data or information using visual representations such as graphs and diagrams.

[1964] "Employee data" is data that includes information such as an employee's skill set, work history, and current task status.

[1965] A "matching algorithm" refers to a method or calculation procedure for finding the optimal combination between multiple elements.

[1966] "Progress" is information that indicates the current degree of achievement or completion of a task or project.

[1967] "Real-time" refers to immediate updates or processing at the current moment or time.

[1968] A "dashboard" is an interface or tool that displays various data and information in a centralized manner, making it easier for administrators to grasp the situation.

[1969] The system of the present invention is designed to improve the efficiency of task management within a company, and is realized through the cooperation of a server, terminals, and users. The processing of the system program will be specifically described below.

[1970] System configuration and functions

[1971] The system provides the following main functions:

[1972] 1. Collecting and saving task data

[1973] A user uses a terminal to enter task data, including details such as the task title, description, deadline, priority, required skills, and dependencies.

[1974] The device sends this task data to the server using an encrypted communication protocol (e.g., HTTPS).

[1975] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[1976] 2. Task Data Analysis and Classification

[1977] The server analyzes the saved task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) to extract keywords and important phrases.

[1978] The server uses machine learning algorithms (e.g., K-means clustering or support vector machines) to classify tasks into categories.

[1979] The server displays the classified task data on a web dashboard (e.g., Grafana or Tableau) for easy user review.

[1980] 3. Collection and storage of employee data

[1981] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[1982] The terminal transmits the entered employee data to the server.

[1983] The server stores the received employee data in a database.

[1984] 4. Matching tasks with employees

[1985] The server combines task data with employee data and applies a matching algorithm (e.g., a recommendation system) that takes into account the task's required skills, priority, employee skill set, and current task load to calculate the optimal match.

[1986] The server determines the optimal task-employee pair, assigns the corresponding task to the appropriate employee, and records this information in a database.

[1987] 5. Notification after task assignment

[1988] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[1989] The terminal receives this notification and informs the user that a task has been assigned to him.

[1990] 6. Real-time management of task progress

[1991] Users (employees) use their own devices to input task progress in real time, reporting progress rates, progress during tasks, problems, etc.

[1992] The terminal transmits the input progress information to the server.

[1993] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[1994] Example: Assigning tasks to a new project

[1995] Example 1: Task assignment for Project "A"

[1996] 1. Enter task data

[1997] The user (project manager) uses a terminal to input the tasks for project "A": "market research," "prototype design," and "client meeting."

[1998] The terminal transmits these task data to the server, which stores the received data in a database.

[1999] 2. Task categorization

[2000] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[2001] The server displays the classification results on a dashboard.

[2002] 3. Enter employee data

[2003] Users (employees X, Y, Z) enter their skill sets and work history into a terminal, which then sends it to the server.

[2004] The server stores the received data in a database.

[2005] 4. Matching tasks with employees

[2006] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z.

[2007] 5. Sending notifications

[2008] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[2009] 6. Progress Management

[2010] Users (employees X, Y, and Z) use their own terminals to input the progress of their tasks, and the terminals send the progress data to the server.

[2011] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing users to grasp the overall progress status in real time.

[2012] Example of generative AI model and prompt

[2013] The system uses a generative AI model to match tasks with employees. Here are some example prompts:

[2014] Prompt Sentence Examples

[2015] "A new task has been created. The task title is 'Market Research' and the required skill is 'Data Analysis'. Please assign an employee with the relevant skills."

[2016] The above is a specific description of the embodiment of the invention.

[2017] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2018] Step 1: Enter task data

[2019] A user (e.g., a project manager) uses a terminal to enter task information (title, description, deadline, priority, required skills, dependencies, etc.) into the system. Task data is entered using a web form.

[2020] Inputs: Task title, task description, due date, priority, required skills, dependencies.

[2021] How it works: The terminal receives input data from the user and verifies the data integrity, for example, whether deadlines are entered in the correct format, whether required skills follow the list format, etc.

[2022] Output: The validated task data.

[2023] Step 2: Sending task data

[2024] The device sends the verified task data to the server using an encrypted protocol (e.g., HTTPS).

[2025] Input: Validated task data.

[2026] How it works: The device sends task data to the server using the HTTPS protocol.

[2027] Output: The task data sent to the server.

[2028] Step 3: Save the task data

[2029] The server stores the received task data in a relational database management system (RDBMS, e.g., MySQL or PostgreSQL).

[2030] Input: The submitted task data.

[2031] What it does: The server opens a database connection and saves the task data, generating a unique task ID and recording it along with the data.

[2032] Output: Task data stored in the database (including task ID).

[2033] Step 4: Analyzing task data

[2034] The server analyzes the stored task data using Natural Language Processing (NLP: e.g., SpaCy or NLTK) libraries to extract keywords and important phrases.

[2035] Input: Saved task data.

[2036] How it works: It uses an NLP library to tokenize (break down) a task description into words and extract important keywords and phrases, such as the phrase "market research."

[2037] Output: Extracted keywords and key phrases.

[2038] Step 5: Classify task data

[2039] The server categorizes tasks based on the extracted keywords and phrases using machine learning algorithms (e.g., K-means clustering and support vector machines).

[2040] Input: Extracted keywords and key phrases.

[2041] How it works: Using a machine learning algorithm, the system classifies a task, for example "market research," into the "research" category, assigns a category label, and updates the results to the database.

[2042] Output: Classification results (task data including category labels).

[2043] Step 6: Visualize task data

[2044] The server prepares the classified task data for display on a web dashboard (e.g., Grafana or Tableau).

[2045] Input: Classified task data.

[2046] Action: The data is converted into a format specified by the visualization tool and displayed on a dashboard. For example, tasks in the "Investigation" category are displayed as a bar graph.

[2047] Output: A visualized dashboard.

[2048] Step 7: Enter employee data

[2049] A user (employee or manager) uses a terminal to enter employee data such as skill sets, work history, and current task status.

[2050] Inputs: Skill set, work history, current task status.

[2051] How it works: The terminal receives employee data and verifies data integrity, e.g., that skill sets are entered in the proper format.

[2052] Output: Validated employee data.

[2053] Step 8: Submit employee data

[2054] The terminal transmits the verified employee data to the server.

[2055] Input: Validated employee data.

[2056] How it works: The device sends employee data to the server using the HTTPS protocol.

[2057] Output: Employee data sent to the server.

[2058] Step 9: Save employee data

[2059] The server stores the received employee data in a database.

[2060] Input: Submitted employee data.

[2061] What happens: The server opens a database connection and saves the employee data, generating a unique employee ID and recording it along with the data.

[2062] Output: Employee data stored in the database, including employee ID.

[2063] Step 10: Applying the matching algorithm

[2064] The server combines the task data with the employee data and applies a matching algorithm (e.g., a recommendation system).

[2065] Input: Classified task data, saved employee data.

[2066] How it works: Calculate the optimal combination by taking into account the required skills of the task, priority, employee skill sets, current task load, etc. For example, use a recommendation system to select employee X who is best suited for the task "market research."

[2067] Output: Matching results (task-employee pairs).

[2068] Step 11: Assign tasks

[2069] The server determines the best task-employee pair and updates the task record in the database.

[2070] Input: Matching results.

[2071] What it does: Accesses the database and updates the task record, recording the ID of the assigned employee and changing the task state to "Assigned."

[2072] Output: The updated task record.

[2073] Step 12: Generate notifications

[2074] The server generates a notification to the employee who has been newly assigned the task.

[2075] Input: The updated task record.

[2076] What it does: Triggers the notification mechanism and generates a notification containing task details and deadlines.

[2077] Output: The generated notification.

[2078] Step 13: Sending notifications

[2079] The server sends the generated notification to the terminal, which receives the notification and displays it to the user.

[2080] Input: The generated notification.

[2081] How it works: The server sends notifications to the device via email or push notification. The device receives the notifications and notifies the user via a screen display or audio alarm.

[2082] Output: The notification displayed to the user.

[2083] Step 14: Enter your progress

[2084] Users (employees) use their own devices to input task progress in real time.

[2085] Input: Progress data (progress rate, progress, issues, etc.).

[2086] Action: The user enters progress data, and the terminal verifies the data integrity, e.g., checks that the progress rate is within the range 0-100%.

[2087] Output: Progress data of the completed validation.

[2088] Step 15: Sending progress data

[2089] The terminal transmits progress information indicating that the verification has been completed to the server.

[2090] Input: Verified progress data.

[2091] How it works: The device sends progress data to the server using the HTTPS protocol.

[2092] Output: Progress data sent to the server.

[2093] Step 16: Saving and Counting Progress Data

[2094] The server stores the received progress data in a database and aggregates the progress status.

[2095] Input: The progress data submitted.

[2096] What it does: The server opens a database connection, stores the progress data, and performs aggregations, such as calculating the overall progress of tasks and assessing the overall progress of the project.

[2097] Output: Aggregated progress data in a database.

[2098] Step 17: View progress on a dashboard

[2099] The server displays the aggregated progress data on a dashboard (e.g., Grafana or Tableau).

[2100] Input: Aggregated progress data.

[2101] How it works: The server converts the data into a format required by the visualization tool and displays it on a dashboard, such as a pie chart or bar graph showing the progress of a project.

[2102] Output: Progress displayed in a visualized dashboard.

[2103] This enables consistent system processing from collecting task data and employee data to assigning tasks and managing progress, making task management within a company more efficient.

[2104] (Application example 1)

[2105] 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."

[2106] In factories, many work devices (e.g., robots) are operating simultaneously, and there is a need to improve the efficiency and optimization of work. However, in current systems, tasks are often assigned to each work device manually, which leads to problems such as human error and complicated task management. In addition, it is difficult to manage progress in real time, which is a cause of reduced overall work efficiency.

[2107] 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.

[2108] In this invention, the server includes means for collecting task data, means for classifying the collected task data using natural language processing and machine learning algorithms, means for visualizing the classification results, means for collecting data on maintenance devices, means for integrating the collected data on maintenance devices and the classified task data using a matching algorithm, means for assigning tasks to the most appropriate maintenance device, means for notifying the assignment results, and means for collecting and updating progress status, thereby enabling automatic assignment of tasks to each maintenance device and real-time progress management.

[2109] "Task data" is data that contains information about a particular task or project.

[2110] "Natural language processing" is a technology that allows computers to understand and process natural language used by humans.

[2111] A "machine learning algorithm" is a computational method for learning patterns from data and making predictions and classifications.

[2112] "Visualization" is a method of visually displaying data and information to make it easier to understand.

[2113] "Work equipment" refers to automated machines, robots, and other equipment used in factories and work sites.

[2114] A "matching algorithm" is a computational method for finding optimal pairings based on specific criteria.

[2115] "Assignment" is the act of distributing a specific task to a corresponding work device or person.

[2116] "Notification" is the act or system of informing interested parties of important information or updates.

[2117] "Progress" is information that indicates how far a task or project has progressed.

[2118] "Collection methods" are the methods and techniques used to gather the necessary data and information.

[2119] "Integration means" are methods and technologies that bring together different data and systems to make them usable.

[2120] This invention is a system for streamlining task management for work equipment in a factory, and is realized through the cooperation of a server, terminals, and users. This system provides the following main functions: collecting and saving task data, classifying and visualizing task data, collecting and saving data on work equipment, matching tasks with work equipment, notifying users after task assignment, and managing task progress in real time.

[2121] Hardware and Software Configuration

[2122] 1. Hardware: Servers, tablets, factory robots.

[2123] 2. Software: Python (backend), Django (web framework), NLP library (e.g. spaCy), machine learning library (e.g. TensorFlow), database (e.g. PostgreSQL), dashboard tool (e.g. Grafana).

[2124] Program processing and natural language explanation

[2125] Collecting and storing task data

[2126] A user (factory manager) uses a tablet to input information about a specific task or project, including the task title, description, deadline, priority, required skills, and dependencies. The server receives this task data and stores it in a database.

[2127] Classifying and visualizing task data

[2128] The server analyzes the received task data using natural language processing (NLP) to extract keywords and important phrases. It then uses machine learning algorithms to categorize the tasks. The results are then visualized on a dashboard for users to review.

[2129] Work equipment data collection and storage

[2130] The user (factory manager) uses a tablet to input the capabilities, current operating status, and skill set of each work device (factory robot). The server receives this data on the work device and stores it in a database.

[2131] Matching tasks and work equipment

[2132] The server combines the task data and the work equipment data and applies a matching algorithm that takes into account the required skills and priorities of the tasks and the current task load of the work equipment to calculate the optimal combination. The optimal work equipment is then assigned to the task.

[2133] Notification after task assignment

[2134] The server generates a notification for the manager of the work device to which the new task has been assigned and sends it to the tablet. The notification includes detailed information about the task and its deadline, and the device receives it to inform the user that a task has been assigned to them.

[2135] Real-time management of task progress

[2136] The user (factory manager) uses a tablet to input task progress status in real time. Progress rates, task progress, problems, etc. are reported, and the server receives, stores, and aggregates this data. The server displays the overall progress status on a dashboard and manages the situation in real time.

[2137] Specific examples

[2138] Prompt Sentence Examples

[2139] Task data input prompt example

[2140] Enter the following task:

[2141] 1. Task title: Inspection work

[2142] 2. Task Description: Inspect product X

[2143] 3. Deadline: 2023-12-01

[2144] 4. Priority: High

[2145] 5. Required Skills: Inspection

[2146] Example of a progress report prompt

[2147] Progress Report:

[2148] 1. Task title: Inspection work

[2149] 2. Progress: 50%

[2150] 3. Current status: Under testing

[2151] 4. Issues: None

[2152] As described above, this system enables efficient task management of work equipment within a factory. Users can easily input task data and progress status via tablet, and the server compiles, analyzes, and visualizes the data, achieving work efficiency and real-time management.

[2153] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2154] Step 1:

[2155] The user (factory manager) uses a tablet to input task data. Detailed information such as the task title, description, deadline, priority, required skills, and dependencies are entered into the tablet. This becomes the input data to the server. The server stores this input data in a database.

[2156] Step 2:

[2157] The server analyzes the stored task data using natural language processing (NLP). Keywords and important phrases are extracted from the task data. The extracted keywords become the output data of the NLP process.

[2158] Step 3:

[2159] The server uses a machine learning algorithm to classify tasks based on the extracted keywords and phrases, generates classified task data, and stores the results in a database. The classification results become the server's output data.

[2160] Step 4:

[2161] The server displays the classified task data on a dashboard. The visualized task data is output to the screen of a display device (e.g., a tablet or PC). Through this dashboard, users can check the task classification results in real time.

[2162] Step 5:

[2163] The user (factory manager) uses a tablet to input data for each work tool (capabilities, skill set, current operating status). This data is input to the server, which then stores the received work tool data in a database.

[2164] Step 6:

[2165] The server integrates the stored task data and data on the work equipment. It applies a dedicated matching algorithm to calculate the optimal combination, taking into account the required skills and priority of the task and the current task load of the work equipment. The calculation results in an optimal task allocation to the work equipment. This allocation result becomes the server's output data.

[2166] Step 7:

[2167] The server generates a notification of the task assignment result and sends it to the device (tablet). The device receives the notification and notifies the user that a new task has been assigned. The user can then check the notification content on the device.

[2168] Step 8:

[2169] The user (factory manager) uses a tablet to input task progress information. This includes detailed progress information such as the progress rate, progress during the task, and any problems. This data is input to the server. The server stores the received progress data in a database and updates the progress status in real time.

[2170] Step 9:

[2171] The server aggregates the saved progress data and displays it on a dashboard, allowing users to check the overall progress in real time. The dashboard visually displays the progress of each task.

[2172] The above are the specific processing steps of the system program that realizes the application example. This flow allows efficient real-time task management of work equipment in a factory.

[2173] 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.

[2174] The system of this invention uses a generative AI interface to visualize and classify tasks across the entire company and assign them appropriately to each employee. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, task allocation takes into account the emotional state of employees. This system is realized with the cooperation of a server, terminals, and users. Below, we will generate a program for the system, explain its processing in natural language, and provide concrete examples.

[2175] System Overview

[2176] The system provides the following main functions:

[2177] 1. Collecting and saving task data

[2178] 2. Classification and visualization of task data

[2179] 3. Collection and storage of employee data

[2180] 4. Matching tasks with employees

[2181] 5. Collecting and analyzing the user's emotional state

[2182] 6. Notification after task assignment

[2183] 7. Considering emotional states when assigning tasks

[2184] 8. Real-time management of task progress

[2185] What the program does

[2186] 1. Collecting and saving task data

[2187] The user inputs task data using a terminal, and details such as task title, description, deadline, priority, required skills, and dependencies are sent to the server.

[2188] The server stores the received task data in a database.

[2189] 2. Classification and visualization of task data

[2190] The server analyzes the stored task data using natural language processing (NLP) to extract keywords and important phrases.

[2191] The server uses machine learning algorithms to categorize tasks.

[2192] The server displays the classified task data on a dashboard for the user to review.

[2193] 3. Collection and storage of employee data

[2194] A user (employee or manager) uses a terminal to enter individual data such as skill set, work history, and current task status.

[2195] The server stores the received employee data in a database.

[2196] 4. Collecting and analyzing the user's emotional state

[2197] The terminal transmits the emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user to the server via the emotion engine.

[2198] The server analyzes the received emotion data in real time and stores it in a database.

[2199] 5. Matching tasks with employees

[2200] The server integrates task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[2201] The server determines the optimal task-employee pair, for example, the task "market research" is assigned to employee X, while also taking into account employee X's emotional state.

[2202] 6. Notification after task assignment

[2203] The server generates a notification to the employee about the newly assigned task, including the task details and deadline.

[2204] The terminal receives the notification and informs the user that a task has been assigned to them.

[2205] 7. Real-time management of task progress

[2206] Users (employees) use terminals to input task progress in real time, and provide detailed reports on progress rates, progress during tasks, problems, etc.

[2207] The server stores the received progress data in a database and displays the aggregated results on a dashboard, allowing the company's overall task progress to be visualized in real time.

[2208] Specific examples

[2209] Example 1: New project task assignments

[2210] 1. Enter task data

[2211] The user (project manager) uses the terminal to input project tasks such as "market research," "prototype design," and "client meeting."

[2212] The server receives this task data and stores it in a database.

[2213] 2. Task categorization

[2214] The server uses natural language processing to analyze the input task description and classify "market research" as "research," "prototype design" as "design," and "client meeting" as "communication."

[2215] The server displays the classification results on a dashboard.

[2216] 3. Enter employee data

[2217] Users (employees X, Y, Z) enter their skill sets and work history on their terminals, and the server stores them in a database.

[2218] 4. Entering Emotion Data

[2219] Users (employees X, Y, and Z) input their emotional state into the terminal, and the server receives the data and stores it in a database.

[2220] 5. Matching tasks with employees and considering their emotional state

[2221] The server assigns the task "market research" to employee X, the task "prototype design" to employee Y, and the task "client meeting" to employee Z, while taking into account the emotional state of the employees.

[2222] 6. Sending Notifications

[2223] The server generates the assignment results and sends notifications to the terminals, which then display the notifications to each employee, informing them that a new task has been assigned to them.

[2224] 7. Progress Management

[2225] Users (employees X, Y, and Z) use their own devices to enter task progress information, and the server receives, stores, and aggregates the data.

[2226] The server displays the overall progress on a dashboard and can manage the status of tasks in real time.

[2227] This concludes the description of a specific embodiment of the system of the present invention. This system has the effects of improving the efficiency of task management in a company, reducing human error, achieving more appropriate task allocation by taking into account the emotional state of employees, and visualizing the overall progress of work in real time.

[2228] The processing flow will be explained below.

[2229] Step 1:

[2230] The user uses the terminal to input details of the new task, such as the title, description, deadline, priority, required skills, dependencies, etc. After completing the input, the terminal sends this data to the server.

[2231] Step 2:

[2232] The server receives task data sent from the terminal and stores it in a database. The server unifies the data format and complements and corrects missing or abnormal values.

[2233] Step 3:

[2234] The server analyzes the stored task data using natural language processing (NLP), extracting keywords and key phrases from task descriptions and analyzing each task in detail.

[2235] Step 4:

[2236] The server uses machine learning algorithms to categorize the analyzed task data, for example, a "market research" task would be classified into the "research" category.

[2237] Step 5:

[2238] The server displays the classified task data on a dashboard, and users (managers and employees) can access the dashboard through a browser and check the task classification results in real time.

[2239] Step 6:

[2240] Users (employees or managers) input their individual data, such as their skill set, work history, and current task status, from their terminals. The terminals then send the input data to the server.

[2241] Step 7:

[2242] The server receives the employee data sent from the device and stores it in a database, updating the skill set and work history to create a complete employee profile.

[2243] Step 8:

[2244] The user (employee) inputs their emotional state (e.g., stress level, fatigue level, motivation, etc.) into the terminal, which then transmits this emotional data to the server.

[2245] Step 9:

[2246] The server analyzes the emotional state data sent from the device using an emotion engine and generates analysis results in real time. The emotional data is stored in a database.

[2247] Step 10:

[2248] The server combines task data, employee data, and emotional data and applies a matching algorithm that takes into account the task's required skills and priority, the employee's skill set, current task load, and emotional state.

[2249] Step 11:

[2250] The server determines the optimal task-employee pair and assigns the task, for example, assigning the task "market research" to employee X, taking into account employee X's emotional state.

[2251] Step 12:

[2252] The server generates a notification to the employee who has been assigned a new task, including details about the task and its due date, and sends the notification to the device.

[2253] Step 13:

[2254] The device receives notifications from the server and notifies the user (employee) that a new task has been assigned to them. Notifications are delivered via pop-up messages, emails, or messaging apps.

[2255] Step 14:

[2256] Users (employees) use terminals to input the progress of tasks in real time, and provide detailed reports on progress rates, progress during the process, problems, etc.

[2257] Step 15:

[2258] The terminal transmits the input progress data to the server.

[2259] Step 16:

[2260] The server stores the received progress data in a database and aggregates the information, updating the progress status in real time.

[2261] Step 17:

[2262] The server displays the progress of tasks across the company on a dashboard, allowing users (managers and employees) to check the progress in real time and take corrective action if necessary.

[2263] Example 2

[2264] 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."

[2265] In corporate task management, it is important to appropriately assign tasks and track progress. However, conventional task management systems often struggle to assign tasks that take into account the emotional state of individual employees, resulting in inefficient work. Furthermore, insufficient task classification and visualization make it difficult to track overall work progress. The present invention aims to solve these problems and improve the efficiency of task management across the entire company.

[2266] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting task information, a means for classifying the collected task information using natural language processing and machine learning algorithms, a means for collecting employee information, a means for collecting and analyzing employee emotional states, a means for integrating the collected employee information and the task information classified with the emotional states using a matching algorithm, and a means for assigning tasks to the most suitable employee. This enables efficient classification, visualization, and assignment of tasks to appropriate employees, consideration of emotional states, and real-time progress management.

[2267] "Task information" refers to detailed information about specific work, such as the content of the work, deadlines, priorities, required skills, and dependencies.

[2268] "Natural language processing" refers to the technology that allows computers to analyze, understand, and appropriately process human language.

[2269] A "machine learning algorithm" refers to a computational method that allows a computer to learn on its own based on data and make predictions and classifications.

[2270] "Employee information" refers to detailed data about individual employees, such as their skill sets, work history, and current task status.

[2271] "Emotional state" refers to information that indicates an employee's psychological and emotional state, such as stress level, fatigue level, and motivation.

[2272] A "matching algorithm" refers to a computational method for determining the optimal task-employee pair based on collected task and employee information.

[2273] "Visualization means" refers to methods or tools for visually displaying data, typically in the form of a dashboard or similar.

[2274] "Communication methods" refer to the methods and tools used to communicate information about assigned tasks to employees.

[2275] "Progress" refers to information that indicates the progress of work, such as how much of a task has been completed or what problems have arisen along the way.

[2276] The system of the present invention uses AI to visualize and classify tasks within a company and appropriately assign them to employees, while also using an emotion engine to allocate tasks while taking into account the emotional state of employees. This system is realized through the cooperation of a server, terminals, and users. The system's program processing is explained below, along with specific examples.

[2277] System Program Processing

[2278] 1. Collecting and saving task information

[2279] The user inputs task information using a terminal, including details such as the specific task title, description, deadline, priority, required skills, and dependencies, and sends them to the server.

[2280] The terminal transmits this information to the server.

[2281] The server stores the received task information in an SQL database (e.g., MySQL or PostgreSQL).

[2282] 2. Classification and visualization of task information

[2283] The server analyzes the stored task information using natural language processing (NLP) algorithms (e.g., Python's NLTK or SpaCy libraries).

[2284] The server extracts important keywords and phrases and categorizes tasks using machine learning algorithms (e.g., k-means clustering).

[2285] The server uses the API of a visualization tool (e.g., Power BI or Tableau) to display the classified task information on a dashboard.

[2286] 3. Collection and storage of employee information

[2287] A user (employee or manager) uses a terminal to input information such as skill set, work history, and current task status.

[2288] The terminal transmits this information to the server.

[2289] The server stores the received employee information in a database.

[2290] 4. Collecting and analyzing employees' emotional states

[2291] The device collects emotional state data (e.g., stress level, fatigue level, motivation, etc.) input by the user, which is then analyzed through an emotion engine (e.g., Microsoft Azure's Emotion API).

[2292] The device invokes the emotion engine, analyzes the emotion data, and sends it to the server.

[2293] The server analyzes the received emotional data in real time and stores it in a database.

[2294] 5. Matching tasks with employees

[2295] The server integrates task information, employee information, and emotional state and applies a matching algorithm (e.g., linear regression model or decision tree).

[2296] The server determines the optimal task-employee pair.

[2297] 6. Notification after task assignment

[2298] The server generates a notification to the employee who has been newly assigned the task.

[2299] The terminal receives the notification and informs the user that a task has been assigned to them.

[2300] 7. Real-time management of task progress

[2301] The user (employee) uses a terminal to input the progress of the task. The progress rate, progress during the task, problems, etc. are reported in detail.

[2302] The device sends progress data to the server.

[2303] The server stores the received progress data in a database and updates the dashboard in real ...

Claims

1. a means for collecting task data; a means for classifying the collected task data using natural language processing and machine learning algorithms; A means for visualizing the classification results; a means of collecting employee data; a means for integrating the collected employee data and the classified task data using a matching algorithm; A means of assigning tasks to the best employees; a means for notifying the allocation result; A means of collecting and updating progress A system including:

2. The system of claim 1 , further comprising: means for displaying the categorized task data on a dashboard.

3. The system of claim 1 further comprising means for collecting employee skill sets and work histories.

Images